2 x Intel Xeon 6780E testing with a Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS) and ASPEED on Ubuntu 24.04 via the Phoronix Test Suite.
Xeon Platinum 8490H Processor: Intel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000590Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Xeon Platinum 8490H 2P Changed Processor to 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads) .
Changed Memory to 1008GB .
Xeon Platinum 8592+ Changed Processor to INTEL XEON PLATINUM 8592+ @ 3.90GHz (64 Cores / 128 Threads) .
Changed Memory to 512GB .
Processor Change: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000200
Xeon Platinum 8592+ 2P Changed Processor to 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads) .
Changed Memory to 1008GB .
Xeon Max 9468 Changed Processor to Intel Xeon Max 9468 @ 3.50GHz (48 Cores / 96 Threads) .
Changed Memory to 576GB .
Processor Change: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290
Xeon Max 9468 2P Changed Processor to 2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads) .
Changed Memory to 1136GB .
Xeon Max 9480 Changed Processor to Intel Xeon Max 9480 @ 3.50GHz (56 Cores / 112 Threads) .
Changed Memory to 576GB .
Xeon Max 9480 2P Changed Processor to 2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads) .
Changed Memory to 1136GB .
Xeon Platinum 8380 2P Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads) , Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS) , Chipset: Intel Ice Lake IEH , Memory: 512GB , Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Monitor: VE228 , Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd0003d1Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Xeon Platinum 8380 Changed Processor to Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads) .
Changed Memory to 256GB .
EPYC 9684X 2P Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads) , Motherboard: AMD Titanite_4G (RTI1007B BIOS) , Chipset: AMD Device 14a4 , Memory: 1520GB , Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9684X Changed Processor to AMD EPYC 9684X 96-Core @ 2.55GHz (96 Cores / 192 Threads) .
Changed Memory to 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG .
EPYC 9654 Changed Processor to AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads) .
EPYC 9654 2P Changed Processor to 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) .
Changed Memory to 1520GB .
EPYC 9754 Changed Processor to AMD EPYC 9754 128-Core @ 2.25GHz (128 Cores / 256 Threads) .
Changed Memory to 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG .
Processor Change: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116
EPYC 9754 2P Changed Processor to 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads) .
Changed Memory to 1520GB .
EPYC 8534P Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads) , Motherboard: AMD Cinnabar (RCB1009C BIOS) , Chipset: AMD Device 14a4, Memory: 6 x 32GB DDR5-4800MT/s Samsung M321R4GA0BB0-CQKMG , Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92 + 2000GB Corsair MP700 PRO , Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00213Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 8534PN Changed Processor to AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads) .
Changed Disk to 2 x 1920GB KIOXIA KCD8XPUG1T92 .
Xeon 6766E 2P Processor: 2 x Intel Xeon 6766E @ 2.70GHz (288 Cores) , Motherboard: Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS) , Chipset: Intel Ice Lake IEH , Memory: 512GB , Disk: 3201GB Micron_7450_MTFDKCB3T2TFS + 2 x 1920GB KIOXIA KCD8XPUG1T92 , Graphics: ASPEED, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Xeon 6766E Changed Processor to Intel Xeon 6766E @ 2.70GHz (144 Cores) .
Changed Memory to 256GB .
Changed Disk to 2 x 1920GB KIOXIA KCD8XPUG1T92 + 3201GB Micron_7450_MTFDKCB3T2TFS .
Xeon 6780E Changed Processor to Intel Xeon 6780E @ 3.00GHz (144 Cores) .
Changed Disk to 3201GB Micron_7450_MTFDKCB3T2TFS + 2 x 1920GB KIOXIA KCD8XPUG1T92 .
Xeon 6780E 2P Changed Processor to 2 x Intel Xeon 6780E @ 3.00GHz (288 Cores) .
Changed Memory to 512GB .
WRF WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.
OpenVKL OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC Xeon Platinum 8380 EPYC 8534PN Xeon Max 9468 EPYC 8534P Xeon 6766E Xeon Max 9480 Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9654 Xeon 6780E 2P EPYC 9684X EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 900 1800 2700 3600 4500 SE +/- 6.81, N = 3 SE +/- 8.17, N = 3 SE +/- 6.66, N = 3 SE +/- 1.20, N = 3 SE +/- 0.58, N = 3 SE +/- 13.96, N = 3 SE +/- 0.67, N = 3 SE +/- 12.02, N = 3 SE +/- 1.53, N = 3 SE +/- 8.62, N = 3 SE +/- 4.36, N = 3 SE +/- 2.08, N = 3 SE +/- 7.31, N = 3 SE +/- 1.20, N = 3 SE +/- 3.61, N = 3 SE +/- 1.00, N = 3 SE +/- 0.88, N = 3 SE +/- 6.74, N = 3 SE +/- 13.62, N = 3 SE +/- 8.67, N = 3 SE +/- 5.36, N = 3 SE +/- 26.33, N = 3 869 1177 1243 1266 1267 1356 1391 1527 1734 1776 1852 2004 2020 2077 2228 2396 2508 2716 3222 3335 3906 4012
Items / Sec Per Watt
OpenBenchmarking.org Items / Sec Per Watt, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon 6780E 2P EPYC 9684X 2P Xeon 6766E 2P EPYC 9654 2P Xeon 6780E Xeon Platinum 8592+ EPYC 9684X Xeon 6766E EPYC 9654 EPYC 9754 2P EPYC 8534P EPYC 9754 EPYC 8534PN 3 6 9 12 15 2.745 2.853 3.162 3.527 3.798 4.129 4.287 5.106 5.391 5.416 5.763 5.786 6.102 6.233 6.261 6.861 7.196 7.601 7.673 9.163 9.457 9.780
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVKL 2.0.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.14 / Avg: 677.76 / Max: 821.93 Min: 190.07 / Avg: 649.08 / Max: 754.84 Min: 209.11 / Avg: 647.03 / Max: 756.03 Min: 172.02 / Avg: 633.5 / Max: 755.3 Min: 79.05 / Avg: 630.97 / Max: 751.76 Min: 57.11 / Avg: 546.55 / Max: 678.78 Min: 40.48 / Avg: 522.89 / Max: 678.27 Min: 102.24 / Avg: 482.91 / Max: 579.87 Min: 63.56 / Avg: 411.4 / Max: 636.51 Min: 33.91 / Avg: 349.21 / Max: 411.78 Min: 106.2 / Avg: 349.12 / Max: 504.22 Min: 78.05 / Avg: 328.39 / Max: 378.11 Min: 75.39 / Avg: 327.25 / Max: 376.15 Min: 57.62 / Avg: 321.66 / Max: 378.49 Min: 35.93 / Avg: 320.1 / Max: 378.34 Min: 28.49 / Avg: 273.27 / Max: 332.24 Min: 21.69 / Avg: 265.2 / Max: 336.16 Min: 51.77 / Avg: 246.36 / Max: 292 Min: 43.61 / Avg: 223.17 / Max: 308.98 Min: 43.67 / Avg: 176.07 / Max: 237.02 Min: 16.98 / Avg: 138.16 / Max: 167.46 Min: 18.05 / Avg: 120.35 / Max: 144.9
RELION RELION - REgularised LIkelihood OptimisatioN - is a stand-alone computer program for Maximum A Posteriori refinement of (multiple) 3D reconstructions or 2D class averages in cryo-electron microscopy (cryo-EM). It is developed in the research group of Sjors Scheres at the MRC Laboratory of Molecular Biology. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better RELION 4.0.1 Test: Basic - Device: CPU Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P EPYC 9754 Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9754 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P 150 300 450 600 750 SE +/- 7.86, N = 9 SE +/- 6.20, N = 3 SE +/- 4.63, N = 3 SE +/- 2.98, N = 3 SE +/- 4.65, N = 9 SE +/- 7.14, N = 9 SE +/- 0.35, N = 3 SE +/- 7.69, N = 9 SE +/- 2.68, N = 7 SE +/- 2.95, N = 3 SE +/- 3.24, N = 12 SE +/- 2.65, N = 3 SE +/- 2.66, N = 12 SE +/- 4.04, N = 12 SE +/- 2.17, N = 3 SE +/- 1.41, N = 3 SE +/- 2.11, N = 12 SE +/- 1.27, N = 15 705.58 496.24 468.69 412.37 384.38 373.18 368.22 360.21 290.45 238.88 214.42 203.41 201.38 201.27 176.42 155.74 145.65 93.17 1. (CXX) g++ options: -fopenmp -std=c++11 -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -ljpeg -lmpi_cxx -lmpi
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RELION 4.0.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 63.79 / Avg: 752.52 / Max: 819.67 Min: 199.08 / Avg: 683.82 / Max: 754.9 Min: 195.56 / Avg: 682.36 / Max: 754.93 Min: 170.14 / Avg: 679.44 / Max: 754.54 Min: 77.4 / Avg: 665.17 / Max: 755.23 Min: 52.45 / Avg: 622.74 / Max: 703.72 Min: 42.44 / Avg: 553.69 / Max: 696.76 Min: 103.02 / Avg: 531.46 / Max: 582.55 Min: 32.42 / Avg: 394.87 / Max: 409.71 Min: 73.55 / Avg: 345.11 / Max: 376.88 Min: 73.36 / Avg: 344.98 / Max: 377.25 Min: 50.74 / Avg: 344.24 / Max: 377.4 Min: 22.57 / Avg: 341.82 / Max: 377.61 Min: 28.15 / Avg: 320.59 / Max: 347.29 Min: 21.86 / Avg: 270.75 / Max: 336.67 Min: 53.81 / Avg: 267.6 / Max: 290.36 Min: 18.83 / Avg: 163.61 / Max: 166.72 Min: 17.41 / Avg: 148.71 / Max: 151.06
NWChem NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.
High Performance Conjugate Gradient HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 Xeon Platinum 8380 EPYC 8534PN EPYC 8534P EPYC 9754 Xeon Max 9468 EPYC 9684X EPYC 9654 Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P 15 30 45 60 75 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.28, N = 5 SE +/- 0.05, N = 3 SE +/- 0.34, N = 9 SE +/- 0.37, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.51, N = 3 SE +/- 0.29, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.94, N = 3 20.41 22.13 22.20 23.63 25.24 27.58 28.32 30.11 30.59 31.07 35.14 41.87 42.52 44.95 54.41 60.85 62.64 69.30 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better High Performance Conjugate Gradient 3.1 X Y Z: 144 144 144 - RT: 60 Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8380 Xeon Max 9468 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9654 EPYC 8534P EPYC 8534PN 0.038 0.076 0.114 0.152 0.19 0.057 0.062 0.069 0.073 0.074 0.077 0.079 0.084 0.088 0.089 0.090 0.092 0.099 0.101 0.103 0.104 0.156 0.169
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon Platinum 8380 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.43 / Avg: 722.2 / Max: 816.31 Min: 192.7 / Avg: 690.6 / Max: 722.1 Min: 162.34 / Avg: 688.79 / Max: 719.93 Min: 78.99 / Avg: 685.14 / Max: 717.63 Min: 208.84 / Avg: 683.79 / Max: 753.27 Min: 55.46 / Avg: 612.13 / Max: 685.77 Min: 42.67 / Avg: 563.2 / Max: 666.57 Min: 101.77 / Avg: 529.99 / Max: 565.31 Min: 76.3 / Avg: 345.19 / Max: 369.22 Min: 74.31 / Avg: 344.79 / Max: 363.36 Min: 62.11 / Avg: 344.43 / Max: 357.3 Min: 24.94 / Avg: 340.38 / Max: 366.08 Min: 33.89 / Avg: 330.25 / Max: 391.86 Min: 28.57 / Avg: 273.24 / Max: 316.28 Min: 52.91 / Avg: 266.5 / Max: 286.68 Min: 16.99 / Avg: 238.17 / Max: 311.47 Min: 18.73 / Avg: 141.98 / Max: 160.79 Min: 18.07 / Avg: 131.23 / Max: 136.75
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 Xeon Platinum 8380 Xeon 6766E EPYC 8534PN Xeon 6780E EPYC 8534P Xeon 6766E 2P Xeon Max 9468 EPYC 9684X Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8380 2P EPYC 9754 EPYC 9684X 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Platinum 8490H EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Platinum 8490H 2P 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.93, N = 9 SE +/- 1.17, N = 3 SE +/- 1.42, N = 4 SE +/- 1.22, N = 3 SE +/- 0.61, N = 3 SE +/- 0.21, N = 3 SE +/- 1.62, N = 4 SE +/- 0.31, N = 3 SE +/- 1.80, N = 3 SE +/- 0.34, N = 3 SE +/- 0.48, N = 3 SE +/- 0.79, N = 3 SE +/- 0.01, N = 3 SE +/- 1.83, N = 3 SE +/- 0.61, N = 3 SE +/- 0.81, N = 3 SE +/- 1.39, N = 3 91.75 91.96 95.63 97.67 101.17 113.42 117.53 121.96 124.60 125.14 127.97 135.17 137.50 138.39 140.01 140.53 145.29 148.45 161.90 169.75 174.93 174.95
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Max 9480 EPYC 9754 2P Xeon 6780E EPYC 9684X Xeon Platinum 8490H Xeon 6766E Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.16 0.32 0.48 0.64 0.8 0.202 0.212 0.227 0.246 0.254 0.257 0.258 0.290 0.296 0.343 0.349 0.364 0.366 0.383 0.385 0.433 0.441 0.469 0.487 0.553 0.659 0.711
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 207.09 / Avg: 684.53 / Max: 724.92 Min: 208.64 / Avg: 684.02 / Max: 721.63 Min: 161.89 / Avg: 678.16 / Max: 719.66 Min: 66.7 / Avg: 606.04 / Max: 658.36 Min: 83.43 / Avg: 585.9 / Max: 658.36 Min: 59.62 / Avg: 547.08 / Max: 589.2 Min: 108.05 / Avg: 506.95 / Max: 588.39 Min: 102.54 / Avg: 504.58 / Max: 542.99 Min: 40.89 / Avg: 478.51 / Max: 540.78 Min: 106.33 / Avg: 441.95 / Max: 500.12 Min: 85.58 / Avg: 343.75 / Max: 366.49 Min: 61.57 / Avg: 342.65 / Max: 363.24 Min: 74.91 / Avg: 342.39 / Max: 362.9 Min: 35.54 / Avg: 316.96 / Max: 353.37 Min: 33.86 / Avg: 299.63 / Max: 330.67 Min: 30.39 / Avg: 287.56 / Max: 321.33 Min: 53.71 / Avg: 263.16 / Max: 276.44 Min: 43.51 / Avg: 255.22 / Max: 299.17 Min: 20.9 / Avg: 244.22 / Max: 295.24 Min: 43.69 / Avg: 208.71 / Max: 235.06 Min: 18.7 / Avg: 153.51 / Max: 165.78 Min: 16.14 / Avg: 134.5 / Max: 142.97
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d EPYC 8534PN EPYC 8534P Xeon Platinum 8380 EPYC 9754 EPYC 9654 Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P 120 240 360 480 600 SE +/- 0.22, N = 3 SE +/- 0.92, N = 3 SE +/- 0.13, N = 3 SE +/- 5.39, N = 3 SE +/- 4.73, N = 3 SE +/- 1.25, N = 3 SE +/- 3.88, N = 4 SE +/- 0.14, N = 3 SE +/- 2.51, N = 3 SE +/- 3.06, N = 9 SE +/- 1.19, N = 3 SE +/- 9.13, N = 9 SE +/- 3.26, N = 9 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.37, N = 3 SE +/- 2.20, N = 12 568.25 567.29 558.38 534.06 466.55 407.59 357.01 351.64 323.25 309.85 292.03 253.32 248.87 196.81 189.69 187.22 171.38 167.13 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 66.18 / Avg: 750.96 / Max: 804.8 Min: 201.23 / Avg: 686.09 / Max: 746.29 Min: 203.67 / Avg: 685.84 / Max: 731.99 Min: 158.32 / Avg: 681.46 / Max: 722.98 Min: 77.71 / Avg: 675.14 / Max: 722.78 Min: 56.03 / Avg: 638.9 / Max: 677.63 Min: 38.21 / Avg: 591.17 / Max: 651.55 Min: 101.33 / Avg: 531.6 / Max: 556.64 Min: 33.87 / Avg: 359.91 / Max: 399.74 Min: 80.13 / Avg: 345.35 / Max: 367.23 Min: 59.93 / Avg: 344.75 / Max: 358.18 Min: 73.01 / Avg: 342.5 / Max: 356.35 Min: 23.89 / Avg: 333.9 / Max: 356.36 Min: 30.46 / Avg: 296.94 / Max: 321.61 Min: 11.29 / Avg: 271.32 / Max: 306.5 Min: 52.82 / Avg: 267.65 / Max: 283.3 Min: 19.39 / Avg: 140.74 / Max: 150 Min: 16.95 / Avg: 129.67 / Max: 136.25
CloverLeaf CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm16 Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ EPYC 9754 Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P EPYC 9654 Xeon Platinum 8490H Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P Xeon Max 9480 2P EPYC 9654 2P Xeon Max 9468 2P EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X 2P Xeon Platinum 8490H 2P 110 220 330 440 550 SE +/- 1.58, N = 3 SE +/- 1.08, N = 3 SE +/- 0.79, N = 3 SE +/- 0.54, N = 3 SE +/- 4.99, N = 9 SE +/- 2.02, N = 3 SE +/- 2.03, N = 3 SE +/- 1.43, N = 3 SE +/- 1.02, N = 3 SE +/- 3.79, N = 9 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 SE +/- 0.00, N = 3 SE +/- 3.41, N = 3 SE +/- 2.11, N = 9 SE +/- 0.12, N = 3 SE +/- 1.56, N = 3 SE +/- 2.24, N = 3 SE +/- 2.04, N = 3 SE +/- 1.60, N = 12 SE +/- 0.59, N = 3 SE +/- 0.74, N = 3 512.36 498.22 495.25 410.59 400.52 378.05 357.57 351.29 349.67 334.30 328.47 314.88 313.50 295.30 269.20 266.10 263.33 245.82 236.81 226.60 223.54 214.80 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better CloverLeaf 1.3 CPU Power Consumption Monitor Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 171.76 / Avg: 685.99 / Max: 712.37 Min: 200.21 / Avg: 680.25 / Max: 711.02 Min: 198.24 / Avg: 677.8 / Max: 709.86 Min: 66.27 / Avg: 538.72 / Max: 566.53 Min: 105.53 / Avg: 529.36 / Max: 542.31 Min: 76.61 / Avg: 524.03 / Max: 570.93 Min: 57.96 / Avg: 483.81 / Max: 500.79 Min: 107.68 / Avg: 466.63 / Max: 492.37 Min: 105.62 / Avg: 440.67 / Max: 468.45 Min: 42.42 / Avg: 388.45 / Max: 400.3 Min: 75.8 / Avg: 346.15 / Max: 373.49 Min: 57.58 / Avg: 346.05 / Max: 371.34 Min: 71.71 / Avg: 345.92 / Max: 368.64 Min: 34.9 / Avg: 301.76 / Max: 361.01 Min: 33.19 / Avg: 289.13 / Max: 310.83 Min: 48.92 / Avg: 267.62 / Max: 276.86 Min: 28.5 / Avg: 250.17 / Max: 287.09 Min: 43.52 / Avg: 205.96 / Max: 212.24 Min: 19.15 / Avg: 200.7 / Max: 237.69 Min: 43.58 / Avg: 186.46 / Max: 191.98 Min: 18.26 / Avg: 143.82 / Max: 147.88 Min: 18.03 / Avg: 132.66 / Max: 136.36
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Gridding Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8592+ Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H EPYC 9754 2P EPYC 9654 EPYC 9654 2P EPYC 9754 EPYC 9684X 2P EPYC 9684X 3K 6K 9K 12K 15K SE +/- 23.56, N = 3 SE +/- 87.89, N = 12 SE +/- 32.87, N = 12 SE +/- 195.28, N = 8 SE +/- 54.27, N = 5 SE +/- 6.18, N = 3 SE +/- 19.36, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 60.72, N = 3 SE +/- 75.19, N = 5 SE +/- 4.15, N = 3 SE +/- 21.01, N = 3 SE +/- 59.24, N = 3 SE +/- 141.43, N = 5 SE +/- 2.09, N = 3 SE +/- 204.28, N = 3 SE +/- 262.30, N = 12 3347.93 3375.32 3406.96 4382.97 5062.07 5172.96 5279.07 5821.46 5826.44 6038.92 7630.06 8088.11 11208.70 12394.60 12708.50 12731.80 14185.10 14955.60 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Result
OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding EPYC 8534P EPYC 8534PN Xeon Platinum 8380 EPYC 9754 Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X EPYC 9654 EPYC 9684X 2P 4K 8K 12K 16K 20K SE +/- 34.17, N = 3 SE +/- 0.54, N = 3 SE +/- 3.76, N = 3 SE +/- 25.80, N = 3 SE +/- 322.56, N = 3 SE +/- 267.65, N = 5 SE +/- 345.37, N = 3 SE +/- 212.00, N = 12 SE +/- 128.32, N = 3 SE +/- 889.21, N = 3 7382.43 7421.23 7425.22 9839.64 9893.32 11941.30 13455.00 14143.10 14217.10 16906.20 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Million Grid Points Per Second Per Watt
OpenBenchmarking.org Million Grid Points Per Second Per Watt, More Is Better ASKAP 1.0 Test: tConvolve MT - Degridding Xeon Platinum 8380 2P EPYC 9654 2P Xeon Platinum 8380 EPYC 9684X 2P EPYC 9754 2P EPYC 9754 EPYC 9684X EPYC 8534P EPYC 8534PN EPYC 9654 20 40 60 80 100 30.49 36.68 40.39 46.19 50.18 76.56 76.92 79.95 85.73 89.45
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASKAP 1.0 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 66.87 / Avg: 365.98 / Max: 703.86 Min: 56.13 / Avg: 325.56 / Max: 537.83 Min: 103.44 / Avg: 324.5 / Max: 557.49 Min: 41.03 / Avg: 268.12 / Max: 506.15 Min: 33.59 / Avg: 183.88 / Max: 366.01 Min: 52.13 / Avg: 183.83 / Max: 281.05 Min: 28.79 / Avg: 158.94 / Max: 298.53 Min: 22.06 / Avg: 128.52 / Max: 260.19 Min: 18.79 / Avg: 92.34 / Max: 148.64 Min: 16.96 / Avg: 86.56 / Max: 131.98
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 Xeon 6766E EPYC 8534PN EPYC 8534P Xeon 6780E EPYC 9654 Xeon Platinum 8490H 2P EPYC 9684X Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ 6 12 18 24 30 SE +/- 0.12, N = 9 SE +/- 0.06, N = 9 SE +/- 0.04, N = 3 SE +/- 0.13, N = 9 SE +/- 0.13, N = 9 SE +/- 0.15, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 7 SE +/- 0.20, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 4 SE +/- 0.16, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.29, N = 3 5.71 6.11 6.61 7.02 7.14 11.01 11.88 13.18 13.26 13.64 13.95 14.08 14.08 14.88 14.92 16.00 16.30 17.70 19.20 19.58 20.25 23.33
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X EPYC 9754 Xeon Max 9468 Xeon Max 9480 EPYC 9654 Xeon Platinum 8490H Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.0284 0.0568 0.0852 0.1136 0.142 0.015 0.018 0.018 0.019 0.019 0.025 0.027 0.027 0.030 0.043 0.057 0.067 0.068 0.068 0.068 0.076 0.080 0.080 0.080 0.088 0.114 0.126
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 199.11 / Avg: 604.22 / Max: 644.89 Min: 199.23 / Avg: 598.06 / Max: 629.15 Min: 78.85 / Avg: 540.82 / Max: 576.97 Min: 161.77 / Avg: 525.94 / Max: 589.73 Min: 63.41 / Avg: 457.61 / Max: 501.36 Min: 56.85 / Avg: 395.96 / Max: 433.04 Min: 102.28 / Avg: 349.96 / Max: 424.69 Min: 107.99 / Avg: 344.44 / Max: 394.7 Min: 105.8 / Avg: 329.47 / Max: 356.81 Min: 40.42 / Avg: 321.8 / Max: 358.12 Min: 76.6 / Avg: 288.21 / Max: 321.16 Min: 77.22 / Avg: 282.52 / Max: 309.36 Min: 59.27 / Avg: 266.18 / Max: 295.86 Min: 33.57 / Avg: 265.19 / Max: 292.3 Min: 34.62 / Avg: 245.31 / Max: 264.74 Min: 54.09 / Avg: 220.44 / Max: 241.42 Min: 27.5 / Avg: 205.23 / Max: 220.66 Min: 43.46 / Avg: 170.76 / Max: 186.26 Min: 21.41 / Avg: 165.14 / Max: 176.25 Min: 43.61 / Avg: 148.21 / Max: 158.39 Min: 20.38 / Avg: 115.97 / Max: 125.68 Min: 16.06 / Avg: 104.56 / Max: 112.26
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6766E Xeon Platinum 8490H Xeon Max 9468 Xeon 6780E Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9654 2P EPYC 9754 EPYC 9684X 2P EPYC 9654 EPYC 9684X 0.2909 0.5818 0.8727 1.1636 1.4545 SE +/- 0.030, N = 12 SE +/- 0.040, N = 12 SE +/- 0.038, N = 9 SE +/- 0.017, N = 9 SE +/- 0.009, N = 12 SE +/- 0.008, N = 12 SE +/- 0.007, N = 3 SE +/- 0.005, N = 12 SE +/- 0.005, N = 3 SE +/- 0.007, N = 3 SE +/- 0.007, N = 3 SE +/- 0.008, N = 12 SE +/- 0.006, N = 5 SE +/- 0.022, N = 9 SE +/- 0.001, N = 3 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 SE +/- 0.004, N = 12 SE +/- 0.001, N = 3 SE +/- 0.006, N = 12 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 1.293 1.149 1.098 1.027 0.815 0.775 0.622 0.589 0.581 0.572 0.572 0.559 0.542 0.525 0.414 0.384 0.329 0.293 0.292 0.289 0.278 0.251 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 16 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6766E 2P Xeon Platinum 8380 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 120 240 360 480 600 Min: 61.31 / Avg: 584.31 / Max: 698.79 Min: 199.74 / Avg: 578.23 / Max: 678.5 Min: 136.51 / Avg: 563.23 / Max: 663.44 Min: 163.81 / Avg: 544.97 / Max: 640.25 Min: 53.13 / Avg: 495.05 / Max: 595.37 Min: 70.21 / Avg: 487.56 / Max: 585.59 Min: 104.48 / Avg: 468.46 / Max: 563.8 Min: 40.49 / Avg: 404.84 / Max: 498.33 Min: 33.83 / Avg: 355.49 / Max: 410.22 Min: 78.53 / Avg: 316.32 / Max: 367.54 Min: 71.87 / Avg: 311.81 / Max: 377.7 Min: 56.77 / Avg: 302.76 / Max: 366.57 Min: 107.71 / Avg: 276.72 / Max: 373.07 Min: 31.51 / Avg: 271.55 / Max: 343.13 Min: 27.65 / Avg: 271.07 / Max: 317.83 Min: 21.35 / Avg: 253.4 / Max: 320.46 Min: 55.77 / Avg: 244.42 / Max: 350.99 Min: 54.25 / Avg: 239.92 / Max: 291.32 Min: 43.45 / Avg: 153.46 / Max: 193.17 Min: 18.63 / Avg: 138.72 / Max: 161.44 Min: 43.55 / Avg: 127.3 / Max: 157.98 Min: 15.23 / Avg: 121.21 / Max: 140.08
OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8380 Xeon Platinum 8490H Xeon 6766E Xeon Max 9468 Xeon 6780E Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X 900K 1800K 2700K 3600K 4500K SE +/- 18635.21, N = 12 SE +/- 30933.90, N = 12 SE +/- 36627.33, N = 9 SE +/- 16726.04, N = 9 SE +/- 13874.42, N = 12 SE +/- 13233.94, N = 12 SE +/- 17697.00, N = 3 SE +/- 13863.97, N = 12 SE +/- 13469.59, N = 3 SE +/- 20350.34, N = 3 SE +/- 20221.52, N = 3 SE +/- 24978.23, N = 12 SE +/- 19583.16, N = 5 SE +/- 74539.48, N = 9 SE +/- 4774.62, N = 3 SE +/- 11512.67, N = 3 SE +/- 13473.87, N = 3 SE +/- 15503.17, N = 3 SE +/- 41074.86, N = 12 SE +/- 71870.42, N = 12 SE +/- 39970.22, N = 3 SE +/- 27594.68, N = 3 778141 881881 920725 976035 1229649 1292122 1607424 1699046 1720762 1748146 1748658 1792636 1846080 1930006 2416375 2606500 3044620 3422492 3422731 3480909 3603261 3989358 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 Xeon 6766E Xeon Platinum 8380 Xeon 6780E EPYC 8534PN EPYC 8534P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9468 EPYC 9684X 2P EPYC 9684X Xeon Max 9480 EPYC 9754 Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9754 2P EPYC 9654 2P Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 40 80 120 160 200 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.48, N = 3 SE +/- 0.54, N = 3 SE +/- 0.14, N = 3 SE +/- 0.50, N = 3 SE +/- 1.39, N = 4 SE +/- 0.63, N = 3 SE +/- 2.00, N = 12 SE +/- 0.46, N = 3 SE +/- 0.58, N = 3 SE +/- 0.18, N = 3 SE +/- 0.57, N = 3 SE +/- 1.04, N = 12 SE +/- 0.66, N = 3 SE +/- 1.40, N = 3 SE +/- 0.03, N = 3 SE +/- 0.21, N = 3 SE +/- 1.57, N = 3 87.17 91.65 92.42 92.82 98.70 103.22 115.12 119.73 120.11 123.37 123.69 125.76 125.91 129.02 131.38 133.87 135.28 138.11 141.95 143.67 150.33 161.06
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 Xeon Max 9480 2P EPYC 9684X 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon 6766E 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6780E EPYC 9684X Xeon Platinum 8490H Xeon 6766E Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.1555 0.311 0.4665 0.622 0.7775 0.200 0.203 0.210 0.242 0.243 0.247 0.252 0.254 0.278 0.291 0.352 0.354 0.363 0.382 0.385 0.425 0.438 0.463 0.485 0.525 0.646 0.691
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X EPYC 9654 Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 196.92 / Avg: 674.95 / Max: 729.37 Min: 203.91 / Avg: 674.94 / Max: 716.61 Min: 163.23 / Avg: 663.98 / Max: 713.39 Min: 58.73 / Avg: 590.53 / Max: 641.68 Min: 84.37 / Avg: 540.26 / Max: 604.56 Min: 53.87 / Avg: 531.98 / Max: 578.15 Min: 100.88 / Avg: 496.59 / Max: 533.47 Min: 107.7 / Avg: 475.01 / Max: 547.45 Min: 43.33 / Avg: 451.33 / Max: 504.94 Min: 104.82 / Avg: 417.33 / Max: 477.08 Min: 77.09 / Avg: 340.59 / Max: 361.18 Min: 73.46 / Avg: 338.38 / Max: 359.94 Min: 59.06 / Avg: 338.33 / Max: 360.73 Min: 33.82 / Avg: 320.09 / Max: 348.64 Min: 29.3 / Avg: 284.71 / Max: 314.17 Min: 33.15 / Avg: 278.36 / Max: 312.29 Min: 54.97 / Avg: 260.49 / Max: 276.51 Min: 43.44 / Avg: 241.64 / Max: 277.25 Min: 20.95 / Avg: 239.33 / Max: 288.65 Min: 43.62 / Avg: 198.95 / Max: 223.14 Min: 18.72 / Avg: 152.81 / Max: 164.9 Min: 16.01 / Avg: 134.32 / Max: 142.38
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 Xeon Platinum 8380 Xeon Max 9468 Xeon 6766E EPYC 8534PN Xeon Max 9480 Xeon 6780E EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 9654 Xeon 6766E 2P EPYC 9684X Xeon Max 9480 2P Xeon 6780E 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 800K 1600K 2400K 3200K 4000K SE +/- 198.68, N = 3 SE +/- 165.80, N = 3 SE +/- 9.55, N = 3 SE +/- 136.07, N = 3 SE +/- 200.66, N = 3 SE +/- 23.84, N = 3 SE +/- 126.84, N = 3 SE +/- 92.46, N = 3 SE +/- 92.62, N = 3 SE +/- 40228.60, N = 3 SE +/- 355.69, N = 3 SE +/- 149.48, N = 3 SE +/- 37.76, N = 3 SE +/- 1576.96, N = 3 SE +/- 277.84, N = 3 SE +/- 205.33, N = 3 SE +/- 444.74, N = 3 SE +/- 862.96, N = 3 SE +/- 6745.42, N = 3 SE +/- 5.26, N = 3 SE +/- 6125.37, N = 3 SE +/- 2222.55, N = 3 587354.8 697707.2 743282.7 810291.8 813667.6 826049.5 881480.8 974189.9 1036735.6 1099481.5 1395446.4 1436324.9 1479879.0 1613828.7 1627941.4 1644363.7 1872096.1 1916162.9 2057021.6 2861959.8 3214376.3 3729470.8 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
verify/s Per Watt
OpenBenchmarking.org verify/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: RSA4096 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6780E Xeon 6766E 2P EPYC 9684X 2P EPYC 9684X Xeon 6766E EPYC 9654 2P EPYC 9654 EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 8534PN 1400 2800 4200 5600 7000 2079.56 2215.41 2215.62 2306.66 2430.79 2489.80 2791.77 2907.57 2997.55 3030.66 3600.28 3735.68 4004.98 4099.33 4121.23 4295.14 4728.28 4919.81 5691.68 5696.67 5836.73 6595.71
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P EPYC 9754 2P Xeon Max 9468 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9480 EPYC 9754 Xeon Max 9468 EPYC 9654 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 64.61 / Avg: 784.12 / Max: 822.1 Min: 165.7 / Avg: 686.36 / Max: 737.53 Min: 70.64 / Avg: 686.24 / Max: 753.6 Min: 199.02 / Avg: 669.72 / Max: 754.93 Min: 43.66 / Avg: 654.68 / Max: 716.5 Min: 198.5 / Avg: 629.88 / Max: 694.83 Min: 59.69 / Avg: 605.29 / Max: 659.72 Min: 99.67 / Avg: 528.71 / Max: 581.74 Min: 107.48 / Avg: 456.73 / Max: 473.49 Min: 32.96 / Avg: 391.59 / Max: 411.04 Min: 104.34 / Avg: 369.51 / Max: 384.07 Min: 32.63 / Avg: 342.08 / Max: 377.97 Min: 56.91 / Avg: 335.05 / Max: 351.44 Min: 74.71 / Avg: 326.8 / Max: 367.81 Min: 19.93 / Avg: 320.74 / Max: 351.44 Min: 73.89 / Avg: 302.47 / Max: 335.7 Min: 27.6 / Avg: 291.95 / Max: 323.61 Min: 52.16 / Avg: 265.1 / Max: 290.58 Min: 43.31 / Avg: 221.12 / Max: 231.86 Min: 43.61 / Avg: 173.05 / Max: 179.47 Min: 15.75 / Avg: 154.87 / Max: 162.9 Min: 16.2 / Avg: 122.85 / Max: 135.57
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.3 Algorithm: RSA4096 Xeon 6766E Xeon 6780E Xeon Platinum 8380 EPYC 8534PN Xeon 6766E 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 20K 40K 60K 80K 100K SE +/- 1.37, N = 3 SE +/- 1.63, N = 3 SE +/- 40.37, N = 3 SE +/- 12.56, N = 3 SE +/- 8.25, N = 3 SE +/- 19.45, N = 3 SE +/- 8.20, N = 3 SE +/- 20.13, N = 3 SE +/- 22.17, N = 3 SE +/- 9.84, N = 3 SE +/- 15.15, N = 3 SE +/- 29.11, N = 3 SE +/- 108.70, N = 3 SE +/- 6.92, N = 3 SE +/- 83.09, N = 3 SE +/- 98.71, N = 3 SE +/- 27.42, N = 3 SE +/- 14.34, N = 3 SE +/- 56.68, N = 3 SE +/- 81.38, N = 3 SE +/- 247.60, N = 3 SE +/- 80.37, N = 3 11348.5 12610.8 18389.3 21047.5 22587.4 22861.0 25098.0 25441.5 25894.6 27431.1 31594.4 35964.9 36371.6 45531.0 48534.8 48996.8 53966.9 54601.1 61499.6 71942.0 98237.0 107830.6 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Timed Linux Kernel Compilation This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: allmodconfig Xeon Platinum 8380 EPYC 8534PN Xeon Max 9468 EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P EPYC 9754 Xeon Platinum 8592+ EPYC 9654 EPYC 9684X Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9754 2P EPYC 9654 2P Xeon 6766E 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon 6780E 2P 130 260 390 520 650 SE +/- 0.35, N = 3 SE +/- 0.78, N = 3 SE +/- 0.61, N = 3 SE +/- 0.91, N = 3 SE +/- 0.67, N = 3 SE +/- 0.80, N = 3 SE +/- 0.92, N = 3 SE +/- 1.05, N = 3 SE +/- 0.72, N = 3 SE +/- 0.49, N = 3 SE +/- 0.37, N = 3 SE +/- 0.76, N = 3 SE +/- 0.67, N = 3 SE +/- 0.56, N = 3 SE +/- 0.73, N = 3 SE +/- 0.86, N = 3 SE +/- 1.31, N = 3 SE +/- 0.49, N = 3 SE +/- 0.81, N = 3 SE +/- 0.56, N = 3 SE +/- 0.98, N = 3 SE +/- 0.90, N = 3 612.78 438.17 428.39 406.41 384.06 362.45 356.99 337.69 316.90 311.83 290.34 274.86 251.20 246.94 231.03 218.57 210.20 197.63 192.10 189.74 182.00 174.27
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Linux Kernel Compilation 6.8 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 150 300 450 600 750 Min: 200.9 / Avg: 639.43 / Max: 753.88 Min: 185.35 / Avg: 634.18 / Max: 755.16 Min: 63.59 / Avg: 621.64 / Max: 829.42 Min: 162.47 / Avg: 610.89 / Max: 756.51 Min: 85.15 / Avg: 585.62 / Max: 755.31 Min: 54.45 / Avg: 525.29 / Max: 678.52 Min: 99.55 / Avg: 491.75 / Max: 583.83 Min: 40.54 / Avg: 484.57 / Max: 689.98 Min: 106.41 / Avg: 416.56 / Max: 664.2 Min: 34.02 / Avg: 348.42 / Max: 413.49 Min: 104.5 / Avg: 339.12 / Max: 521.39 Min: 70.17 / Avg: 330.93 / Max: 375.87 Min: 81.1 / Avg: 330.36 / Max: 377.46 Min: 56.91 / Avg: 323.36 / Max: 378.1 Min: 25.82 / Avg: 317.64 / Max: 378.37 Min: 27.23 / Avg: 282.28 / Max: 331.17 Min: 19.75 / Avg: 262.8 / Max: 335.9 Min: 50.2 / Avg: 256.23 / Max: 291.69 Min: 43.47 / Avg: 255.14 / Max: 329.17 Min: 43.57 / Avg: 201.59 / Max: 252.67 Min: 16.91 / Avg: 150.79 / Max: 171.19 Min: 16.08 / Avg: 129.6 / Max: 144.82
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 1024 CPU threads. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9754 EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 90M 180M 270M 360M 450M SE +/- 1466028.98, N = 9 SE +/- 1751369.24, N = 12 SE +/- 629927.17, N = 3 SE +/- 2147688.02, N = 12 SE +/- 1304590.97, N = 3 SE +/- 2397455.91, N = 12 SE +/- 1325249.25, N = 3 SE +/- 2966712.90, N = 9 SE +/- 3565305.92, N = 15 SE +/- 1441726.26, N = 3 SE +/- 4344961.90, N = 10 SE +/- 2925715.37, N = 11 SE +/- 2148606.38, N = 4 SE +/- 4652276.19, N = 12 SE +/- 3170744.86, N = 15 SE +/- 2268830.04, N = 3 SE +/- 2482737.87, N = 3 SE +/- 2692064.58, N = 4 SE +/- 3095674.84, N = 3 SE +/- 7961094.38, N = 12 SE +/- 2356843.91, N = 3 SE +/- 919073.22, N = 3 51099545 68019088 73592230 90658156 96887479 99198144 104597200 109766345 122794246 125194066 137977203 149409082 187761769 189763799 197708350 214524659 222610378 235445499 266919825 301202232 370751530 399124223 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver
Nodes Per Second Per Watt
OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better Stockfish 16.1 Chess Benchmark Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon 6780E Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6766E EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 8534P EPYC 9654 EPYC 9754 EPYC 8534PN 130K 260K 390K 520K 650K 193986.52 199243.06 201379.09 202981.45 215737.78 219573.26 276776.39 285328.34 325017.74 331127.60 403742.35 431231.39 470216.10 496138.40 509643.71 520707.98 540060.41 555213.84 568916.36 569277.48 571475.98 621037.11
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Stockfish 16.1 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 70.77 / Avg: 766.5 / Max: 822.06 Min: 57.4 / Avg: 686.5 / Max: 751.79 Min: 195.85 / Avg: 680.45 / Max: 758.53 Min: 203.83 / Avg: 679.75 / Max: 756.48 Min: 166.29 / Avg: 678.39 / Max: 758.17 Min: 78.55 / Avg: 672.28 / Max: 755.5 Min: 37.25 / Avg: 640.56 / Max: 735.74 Min: 109.43 / Avg: 618.97 / Max: 701.47 Min: 100.78 / Avg: 519.4 / Max: 581.59 Min: 105.79 / Avg: 474.56 / Max: 541.15 Min: 35.5 / Avg: 386.38 / Max: 410.66 Min: 30.05 / Avg: 347.3 / Max: 373.1 Min: 71.31 / Avg: 341.39 / Max: 379.06 Min: 74.29 / Avg: 341.12 / Max: 366.15 Min: 56.83 / Avg: 339.56 / Max: 379.91 Min: 22.35 / Avg: 337.72 / Max: 370.84 Min: 21.51 / Avg: 332.06 / Max: 363.69 Min: 43.61 / Avg: 310.08 / Max: 337.09 Min: 53.05 / Avg: 263.42 / Max: 290.77 Min: 43.78 / Avg: 240.94 / Max: 270.17 Min: 17.26 / Avg: 174.36 / Max: 184.62 Min: 16.19 / Avg: 145.98 / Max: 155.71
Apache IoTDB Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 Xeon 6766E 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon 6766E Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon 6780E Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9684X 2P EPYC 9654 2P EPYC 9754 EPYC 9654 EPYC 9684X 20 40 60 80 100 SE +/- 1.37, N = 3 SE +/- 0.53, N = 3 SE +/- 0.65, N = 3 SE +/- 0.43, N = 3 SE +/- 1.11, N = 4 SE +/- 1.01, N = 3 SE +/- 1.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.48, N = 3 SE +/- 0.87, N = 3 SE +/- 0.15, N = 3 SE +/- 0.15, N = 3 SE +/- 0.80, N = 7 SE +/- 0.68, N = 3 SE +/- 0.79, N = 12 SE +/- 0.31, N = 3 SE +/- 0.03, N = 3 SE +/- 0.59, N = 12 SE +/- 0.65, N = 12 SE +/- 0.10, N = 3 SE +/- 0.31, N = 3 SE +/- 0.23, N = 3 107.28 102.67 101.49 100.29 95.39 94.84 92.23 90.31 90.02 89.53 85.16 84.59 82.73 81.73 66.54 65.66 64.93 61.46 61.07 58.11 53.77 52.93
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Apache IoTDB 1.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 120 240 360 480 600 Min: 218.55 / Avg: 495.29 / Max: 662.8 Min: 212.09 / Avg: 494.07 / Max: 662.92 Min: 171.93 / Avg: 425.12 / Max: 596.94 Min: 77 / Avg: 337.01 / Max: 603.62 Min: 106.1 / Avg: 305.48 / Max: 479.29 Min: 74.41 / Avg: 298.36 / Max: 505.37 Min: 56.18 / Avg: 264.94 / Max: 455.88 Min: 86.91 / Avg: 254.04 / Max: 360.99 Min: 72.55 / Avg: 249.87 / Max: 361.66 Min: 41.52 / Avg: 220.99 / Max: 367.41 Min: 60.93 / Avg: 216.73 / Max: 347.32 Min: 60.48 / Avg: 192.21 / Max: 328.62 Min: 104.7 / Avg: 186.81 / Max: 319.27 Min: 55.72 / Avg: 176.97 / Max: 287.98 Min: 33.72 / Avg: 171.59 / Max: 347.45 Min: 34.95 / Avg: 157 / Max: 310.81 Min: 25.56 / Avg: 138.03 / Max: 271.74 Min: 21.8 / Avg: 110.92 / Max: 210.79 Min: 43.43 / Avg: 87.52 / Max: 193.65 Min: 17.66 / Avg: 82.51 / Max: 146.09 Min: 33.17 / Avg: 80.98 / Max: 175.95 Min: 16.39 / Avg: 76.32 / Max: 126.8
OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 800 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 100 Xeon 6766E 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon 6766E Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon 6780E Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9684X 2P EPYC 9654 2P EPYC 9754 EPYC 9654 EPYC 9684X 30M 60M 90M 120M 150M SE +/- 769517.20, N = 3 SE +/- 365828.34, N = 3 SE +/- 207721.96, N = 3 SE +/- 306106.55, N = 3 SE +/- 872659.60, N = 4 SE +/- 594234.55, N = 3 SE +/- 928557.10, N = 3 SE +/- 84917.07, N = 3 SE +/- 435900.66, N = 3 SE +/- 782176.98, N = 3 SE +/- 276414.35, N = 3 SE +/- 174748.00, N = 3 SE +/- 862582.24, N = 7 SE +/- 739343.51, N = 3 SE +/- 1225528.40, N = 12 SE +/- 576868.09, N = 3 SE +/- 41021.96, N = 3 SE +/- 1058559.19, N = 12 SE +/- 1249999.63, N = 12 SE +/- 263772.09, N = 3 SE +/- 665173.47, N = 3 SE +/- 538692.55, N = 3 71664005 75178480 75740139 76729495 80139566 80770465 83651785 85117897 85744542 86354518 90871770 90973414 92771639 94616807 115317834 116879799 117884977 124947288 125595607 131781309 142102254 144760448
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN Xeon 6780E EPYC 9684X EPYC 9654 Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 6 12 18 24 30 SE +/- 0.11, N = 9 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.13, N = 9 SE +/- 0.14, N = 9 SE +/- 0.02, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.18, N = 7 SE +/- 0.18, N = 7 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 5.75 6.33 6.65 7.07 7.20 10.91 11.74 13.28 13.28 13.61 13.95 14.05 14.59 14.74 14.76 16.17 16.68 17.55 19.29 19.47 20.46 23.41
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9480 EPYC 9754 EPYC 9654 Xeon Max 9468 Xeon Platinum 8490H Xeon 6766E Xeon Platinum 8380 Xeon 6780E Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.0286 0.0572 0.0858 0.1144 0.143 0.016 0.018 0.018 0.018 0.019 0.024 0.028 0.029 0.030 0.042 0.057 0.066 0.066 0.068 0.069 0.077 0.079 0.080 0.080 0.088 0.114 0.127
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 191.23 / Avg: 602.51 / Max: 639.79 Min: 204.68 / Avg: 599.73 / Max: 629.45 Min: 83.37 / Avg: 541.35 / Max: 576.05 Min: 167.37 / Avg: 511.16 / Max: 589.71 Min: 66.98 / Avg: 454.4 / Max: 498.76 Min: 57.69 / Avg: 396.9 / Max: 434.4 Min: 108.01 / Avg: 376.47 / Max: 395.86 Min: 96.51 / Avg: 349.52 / Max: 424.02 Min: 104.97 / Avg: 340.5 / Max: 358.58 Min: 40.81 / Avg: 321.68 / Max: 356.16 Min: 70.87 / Avg: 291.39 / Max: 322.93 Min: 74.15 / Avg: 282.4 / Max: 310.35 Min: 60.34 / Avg: 265.81 / Max: 296.61 Min: 33.85 / Avg: 264.62 / Max: 291.43 Min: 35.28 / Avg: 245.06 / Max: 264.04 Min: 55.66 / Avg: 220.18 / Max: 241.46 Min: 29.11 / Avg: 205.3 / Max: 221.54 Min: 43.48 / Avg: 170.8 / Max: 185.92 Min: 22.02 / Avg: 164.54 / Max: 175.34 Min: 43.61 / Avg: 148.25 / Max: 158.74 Min: 20.79 / Avg: 116.41 / Max: 125.98 Min: 17.18 / Avg: 104.85 / Max: 112.82
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P EPYC 9654 EPYC 9684X Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 9 SE +/- 0.15, N = 9 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.17, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 SE +/- 0.21, N = 3 SE +/- 0.15, N = 12 SE +/- 0.05, N = 3 SE +/- 0.19, N = 5 SE +/- 0.17, N = 12 SE +/- 0.18, N = 3 SE +/- 0.34, N = 3 5.79 6.15 6.59 7.04 7.08 10.88 11.95 13.00 13.15 13.19 13.84 13.89 14.03 14.96 15.11 15.84 16.25 17.73 19.01 19.24 20.13 23.49
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9480 EPYC 9754 Xeon Max 9468 EPYC 9654 Xeon Platinum 8490H Xeon 6780E Xeon Platinum 8380 Xeon 6766E Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.0284 0.0568 0.0852 0.1136 0.142 0.016 0.018 0.018 0.018 0.019 0.025 0.027 0.027 0.030 0.043 0.057 0.066 0.066 0.067 0.068 0.076 0.076 0.080 0.081 0.089 0.114 0.126
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 193.13 / Avg: 605.19 / Max: 641.47 Min: 211.71 / Avg: 595.73 / Max: 626.88 Min: 76.4 / Avg: 541.7 / Max: 581.39 Min: 161.59 / Avg: 520.21 / Max: 588.55 Min: 64.18 / Avg: 455.72 / Max: 501.58 Min: 39.14 / Avg: 396.83 / Max: 432.36 Min: 107.82 / Avg: 374.58 / Max: 394.46 Min: 100.57 / Avg: 349.16 / Max: 423.16 Min: 104.9 / Avg: 330.33 / Max: 356.82 Min: 40.59 / Avg: 320.17 / Max: 358.77 Min: 77.61 / Avg: 291.69 / Max: 322.84 Min: 73.58 / Avg: 282.03 / Max: 308.67 Min: 59.17 / Avg: 265.52 / Max: 295.66 Min: 34.31 / Avg: 264.8 / Max: 291.45 Min: 32.56 / Avg: 244.28 / Max: 263 Min: 55.98 / Avg: 220.28 / Max: 241.66 Min: 26.78 / Avg: 205 / Max: 221.09 Min: 43.44 / Avg: 170.28 / Max: 183.58 Min: 21.08 / Avg: 164.98 / Max: 175.44 Min: 43.61 / Avg: 148.31 / Max: 158.76 Min: 17.98 / Avg: 115.9 / Max: 125.2 Min: 15.84 / Avg: 103.98 / Max: 111.57
SecureMark SecureMark is an objective, standardized benchmarking framework for measuring the efficiency of cryptographic processing solutions developed by EEMBC. SecureMark-TLS is benchmarking Transport Layer Security performance with a focus on IoT/edge computing. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Xeon 6766E Xeon 6766E 2P Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 8534P EPYC 8534PN EPYC 9754 EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Max 9468 EPYC 9654 EPYC 9654 2P EPYC 9684X EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 70K 140K 210K 280K 350K SE +/- 553.57, N = 3 SE +/- 722.69, N = 3 SE +/- 1219.44, N = 3 SE +/- 406.59, N = 3 SE +/- 285.52, N = 3 SE +/- 372.88, N = 3 SE +/- 372.96, N = 3 SE +/- 542.88, N = 3 SE +/- 457.42, N = 3 SE +/- 553.62, N = 3 SE +/- 330.95, N = 3 SE +/- 625.56, N = 3 SE +/- 670.43, N = 3 SE +/- 196.24, N = 3 SE +/- 384.08, N = 3 SE +/- 256.85, N = 3 SE +/- 361.20, N = 3 SE +/- 389.81, N = 3 SE +/- 415.71, N = 3 SE +/- 809.90, N = 3 SE +/- 411.11, N = 3 SE +/- 209.97, N = 3 196740 197298 217536 220051 231076 231357 250024 250162 250695 251075 275472 277205 277260 277298 277589 277647 298341 299610 300833 301740 308434 309896 1. (CC) gcc options: -pedantic -O3
marks Per Watt
OpenBenchmarking.org marks Per Watt, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 EPYC 9684X Xeon Platinum 8490H EPYC 9654 EPYC 9754 Xeon Platinum 8592+ Xeon 6766E EPYC 8534P EPYC 8534PN Xeon 6780E 1100 2200 3300 4400 5500 973.55 986.37 1152.38 1185.32 1197.70 1242.56 1272.88 1278.59 1847.99 2010.97 2198.71 2308.76 2364.52 2686.16 3029.20 3034.03 3204.23 3643.38 4501.16 4697.25 4781.86 4990.15
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SecureMark 1.0.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8490H 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 60 120 180 240 300 Min: 124.02 / Avg: 284.83 / Max: 338.05 Min: 137.33 / Avg: 281.43 / Max: 342.59 Min: 60.77 / Avg: 261.84 / Max: 267.2 Min: 78.38 / Avg: 248.23 / Max: 290.1 Min: 56.74 / Avg: 235.38 / Max: 240.55 Min: 171.99 / Avg: 232.4 / Max: 318.93 Min: 41.92 / Avg: 196.37 / Max: 200.73 Min: 97.89 / Avg: 192.93 / Max: 216.11 Min: 85.74 / Avg: 126.1 / Max: 134.53 Min: 74.22 / Avg: 120.26 / Max: 126.65 Min: 31.06 / Avg: 111.99 / Max: 116.51 Min: 106.5 / Avg: 108.17 / Max: 111.72 Min: 103.87 / Avg: 106.76 / Max: 110.05 Min: 28.33 / Avg: 98.33 / Max: 101.2 Min: 49.93 / Avg: 97.85 / Max: 101.93 Min: 53.54 / Avg: 91.51 / Max: 104.77 Min: 33.51 / Avg: 85.06 / Max: 96.45 Min: 18.81 / Avg: 78.24 / Max: 81.48 Min: 16.16 / Avg: 53.23 / Max: 56.82 Min: 14.73 / Avg: 52.31 / Max: 55.82 Min: 43.33 / Avg: 44.1 / Max: 46.18 Min: 43.5 / Avg: 43.71 / Max: 45.5
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 8534PN Xeon 6780E 2P EPYC 8534P Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 9754 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9754 Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X 130 260 390 520 650 SE +/- 1.27, N = 3 SE +/- 1.59, N = 3 SE +/- 5.23, N = 3 SE +/- 3.52, N = 3 SE +/- 1.77, N = 3 SE +/- 4.79, N = 3 SE +/- 2.14, N = 3 SE +/- 1.22, N = 3 SE +/- 6.21, N = 5 SE +/- 5.39, N = 5 SE +/- 3.62, N = 6 SE +/- 3.32, N = 3 SE +/- 6.03, N = 3 SE +/- 3.54, N = 12 SE +/- 3.60, N = 3 SE +/- 3.45, N = 3 SE +/- 3.08, N = 3 SE +/- 2.55, N = 3 SE +/- 10.00, N = 3 SE +/- 2.03, N = 3 SE +/- 4.03, N = 3 SE +/- 4.34, N = 3 295.06 320.87 335.46 337.75 338.84 342.99 379.92 400.52 427.95 438.60 458.23 458.96 470.02 471.79 476.91 481.66 501.07 501.63 525.23 526.36 559.55 595.19
Queries Per Minute, Geo Mean Per Watt
OpenBenchmarking.org Queries Per Minute, Geo Mean Per Watt, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 8534P EPYC 9754 EPYC 8534PN Xeon 6780E Xeon 6766E 1.1063 2.2126 3.3189 4.4252 5.5315 1.012 1.043 1.068 1.265 1.289 1.676 1.857 1.870 1.966 1.967 1.974 2.038 2.049 2.341 2.599 3.709 4.053 4.085 4.182 4.366 4.737 4.917
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ClickHouse 22.12.3.5 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 130 260 390 520 650 Min: 199.78 / Avg: 469.37 / Max: 713.86 Min: 199.33 / Avg: 466.07 / Max: 698.95 Min: 157.92 / Avg: 396.39 / Max: 673.71 Min: 77.74 / Avg: 340.3 / Max: 642.4 Min: 64.74 / Avg: 314 / Max: 643.44 Min: 101.69 / Avg: 282.88 / Max: 572.19 Min: 54.72 / Avg: 280.91 / Max: 531.55 Min: 77.89 / Avg: 241.61 / Max: 372.85 Min: 70.28 / Avg: 238.9 / Max: 367.38 Min: 40.81 / Avg: 230.4 / Max: 456.57 Min: 52.84 / Avg: 205.71 / Max: 375.59 Min: 26.54 / Avg: 176.29 / Max: 377.99 Min: 52.36 / Avg: 174.43 / Max: 288.3 Min: 107.74 / Avg: 164.81 / Max: 404.79 Min: 29.83 / Avg: 160.48 / Max: 343.21 Min: 62.49 / Avg: 157.43 / Max: 363.95 Min: 28.3 / Avg: 138.04 / Max: 305.03 Min: 20.77 / Avg: 109.76 / Max: 265.96 Min: 43.42 / Avg: 84.55 / Max: 263.64 Min: 18.06 / Avg: 82.96 / Max: 166.09 Min: 43.57 / Avg: 77.27 / Max: 231.46 Min: 15.83 / Avg: 76.83 / Max: 137.9
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 8534P EPYC 8534PN Xeon 6780E 2P Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9754 Xeon Platinum 8592+ Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9654 EPYC 9684X 130 260 390 520 650 SE +/- 3.61, N = 3 SE +/- 1.53, N = 3 SE +/- 2.99, N = 3 SE +/- 5.72, N = 3 SE +/- 3.25, N = 3 SE +/- 0.73, N = 3 SE +/- 3.34, N = 3 SE +/- 2.12, N = 3 SE +/- 4.85, N = 5 SE +/- 3.10, N = 5 SE +/- 9.26, N = 3 SE +/- 2.86, N = 6 SE +/- 1.94, N = 3 SE +/- 3.17, N = 12 SE +/- 4.95, N = 3 SE +/- 2.93, N = 3 SE +/- 0.19, N = 3 SE +/- 3.26, N = 3 SE +/- 6.78, N = 3 SE +/- 8.37, N = 3 SE +/- 3.14, N = 3 SE +/- 0.42, N = 3 295.43 320.17 337.32 337.44 339.50 339.67 381.05 403.96 420.35 443.58 450.12 455.79 465.06 467.96 474.68 486.05 499.18 507.56 528.21 529.80 562.50 597.73
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9754 Xeon Platinum 8592+ Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X 120 240 360 480 600 SE +/- 1.56, N = 3 SE +/- 1.51, N = 3 SE +/- 1.88, N = 3 SE +/- 1.57, N = 3 SE +/- 1.56, N = 3 SE +/- 3.71, N = 3 SE +/- 2.21, N = 3 SE +/- 1.12, N = 3 SE +/- 4.49, N = 5 SE +/- 4.12, N = 5 SE +/- 2.78, N = 3 SE +/- 4.18, N = 6 SE +/- 2.85, N = 3 SE +/- 3.85, N = 12 SE +/- 5.88, N = 3 SE +/- 3.41, N = 3 SE +/- 4.37, N = 3 SE +/- 1.35, N = 3 SE +/- 6.05, N = 3 SE +/- 4.34, N = 3 SE +/- 5.33, N = 3 SE +/- 7.88, N = 3 285.17 311.63 322.69 323.59 326.65 333.06 365.62 388.29 411.26 423.30 433.79 437.20 446.40 460.66 461.62 465.50 485.63 491.89 504.84 513.92 536.82 566.31
Apache IoTDB Apache IotDB is a time series database and this benchmark is facilitated using the IoT Benchmaark [https://github.com/thulab/iot-benchmark/]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Average Latency, Fewer Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon 6766E Xeon Max 9480 Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9684X 2P EPYC 9654 2P EPYC 9754 EPYC 9654 EPYC 9684X 80 160 240 320 400 SE +/- 3.93, N = 12 SE +/- 5.20, N = 3 SE +/- 3.47, N = 3 SE +/- 2.59, N = 12 SE +/- 4.06, N = 3 SE +/- 3.74, N = 12 SE +/- 3.79, N = 8 SE +/- 5.15, N = 3 SE +/- 1.12, N = 3 SE +/- 5.07, N = 3 SE +/- 4.45, N = 3 SE +/- 2.20, N = 3 SE +/- 3.40, N = 12 SE +/- 3.41, N = 3 SE +/- 2.16, N = 15 SE +/- 0.38, N = 3 SE +/- 0.82, N = 3 SE +/- 1.87, N = 3 SE +/- 3.49, N = 3 SE +/- 1.41, N = 3 SE +/- 1.96, N = 3 SE +/- 1.71, N = 3 380.33 377.58 349.42 328.41 326.53 325.97 317.36 314.44 312.32 309.03 296.36 294.33 286.78 280.26 253.13 251.47 251.05 246.08 240.43 227.40 211.85 209.68
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Apache IoTDB 1.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 204.98 / Avg: 492.49 / Max: 690.42 Min: 207 / Avg: 485.64 / Max: 662.26 Min: 174.02 / Avg: 422.43 / Max: 631.3 Min: 76.05 / Avg: 329.73 / Max: 605.38 Min: 105.33 / Avg: 293.48 / Max: 476.12 Min: 68.46 / Avg: 291.76 / Max: 496.27 Min: 52.66 / Avg: 254.51 / Max: 448.61 Min: 74.42 / Avg: 245.7 / Max: 359.89 Min: 75.58 / Avg: 242.09 / Max: 358.23 Min: 43.37 / Avg: 215.97 / Max: 369.95 Min: 58.74 / Avg: 204.83 / Max: 345.97 Min: 95.98 / Avg: 192.34 / Max: 351.09 Min: 61.74 / Avg: 182.78 / Max: 332.16 Min: 51.86 / Avg: 163.52 / Max: 286.64 Min: 33.32 / Avg: 159.48 / Max: 348.24 Min: 35.8 / Avg: 141.12 / Max: 306.16 Min: 30.38 / Avg: 122.12 / Max: 263.01 Min: 21.99 / Avg: 100.77 / Max: 212.81 Min: 43.44 / Avg: 82.74 / Max: 200.76 Min: 43.59 / Avg: 76.38 / Max: 156.34 Min: 15.92 / Avg: 72.92 / Max: 146.34 Min: 17.44 / Avg: 68.28 / Max: 132.65
OpenBenchmarking.org point/sec, More Is Better Apache IoTDB 1.2 Device Count: 500 - Batch Size Per Write: 100 - Sensor Count: 800 - Client Number: 400 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon 6766E Xeon Max 9468 Xeon Max 9480 Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9754 2P EPYC 8534PN EPYC 8534P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 EPYC 9654 EPYC 9684X 30M 60M 90M 120M 150M SE +/- 531367.14, N = 12 SE +/- 796440.21, N = 3 SE +/- 661234.22, N = 3 SE +/- 565297.90, N = 12 SE +/- 574699.97, N = 12 SE +/- 88241.50, N = 3 SE +/- 692701.79, N = 8 SE +/- 111181.55, N = 3 SE +/- 662950.65, N = 3 SE +/- 1037167.36, N = 3 SE +/- 441557.52, N = 3 SE +/- 308756.34, N = 3 SE +/- 761276.42, N = 12 SE +/- 746822.47, N = 3 SE +/- 666882.79, N = 15 SE +/- 412757.79, N = 3 SE +/- 13050.78, N = 3 SE +/- 353097.82, N = 3 SE +/- 1152766.29, N = 3 SE +/- 68559.13, N = 3 SE +/- 255887.16, N = 3 SE +/- 371659.60, N = 3 67599793 68320800 74653007 77501248 78057728 78823112 80169620 81900477 82455664 83475645 87190397 87797206 89231850 92709751 103630483 105138551 105432862 106778379 108821580 116685326 125562060 126161028
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Chrysler Neon 1M Xeon Platinum 8380 EPYC 8534PN EPYC 8534P EPYC 9754 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P EPYC 9654 Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X EPYC 9684X 2P 70 140 210 280 350 SE +/- 0.13, N = 3 SE +/- 0.50, N = 3 SE +/- 0.47, N = 3 SE +/- 1.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 SE +/- 0.15, N = 3 SE +/- 0.78, N = 3 SE +/- 1.51, N = 8 SE +/- 0.20, N = 3 SE +/- 0.13, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 1.00, N = 10 SE +/- 0.14, N = 3 SE +/- 0.71, N = 12 SE +/- 0.49, N = 3 SE +/- 0.46, N = 3 343.16 300.69 297.25 231.96 228.74 212.99 207.20 185.03 176.14 157.56 125.15 117.91 115.89 93.99 86.93 77.64 77.32 49.55
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2023.09.15 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon Platinum 8380 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 197.55 / Avg: 624.98 / Max: 753.94 Min: 213.51 / Avg: 619.95 / Max: 751.65 Min: 168.54 / Avg: 600.33 / Max: 753.81 Min: 82.45 / Avg: 561.7 / Max: 752.76 Min: 68.17 / Avg: 526.7 / Max: 819.28 Min: 59.6 / Avg: 495.69 / Max: 689.03 Min: 105.1 / Avg: 469.12 / Max: 579.49 Min: 42.16 / Avg: 450.48 / Max: 658.58 Min: 83.35 / Avg: 329.11 / Max: 376.3 Min: 72.8 / Avg: 328.51 / Max: 377.04 Min: 59.23 / Avg: 321.19 / Max: 377.05 Min: 33.32 / Avg: 313.77 / Max: 375.72 Min: 33.17 / Avg: 309.02 / Max: 409.54 Min: 28.56 / Avg: 270.92 / Max: 332.67 Min: 52.15 / Avg: 250.92 / Max: 289.23 Min: 21.25 / Avg: 249.04 / Max: 321.21 Min: 18.8 / Avg: 143.22 / Max: 157.87 Min: 17.52 / Avg: 128.33 / Max: 140.79
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms Xeon 6766E Xeon 6780E Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8380 Xeon Platinum 8592+ Xeon Max 9468 EPYC 8534PN Xeon Max 9480 EPYC 8534P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9754 EPYC 9684X EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 2 4 6 8 10 SE +/- 0.00423, N = 3 SE +/- 0.00540, N = 3 SE +/- 0.03216, N = 9 SE +/- 0.04439, N = 8 SE +/- 0.01396, N = 15 SE +/- 0.04403, N = 15 SE +/- 0.00653, N = 3 SE +/- 0.02648, N = 15 SE +/- 0.05087, N = 15 SE +/- 0.00540, N = 3 SE +/- 0.05862, N = 15 SE +/- 0.00440, N = 3 SE +/- 0.00911, N = 3 SE +/- 0.05463, N = 15 SE +/- 0.05644, N = 12 SE +/- 0.08185, N = 13 SE +/- 0.00537, N = 3 SE +/- 0.00847, N = 3 SE +/- 0.00206, N = 3 SE +/- 0.02927, N = 3 SE +/- 0.00332, N = 3 SE +/- 0.01739, N = 3 0.52357 0.56717 0.57694 0.70757 1.05274 1.10900 1.11056 1.43787 1.45223 1.46163 1.50214 1.51901 1.61232 1.76778 1.88679 2.25422 2.87877 2.88869 3.41085 5.27839 5.83606 6.38343
ns/day Per Watt
OpenBenchmarking.org ns/day Per Watt, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms Xeon Platinum 8490H 2P Xeon 6780E 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6766E 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 8534P EPYC 8534PN EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 0.0052 0.0104 0.0156 0.0208 0.026 0.002 0.002 0.003 0.003 0.003 0.004 0.004 0.004 0.004 0.004 0.005 0.005 0.005 0.006 0.012 0.012 0.012 0.013 0.014 0.018 0.019 0.023
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAMD 3.0b6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon Max 9480 EPYC 9654 2P Xeon Max 9468 EPYC 9684X Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8592+ EPYC 9754 2P Xeon 6766E 2P EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 140 280 420 560 700 Min: 194.25 / Avg: 565.07 / Max: 686.05 Min: 192.28 / Avg: 560.13 / Max: 714.79 Min: 163.14 / Avg: 552.42 / Max: 653.46 Min: 73.13 / Avg: 510.74 / Max: 686.96 Min: 103.57 / Avg: 411.33 / Max: 527.15 Min: 65.49 / Avg: 343.59 / Max: 811.63 Min: 72.24 / Avg: 295.54 / Max: 371.41 Min: 57.51 / Avg: 289.28 / Max: 672.46 Min: 71.79 / Avg: 281.33 / Max: 364.12 Min: 32.28 / Avg: 274.76 / Max: 406.72 Min: 55.23 / Avg: 273.91 / Max: 344.33 Min: 62.83 / Avg: 273.53 / Max: 463.21 Min: 33.09 / Avg: 260.62 / Max: 349.3 Min: 42.36 / Avg: 249.94 / Max: 651.86 Min: 104.7 / Avg: 241.31 / Max: 387.86 Min: 28.55 / Avg: 235.77 / Max: 330 Min: 51.87 / Avg: 233.31 / Max: 276.8 Min: 21.48 / Avg: 206.2 / Max: 309.47 Min: 43.54 / Avg: 140.31 / Max: 283.29 Min: 18.33 / Avg: 130.18 / Max: 164.25 Min: 43.64 / Avg: 119.15 / Max: 229.24 Min: 15.81 / Avg: 114.62 / Max: 140.3
Timed Gem5 Compilation This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 23.0.1 Time To Compile Xeon Platinum 8380 Xeon 6766E Xeon 6766E 2P EPYC 8534PN EPYC 8534P Xeon 6780E Xeon 6780E 2P Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9754 Xeon Platinum 8490H EPYC 9754 2P Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 60 120 180 240 300 SE +/- 3.88, N = 3 SE +/- 3.60, N = 3 SE +/- 0.78, N = 3 SE +/- 0.97, N = 3 SE +/- 1.99, N = 9 SE +/- 1.47, N = 3 SE +/- 2.61, N = 3 SE +/- 2.59, N = 4 SE +/- 1.04, N = 3 SE +/- 2.11, N = 6 SE +/- 1.88, N = 3 SE +/- 0.92, N = 3 SE +/- 1.73, N = 3 SE +/- 2.17, N = 3 SE +/- 2.24, N = 4 SE +/- 1.72, N = 3 SE +/- 1.01, N = 3 SE +/- 0.58, N = 3 SE +/- 2.15, N = 3 SE +/- 0.72, N = 3 SE +/- 1.16, N = 3 SE +/- 0.89, N = 3 275.71 267.95 252.97 251.61 242.93 238.43 233.21 220.57 219.67 215.50 212.55 210.93 192.98 187.51 185.30 184.30 181.63 178.28 176.88 164.90 161.94 157.36
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Gem5 Compilation 23.0.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 140 280 420 560 700 Min: 177.84 / Avg: 479.92 / Max: 746.22 Min: 191.44 / Avg: 472.13 / Max: 747.43 Min: 160.34 / Avg: 415.56 / Max: 738.65 Min: 43.96 / Avg: 377.81 / Max: 753.32 Min: 65.57 / Avg: 360.36 / Max: 822.7 Min: 97.98 / Avg: 327.07 / Max: 580.5 Min: 55.44 / Avg: 320.45 / Max: 676.84 Min: 40.43 / Avg: 270.24 / Max: 677.31 Min: 40.79 / Avg: 257.31 / Max: 376.35 Min: 67.72 / Avg: 254.21 / Max: 375.35 Min: 55.65 / Avg: 228.11 / Max: 376.67 Min: 33.1 / Avg: 215.42 / Max: 377.33 Min: 29.1 / Avg: 201.66 / Max: 413.09 Min: 50.89 / Avg: 194.29 / Max: 291.11 Min: 55.47 / Avg: 178.9 / Max: 585.97 Min: 29.61 / Avg: 170.81 / Max: 332.22 Min: 104.15 / Avg: 164.39 / Max: 501.65 Min: 21.18 / Avg: 144.58 / Max: 331.44 Min: 43.31 / Avg: 103.5 / Max: 281.26 Min: 17.32 / Avg: 96.65 / Max: 166.6 Min: 43.55 / Avg: 90.66 / Max: 234.37 Min: 16.66 / Avg: 87.52 / Max: 141.58
LAMMPS Molecular Dynamics Simulator LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X EPYC 9754 Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 14 28 42 56 70 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.30, N = 3 SE +/- 0.19, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 21.38 25.33 27.53 28.28 32.16 34.89 35.70 37.46 42.51 46.71 46.89 47.99 50.52 51.82 56.40 57.10 58.84 62.00 1. (CXX) g++ options: -O3 -lm -ldl
ns/day Per Watt
OpenBenchmarking.org ns/day Per Watt, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.0432 0.0864 0.1296 0.1728 0.216 0.067 0.068 0.074 0.076 0.079 0.080 0.082 0.084 0.090 0.093 0.094 0.102 0.110 0.117 0.133 0.151 0.180 0.192
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 64.31 / Avg: 785.79 / Max: 819.57 Min: 186.6 / Avg: 685.33 / Max: 753.98 Min: 192.84 / Avg: 682.64 / Max: 752.01 Min: 165.47 / Avg: 680.62 / Max: 754.38 Min: 65.48 / Avg: 673.08 / Max: 752.97 Min: 55.66 / Avg: 633.05 / Max: 669.84 Min: 40.67 / Avg: 624.63 / Max: 672.65 Min: 97.85 / Avg: 530.19 / Max: 581.83 Min: 31.69 / Avg: 399.48 / Max: 409.61 Min: 75.25 / Avg: 345.23 / Max: 374.68 Min: 77.1 / Avg: 344.05 / Max: 376.79 Min: 61.2 / Avg: 343.29 / Max: 376.01 Min: 22.64 / Avg: 341.9 / Max: 376.37 Min: 29.12 / Avg: 318.64 / Max: 329.98 Min: 19.76 / Avg: 318.23 / Max: 330.98 Min: 52.92 / Avg: 266.98 / Max: 289.96 Min: 15.99 / Avg: 153.16 / Max: 156.26 Min: 15.43 / Avg: 132.09 / Max: 137.27
Timed Node.js Compilation This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 21.7.2 Time To Compile Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 Xeon 6766E Xeon 6780E Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9754 Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9654 EPYC 9684X EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P 90 180 270 360 450 SE +/- 0.22, N = 3 SE +/- 0.68, N = 3 SE +/- 0.19, N = 3 SE +/- 0.17, N = 3 SE +/- 0.53, N = 3 SE +/- 0.71, N = 3 SE +/- 0.74, N = 3 SE +/- 0.15, N = 3 SE +/- 0.51, N = 3 SE +/- 0.52, N = 3 SE +/- 1.20, N = 3 SE +/- 0.72, N = 3 SE +/- 0.84, N = 3 SE +/- 0.60, N = 3 SE +/- 0.48, N = 3 SE +/- 0.52, N = 3 SE +/- 0.59, N = 3 SE +/- 0.50, N = 3 SE +/- 1.51, N = 3 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 1.19, N = 3 423.63 303.42 288.12 277.53 270.38 254.00 252.65 246.85 228.57 214.43 187.65 186.10 175.63 173.09 172.99 171.17 164.02 147.84 147.74 145.41 118.90 114.91
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Node.js Compilation 21.7.2 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 200.82 / Avg: 601.52 / Max: 753.5 Min: 190.08 / Avg: 584.7 / Max: 754.37 Min: 157.7 / Avg: 555.35 / Max: 756.3 Min: 82.39 / Avg: 529.15 / Max: 756.15 Min: 61.4 / Avg: 490.25 / Max: 822.63 Min: 96.84 / Avg: 455.83 / Max: 582.18 Min: 55.68 / Avg: 430.05 / Max: 696.5 Min: 41.45 / Avg: 361.3 / Max: 676 Min: 74.34 / Avg: 318.88 / Max: 376.31 Min: 84.71 / Avg: 317.34 / Max: 376.11 Min: 56.59 / Avg: 305.63 / Max: 376.82 Min: 33.43 / Avg: 295.74 / Max: 377.74 Min: 30.95 / Avg: 289.15 / Max: 411.31 Min: 106.88 / Avg: 287.54 / Max: 584 Min: 104.39 / Avg: 256.25 / Max: 503.96 Min: 50.7 / Avg: 248.06 / Max: 290.96 Min: 29.13 / Avg: 242.47 / Max: 351.76 Min: 21.84 / Avg: 210.13 / Max: 338.39 Min: 43.35 / Avg: 170.44 / Max: 300.92 Min: 43.59 / Avg: 148.97 / Max: 246.66 Min: 18.11 / Avg: 134.67 / Max: 172.23 Min: 16.32 / Avg: 118.09 / Max: 147.17
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA256 Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 8534PN EPYC 8534P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 Xeon 6766E Xeon Platinum 8592+ 2P EPYC 9684X Xeon 6780E EPYC 9754 EPYC 9654 2P Xeon 6766E 2P EPYC 9684X 2P Xeon 6780E 2P EPYC 9754 2P 70000M 140000M 210000M 280000M 350000M SE +/- 8534071.27, N = 3 SE +/- 27466135.54, N = 3 SE +/- 33334799.97, N = 3 SE +/- 919807437.76, N = 12 SE +/- 159515825.53, N = 3 SE +/- 23323764.84, N = 3 SE +/- 64797308.82, N = 3 SE +/- 10642001.84, N = 3 SE +/- 126029257.64, N = 3 SE +/- 70647143.49, N = 3 SE +/- 66583540.43, N = 3 SE +/- 38601729.93, N = 3 SE +/- 34216643.88, N = 3 SE +/- 29142783.86, N = 3 SE +/- 146384349.91, N = 3 SE +/- 242095363.59, N = 3 SE +/- 34182873.86, N = 3 SE +/- 210407867.05, N = 3 SE +/- 97765007.32, N = 3 SE +/- 160246527.97, N = 3 SE +/- 228931567.43, N = 3 SE +/- 80639802.67, N = 3 27858504490 44439185187 51840436763 54530700576 61806994523 66573957920 67806730387 74584721007 88635753413 103382860113 119106802107 126475137690 129975994733 131976050120 138409588983 144163027280 161269162280 251645629887 256330349777 276267766403 287035041140 320258686237 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: SHA256 Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon 6780E 2P EPYC 8534PN Xeon 6780E Xeon 6766E 2P Xeon 6766E 130M 260M 390M 520M 650M 103421352.66 105324899.05 149911179.45 157500377.52 160789835.78 167457577.18 179424218.79 189585676.93 193109819.08 195213927.96 344443539.20 345260515.93 378210579.19 386445411.79 469088919.27 471857277.56 481947170.76 507731880.45 511227929.81 516781889.88 578313018.50 611047359.48
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9468 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 69.9 / Avg: 802.07 / Max: 822.12 Min: 71.86 / Avg: 683.42 / Max: 754.43 Min: 42.79 / Avg: 678.72 / Max: 712.84 Min: 59.61 / Avg: 665.36 / Max: 734.49 Min: 163.14 / Avg: 663.83 / Max: 754.31 Min: 186.31 / Avg: 642.97 / Max: 734.25 Min: 182.49 / Avg: 591.26 / Max: 697.86 Min: 108.39 / Avg: 565.33 / Max: 713.33 Min: 100.31 / Avg: 527.27 / Max: 585.66 Min: 105.85 / Avg: 443.24 / Max: 540.57 Min: 34.63 / Avg: 400.88 / Max: 411.05 Min: 32.34 / Avg: 341.03 / Max: 377.49 Min: 22.61 / Avg: 334.62 / Max: 353.13 Min: 29.19 / Avg: 327.28 / Max: 361.5 Min: 57.24 / Avg: 326.01 / Max: 380.05 Min: 82.11 / Avg: 309.57 / Max: 363.52 Min: 75.75 / Avg: 282.15 / Max: 323.37 Min: 43.49 / Avg: 278.96 / Max: 357.32 Min: 52.69 / Avg: 264.5 / Max: 291.33 Min: 43.63 / Avg: 212.71 / Max: 270.71 Min: 18.27 / Avg: 159 / Max: 170.75 Min: 17.53 / Avg: 132.64 / Max: 140.44
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: GoogLeNet Xeon 6766E Xeon Platinum 8380 EPYC 8534PN Xeon 6780E EPYC 8534P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P EPYC 9684X EPYC 9754 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X 2P Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9654 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 2P 130 260 390 520 650 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.19, N = 3 SE +/- 0.06, N = 3 SE +/- 1.19, N = 3 SE +/- 1.26, N = 3 SE +/- 0.41, N = 3 SE +/- 0.37, N = 3 SE +/- 0.25, N = 3 SE +/- 3.05, N = 12 SE +/- 12.03, N = 12 SE +/- 0.34, N = 3 SE +/- 3.68, N = 3 SE +/- 1.60, N = 3 SE +/- 1.14, N = 3 SE +/- 4.02, N = 10 SE +/- 2.46, N = 3 SE +/- 5.11, N = 3 SE +/- 2.62, N = 3 SE +/- 1.52, N = 3 SE +/- 5.63, N = 6 278.05 290.16 295.29 298.16 313.50 354.81 378.79 383.57 398.40 411.05 425.25 450.61 461.23 462.78 464.78 467.91 470.95 477.33 525.84 576.08 577.76 588.43
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: GoogLeNet Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6780E 2P EPYC 9684X 2P Xeon 6766E 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Max 9468 Xeon 6780E Xeon Max 9480 EPYC 9754 2P EPYC 9684X Xeon 6766E Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.5085 1.017 1.5255 2.034 2.5425 0.696 0.710 0.734 0.747 0.781 0.813 0.871 0.960 0.974 1.110 1.137 1.140 1.180 1.245 1.293 1.298 1.378 1.511 1.646 1.824 2.098 2.260
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon 6780E Xeon Platinum 8380 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 204.77 / Avg: 672.55 / Max: 725.44 Min: 205.47 / Avg: 671.88 / Max: 722 Min: 163.66 / Avg: 661.11 / Max: 719.14 Min: 65.4 / Avg: 622.34 / Max: 677.73 Min: 81.09 / Avg: 593.47 / Max: 647.85 Min: 60.16 / Avg: 547.94 / Max: 597.52 Min: 109.13 / Avg: 515.79 / Max: 577.43 Min: 104.77 / Avg: 505.8 / Max: 538.69 Min: 41.61 / Avg: 472.75 / Max: 541.37 Min: 106.15 / Avg: 454.45 / Max: 503.93 Min: 83.34 / Avg: 337.62 / Max: 362.35 Min: 73.74 / Avg: 337.25 / Max: 358.42 Min: 62.15 / Avg: 334.67 / Max: 366.71 Min: 33.11 / Avg: 328.89 / Max: 367.06 Min: 35.37 / Avg: 306.26 / Max: 336.64 Min: 16.07 / Avg: 286.15 / Max: 318.45 Min: 43.63 / Avg: 261.65 / Max: 298.46 Min: 52.49 / Avg: 261.52 / Max: 277.08 Min: 19.9 / Avg: 247.07 / Max: 298.24 Min: 43.64 / Avg: 214.28 / Max: 238.23 Min: 18.68 / Avg: 149.41 / Max: 158.78 Min: 16.37 / Avg: 130.65 / Max: 139.18
FFmpeg This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Platform Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.27, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 26.90 27.17 28.39 29.94 43.55 44.01 45.95 46.59 46.86 46.87 47.13 47.31 47.32 48.35 48.76 49.79 52.79 53.22 53.92 55.11 55.38 55.61 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Platform Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 0.1575 0.315 0.4725 0.63 0.7875 0.104 0.106 0.133 0.168 0.184 0.192 0.203 0.210 0.212 0.222 0.224 0.230 0.267 0.303 0.329 0.399 0.452 0.498 0.498 0.516 0.675 0.700
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better FFmpeg 7.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 90 180 270 360 450 Min: 205.4 / Avg: 441.78 / Max: 509.36 Min: 212.12 / Avg: 439.49 / Max: 489.04 Min: 161.47 / Avg: 365.67 / Max: 399.89 Min: 68.77 / Avg: 316.56 / Max: 368.13 Min: 61.23 / Avg: 286.98 / Max: 323.54 Min: 57.48 / Avg: 260.25 / Max: 290.76 Min: 100.74 / Avg: 237.01 / Max: 295.05 Min: 81.77 / Avg: 228.19 / Max: 273.56 Min: 76.85 / Avg: 225.5 / Max: 260.64 Min: 39.9 / Avg: 210.51 / Max: 233.46 Min: 62.31 / Avg: 186.7 / Max: 222.86 Min: 27.23 / Avg: 163.84 / Max: 212.24 Min: 49.55 / Avg: 145.35 / Max: 194.36 Min: 28.08 / Avg: 138.95 / Max: 171.83 Min: 61.79 / Avg: 127.88 / Max: 169.4 Min: 27.62 / Avg: 123.14 / Max: 151.27 Min: 56.04 / Avg: 117.19 / Max: 147.2 Min: 20.65 / Avg: 94.97 / Max: 114.96 Min: 15.65 / Avg: 69.43 / Max: 88.73 Min: 15.45 / Avg: 66.97 / Max: 86.23 Min: 43.43 / Avg: 58 / Max: 86.79 Min: 43.59 / Avg: 54.55 / Max: 78.03
Result
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Video On Demand Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 12 24 36 48 60 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.43, N = 3 SE +/- 0.13, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 26.89 27.17 28.39 29.95 43.80 44.13 45.29 46.79 46.88 46.93 47.14 47.33 47.34 48.14 48.77 49.84 52.81 53.29 53.99 55.01 55.56 55.59 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Video On Demand Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon 6766E EPYC 9754 Xeon 6780E EPYC 8534P EPYC 8534PN 0.1577 0.3154 0.4731 0.6308 0.7885 0.102 0.107 0.133 0.168 0.184 0.191 0.203 0.210 0.211 0.222 0.224 0.229 0.267 0.303 0.329 0.400 0.452 0.498 0.499 0.516 0.675 0.701
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better FFmpeg 7.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 90 180 270 360 450 Min: 207.79 / Avg: 444.37 / Max: 498.92 Min: 214.26 / Avg: 439.08 / Max: 477.53 Min: 163.78 / Avg: 366.29 / Max: 401.74 Min: 70.84 / Avg: 317.18 / Max: 370.52 Min: 64.38 / Avg: 287.45 / Max: 321.56 Min: 56.36 / Avg: 260.19 / Max: 290.84 Min: 100.82 / Avg: 237.65 / Max: 291.56 Min: 85.24 / Avg: 228.49 / Max: 271.74 Min: 78.38 / Avg: 225.58 / Max: 260.03 Min: 40.07 / Avg: 210.54 / Max: 233.66 Min: 60.59 / Avg: 186.45 / Max: 226 Min: 27.6 / Avg: 164.12 / Max: 212.91 Min: 51.94 / Avg: 145.51 / Max: 200.88 Min: 33.72 / Avg: 139.07 / Max: 174.07 Min: 60.98 / Avg: 127.77 / Max: 168.5 Min: 28.98 / Avg: 123.07 / Max: 151.95 Min: 103.99 / Avg: 117.45 / Max: 147.92 Min: 19.72 / Avg: 94.92 / Max: 115.72 Min: 15.96 / Avg: 69.48 / Max: 89.87 Min: 16.1 / Avg: 66.97 / Max: 83.84 Min: 29 / Avg: 58.08 / Max: 84.77 Min: 43.59 / Avg: 54.51 / Max: 76.42
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard EPYC 8534PN EPYC 9654 2P EPYC 8534P EPYC 9754 2P Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X Xeon 6780E EPYC 9754 Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 50 100 150 200 250 SE +/- 7.19, N = 15 SE +/- 0.35, N = 3 SE +/- 6.87, N = 12 SE +/- 2.91, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 2.18, N = 15 SE +/- 4.84, N = 15 SE +/- 4.76, N = 12 SE +/- 0.21, N = 3 SE +/- 2.29, N = 15 SE +/- 2.32, N = 15 SE +/- 6.41, N = 15 SE +/- 3.36, N = 15 SE +/- 2.59, N = 15 SE +/- 5.82, N = 12 SE +/- 0.09, N = 3 SE +/- 1.55, N = 15 SE +/- 0.71, N = 3 SE +/- 0.44, N = 3 SE +/- 0.69, N = 15 226.63 220.35 216.70 203.57 194.11 188.30 182.36 182.27 182.02 178.03 174.14 166.79 160.53 155.79 139.10 121.78 121.67 116.32 110.97 109.67 100.74 92.35 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 Xeon Platinum 8380 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 64.5 / Avg: 611.91 / Max: 674.71 Min: 60.03 / Avg: 522.44 / Max: 571.64 Min: 100.08 / Avg: 498.61 / Max: 537.57 Min: 108.32 / Avg: 473.62 / Max: 514.95 Min: 41.83 / Avg: 453.96 / Max: 496.3 Min: 105.71 / Avg: 414.92 / Max: 451.7 Min: 33.76 / Avg: 321.88 / Max: 360.42 Min: 27.94 / Avg: 273.66 / Max: 300.92 Min: 53.6 / Avg: 252.85 / Max: 280.59 Min: 43.58 / Avg: 243.68 / Max: 263.63 Min: 21.08 / Avg: 240.98 / Max: 267.52 Min: 43.7 / Avg: 200.72 / Max: 216.16 Min: 19.31 / Avg: 140.51 / Max: 154.48 Min: 17.45 / Avg: 121.04 / Max: 134.63
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard EPYC 8534PN EPYC 9654 2P EPYC 8534P EPYC 9754 2P Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X Xeon 6780E EPYC 9754 Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 3 6 9 12 15 SE +/- 0.11914, N = 15 SE +/- 0.00718, N = 3 SE +/- 0.14467, N = 12 SE +/- 0.07023, N = 3 SE +/- 0.00154, N = 3 SE +/- 0.00241, N = 3 SE +/- 0.00381, N = 3 SE +/- 0.06453, N = 15 SE +/- 0.15150, N = 15 SE +/- 0.16422, N = 12 SE +/- 0.00692, N = 3 SE +/- 0.08489, N = 15 SE +/- 0.08940, N = 15 SE +/- 0.22869, N = 15 SE +/- 0.15651, N = 15 SE +/- 0.16487, N = 15 SE +/- 0.34632, N = 12 SE +/- 0.00664, N = 3 SE +/- 0.11577, N = 15 SE +/- 0.05824, N = 3 SE +/- 0.04271, N = 3 SE +/- 0.07619, N = 15 4.46533 4.53817 4.66491 4.91420 5.15166 5.31050 5.48343 5.49711 5.55018 5.66508 5.74234 6.01164 6.24740 6.54965 7.24187 8.26016 8.39962 8.59719 9.03367 9.11885 9.92684 10.83623 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Standard EPYC 8534PN EPYC 9654 2P EPYC 8534P EPYC 9754 2P Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X Xeon 6780E EPYC 9754 Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 50 100 150 200 250 SE +/- 7.19, N = 15 SE +/- 0.35, N = 3 SE +/- 6.87, N = 12 SE +/- 2.91, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 SE +/- 2.18, N = 15 SE +/- 4.84, N = 15 SE +/- 4.76, N = 12 SE +/- 0.21, N = 3 SE +/- 2.29, N = 15 SE +/- 2.32, N = 15 SE +/- 6.41, N = 15 SE +/- 3.36, N = 15 SE +/- 2.59, N = 15 SE +/- 5.82, N = 12 SE +/- 0.09, N = 3 SE +/- 1.55, N = 15 SE +/- 0.71, N = 3 SE +/- 0.44, N = 3 SE +/- 0.69, N = 15 226.63 220.35 216.70 203.57 194.11 188.30 182.36 182.27 182.02 178.03 174.14 166.79 160.53 155.79 139.10 121.78 121.67 116.32 110.97 109.67 100.74 92.35 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
FFmpeg This is a benchmark of the FFmpeg multimedia framework. The FFmpeg test profile is making use of a modified version of vbench from Columbia University's Architecture and Design Lab (ARCADE) [http://arcade.cs.columbia.edu/vbench/] that is a benchmark for video-as-a-service workloads. The test profile offers the options of a range of vbench scenarios based on freely distributable video content and offers the options of using the x264 or x265 video encoders for transcoding. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org FPS, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Upload Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P EPYC 8534P EPYC 8534PN EPYC 9754 2P Xeon Max 9480 2P Xeon Max 9468 EPYC 9754 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 13.90 14.01 14.87 15.47 21.73 21.96 22.34 23.25 23.27 23.28 23.30 23.33 23.36 23.77 24.56 24.97 26.41 26.80 26.93 27.43 27.61 27.66 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
FPS Per Watt
OpenBenchmarking.org FPS Per Watt, More Is Better FFmpeg 7.0 Encoder: libx265 - Scenario: Upload Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 0.0826 0.1652 0.2478 0.3304 0.413 0.052 0.054 0.069 0.095 0.097 0.098 0.104 0.108 0.110 0.113 0.121 0.121 0.142 0.167 0.179 0.210 0.237 0.258 0.270 0.283 0.354 0.367
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better FFmpeg 7.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 90 180 270 360 450 Min: 200.59 / Avg: 429.86 / Max: 523.1 Min: 200.89 / Avg: 428.04 / Max: 517.82 Min: 169.76 / Avg: 355.39 / Max: 439.92 Min: 74.8 / Avg: 282.67 / Max: 421.23 Min: 60.82 / Avg: 280.31 / Max: 349.69 Min: 57.5 / Avg: 253.71 / Max: 316.9 Min: 101.47 / Avg: 224.76 / Max: 314.49 Min: 73.34 / Avg: 216.54 / Max: 288.18 Min: 77.87 / Avg: 215.12 / Max: 282.66 Min: 40.21 / Avg: 205.67 / Max: 248.29 Min: 59.92 / Avg: 175.77 / Max: 260.15 Min: 33.49 / Avg: 150.78 / Max: 267.25 Min: 32.37 / Avg: 131.52 / Max: 197.98 Min: 54.29 / Avg: 131.33 / Max: 221.85 Min: 105.83 / Avg: 122.91 / Max: 188.11 Min: 28.66 / Avg: 116.46 / Max: 162.4 Min: 103.98 / Avg: 114.66 / Max: 149.44 Min: 21.11 / Avg: 90.52 / Max: 130.74 Min: 17.2 / Avg: 65.65 / Max: 103.63 Min: 16.42 / Avg: 63.46 / Max: 99.36 Min: 26.8 / Avg: 54.72 / Max: 93.15 Min: 21.91 / Avg: 51.98 / Max: 83.48
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average Latency Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 2P EPYC 8534PN Xeon Max 9468 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8380 EPYC 8534P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 EPYC 9754 Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6766E EPYC 9684X EPYC 9654 Xeon 6780E 7 14 21 28 35 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 SE +/- 0.32, N = 12 SE +/- 0.25, N = 12 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 12 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 30.20 28.81 26.29 18.16 18.06 18.05 16.96 16.88 16.66 16.34 16.32 14.86 14.29 14.04 13.85 13.84 13.69 13.26 12.63 12.58 12.50 11.54 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 16 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 197.27 / Avg: 561.38 / Max: 632.44 Min: 201.21 / Avg: 553.8 / Max: 622.91 Min: 162.26 / Avg: 519.08 / Max: 620.62 Min: 42.76 / Avg: 483.2 / Max: 581.92 Min: 103.15 / Avg: 454.63 / Max: 533.63 Min: 48.63 / Avg: 431.32 / Max: 519.43 Min: 37.64 / Avg: 361.97 / Max: 439.12 Min: 71.52 / Avg: 361.27 / Max: 515.84 Min: 86.13 / Avg: 315.59 / Max: 351.55 Min: 69.55 / Avg: 311.42 / Max: 350.84 Min: 54.62 / Avg: 299.36 / Max: 354.29 Min: 32.63 / Avg: 299.03 / Max: 361.05 Min: 31.89 / Avg: 275.46 / Max: 347.94 Min: 107.64 / Avg: 262.99 / Max: 345.55 Min: 19.41 / Avg: 254.31 / Max: 305.58 Min: 104.31 / Avg: 242.14 / Max: 314.19 Min: 54.49 / Avg: 239.87 / Max: 290.09 Min: 21.27 / Avg: 207.74 / Max: 251.71 Min: 43.39 / Avg: 172.92 / Max: 212.03 Min: 43.52 / Avg: 150.61 / Max: 191.14 Min: 16.91 / Avg: 135.16 / Max: 158.27 Min: 15.4 / Avg: 110.68 / Max: 134.33
OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Write Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P EPYC 8534PN EPYC 9654 2P Xeon Max 9468 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8380 EPYC 8534P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 EPYC 9754 Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6766E EPYC 9684X EPYC 9654 Xeon 6780E 20K 40K 60K 80K 100K SE +/- 106.16, N = 3 SE +/- 163.06, N = 3 SE +/- 221.82, N = 3 SE +/- 1059.49, N = 12 SE +/- 299.71, N = 3 SE +/- 865.71, N = 12 SE +/- 195.77, N = 3 SE +/- 58.85, N = 3 SE +/- 440.63, N = 3 SE +/- 434.11, N = 12 SE +/- 175.33, N = 3 SE +/- 137.82, N = 3 SE +/- 95.84, N = 3 SE +/- 78.02, N = 3 SE +/- 143.25, N = 3 SE +/- 242.45, N = 3 SE +/- 656.63, N = 3 SE +/- 198.41, N = 3 SE +/- 186.80, N = 3 SE +/- 87.23, N = 3 SE +/- 232.97, N = 3 SE +/- 232.81, N = 3 33110 34716 38043 55272 55395 55505 58952 59228 60046 61233 61272 67315 69969 71227 72225 72244 73042 75396 79191 79492 79987 86677 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Barbershop - Compute: CPU-Only Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9754 Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 100 200 300 400 500 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 1.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.69, N = 3 SE +/- 0.25, N = 3 SE +/- 0.33, N = 3 SE +/- 0.08, N = 3 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 SE +/- 0.42, N = 3 SE +/- 0.25, N = 3 SE +/- 0.21, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.41, N = 3 SE +/- 0.17, N = 3 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 456.81 320.11 290.56 263.76 261.97 240.13 236.73 235.31 191.20 174.49 169.44 156.70 141.54 139.25 125.87 123.90 114.76 106.48 97.18 79.05 67.52 65.58
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 68.76 / Avg: 738.74 / Max: 823.72 Min: 206.17 / Avg: 675.87 / Max: 751.49 Min: 209.81 / Avg: 673.68 / Max: 752.4 Min: 167.6 / Avg: 666.99 / Max: 755.27 Min: 79.57 / Avg: 660.14 / Max: 755.17 Min: 58.63 / Avg: 632.52 / Max: 694.54 Min: 41.32 / Avg: 614.31 / Max: 703.89 Min: 104.16 / Avg: 521 / Max: 582.69 Min: 108.93 / Avg: 517.76 / Max: 626.1 Min: 106.4 / Avg: 442.07 / Max: 501.67 Min: 35.25 / Avg: 388.09 / Max: 411.05 Min: 73.43 / Avg: 343.06 / Max: 375.17 Min: 85.64 / Avg: 342.89 / Max: 377.27 Min: 60.47 / Avg: 340.87 / Max: 376.73 Min: 33.95 / Avg: 339.43 / Max: 377.51 Min: 23.25 / Avg: 321.43 / Max: 348.37 Min: 27.59 / Avg: 319.36 / Max: 343.48 Min: 43.73 / Avg: 282.74 / Max: 303.29 Min: 52.6 / Avg: 265.95 / Max: 290.85 Min: 43.74 / Avg: 219.92 / Max: 232.7 Min: 17.05 / Avg: 166.92 / Max: 172.9 Min: 17.54 / Avg: 139.56 / Max: 146.03
Numpy Benchmark This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Score, More Is Better Numpy Benchmark Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X 120 240 360 480 600 SE +/- 0.30, N = 3 SE +/- 0.37, N = 3 SE +/- 0.47, N = 3 SE +/- 2.24, N = 3 SE +/- 1.52, N = 3 SE +/- 2.23, N = 3 SE +/- 1.34, N = 3 SE +/- 0.72, N = 3 SE +/- 0.25, N = 3 SE +/- 0.96, N = 3 SE +/- 1.13, N = 3 SE +/- 1.30, N = 3 SE +/- 0.33, N = 3 SE +/- 0.26, N = 3 SE +/- 0.60, N = 3 SE +/- 0.79, N = 3 SE +/- 1.42, N = 3 SE +/- 1.84, N = 3 SE +/- 0.38, N = 3 SE +/- 2.28, N = 3 SE +/- 0.60, N = 3 SE +/- 1.85, N = 3 258.49 261.19 283.52 284.33 394.71 400.64 418.89 421.99 422.76 425.46 435.21 439.84 455.57 456.18 461.61 464.72 519.89 520.22 529.03 529.80 540.96 542.15
Score Per Watt
OpenBenchmarking.org Score Per Watt, More Is Better Numpy Benchmark Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 2 4 6 8 10 1.343 1.375 1.716 2.071 2.079 2.170 2.249 2.360 2.382 2.603 3.164 3.290 4.043 4.183 4.854 5.255 5.359 5.405 5.817 6.244 7.918 7.962
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Numpy Benchmark CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9684X Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 80 160 240 320 400 Min: 137.87 / Avg: 324.03 / Max: 425.17 Min: 203.89 / Avg: 319.82 / Max: 421.94 Min: 168.75 / Avg: 265.77 / Max: 348.44 Min: 64.52 / Avg: 260.26 / Max: 267.94 Min: 57.9 / Avg: 235.19 / Max: 242.43 Min: 78.29 / Avg: 220.31 / Max: 293.25 Min: 38.63 / Avg: 194.78 / Max: 202.23 Min: 99.11 / Avg: 190.58 / Max: 201.58 Min: 82.95 / Avg: 146.89 / Max: 202.52 Min: 73.46 / Avg: 140.29 / Max: 199.25 Min: 32.28 / Avg: 111.7 / Max: 116.99 Min: 59.12 / Avg: 108.92 / Max: 159.89 Min: 53.93 / Avg: 108.91 / Max: 127.19 Min: 104.03 / Avg: 108.54 / Max: 129.89 Min: 48.6 / Avg: 99.09 / Max: 103.63 Min: 33.91 / Avg: 98.99 / Max: 138.69 Min: 26.33 / Avg: 98.86 / Max: 103.35 Min: 20.13 / Avg: 78.72 / Max: 83.54 Min: 16.02 / Avg: 53.3 / Max: 57.51 Min: 14.57 / Avg: 52.61 / Max: 56.75 Min: 43.42 / Avg: 45.54 / Max: 66.48 Min: 21.86 / Avg: 44.9 / Max: 66.76
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU Xeon Platinum 8380 Xeon Max 9468 Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 8534P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X EPYC 9754 EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 5 10 15 20 25 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.22, N = 12 SE +/- 0.22, N = 15 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 15 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.20, N = 15 SE +/- 0.23, N = 15 SE +/- 0.24, N = 15 SE +/- 0.13, N = 3 SE +/- 0.18, N = 15 SE +/- 0.28, N = 15 SE +/- 0.12, N = 3 SE +/- 1.02, N = 15 SE +/- 0.91, N = 15 5.63 7.46 7.71 7.99 8.00 8.48 8.72 8.98 9.38 9.39 9.40 10.09 10.17 10.44 11.12 12.74 14.29 16.21 16.79 17.89 22.00 22.58
M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X Xeon 6780E EPYC 9654 Xeon 6766E EPYC 9754 EPYC 8534P EPYC 8534PN 0.0149 0.0298 0.0447 0.0596 0.0745 0.015 0.016 0.017 0.018 0.019 0.022 0.023 0.023 0.024 0.026 0.026 0.029 0.031 0.031 0.039 0.042 0.045 0.048 0.052 0.054 0.060 0.066
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.6 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon 6780E 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon 6766E 2P Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 150 300 450 600 750 Min: 65.89 / Avg: 739.45 / Max: 837.69 Min: 203.55 / Avg: 668.4 / Max: 754.98 Min: 195.7 / Avg: 665.76 / Max: 753.2 Min: 173.98 / Avg: 664.56 / Max: 753.01 Min: 76.68 / Avg: 654.92 / Max: 755.35 Min: 59.66 / Avg: 573.93 / Max: 661.76 Min: 42.95 / Avg: 561.1 / Max: 675.69 Min: 101.11 / Avg: 511.71 / Max: 580 Min: 34.75 / Avg: 384.12 / Max: 412.45 Min: 79.88 / Avg: 341.83 / Max: 482.57 Min: 74.56 / Avg: 331.26 / Max: 374.04 Min: 59.67 / Avg: 330.53 / Max: 373.83 Min: 72.86 / Avg: 330.29 / Max: 377.65 Min: 24.28 / Avg: 326.43 / Max: 375.69 Min: 20.73 / Avg: 311.89 / Max: 340.37 Min: 29.9 / Avg: 299.39 / Max: 326.71 Min: 104.02 / Avg: 295.99 / Max: 409.35 Min: 51.32 / Avg: 255.3 / Max: 289.97 Min: 43.51 / Avg: 225.44 / Max: 288.32 Min: 43.65 / Avg: 180.3 / Max: 223.44 Min: 18.62 / Avg: 156.14 / Max: 171.55 Min: 18.19 / Avg: 128.95 / Max: 140.58
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9684X Xeon 6766E 2P EPYC 9754 Xeon 6780E 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 500000M 1000000M 1500000M 2000000M 2500000M SE +/- 706172241.68, N = 3 SE +/- 409615403.40, N = 3 SE +/- 530918594.60, N = 3 SE +/- 195953395.92, N = 3 SE +/- 129279575.06, N = 3 SE +/- 43545680.66, N = 3 SE +/- 56355870.99, N = 3 SE +/- 28627701.54, N = 3 SE +/- 266669781.18, N = 3 SE +/- 1253503549.61, N = 3 SE +/- 164763342.54, N = 3 SE +/- 570058274.06, N = 3 SE +/- 429428665.34, N = 3 SE +/- 49279694.68, N = 3 SE +/- 333650111.34, N = 3 SE +/- 268465891.11, N = 3 SE +/- 697208281.49, N = 3 SE +/- 159598753.20, N = 3 SE +/- 1622921637.03, N = 3 SE +/- 337702856.52, N = 3 SE +/- 1428966819.54, N = 3 SE +/- 1841260363.24, N = 3 399526815427 488965390857 539784931373 565720767783 638453203763 641200848170 747710702660 768804693697 807229265300 889567506540 897288436123 996007109267 1096082199713 1167221141870 1266882866653 1277583382757 1484669627050 1533026300727 1769313146013 1785006879067 1990352059967 2316611945283 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon 6780E 2P Xeon Max 9468 2P Xeon 6780E Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon 6766E Xeon Platinum 8490H EPYC 9684X 2P EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9654 2P EPYC 9654 EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 8534PN 700M 1400M 2100M 2800M 3500M 1510207805.12 1525932773.14 1953802430.20 1967868118.18 1970077384.37 2035473064.32 2168460340.43 2214398499.06 2230951841.30 2275619248.61 2305290901.87 2333237948.27 2480518885.86 2482510440.03 2589909503.87 2600338214.73 2638396952.00 2686039538.13 3225126995.22 3291374680.15 3351926704.37 3483917754.10
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9754 Xeon Platinum 8592+ Xeon Max 9480 EPYC 9654 Xeon Platinum 8490H Xeon 6780E Xeon Max 9468 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 68.36 / Avg: 802.39 / Max: 822.1 Min: 40.47 / Avg: 703.84 / Max: 726.54 Min: 187.64 / Avg: 684.67 / Max: 756.52 Min: 68.61 / Avg: 683.16 / Max: 735.37 Min: 56.69 / Avg: 676.55 / Max: 719.01 Min: 164.19 / Avg: 673.67 / Max: 754.31 Min: 201.68 / Avg: 649.22 / Max: 717.93 Min: 110.15 / Avg: 648.42 / Max: 712.91 Min: 101.06 / Avg: 529.01 / Max: 581.52 Min: 109.26 / Avg: 491.31 / Max: 541.12 Min: 34.83 / Avg: 401.21 / Max: 411.04 Min: 22.8 / Avg: 348.22 / Max: 361.46 Min: 21.98 / Avg: 342.1 / Max: 376.9 Min: 73.91 / Avg: 337.66 / Max: 377.26 Min: 28.74 / Avg: 334.06 / Max: 354.77 Min: 57.48 / Avg: 329.5 / Max: 379.19 Min: 43.57 / Avg: 324.08 / Max: 356.29 Min: 72.06 / Avg: 315.01 / Max: 350.37 Min: 54.11 / Avg: 264.55 / Max: 290.68 Min: 43.71 / Avg: 245.4 / Max: 270.99 Min: 17.13 / Avg: 167.37 / Max: 173.46 Min: 17.62 / Avg: 140.35 / Max: 146.9
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon 6766E Xeon Max 9468 Xeon 6780E Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9684X Xeon 6766E 2P EPYC 9754 Xeon Max 9468 2P Xeon 6780E 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 400000M 800000M 1200000M 1600000M 2000000M SE +/- 81945775.93, N = 3 SE +/- 3442274884.66, N = 3 SE +/- 148092414.72, N = 3 SE +/- 34244051.67, N = 3 SE +/- 119857064.56, N = 3 SE +/- 317370827.95, N = 3 SE +/- 63026881.96, N = 3 SE +/- 2848140790.67, N = 3 SE +/- 116420153.53, N = 3 SE +/- 3966858436.56, N = 3 SE +/- 818689705.82, N = 3 SE +/- 671752057.50, N = 3 SE +/- 252081360.30, N = 3 SE +/- 290015345.25, N = 3 SE +/- 108288170.03, N = 3 SE +/- 301551944.80, N = 3 SE +/- 112278705.55, N = 3 SE +/- 1397764228.85, N = 3 SE +/- 1320809584.03, N = 3 SE +/- 2225250504.62, N = 3 SE +/- 1859275059.09, N = 3 SE +/- 1791964708.17, N = 3 356062040883 415893963207 462309750530 506301374623 507456728087 568937578313 592014115453 700239352717 712485411447 744387683670 767696553667 859720599963 979419388797 997539007873 1011898993323 1125373041173 1181148957353 1369534328470 1497529939377 1526505465813 1714061761087 1983103026700 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 2P Xeon 6780E Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon 6766E EPYC 9684X 2P EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9654 EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 8534PN 600M 1200M 1800M 2400M 3000M 1344485766.05 1345006115.81 1587520126.44 1651813451.15 1735227671.90 1745319585.66 1758065363.32 1789501537.54 1993158291.38 1998240264.78 2048623453.07 2061752146.93 2139406659.57 2144285710.42 2177657519.61 2193171119.61 2286984508.79 2331206946.71 2800094011.98 2844279712.45 2889219779.92 2991193842.10
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P EPYC 9654 2P Xeon 6780E 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9480 EPYC 9654 Xeon 6780E Xeon Max 9468 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 64.77 / Avg: 801.19 / Max: 822.22 Min: 42.68 / Avg: 697.23 / Max: 724.85 Min: 152.63 / Avg: 685.37 / Max: 754.67 Min: 67.1 / Avg: 682.81 / Max: 732.1 Min: 191.65 / Avg: 676.75 / Max: 755.44 Min: 59.32 / Avg: 667.48 / Max: 710.25 Min: 109.57 / Avg: 648.54 / Max: 712.9 Min: 186.02 / Avg: 637.41 / Max: 707.3 Min: 103.41 / Avg: 529.73 / Max: 581.31 Min: 108.93 / Avg: 491.39 / Max: 542.48 Min: 34.11 / Avg: 400.94 / Max: 411.04 Min: 22.57 / Avg: 345.26 / Max: 357.86 Min: 23.55 / Avg: 341.83 / Max: 377.46 Min: 57.11 / Avg: 341.81 / Max: 377.46 Min: 76.66 / Avg: 330.83 / Max: 377.06 Min: 29.29 / Avg: 329.31 / Max: 350.94 Min: 43.56 / Avg: 323.62 / Max: 356.6 Min: 69.15 / Avg: 307.21 / Max: 344.49 Min: 52.04 / Avg: 264.83 / Max: 290.23 Min: 43.78 / Avg: 245.57 / Max: 271.22 Min: 17.84 / Avg: 165.11 / Max: 170.43 Min: 16.68 / Avg: 139.04 / Max: 145.32
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P EPYC 9754 Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 300000M 600000M 900000M 1200000M 1500000M SE +/- 11028602.79, N = 3 SE +/- 39095934.62, N = 3 SE +/- 151152302.42, N = 3 SE +/- 415487944.57, N = 3 SE +/- 312824840.64, N = 3 SE +/- 71110585.03, N = 3 SE +/- 9570566.28, N = 3 SE +/- 232288636.76, N = 3 SE +/- 3335467.26, N = 3 SE +/- 11835135.62, N = 3 SE +/- 63366974.35, N = 3 SE +/- 352722951.98, N = 3 SE +/- 329510485.23, N = 3 SE +/- 151272595.84, N = 3 SE +/- 863978337.15, N = 3 SE +/- 94935214.36, N = 3 SE +/- 271318554.29, N = 3 SE +/- 170968063.89, N = 3 SE +/- 303075210.03, N = 3 SE +/- 80233613.02, N = 3 SE +/- 874940734.18, N = 3 SE +/- 63368290.15, N = 3 177249062183 196920683270 212294883830 226597354153 263740690067 282053327077 307068938377 316126421173 344150916937 352826821653 391911225480 425451190063 449908494927 503311021123 522912403347 544904084773 624402972947 656396329387 684284382760 1001502634860 1086618191950 1306928507573 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 Xeon 6780E 2P Xeon 6780E Xeon Max 9468 2P Xeon Platinum 8380 Xeon 6766E 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon 6766E Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 9754 2P EPYC 9754 EPYC 8534P EPYC 8534PN 400M 800M 1200M 1600M 2000M 712317847.22 730208953.76 774438543.71 802490465.58 804207062.62 804835329.47 811931853.54 846331621.99 852735838.29 862670148.37 936302176.04 977212174.27 1003586866.34 1008751851.93 1353849347.71 1361592598.33 1480134319.02 1510491450.86 1778324265.62 1795036060.88 1824186596.16 2009755510.33
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9754 Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9468 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 150 300 450 600 750 Min: 70.23 / Avg: 802.61 / Max: 826.12 Min: 42.15 / Avg: 734.92 / Max: 800.62 Min: 70.13 / Avg: 681.84 / Max: 728.96 Min: 59.94 / Avg: 676.63 / Max: 728.84 Min: 168.89 / Avg: 666.88 / Max: 755.69 Min: 183.97 / Avg: 617.86 / Max: 744.83 Min: 197.94 / Avg: 580.95 / Max: 674.82 Min: 109.96 / Avg: 550.19 / Max: 629.46 Min: 101.74 / Avg: 528.62 / Max: 581.46 Min: 108.7 / Avg: 438.73 / Max: 492.61 Min: 34.55 / Avg: 400.2 / Max: 411.05 Min: 22.28 / Avg: 365.67 / Max: 391.73 Min: 22.69 / Avg: 341.17 / Max: 376.63 Min: 30.31 / Avg: 333.21 / Max: 358.89 Min: 54.19 / Avg: 323.5 / Max: 377.22 Min: 73.21 / Avg: 309.29 / Max: 373.85 Min: 71.67 / Avg: 279.08 / Max: 326.73 Min: 43.55 / Avg: 269.68 / Max: 311.17 Min: 54.01 / Avg: 264.55 / Max: 291.24 Min: 43.7 / Avg: 205.47 / Max: 234.45 Min: 17.59 / Avg: 168.33 / Max: 176.1 Min: 15.27 / Avg: 140.34 / Max: 147.74
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA512 Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P EPYC 8534PN Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 8534P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon 6766E Xeon Platinum 8490H 2P Xeon 6780E EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 Xeon 6766E 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9684X 2P EPYC 9754 2P 20000M 40000M 60000M 80000M 100000M SE +/- 6313493.56, N = 3 SE +/- 500176.69, N = 3 SE +/- 1250834.62, N = 3 SE +/- 20492408.59, N = 3 SE +/- 9990938.84, N = 3 SE +/- 203213936.42, N = 3 SE +/- 37654528.63, N = 3 SE +/- 15082903.45, N = 3 SE +/- 3500318.33, N = 3 SE +/- 14339684.98, N = 3 SE +/- 6285194.15, N = 3 SE +/- 14430784.68, N = 3 SE +/- 481040738.21, N = 3 SE +/- 24045021.87, N = 3 SE +/- 55712209.05, N = 3 SE +/- 14734422.48, N = 3 SE +/- 5822493.86, N = 3 SE +/- 66704467.17, N = 3 SE +/- 37307640.51, N = 3 SE +/- 64065176.93, N = 3 SE +/- 44023374.36, N = 3 SE +/- 17716195.81, N = 3 10980940093 16199261277 18893980783 22079539900 22194470973 22219927723 23886054770 24378460820 32304222993 37564522053 39627575497 40605137923 42846254477 45088755640 45865131913 46520760707 52746634113 78599395230 78822257383 89194416857 91455971200 104776633047 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: SHA512 Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 Xeon 6780E 2P Xeon 6780E EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon 6766E 2P EPYC 8534PN Xeon 6766E 40M 80M 120M 160M 200M 41470367.43 42041804.18 51580447.52 54000562.67 55449110.37 57121711.23 62457308.50 65144677.30 67966151.09 69884736.57 114225793.10 114623223.18 125714359.16 128564080.98 137868745.00 139323873.72 154425638.15 154893248.59 157697655.07 159806130.44 165874523.26 165922834.04
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P EPYC 9754 2P Xeon 6780E 2P EPYC 9654 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9754 Xeon Max 9480 Xeon 6780E EPYC 9654 Xeon Max 9468 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 66.79 / Avg: 800.66 / Max: 822.16 Min: 158.63 / Avg: 686.01 / Max: 753.85 Min: 66.13 / Avg: 684.47 / Max: 754.35 Min: 194.96 / Avg: 677.46 / Max: 722.73 Min: 42.68 / Avg: 676.44 / Max: 705.8 Min: 108.54 / Avg: 646.95 / Max: 712.56 Min: 59.93 / Avg: 626.99 / Max: 687.56 Min: 190.86 / Avg: 626.29 / Max: 729.82 Min: 105.66 / Avg: 525.18 / Max: 583.12 Min: 106.79 / Avg: 491.84 / Max: 540.07 Min: 34.64 / Avg: 400.14 / Max: 413.51 Min: 23.35 / Avg: 341.79 / Max: 377.28 Min: 56.54 / Avg: 341.09 / Max: 377.07 Min: 21.49 / Avg: 334.48 / Max: 349.67 Min: 74.41 / Avg: 330.77 / Max: 354.3 Min: 43.5 / Avg: 323.63 / Max: 356.46 Min: 28.99 / Avg: 308.23 / Max: 338.17 Min: 71.29 / Avg: 299.98 / Max: 317.48 Min: 53.35 / Avg: 264.79 / Max: 291.44 Min: 43.65 / Avg: 244.72 / Max: 270.07 Min: 18.44 / Avg: 157.87 / Max: 169.7 Min: 15.55 / Avg: 133.8 / Max: 143.63
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 200000M 400000M 600000M 800000M 1000000M SE +/- 2360978.39, N = 3 SE +/- 18243420.30, N = 3 SE +/- 255765711.98, N = 3 SE +/- 6370607.14, N = 3 SE +/- 37795783.50, N = 3 SE +/- 65233629.47, N = 3 SE +/- 24234601.89, N = 3 SE +/- 120899798.30, N = 3 SE +/- 766713911.50, N = 3 SE +/- 37182497.08, N = 3 SE +/- 38565703.74, N = 3 SE +/- 31274617.76, N = 3 SE +/- 4148679.28, N = 3 SE +/- 29295317.86, N = 3 SE +/- 36941390.18, N = 3 SE +/- 4478378.70, N = 3 SE +/- 132227134.30, N = 3 SE +/- 82161991.11, N = 3 SE +/- 151303743.70, N = 3 SE +/- 6119305.11, N = 3 SE +/- 558033954.71, N = 3 SE +/- 19082587.00, N = 3 120591787257 134033039090 146156212950 161321058213 187796174440 193305093643 211185661727 223625738013 225038850730 240005135153 266583857887 293502122413 320396720447 350960998357 372735215297 383925652077 442202532977 444099144270 457039748870 698925822223 767652719547 906028608990 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 Xeon 6780E 2P Xeon 6780E Xeon 6766E 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 Xeon 6766E Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9684X EPYC 9684X 2P EPYC 9654 2P EPYC 9654 EPYC 9754 2P EPYC 9754 EPYC 8534P EPYC 8534PN 300M 600M 900M 1200M 1500M 471667041.65 483646931.54 536427227.19 542055990.77 552257367.63 554436256.62 568545794.25 569925760.92 574875604.57 603664493.39 644676877.17 648595124.99 658820863.84 666607882.23 957073830.82 957228032.13 1039886433.31 1061980440.86 1244610923.33 1269363721.24 1287300050.02 1388893901.10
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9654 Xeon Max 9480 Xeon Max 9468 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 68.91 / Avg: 801.95 / Max: 822.13 Min: 41.79 / Avg: 727.96 / Max: 758.79 Min: 163.33 / Avg: 685.93 / Max: 736.16 Min: 79.72 / Avg: 684.71 / Max: 754.83 Min: 54.76 / Avg: 672.12 / Max: 721.51 Min: 193.92 / Avg: 648.38 / Max: 695.92 Min: 186.72 / Avg: 591.08 / Max: 630.87 Min: 109.07 / Avg: 565.2 / Max: 671.32 Min: 104.8 / Avg: 529.37 / Max: 582.49 Min: 107.32 / Avg: 447.17 / Max: 525.92 Min: 35.8 / Avg: 401.15 / Max: 411.05 Min: 21.97 / Avg: 360.05 / Max: 375.06 Min: 21.83 / Avg: 339.43 / Max: 376.89 Min: 58.01 / Avg: 337.59 / Max: 352.56 Min: 27.82 / Avg: 330.48 / Max: 353.86 Min: 71.53 / Avg: 311.09 / Max: 362.15 Min: 74.91 / Avg: 283.74 / Max: 304.03 Min: 43.58 / Avg: 277.13 / Max: 331.03 Min: 54.07 / Avg: 264.65 / Max: 291.12 Min: 43.7 / Avg: 211.59 / Max: 250.8 Min: 16.74 / Avg: 164.05 / Max: 171.53 Min: 14.85 / Avg: 139.18 / Max: 148.57
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P Xeon 6766E EPYC 9754 Xeon 6780E EPYC 8534PN EPYC 8534P EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ 14 28 42 56 70 SE +/- 0.22, N = 12 SE +/- 0.03, N = 3 SE +/- 0.13, N = 9 SE +/- 0.23, N = 3 SE +/- 0.29, N = 12 SE +/- 0.24, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 SE +/- 0.38, N = 15 SE +/- 0.21, N = 3 SE +/- 0.34, N = 15 SE +/- 0.30, N = 15 SE +/- 0.26, N = 3 SE +/- 0.17, N = 3 SE +/- 0.72, N = 3 SE +/- 0.43, N = 15 SE +/- 0.12, N = 3 SE +/- 0.19, N = 3 13.76 14.81 15.97 16.24 16.82 26.91 27.53 30.87 33.18 33.76 34.65 34.69 37.45 37.55 37.84 40.83 41.65 48.99 51.05 51.86 56.44 63.30
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 EPYC 9684X 2P EPYC 9654 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X EPYC 9754 EPYC 9654 Xeon Max 9480 Xeon Max 9468 Xeon 6766E Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.0747 0.1494 0.2241 0.2988 0.3735 0.040 0.044 0.045 0.045 0.046 0.066 0.073 0.077 0.080 0.114 0.149 0.175 0.178 0.188 0.192 0.194 0.194 0.225 0.236 0.258 0.305 0.332
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 176.16 / Avg: 577.13 / Max: 637.06 Min: 202.76 / Avg: 570.95 / Max: 625.38 Min: 79.08 / Avg: 511.14 / Max: 575.41 Min: 161.18 / Avg: 490.32 / Max: 568.06 Min: 63.73 / Avg: 418.64 / Max: 475.03 Min: 58.93 / Avg: 369.53 / Max: 409.87 Min: 108.16 / Avg: 354.05 / Max: 391.41 Min: 105.19 / Avg: 327.79 / Max: 351.26 Min: 98.32 / Avg: 327.4 / Max: 419.31 Min: 39.07 / Avg: 298.03 / Max: 341.96 Min: 70.81 / Avg: 276.02 / Max: 323.04 Min: 74.44 / Avg: 265.6 / Max: 309.82 Min: 59.74 / Avg: 250.75 / Max: 298.2 Min: 34.92 / Avg: 245.26 / Max: 293.93 Min: 35.86 / Avg: 232.68 / Max: 261.18 Min: 56.55 / Avg: 207.89 / Max: 238.03 Min: 30.14 / Avg: 194.55 / Max: 219.58 Min: 43.48 / Avg: 159.18 / Max: 178.15 Min: 21.06 / Avg: 157.61 / Max: 175.55 Min: 43.57 / Avg: 138.61 / Max: 153.19 Min: 18.44 / Avg: 110.66 / Max: 125.07 Min: 17.13 / Avg: 99.8 / Max: 111.33
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: CPU Xeon Platinum 8380 Xeon Max 9468 Xeon 6766E 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon Max 9468 2P Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Max 9480 2P Xeon 6766E Xeon Platinum 8592+ Xeon 6780E Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9654 EPYC 9754 EPYC 9684X 3 6 9 12 15 SE +/- 0.06, N = 15 SE +/- 0.03, N = 3 SE +/- 0.10, N = 15 SE +/- 0.07, N = 15 SE +/- 0.08, N = 15 SE +/- 0.22, N = 12 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 15 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.17, N = 12 SE +/- 0.08, N = 15 SE +/- 0.11, N = 15 SE +/- 0.12, N = 15 SE +/- 0.10, N = 7 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 4.29 6.30 6.41 6.43 6.74 6.81 6.82 6.93 7.10 7.38 7.41 7.90 8.06 8.47 8.82 8.88 9.65 10.56 10.61 11.34 12.41 12.43
M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.6 Scene: LuxCore Benchmark - Acceleration: CPU Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 EPYC 9684X 2P Xeon Max 9468 EPYC 9654 2P Xeon 6780E 2P Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9684X Xeon 6780E EPYC 9654 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 0.0119 0.0238 0.0357 0.0476 0.0595 0.010 0.011 0.013 0.014 0.014 0.017 0.017 0.019 0.020 0.020 0.021 0.021 0.022 0.022 0.025 0.034 0.039 0.040 0.043 0.046 0.049 0.053
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.6 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9754 EPYC 9654 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 205.6 / Avg: 650.43 / Max: 750.56 Min: 129.79 / Avg: 649.71 / Max: 752.19 Min: 178.58 / Avg: 636.83 / Max: 753.39 Min: 83.65 / Avg: 634.64 / Max: 754.69 Min: 38.08 / Avg: 620.51 / Max: 723.33 Min: 58.25 / Avg: 537.06 / Max: 610.46 Min: 101 / Avg: 492.26 / Max: 580.68 Min: 40.41 / Avg: 450.3 / Max: 521.1 Min: 34.2 / Avg: 365.21 / Max: 410.93 Min: 107.86 / Avg: 344.5 / Max: 460.96 Min: 85.32 / Avg: 325.06 / Max: 364.85 Min: 74.54 / Avg: 324.24 / Max: 366.89 Min: 62.21 / Avg: 319.52 / Max: 375.32 Min: 34.18 / Avg: 318.84 / Max: 374.24 Min: 104.76 / Avg: 297.7 / Max: 400.24 Min: 23.22 / Avg: 288.11 / Max: 334.63 Min: 28.93 / Avg: 284.2 / Max: 318.53 Min: 52.8 / Avg: 250 / Max: 286.38 Min: 43.54 / Avg: 215.89 / Max: 253.56 Min: 43.63 / Avg: 172.93 / Max: 201.7 Min: 18.49 / Avg: 149.9 / Max: 169.31 Min: 17.5 / Avg: 131.25 / Max: 148.58
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 Xeon 6766E 2P EPYC 9754 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 Xeon 6766E Xeon 6780E Xeon Max 9480 2P EPYC 8534PN EPYC 8534P EPYC 9654 Xeon Platinum 8490H 2P EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8592+ 6 12 18 24 30 SE +/- 0.17, N = 9 SE +/- 0.15, N = 12 SE +/- 0.07, N = 3 SE +/- 0.27, N = 9 SE +/- 0.20, N = 12 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 8 SE +/- 0.06, N = 3 SE +/- 0.17, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 4 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.19, N = 5 SE +/- 0.18, N = 3 SE +/- 0.16, N = 3 SE +/- 0.09, N = 3 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 6.47 6.64 7.10 8.27 8.35 13.05 13.39 14.53 14.86 15.11 15.25 15.57 15.77 15.86 16.68 17.57 17.91 18.07 19.41 19.99 22.27 27.21
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 EPYC 9684X 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9684X Xeon Max 9468 Xeon Platinum 8490H EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.0351 0.0702 0.1053 0.1404 0.1755 0.020 0.020 0.020 0.022 0.022 0.026 0.031 0.033 0.034 0.056 0.067 0.069 0.076 0.080 0.081 0.084 0.092 0.096 0.111 0.113 0.146 0.156
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 196.56 / Avg: 578.74 / Max: 617.41 Min: 196.88 / Avg: 571.95 / Max: 613.16 Min: 79.16 / Avg: 511.35 / Max: 559.55 Min: 162.11 / Avg: 476.49 / Max: 563.05 Min: 61.36 / Avg: 418.43 / Max: 475.94 Min: 55.84 / Avg: 369.03 / Max: 409.77 Min: 107.67 / Avg: 362.4 / Max: 382.35 Min: 54.23 / Avg: 317.38 / Max: 347.71 Min: 20.22 / Avg: 296.81 / Max: 327.42 Min: 102.12 / Avg: 295.35 / Max: 320.3 Min: 73.16 / Avg: 270.76 / Max: 301.09 Min: 73.95 / Avg: 262.34 / Max: 291.94 Min: 58.34 / Avg: 242.81 / Max: 264.97 Min: 33.7 / Avg: 239.78 / Max: 273.27 Min: 30.38 / Avg: 228.52 / Max: 247.96 Min: 55.11 / Avg: 200.49 / Max: 223.6 Min: 27.2 / Avg: 192.05 / Max: 207.21 Min: 43.41 / Avg: 158.21 / Max: 172.64 Min: 19.56 / Avg: 155.97 / Max: 167.94 Min: 43.54 / Avg: 139.02 / Max: 150.49 Min: 16.21 / Avg: 104.37 / Max: 113.9 Min: 16.2 / Avg: 97.09 / Max: 104.85
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 2P Xeon 6766E Xeon Max 9468 Xeon 6780E Xeon Platinum 8490H Xeon Max 9480 Xeon Platinum 8592+ EPYC 9754 Xeon 6766E 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 7K 14K 21K 28K 35K SE +/- 32.20, N = 2 SE +/- 41.94, N = 3 SE +/- 30.53, N = 3 SE +/- 49.14, N = 12 SE +/- 19.74, N = 3 SE +/- 12.93, N = 3 SE +/- 43.00, N = 3 SE +/- 23.16, N = 3 SE +/- 14.78, N = 3 SE +/- 44.68, N = 3 SE +/- 61.27, N = 3 SE +/- 53.95, N = 3 SE +/- 14.02, N = 3 SE +/- 43.14, N = 3 SE +/- 4.03, N = 3 SE +/- 7.44, N = 3 SE +/- 117.32, N = 3 SE +/- 10.36, N = 3 SE +/- 64.69, N = 3 SE +/- 46.94, N = 3 SE +/- 290.50, N = 3 SE +/- 95.10, N = 3 2593.2 4564.3 4660.0 5230.9 5315.7 5446.8 5753.9 5808.8 6122.3 8378.3 9320.5 10431.6 10975.8 11147.2 11263.2 12115.0 14207.7 15786.6 16324.7 17873.1 26702.7 31157.8 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
H/s Per Watt
OpenBenchmarking.org H/s Per Watt, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon 6780E 2P Xeon 6766E 2P Xeon 6780E Xeon 6766E EPYC 8534P EPYC 9754 2P EPYC 8534PN EPYC 9754 EPYC 9684X EPYC 9684X 2P EPYC 9654 2P EPYC 9654 11 22 33 44 55 9.798 10.183 16.293 16.636 16.828 17.114 17.929 18.002 25.015 25.291 27.676 28.504 29.190 30.621 33.466 36.168 36.236 40.166 42.004 44.082 45.051 46.688
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xmrig 6.21 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9468 EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 60.4 / Avg: 706.81 / Max: 819.97 Min: 201.16 / Avg: 673.63 / Max: 702.68 Min: 188.92 / Avg: 672.99 / Max: 738.06 Min: 159.48 / Avg: 669.3 / Max: 730.91 Min: 73.19 / Avg: 645.48 / Max: 743.36 Min: 54.62 / Avg: 592.72 / Max: 673.62 Min: 95.12 / Avg: 513.7 / Max: 535.43 Min: 38.53 / Avg: 494.18 / Max: 551.71 Min: 104.75 / Avg: 402.77 / Max: 425.84 Min: 36 / Avg: 375.84 / Max: 410.13 Min: 103.58 / Avg: 365.97 / Max: 390.52 Min: 75.82 / Avg: 341.47 / Max: 356.09 Min: 55.89 / Avg: 339.42 / Max: 349.66 Min: 24.38 / Avg: 334.94 / Max: 357.54 Min: 73.18 / Avg: 327.41 / Max: 335.76 Min: 30.21 / Avg: 304.31 / Max: 328.13 Min: 53.3 / Avg: 264.66 / Max: 271.14 Min: 21.91 / Avg: 232.05 / Max: 250.74 Min: 43.43 / Avg: 197.12 / Max: 203.16 Min: 43.68 / Avg: 173.6 / Max: 178.87 Min: 17.62 / Avg: 139.24 / Max: 143.75 Min: 15.67 / Avg: 125.96 / Max: 131.33
LuxCoreRender LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6780E Xeon 6766E Xeon Max 9480 2P Xeon 6766E 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9754 EPYC 9684X EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 SE +/- 0.28, N = 15 SE +/- 0.46, N = 12 SE +/- 0.16, N = 15 SE +/- 0.46, N = 15 SE +/- 0.12, N = 3 SE +/- 0.30, N = 15 SE +/- 0.18, N = 15 SE +/- 0.07, N = 3 SE +/- 0.28, N = 5 SE +/- 0.84, N = 15 SE +/- 1.12, N = 15 SE +/- 1.06, N = 15 8.82 11.86 12.50 13.00 13.46 13.81 14.31 14.74 15.83 15.90 16.64 16.88 16.91 17.45 18.70 19.91 21.32 23.76 24.69 29.61 32.26 33.08
M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X 2P Xeon 6780E 2P EPYC 9654 2P Xeon 6766E 2P EPYC 9754 2P EPYC 9684X Xeon 6780E EPYC 9654 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 0.0227 0.0454 0.0681 0.0908 0.1135 0.025 0.026 0.029 0.029 0.031 0.035 0.036 0.038 0.042 0.046 0.046 0.048 0.051 0.053 0.059 0.066 0.071 0.072 0.080 0.083 0.092 0.101
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.6 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 150 300 450 600 750 Min: 66.69 / Avg: 722.97 / Max: 825.83 Min: 201.92 / Avg: 656.25 / Max: 748.81 Min: 204.79 / Avg: 656.04 / Max: 751.44 Min: 172.79 / Avg: 646.27 / Max: 748.56 Min: 82.44 / Avg: 639.12 / Max: 751.58 Min: 57.15 / Avg: 586.21 / Max: 670.16 Min: 41.55 / Avg: 551.09 / Max: 677.8 Min: 100.16 / Avg: 499.14 / Max: 582.6 Min: 33.09 / Avg: 373.72 / Max: 411.13 Min: 107.87 / Avg: 364.17 / Max: 576.89 Min: 83.75 / Avg: 327.46 / Max: 377.5 Min: 75.77 / Avg: 326.79 / Max: 375.2 Min: 61.77 / Avg: 323.08 / Max: 377.72 Min: 104.86 / Avg: 321.3 / Max: 495.12 Min: 34.75 / Avg: 320.73 / Max: 377.48 Min: 22.04 / Avg: 298.61 / Max: 336.88 Min: 27.54 / Avg: 296.6 / Max: 330.72 Min: 53 / Avg: 249.69 / Max: 290.48 Min: 43.49 / Avg: 223.98 / Max: 283.31 Min: 43.68 / Avg: 191.46 / Max: 222.84 Min: 19.16 / Avg: 150.1 / Max: 167.85 Min: 17.62 / Avg: 128.09 / Max: 142.09
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon Platinum 8380 2P EPYC 8534P Xeon Max 9480 Xeon 6766E Xeon 6780E Xeon Platinum 8490H EPYC 9654 Xeon Max 9468 2P Xeon Platinum 8592+ EPYC 9684X Xeon 6766E 2P Xeon Max 9480 2P EPYC 9754 Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P 13 26 39 52 65 SE +/- 0.00909, N = 3 SE +/- 0.00932, N = 3 SE +/- 0.00583, N = 3 SE +/- 0.03711, N = 3 SE +/- 0.01395, N = 3 SE +/- 0.03593, N = 3 SE +/- 0.00610, N = 3 SE +/- 0.01460, N = 3 SE +/- 0.00525, N = 3 SE +/- 0.01265, N = 3 SE +/- 0.05872, N = 3 SE +/- 0.04057, N = 3 SE +/- 0.01858, N = 3 SE +/- 0.04097, N = 3 SE +/- 0.04134, N = 3 SE +/- 0.02252, N = 3 SE +/- 0.02131, N = 3 SE +/- 0.02499, N = 3 SE +/- 0.04960, N = 3 SE +/- 0.04682, N = 3 SE +/- 0.01792, N = 3 SE +/- 0.01106, N = 3 9.70022 16.08690 16.45050 17.62220 17.94480 18.48510 19.42510 21.51470 21.89320 28.06890 29.34960 30.67990 32.52320 32.79790 33.12750 35.14640 36.24640 38.22690 47.52670 53.93480 55.25760 56.44850
Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon 6780E 2P EPYC 9684X Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9654 EPYC 9754 2P Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 0.0326 0.0652 0.0978 0.1304 0.163 0.039 0.041 0.047 0.053 0.061 0.061 0.063 0.074 0.081 0.086 0.091 0.094 0.098 0.106 0.106 0.107 0.107 0.121 0.133 0.136 0.139 0.145
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 3.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon Max 9468 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.89 / Avg: 682.63 / Max: 796.5 Min: 200.54 / Avg: 630.06 / Max: 725.99 Min: 191.04 / Avg: 627.62 / Max: 711.24 Min: 168.54 / Avg: 625.45 / Max: 728.13 Min: 67.98 / Avg: 591.05 / Max: 725.39 Min: 60.52 / Avg: 553.25 / Max: 625.16 Min: 42.57 / Avg: 526.9 / Max: 623.56 Min: 95.5 / Avg: 453.46 / Max: 555.04 Min: 108.67 / Avg: 386.65 / Max: 484.75 Min: 35.05 / Avg: 332.91 / Max: 399.84 Min: 105.71 / Avg: 310.52 / Max: 393.05 Min: 76.7 / Avg: 301.86 / Max: 366.25 Min: 59.59 / Avg: 296.81 / Max: 366.58 Min: 25.32 / Avg: 288.49 / Max: 368.86 Min: 22.25 / Avg: 264.01 / Max: 319.18 Min: 28.04 / Avg: 261.28 / Max: 302.78 Min: 74.87 / Avg: 255.3 / Max: 321.66 Min: 52.66 / Avg: 239.04 / Max: 286.42 Min: 43.6 / Avg: 178.41 / Max: 247.31 Min: 43.64 / Avg: 142.92 / Max: 193.36 Min: 18.42 / Avg: 129.01 / Max: 155.58 Min: 16.2 / Avg: 113.27 / Max: 134.96
RocksDB This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Read While Writing Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 8534PN EPYC 8534P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon 6766E Xeon 6780E Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9654 EPYC 9754 EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P 6M 12M 18M 24M 30M SE +/- 23120.76, N = 3 SE +/- 26369.56, N = 3 SE +/- 83772.27, N = 13 SE +/- 61518.27, N = 10 SE +/- 28201.44, N = 3 SE +/- 81998.56, N = 3 SE +/- 28098.62, N = 3 SE +/- 218479.19, N = 15 SE +/- 113154.86, N = 4 SE +/- 254193.37, N = 15 SE +/- 45015.86, N = 3 SE +/- 136761.19, N = 4 SE +/- 343737.14, N = 15 SE +/- 215352.04, N = 15 SE +/- 93669.97, N = 15 SE +/- 36524.26, N = 3 SE +/- 109424.14, N = 3 SE +/- 236709.61, N = 3 SE +/- 506458.47, N = 15 SE +/- 273109.47, N = 3 SE +/- 426084.70, N = 15 SE +/- 726178.20, N = 12 5539870 7366500 7439663 7841738 8926893 8934176 9333645 9624417 9836689 11223329 11340389 11864815 12321300 12425519 14158419 14608544 15776186 19851664 20108289 22900152 24466143 27059786 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Op/s Per Watt
OpenBenchmarking.org Op/s Per Watt, More Is Better RocksDB 9.0 Test: Read While Writing Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 9754 2P EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN Xeon 6780E 2P Xeon 6766E 2P 15K 30K 45K 60K 75K 14775.49 16920.46 18781.27 19253.52 21648.99 22200.62 22256.95 22369.26 23723.76 27560.28 29572.89 34889.65 36906.83 45330.18 48605.69 52342.46 56900.62 60067.21 63183.03 66672.70 67516.29 69851.75
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RocksDB 9.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.1 / Avg: 671.28 / Max: 820.11 Min: 185.7 / Avg: 663.3 / Max: 752.58 Min: 157.04 / Avg: 656.04 / Max: 755.91 Min: 200.41 / Avg: 651.38 / Max: 755.47 Min: 56.63 / Avg: 576.34 / Max: 690.47 Min: 67.94 / Avg: 558.28 / Max: 752.93 Min: 98.57 / Avg: 510.9 / Max: 583.45 Min: 43.23 / Avg: 505.19 / Max: 682.09 Min: 108.91 / Avg: 400.79 / Max: 709.44 Min: 34.3 / Avg: 383.63 / Max: 411.02 Min: 107.56 / Avg: 350.26 / Max: 540.44 Min: 72.31 / Avg: 332.58 / Max: 376.04 Min: 74.89 / Avg: 331.82 / Max: 375.82 Min: 52.65 / Avg: 330.54 / Max: 376.66 Min: 33.11 / Avg: 323.9 / Max: 378.14 Min: 22 / Avg: 301.4 / Max: 339.84 Min: 24.6 / Avg: 300.55 / Max: 337.2 Min: 55.14 / Avg: 255.9 / Max: 290.56 Min: 43.57 / Avg: 208.52 / Max: 356.32 Min: 43.66 / Avg: 179.48 / Max: 270.38 Min: 17.34 / Avg: 155.39 / Max: 168.8 Min: 17.36 / Avg: 134 / Max: 149.2
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Platinum 8380 EPYC 8534P EPYC 9754 2P EPYC 8534PN EPYC 9754 EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X 11 22 33 44 55 SE +/- 0.36, N = 11 SE +/- 0.35, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.40, N = 3 SE +/- 0.33, N = 3 SE +/- 0.31, N = 3 SE +/- 0.11, N = 3 SE +/- 0.35, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.63, N = 15 SE +/- 0.23, N = 15 SE +/- 0.61, N = 15 SE +/- 0.45, N = 15 SE +/- 0.61, N = 15 SE +/- 0.50, N = 15 SE +/- 0.40, N = 15 SE +/- 0.61, N = 15 47.20 43.81 41.08 36.78 36.23 36.00 33.99 33.33 29.76 29.75 29.41 29.02 28.85 28.02 27.93 27.90 26.83 26.45 25.32 23.92 22.79 21.58 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 90 180 270 360 450 Min: 60.67 / Avg: 475.62 / Max: 514.58 Min: 103.45 / Avg: 419.57 / Max: 461.32 Min: 54.43 / Avg: 417.34 / Max: 450.65 Min: 40.25 / Avg: 308.06 / Max: 331.38 Min: 31.9 / Avg: 250.92 / Max: 275.39 Min: 106.43 / Avg: 248.46 / Max: 271.28 Min: 104.4 / Avg: 226.53 / Max: 245.57 Min: 53.43 / Avg: 226.19 / Max: 247.32 Min: 26.28 / Avg: 211.37 / Max: 231.46 Min: 19.69 / Avg: 171.56 / Max: 188.27 Min: 43.52 / Avg: 154.49 / Max: 168.64 Min: 43.64 / Avg: 132.23 / Max: 144.22 Min: 18.14 / Avg: 109.41 / Max: 118.96 Min: 16.01 / Avg: 98.3 / Max: 106.86
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Platinum 8380 EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9754 EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X 11 22 33 44 55 SE +/- 0.16, N = 11 SE +/- 0.18, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.31, N = 3 SE +/- 0.26, N = 3 SE +/- 0.27, N = 3 SE +/- 0.09, N = 3 SE +/- 0.40, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.27, N = 15 SE +/- 0.87, N = 15 SE +/- 0.82, N = 15 SE +/- 0.63, N = 15 SE +/- 0.92, N = 15 SE +/- 0.91, N = 15 SE +/- 0.76, N = 15 SE +/- 1.36, N = 15 21.20 22.83 24.34 27.18 27.61 27.78 29.43 30.00 33.60 33.61 34.00 34.46 34.66 35.69 35.87 36.08 37.53 37.96 39.80 42.07 44.06 46.88 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Platinum 8380 EPYC 8534P EPYC 9754 2P EPYC 8534PN EPYC 9754 EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X 11 22 33 44 55 SE +/- 0.36, N = 11 SE +/- 0.35, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.40, N = 3 SE +/- 0.33, N = 3 SE +/- 0.31, N = 3 SE +/- 0.11, N = 3 SE +/- 0.35, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.63, N = 15 SE +/- 0.23, N = 15 SE +/- 0.61, N = 15 SE +/- 0.45, N = 15 SE +/- 0.61, N = 15 SE +/- 0.50, N = 15 SE +/- 0.40, N = 15 SE +/- 0.61, N = 15 47.20 43.81 41.08 36.78 36.23 36.00 33.99 33.33 29.76 29.75 29.41 29.02 28.85 28.02 27.93 27.90 26.83 26.45 25.32 23.92 22.79 21.58 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenFOAM OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time EPYC 9754 2P EPYC 8534PN Xeon Platinum 8380 EPYC 9754 EPYC 8534P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X 2P Xeon Max 9468 2P EPYC 9684X 40 80 120 160 200 192.42 188.37 182.24 167.41 163.70 162.32 162.03 160.73 159.31 153.12 150.67 148.40 140.48 139.62 136.40 135.52 134.78 118.54 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
Timed LLVM Compilation This test times how long it takes to compile/build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 16.0 Build System: Ninja Xeon Platinum 8380 EPYC 8534PN Xeon Max 9468 EPYC 8534P Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon 6766E Xeon 6780E Xeon Platinum 8592+ EPYC 9754 Xeon 6766E 2P EPYC 9654 Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6780E 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 60 120 180 240 300 SE +/- 1.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 SE +/- 0.20, N = 3 SE +/- 0.36, N = 3 SE +/- 0.37, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.74, N = 3 SE +/- 1.52, N = 3 SE +/- 0.31, N = 3 SE +/- 0.17, N = 3 SE +/- 0.79, N = 3 SE +/- 0.05, N = 3 SE +/- 0.27, N = 3 SE +/- 0.15, N = 3 SE +/- 0.27, N = 3 SE +/- 0.45, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 298.41 215.93 212.48 205.01 197.84 194.38 187.02 184.20 169.45 165.05 146.76 138.57 135.67 134.42 128.07 125.27 124.46 122.31 106.82 101.56 94.81 89.28
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed LLVM Compilation 16.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 201.26 / Avg: 591.84 / Max: 754.62 Min: 206.76 / Avg: 582.56 / Max: 754.19 Min: 162.49 / Avg: 544.93 / Max: 754.95 Min: 81.57 / Avg: 519.72 / Max: 754.2 Min: 69.22 / Avg: 491.18 / Max: 825.37 Min: 106.11 / Avg: 438.51 / Max: 581.89 Min: 52.7 / Avg: 427.31 / Max: 682.72 Min: 41.44 / Avg: 382.15 / Max: 678.1 Min: 74.97 / Avg: 314.74 / Max: 377.51 Min: 83.29 / Avg: 311.03 / Max: 377.86 Min: 58.01 / Avg: 298.24 / Max: 377.21 Min: 33.37 / Avg: 291.41 / Max: 377.45 Min: 33.31 / Avg: 289.22 / Max: 411.83 Min: 107.08 / Avg: 281.29 / Max: 590.24 Min: 104.24 / Avg: 248.44 / Max: 496.75 Min: 51.36 / Avg: 243.86 / Max: 291.49 Min: 28.01 / Avg: 241.32 / Max: 332.83 Min: 21.92 / Avg: 221.05 / Max: 334.41 Min: 43.38 / Avg: 172.6 / Max: 293.27 Min: 43.51 / Avg: 148.04 / Max: 239.55 Min: 16.99 / Avg: 134 / Max: 170.95 Min: 15.37 / Avg: 117.14 / Max: 147.36
Memcached Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 9654 EPYC 9654 2P EPYC 9684X EPYC 9684X 2P 2M 4M 6M 8M 10M SE +/- 16910.46, N = 15 SE +/- 16926.98, N = 15 SE +/- 19070.02, N = 15 SE +/- 19998.04, N = 15 SE +/- 50660.01, N = 15 SE +/- 26891.33, N = 3 SE +/- 24083.78, N = 3 SE +/- 35300.21, N = 3 SE +/- 52575.97, N = 3 SE +/- 21428.06, N = 3 SE +/- 25335.31, N = 3 SE +/- 35182.67, N = 3 SE +/- 101903.23, N = 15 SE +/- 38410.91, N = 15 SE +/- 41123.40, N = 3 SE +/- 36366.89, N = 3 SE +/- 14591.70, N = 3 SE +/- 38372.96, N = 3 SE +/- 29027.89, N = 3 SE +/- 83562.82, N = 3 SE +/- 58081.25, N = 3 SE +/- 27143.58, N = 3 1783869.96 1821144.00 2299150.51 2339570.28 3245908.40 3373323.92 3392842.38 3780240.56 4315467.17 4384040.52 4481667.95 4752673.79 4814941.53 4826284.80 5820618.18 6198256.72 7645325.70 7736018.74 8220895.45 8498306.78 8634258.39 8683410.79 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Ops/sec Per Watt
OpenBenchmarking.org Ops/sec Per Watt, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ Xeon 6780E EPYC 9754 2P Xeon Platinum 8380 Xeon 6766E EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 11K 22K 33K 44K 55K 5947.33 5975.55 6127.33 7280.70 7668.81 8031.40 10688.23 14272.39 15062.13 15564.53 15985.01 17990.14 18089.30 18800.36 19415.88 20130.49 21456.14 25824.73 31074.26 32910.93 44935.74 51146.06
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Memcached 1.6.19 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9654 Xeon Platinum 8592+ Xeon 6780E 2P Xeon Platinum 8380 EPYC 9754 Xeon 6766E 2P EPYC 8534P Xeon 6780E EPYC 8534PN Xeon 6766E 110 220 330 440 550 Min: 189.98 / Avg: 567.79 / Max: 640.73 Min: 197.32 / Avg: 550.54 / Max: 613.93 Min: 165.51 / Avg: 545.78 / Max: 623.84 Min: 64.05 / Avg: 543.22 / Max: 637.08 Min: 62.89 / Avg: 492.94 / Max: 577.85 Min: 55.17 / Avg: 472.39 / Max: 548.36 Min: 98.17 / Avg: 450.49 / Max: 528.19 Min: 40.14 / Avg: 393.77 / Max: 460.35 Min: 33.48 / Avg: 334.34 / Max: 390.93 Min: 56.01 / Avg: 302.36 / Max: 343.09 Min: 70.74 / Avg: 291.06 / Max: 331.31 Min: 53.66 / Avg: 287.94 / Max: 334.72 Min: 26.63 / Avg: 264.56 / Max: 307.16 Min: 24.01 / Avg: 262.73 / Max: 308.93 Min: 107.52 / Avg: 250.13 / Max: 283.85 Min: 53.19 / Avg: 239.75 / Max: 291.89 Min: 21.61 / Avg: 235.06 / Max: 274.9 Min: 104.69 / Avg: 222.11 / Max: 257.75 Min: 19.03 / Avg: 137.94 / Max: 159.73 Min: 43.41 / Avg: 124.44 / Max: 142.61 Min: 16.61 / Avg: 113.8 / Max: 137.75 Min: 43.49 / Avg: 107.16 / Max: 120.67
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E EPYC 9654 2P EPYC 9684X 2P Xeon 6780E EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8380 2P EPYC 9654 EPYC 9684X Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.06840, N = 3 SE +/- 0.00701, N = 3 SE +/- 0.10131, N = 15 SE +/- 0.08614, N = 3 SE +/- 0.20624, N = 12 SE +/- 0.14799, N = 15 SE +/- 0.03249, N = 3 SE +/- 0.07891, N = 15 SE +/- 0.06816, N = 3 SE +/- 0.01358, N = 3 SE +/- 0.09530, N = 15 SE +/- 0.03225, N = 3 SE +/- 0.05392, N = 15 SE +/- 0.04633, N = 15 SE +/- 0.01280, N = 3 SE +/- 0.08822, N = 15 SE +/- 0.01598, N = 3 SE +/- 0.03815, N = 5 SE +/- 0.02572, N = 3 SE +/- 0.01810, N = 3 SE +/- 0.02187, N = 3 SE +/- 0.01476, N = 3 12.43450 11.48200 8.51808 7.68977 7.55558 7.09682 6.97509 6.22791 6.17796 5.83954 5.74491 5.62517 4.74221 4.57029 4.49317 4.46135 4.10914 3.37034 3.18392 3.17002 3.02897 2.98306 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 60.4 / Avg: 551.5 / Max: 590.7 Min: 55.26 / Avg: 482.11 / Max: 517.72 Min: 101.4 / Avg: 445.3 / Max: 473.57 Min: 39.76 / Avg: 407.81 / Max: 436.29 Min: 108.03 / Avg: 350.61 / Max: 370.78 Min: 104.79 / Avg: 305.05 / Max: 321.54 Min: 31.68 / Avg: 288.98 / Max: 309.48 Min: 29.39 / Avg: 241.91 / Max: 260.94 Min: 54.43 / Avg: 235.28 / Max: 251.36 Min: 15.87 / Avg: 195.33 / Max: 210.52 Min: 43.64 / Avg: 174.72 / Max: 185.33 Min: 43.68 / Avg: 148.15 / Max: 156.57 Min: 17.38 / Avg: 123.79 / Max: 132.65 Min: 15.97 / Avg: 109.73 / Max: 119.37
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E EPYC 9654 2P EPYC 9684X 2P Xeon 6780E EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8380 2P EPYC 9654 EPYC 9684X Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8380 70 140 210 280 350 SE +/- 0.44, N = 3 SE +/- 0.05, N = 3 SE +/- 1.44, N = 15 SE +/- 1.47, N = 3 SE +/- 3.84, N = 12 SE +/- 3.21, N = 15 SE +/- 0.67, N = 3 SE +/- 2.12, N = 15 SE +/- 1.78, N = 3 SE +/- 0.40, N = 3 SE +/- 2.72, N = 15 SE +/- 1.01, N = 3 SE +/- 2.40, N = 15 SE +/- 2.24, N = 15 SE +/- 0.64, N = 3 SE +/- 4.35, N = 15 SE +/- 0.95, N = 3 SE +/- 3.31, N = 5 SE +/- 2.52, N = 3 SE +/- 1.80, N = 3 SE +/- 2.40, N = 3 SE +/- 1.65, N = 3 80.42 87.09 117.62 130.06 133.49 141.83 143.36 160.90 161.89 171.23 174.68 177.76 211.19 219.06 222.52 225.31 243.34 296.80 314.06 315.41 330.10 335.15 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E EPYC 9654 2P EPYC 9684X 2P Xeon 6780E EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8380 2P EPYC 9654 EPYC 9684X Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8380 3 6 9 12 15 SE +/- 0.06840, N = 3 SE +/- 0.00701, N = 3 SE +/- 0.10131, N = 15 SE +/- 0.08614, N = 3 SE +/- 0.20624, N = 12 SE +/- 0.14799, N = 15 SE +/- 0.03249, N = 3 SE +/- 0.07891, N = 15 SE +/- 0.06816, N = 3 SE +/- 0.01358, N = 3 SE +/- 0.09530, N = 15 SE +/- 0.03225, N = 3 SE +/- 0.05392, N = 15 SE +/- 0.04633, N = 15 SE +/- 0.01280, N = 3 SE +/- 0.08822, N = 15 SE +/- 0.01598, N = 3 SE +/- 0.03815, N = 5 SE +/- 0.02572, N = 3 SE +/- 0.01810, N = 3 SE +/- 0.02187, N = 3 SE +/- 0.01476, N = 3 12.43450 11.48200 8.51808 7.68977 7.55558 7.09682 6.97509 6.22791 6.17796 5.83954 5.74491 5.62517 4.74221 4.57029 4.49317 4.46135 4.10914 3.37034 3.18392 3.17002 3.02897 2.98306 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: ATPase with 327,506 Atoms Xeon Platinum 8490H 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8380 Xeon 6780E Xeon 6766E Xeon Platinum 8592+ EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 9754 EPYC 9654 EPYC 9684X EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 5 10 15 20 25 SE +/- 0.17435, N = 15 SE +/- 0.20408, N = 12 SE +/- 0.19805, N = 15 SE +/- 0.44989, N = 15 SE +/- 0.21567, N = 12 SE +/- 0.02582, N = 3 SE +/- 0.17734, N = 15 SE +/- 0.02593, N = 3 SE +/- 0.54361, N = 15 SE +/- 0.00431, N = 4 SE +/- 0.04338, N = 5 SE +/- 0.34017, N = 12 SE +/- 0.14537, N = 15 SE +/- 0.16058, N = 15 SE +/- 0.07204, N = 4 SE +/- 0.26203, N = 15 SE +/- 0.04917, N = 5 SE +/- 0.01368, N = 5 SE +/- 0.02148, N = 6 SE +/- 0.04751, N = 3 SE +/- 0.02125, N = 3 SE +/- 0.08771, N = 3 2.21948 2.39770 2.55400 2.56319 2.97021 3.60479 3.76348 3.76811 4.64814 5.44971 5.70672 5.85267 5.92501 5.97130 6.72663 7.30065 7.99756 8.18275 9.33534 17.81105 18.97454 20.75259
ns/day Per Watt
OpenBenchmarking.org ns/day Per Watt, More Is Better NAMD 3.0b6 Input: ATPase with 327,506 Atoms Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8592+ Xeon Max 9480 Xeon Max 9468 Xeon 6780E Xeon 6766E EPYC 9654 EPYC 9754 EPYC 9684X EPYC 8534P EPYC 8534PN EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P 0.0189 0.0378 0.0567 0.0756 0.0945 0.004 0.005 0.009 0.011 0.011 0.012 0.014 0.017 0.017 0.020 0.022 0.024 0.029 0.034 0.044 0.048 0.052 0.052 0.056 0.064 0.068 0.084
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAMD 3.0b6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon Max 9480 Xeon 6780E 2P EPYC 9654 2P Xeon Platinum 8490H Xeon Max 9468 Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9754 2P Xeon Platinum 8380 EPYC 9654 EPYC 9684X EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 190.7 / Avg: 550.3 / Max: 686.19 Min: 165.98 / Avg: 533.68 / Max: 633.47 Min: 194.24 / Avg: 522.05 / Max: 693.75 Min: 75.47 / Avg: 484.77 / Max: 671.95 Min: 101.59 / Avg: 389.17 / Max: 564.97 Min: 62.44 / Avg: 326.5 / Max: 779.77 Min: 73.99 / Avg: 269.88 / Max: 376.76 Min: 106.87 / Avg: 266.5 / Max: 492.66 Min: 58.84 / Avg: 262.91 / Max: 648.62 Min: 55.01 / Avg: 258.53 / Max: 352.06 Min: 73.54 / Avg: 248.99 / Max: 374.54 Min: 72.63 / Avg: 236.64 / Max: 427.46 Min: 33.34 / Avg: 236.13 / Max: 373.62 Min: 40.88 / Avg: 225.05 / Max: 615.88 Min: 54.68 / Avg: 216.04 / Max: 281.76 Min: 27.01 / Avg: 187.68 / Max: 312.41 Min: 29.28 / Avg: 180.85 / Max: 379.02 Min: 20.68 / Avg: 165.67 / Max: 289.24 Min: 43.48 / Avg: 132.04 / Max: 342.42 Min: 43.66 / Avg: 112.28 / Max: 262.76 Min: 17 / Avg: 109.51 / Max: 166.07 Min: 16.45 / Avg: 96.77 / Max: 141.98
Speedb Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read While Writing Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon 6766E Xeon Platinum 8592+ 2P Xeon 6780E EPYC 9654 EPYC 9684X EPYC 9754 Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 8M 16M 24M 32M 40M SE +/- 48302.92, N = 15 SE +/- 88257.34, N = 3 SE +/- 93731.24, N = 7 SE +/- 62510.72, N = 3 SE +/- 48351.08, N = 3 SE +/- 86788.79, N = 3 SE +/- 88013.69, N = 15 SE +/- 143570.67, N = 4 SE +/- 171807.74, N = 3 SE +/- 197596.27, N = 3 SE +/- 239363.92, N = 3 SE +/- 45758.35, N = 3 SE +/- 195912.00, N = 15 SE +/- 75416.94, N = 3 SE +/- 170909.18, N = 3 SE +/- 118870.12, N = 3 SE +/- 172052.60, N = 3 SE +/- 138092.00, N = 3 SE +/- 223786.94, N = 15 SE +/- 746932.76, N = 15 SE +/- 651901.79, N = 15 SE +/- 803844.71, N = 15 7147120 8795408 9988176 10695360 11795318 11882103 12053901 12168413 13859254 15354400 17297027 17548934 17585737 17945745 18024993 19595777 22829426 27630781 27657776 30324596 33307574 36593204 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Op/s Per Watt
OpenBenchmarking.org Op/s Per Watt, More Is Better Speedb 2.7 Test: Read While Writing Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9684X 2P EPYC 9654 2P EPYC 9654 Xeon 6780E 2P Xeon 6766E 2P EPYC 8534P EPYC 9754 2P Xeon 6780E EPYC 9754 EPYC 8534PN Xeon 6766E 20K 40K 60K 80K 100K 21183.20 23023.23 23084.61 26260.05 26509.91 27890.69 29984.58 30648.42 32356.04 37383.41 57032.77 57884.56 61034.97 63472.87 69360.79 77049.13 79851.05 85339.03 90565.21 93506.84 97163.65 103697.42
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Speedb 2.7 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 210.91 / Avg: 666.91 / Max: 751.13 Min: 164.82 / Avg: 658.68 / Max: 750.75 Min: 210.71 / Avg: 654.26 / Max: 754.28 Min: 64.91 / Avg: 575.41 / Max: 820.95 Min: 78.24 / Avg: 573.79 / Max: 750.97 Min: 105.62 / Avg: 510.96 / Max: 581.73 Min: 56.42 / Avg: 496.84 / Max: 614.4 Min: 41.53 / Avg: 428.8 / Max: 640.33 Min: 108.97 / Avg: 398.75 / Max: 547.56 Min: 107.63 / Avg: 358.61 / Max: 475.78 Min: 32.81 / Avg: 343.59 / Max: 411.18 Min: 74.62 / Avg: 333.11 / Max: 375.39 Min: 78.68 / Avg: 331.78 / Max: 377.28 Min: 52.35 / Avg: 330.55 / Max: 376.19 Min: 34.03 / Avg: 325.5 / Max: 377.13 Min: 26.3 / Avg: 283.98 / Max: 305.25 Min: 52.53 / Avg: 256.25 / Max: 291.99 Min: 22.4 / Avg: 244.15 / Max: 314.31 Min: 43.55 / Avg: 198.15 / Max: 300.83 Min: 43.64 / Avg: 169.23 / Max: 238.92 Min: 17.32 / Avg: 150.95 / Max: 163.43 Min: 17.9 / Avg: 122.29 / Max: 139.21
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P Xeon 6766E EPYC 9754 Xeon 6780E EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 14 28 42 56 70 SE +/- 0.23, N = 9 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.35, N = 12 SE +/- 0.37, N = 12 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 SE +/- 0.33, N = 5 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.26, N = 3 SE +/- 0.50, N = 3 SE +/- 0.40, N = 15 SE +/- 0.46, N = 4 SE +/- 0.12, N = 3 SE +/- 0.51, N = 3 SE +/- 0.14, N = 3 SE +/- 0.62, N = 3 SE +/- 0.71, N = 3 SE +/- 0.24, N = 3 SE +/- 0.12, N = 3 13.68 14.84 16.10 17.07 17.28 26.89 27.68 30.69 33.23 33.49 34.71 35.01 37.08 37.75 38.30 40.77 42.35 48.99 51.35 51.55 56.01 63.06
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 EPYC 9684X 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X EPYC 9754 EPYC 9654 Xeon Max 9480 Xeon Max 9468 Xeon 6780E Xeon 6766E Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.0761 0.1522 0.2283 0.3044 0.3805 0.042 0.044 0.045 0.046 0.046 0.066 0.074 0.076 0.080 0.116 0.150 0.175 0.179 0.186 0.193 0.193 0.194 0.223 0.236 0.258 0.308 0.338
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 194.23 / Avg: 577.63 / Max: 637.3 Min: 202.91 / Avg: 568.79 / Max: 623.75 Min: 81.92 / Avg: 507.01 / Max: 574.06 Min: 162.87 / Avg: 486.48 / Max: 565.96 Min: 62.55 / Avg: 415.63 / Max: 466.73 Min: 54.65 / Avg: 367.41 / Max: 412.66 Min: 108.31 / Avg: 363.14 / Max: 388.67 Min: 104.56 / Avg: 326.43 / Max: 349.99 Min: 100.89 / Avg: 325.09 / Max: 418.72 Min: 40.2 / Avg: 299.48 / Max: 333.06 Min: 76.06 / Avg: 275.89 / Max: 319.9 Min: 73.38 / Avg: 266.73 / Max: 308.34 Min: 60.41 / Avg: 250.31 / Max: 298.35 Min: 35.31 / Avg: 244 / Max: 293.19 Min: 35.79 / Avg: 231.06 / Max: 261.25 Min: 53.3 / Avg: 207.69 / Max: 238.28 Min: 28.44 / Avg: 195.3 / Max: 220.5 Min: 43.46 / Avg: 159.15 / Max: 179.26 Min: 21.23 / Avg: 158.01 / Max: 176.03 Min: 43.6 / Avg: 138.69 / Max: 152.97 Min: 19.48 / Avg: 108.57 / Max: 123.57 Min: 15.03 / Avg: 98.23 / Max: 110.34
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P EPYC 8534P EPYC 9754 EPYC 8534PN Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 40 80 120 160 200 SE +/- 1.15, N = 3 SE +/- 0.28, N = 3 SE +/- 0.34, N = 3 SE +/- 0.35, N = 3 SE +/- 1.27, N = 15 SE +/- 0.98, N = 15 SE +/- 0.56, N = 15 SE +/- 0.07, N = 3 SE +/- 0.40, N = 15 SE +/- 0.31, N = 15 SE +/- 0.18, N = 3 SE +/- 0.36, N = 3 SE +/- 0.39, N = 13 SE +/- 0.28, N = 4 SE +/- 0.21, N = 3 SE +/- 0.03, N = 3 SE +/- 0.33, N = 3 SE +/- 0.09, N = 3 SE +/- 0.32, N = 15 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 179.14 167.97 106.69 96.69 55.92 42.89 42.51 32.92 32.47 32.23 29.44 27.59 26.09 25.48 24.65 24.11 23.66 21.96 21.22 19.60 18.93 15.04 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 58.32 / Avg: 553.19 / Max: 601.27 Min: 56.82 / Avg: 486.07 / Max: 528.33 Min: 99.93 / Avg: 462.76 / Max: 500.69 Min: 37.61 / Avg: 403.98 / Max: 434.7 Min: 107.32 / Avg: 350.27 / Max: 375.87 Min: 103.92 / Avg: 301.78 / Max: 322.43 Min: 34.41 / Avg: 294.42 / Max: 320.91 Min: 25.68 / Avg: 250.64 / Max: 270.41 Min: 53.12 / Avg: 250.25 / Max: 269.16 Min: 20.36 / Avg: 200.16 / Max: 217.19 Min: 43.54 / Avg: 183.75 / Max: 198.81 Min: 43.72 / Avg: 151.02 / Max: 162.14 Min: 17.21 / Avg: 132.4 / Max: 145.89 Min: 16.31 / Avg: 120.57 / Max: 131.45
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P EPYC 8534P EPYC 9754 EPYC 8534PN Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 15 30 45 60 75 SE +/- 0.03571, N = 3 SE +/- 0.00992, N = 3 SE +/- 0.02972, N = 3 SE +/- 0.03724, N = 3 SE +/- 0.40826, N = 15 SE +/- 0.56636, N = 15 SE +/- 0.31646, N = 15 SE +/- 0.06539, N = 3 SE +/- 0.38216, N = 15 SE +/- 0.29092, N = 15 SE +/- 0.20595, N = 3 SE +/- 0.47575, N = 3 SE +/- 0.50579, N = 13 SE +/- 0.42374, N = 4 SE +/- 0.34209, N = 3 SE +/- 0.05911, N = 3 SE +/- 0.58786, N = 3 SE +/- 0.18826, N = 3 SE +/- 0.69010, N = 15 SE +/- 0.54692, N = 3 SE +/- 0.16471, N = 3 SE +/- 0.82440, N = 3 5.58241 5.95283 9.37294 10.34250 18.01330 23.49600 23.57860 30.37430 30.85720 31.06440 33.96210 36.24930 38.42400 39.25860 40.56710 41.47450 42.27470 45.54140 47.27030 51.01720 52.81670 66.51620 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P EPYC 8534P EPYC 9754 EPYC 8534PN Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 40 80 120 160 200 SE +/- 1.15, N = 3 SE +/- 0.28, N = 3 SE +/- 0.34, N = 3 SE +/- 0.35, N = 3 SE +/- 1.27, N = 15 SE +/- 0.98, N = 15 SE +/- 0.56, N = 15 SE +/- 0.07, N = 3 SE +/- 0.40, N = 15 SE +/- 0.31, N = 15 SE +/- 0.18, N = 3 SE +/- 0.36, N = 3 SE +/- 0.39, N = 13 SE +/- 0.28, N = 4 SE +/- 0.21, N = 3 SE +/- 0.03, N = 3 SE +/- 0.33, N = 3 SE +/- 0.09, N = 3 SE +/- 0.32, N = 15 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 179.14 167.97 106.69 96.69 55.92 42.89 42.51 32.92 32.47 32.23 29.44 27.59 26.09 25.48 24.65 24.11 23.66 21.96 21.22 19.60 18.93 15.04 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9654 EPYC 9684X Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 30 60 90 120 150 SE +/- 6.85, N = 15 SE +/- 6.88, N = 15 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.90, N = 6 SE +/- 2.33, N = 12 SE +/- 2.80, N = 15 SE +/- 0.70, N = 15 SE +/- 1.26, N = 3 SE +/- 0.51, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.62, N = 3 SE +/- 0.68, N = 3 SE +/- 1.12, N = 15 SE +/- 0.29, N = 3 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 SE +/- 1.84, N = 12 SE +/- 0.44, N = 3 SE +/- 0.44, N = 3 SE +/- 0.04, N = 3 155.90 141.57 124.06 111.87 93.83 93.64 90.06 87.66 86.65 80.72 72.12 71.56 60.36 60.11 55.90 54.28 49.97 49.64 48.47 47.24 44.60 39.75 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X Xeon Platinum 8380 Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 90 180 270 360 450 Min: 63.67 / Avg: 460.32 / Max: 497.92 Min: 95.98 / Avg: 424.24 / Max: 455.9 Min: 56.36 / Avg: 405.91 / Max: 434.32 Min: 38.39 / Avg: 302.95 / Max: 323.86 Min: 33.42 / Avg: 261.74 / Max: 283.2 Min: 51.89 / Avg: 246.13 / Max: 266.29 Min: 106.24 / Avg: 233.19 / Max: 250.31 Min: 29.64 / Avg: 222.91 / Max: 240.57 Min: 104.06 / Avg: 210.79 / Max: 227.9 Min: 20.33 / Avg: 188.2 / Max: 202.92 Min: 43.51 / Avg: 163.29 / Max: 175 Min: 43.62 / Avg: 139.52 / Max: 148.88 Min: 16.8 / Avg: 119.38 / Max: 129.78 Min: 16.97 / Avg: 101.89 / Max: 112.56
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9654 EPYC 9684X Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 6 12 18 24 30 SE +/- 0.31004, N = 15 SE +/- 0.36771, N = 15 SE +/- 0.00331, N = 3 SE +/- 0.00509, N = 3 SE +/- 0.10002, N = 6 SE +/- 0.26635, N = 12 SE +/- 0.38561, N = 15 SE +/- 0.09294, N = 15 SE +/- 0.16639, N = 3 SE +/- 0.07825, N = 3 SE +/- 0.03352, N = 3 SE +/- 0.03564, N = 3 SE +/- 0.16743, N = 3 SE +/- 0.18711, N = 3 SE +/- 0.35497, N = 15 SE +/- 0.09869, N = 3 SE +/- 0.09194, N = 3 SE +/- 0.07031, N = 3 SE +/- 0.58074, N = 12 SE +/- 0.19764, N = 3 SE +/- 0.21982, N = 3 SE +/- 0.02370, N = 3 6.60471 7.31285 8.06013 8.93833 10.66150 10.75188 11.27070 11.41820 11.54470 12.38840 13.86470 13.97450 16.57050 16.63940 17.98730 18.42220 20.01030 20.14530 20.87230 21.17020 22.42510 25.15910 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9654 EPYC 9684X Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 30 60 90 120 150 SE +/- 6.85, N = 15 SE +/- 6.88, N = 15 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.90, N = 6 SE +/- 2.33, N = 12 SE +/- 2.80, N = 15 SE +/- 0.70, N = 15 SE +/- 1.26, N = 3 SE +/- 0.51, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.62, N = 3 SE +/- 0.68, N = 3 SE +/- 1.12, N = 15 SE +/- 0.29, N = 3 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 SE +/- 1.84, N = 12 SE +/- 0.44, N = 3 SE +/- 0.44, N = 3 SE +/- 0.04, N = 3 155.90 141.57 124.06 111.87 93.83 93.64 90.06 87.66 86.65 80.72 72.12 71.56 60.36 60.11 55.90 54.28 49.97 49.64 48.47 47.24 44.60 39.75 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9754 EPYC 8534P EPYC 9654 2P EPYC 9684X 2P Xeon 6766E EPYC 8534PN Xeon 6780E Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 0.8143 1.6286 2.4429 3.2572 4.0715 SE +/- 0.01119, N = 3 SE +/- 0.03971, N = 3 SE +/- 0.02347, N = 11 SE +/- 0.01501, N = 3 SE +/- 0.02450, N = 4 SE +/- 0.02209, N = 15 SE +/- 0.03659, N = 15 SE +/- 0.00335, N = 3 SE +/- 0.03117, N = 3 SE +/- 0.00120, N = 3 SE +/- 0.01853, N = 5 SE +/- 0.02493, N = 15 SE +/- 0.00498, N = 3 SE +/- 0.01470, N = 3 SE +/- 0.01405, N = 15 SE +/- 0.02289, N = 15 SE +/- 0.01456, N = 3 SE +/- 0.02719, N = 15 SE +/- 0.01541, N = 3 SE +/- 0.00236, N = 3 SE +/- 0.01594, N = 3 SE +/- 0.00291, N = 3 3.61920 3.41537 3.16441 2.61653 2.25716 2.25020 2.24645 2.24323 2.23868 2.07288 1.71875 1.66046 1.65270 1.48596 1.43573 1.42849 1.41662 1.37831 1.32454 1.17561 1.17292 1.10042 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 65.24 / Avg: 542.12 / Max: 580.41 Min: 57.3 / Avg: 472.8 / Max: 505.93 Min: 51.38 / Avg: 431.96 / Max: 458.85 Min: 42.05 / Avg: 397.19 / Max: 423.71 Min: 108.14 / Avg: 349.02 / Max: 367.93 Min: 104.87 / Avg: 303.41 / Max: 320.11 Min: 35.78 / Avg: 264.82 / Max: 285.07 Min: 54.86 / Avg: 232.56 / Max: 248.24 Min: 26 / Avg: 222.45 / Max: 240.99 Min: 19.01 / Avg: 179.59 / Max: 191.94 Min: 43.58 / Avg: 171.22 / Max: 182.02 Min: 43.72 / Avg: 146.19 / Max: 154.64 Min: 19.26 / Avg: 116.04 / Max: 124.74 Min: 17.14 / Avg: 106.46 / Max: 113.35
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9754 EPYC 8534P EPYC 9654 2P Xeon 6766E EPYC 8534PN EPYC 9684X 2P Xeon 6780E Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 200 400 600 800 1000 SE +/- 0.86, N = 3 SE +/- 3.37, N = 3 SE +/- 2.36, N = 11 SE +/- 2.19, N = 3 SE +/- 4.84, N = 4 SE +/- 4.37, N = 15 SE +/- 0.67, N = 3 SE +/- 6.13, N = 3 SE +/- 7.76, N = 15 SE +/- 0.28, N = 3 SE +/- 6.21, N = 5 SE +/- 9.50, N = 15 SE +/- 1.83, N = 3 SE +/- 6.60, N = 3 SE +/- 6.50, N = 15 SE +/- 10.46, N = 15 SE +/- 7.34, N = 3 SE +/- 12.91, N = 15 SE +/- 8.88, N = 3 SE +/- 1.66, N = 3 SE +/- 11.46, N = 3 SE +/- 2.43, N = 3 276.24 292.79 316.11 382.10 443.06 444.85 445.62 446.69 446.81 482.21 581.77 604.05 604.76 672.92 696.98 701.72 705.61 728.47 754.81 849.56 852.33 908.19 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Standard Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9754 EPYC 8534P EPYC 9654 2P EPYC 9684X 2P Xeon 6766E EPYC 8534PN Xeon 6780E Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 0.8143 1.6286 2.4429 3.2572 4.0715 SE +/- 0.01119, N = 3 SE +/- 0.03971, N = 3 SE +/- 0.02347, N = 11 SE +/- 0.01501, N = 3 SE +/- 0.02450, N = 4 SE +/- 0.02209, N = 15 SE +/- 0.03659, N = 15 SE +/- 0.00335, N = 3 SE +/- 0.03117, N = 3 SE +/- 0.00120, N = 3 SE +/- 0.01853, N = 5 SE +/- 0.02493, N = 15 SE +/- 0.00498, N = 3 SE +/- 0.01470, N = 3 SE +/- 0.01405, N = 15 SE +/- 0.02289, N = 15 SE +/- 0.01456, N = 3 SE +/- 0.02719, N = 15 SE +/- 0.01541, N = 3 SE +/- 0.00236, N = 3 SE +/- 0.01594, N = 3 SE +/- 0.00291, N = 3 3.61920 3.41537 3.16441 2.61653 2.25716 2.25020 2.24645 2.24323 2.23868 2.07288 1.71875 1.66046 1.65270 1.48596 1.43573 1.42849 1.41662 1.37831 1.32454 1.17561 1.17292 1.10042 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Llamafile Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.7 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU Xeon Max 9468 Xeon Max 9480 Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9754 2P EPYC 8534PN EPYC 8534P EPYC 9684X 2P EPYC 9654 2P Xeon 6766E Xeon 6780E Xeon Platinum 8490H EPYC 9754 EPYC 9654 EPYC 9684X 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.12, N = 6 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 1.47 1.54 1.54 1.77 2.56 2.67 3.05 3.10 3.82 4.08 4.41 4.63 5.11 5.16 5.24 5.24 5.39 5.58 5.85 7.47 8.35 8.48
Tokens Per Second Per Watt
OpenBenchmarking.org Tokens Per Second Per Watt, More Is Better Llamafile 0.7 Test: wizardcoder-python-34b-v1.0.Q6_K - Acceleration: CPU Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 Xeon 6780E EPYC 9684X Xeon 6766E EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.0099 0.0198 0.0297 0.0396 0.0495 0.002 0.003 0.005 0.005 0.005 0.006 0.006 0.007 0.007 0.009 0.011 0.011 0.013 0.018 0.018 0.028 0.029 0.031 0.034 0.037 0.038 0.044
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Llamafile 0.7 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9468 EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 184.95 / Avg: 639.77 / Max: 696.32 Min: 203.4 / Avg: 633.28 / Max: 704.68 Min: 170.34 / Avg: 630.52 / Max: 723.74 Min: 85.64 / Avg: 568.91 / Max: 665.68 Min: 65.77 / Avg: 568.13 / Max: 708.34 Min: 101.74 / Avg: 484.21 / Max: 566.46 Min: 58.45 / Avg: 480.08 / Max: 600.8 Min: 41.26 / Avg: 412.48 / Max: 564 Min: 108.26 / Avg: 383.74 / Max: 590.61 Min: 105.02 / Avg: 350.49 / Max: 483.96 Min: 86.22 / Avg: 325.29 / Max: 362.03 Min: 53.92 / Avg: 317.1 / Max: 376.78 Min: 33.89 / Avg: 307.46 / Max: 338.87 Min: 72.56 / Avg: 306.79 / Max: 356.97 Min: 29.28 / Avg: 296.68 / Max: 399.75 Min: 51.16 / Avg: 250.18 / Max: 288.75 Min: 30.07 / Avg: 245.28 / Max: 317.66 Min: 21.63 / Avg: 203.84 / Max: 298.7 Min: 43.53 / Avg: 201.04 / Max: 326.57 Min: 43.73 / Avg: 175.78 / Max: 254.24 Min: 17.14 / Avg: 135.55 / Max: 164.93 Min: 16.37 / Avg: 115.77 / Max: 139.52
Timed Godot Game Engine Compilation This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile Xeon Platinum 8380 Xeon 6766E Xeon 6766E 2P EPYC 8534PN EPYC 8534P Xeon 6780E Xeon Platinum 8380 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H EPYC 9754 EPYC 9754 2P Xeon Max 9468 2P Xeon Platinum 8592+ Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9654 2P EPYC 9684X 2P 40 80 120 160 200 SE +/- 0.22, N = 3 SE +/- 0.16, N = 3 SE +/- 0.64, N = 3 SE +/- 0.16, N = 3 SE +/- 0.32, N = 3 SE +/- 0.73, N = 3 SE +/- 0.69, N = 3 SE +/- 0.18, N = 3 SE +/- 1.40, N = 3 SE +/- 0.32, N = 3 SE +/- 0.76, N = 3 SE +/- 0.20, N = 3 SE +/- 0.55, N = 3 SE +/- 0.56, N = 3 SE +/- 0.91, N = 3 SE +/- 1.69, N = 3 SE +/- 0.56, N = 3 SE +/- 0.16, N = 3 SE +/- 0.29, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.62, N = 3 187.88 165.41 160.46 159.62 154.01 152.23 151.54 149.38 148.99 143.81 140.23 128.28 126.11 123.88 122.72 122.70 118.57 111.69 103.38 103.35 102.58 96.16
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Godot Game Engine Compilation 4.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 140 280 420 560 700 Min: 199.22 / Avg: 527.95 / Max: 724.51 Min: 197.93 / Avg: 519.6 / Max: 744.47 Min: 154.59 / Avg: 461.39 / Max: 752.04 Min: 82.98 / Avg: 430.41 / Max: 750.75 Min: 65.36 / Avg: 383.39 / Max: 820.55 Min: 97.52 / Avg: 352.55 / Max: 559.9 Min: 58.53 / Avg: 338.4 / Max: 689.21 Min: 76.87 / Avg: 285.63 / Max: 375.65 Min: 82.82 / Avg: 282.51 / Max: 375.66 Min: 39.69 / Avg: 276.98 / Max: 673.64 Min: 55.69 / Avg: 255.97 / Max: 375.31 Min: 33.4 / Avg: 236.2 / Max: 374.96 Min: 33.53 / Avg: 222.04 / Max: 410.61 Min: 50.66 / Avg: 217.11 / Max: 290.99 Min: 106.86 / Avg: 202.24 / Max: 626.79 Min: 24.79 / Avg: 188.63 / Max: 336.96 Min: 103.92 / Avg: 184.93 / Max: 507.62 Min: 18.92 / Avg: 152.32 / Max: 333.75 Min: 43.34 / Avg: 124.67 / Max: 295.77 Min: 18.58 / Avg: 110.14 / Max: 169.2 Min: 43.52 / Avg: 109.04 / Max: 243.23 Min: 16.76 / Avg: 97.75 / Max: 142.01
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6766E EPYC 9754 Xeon 6780E EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 14 28 42 56 70 SE +/- 0.28, N = 12 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.32, N = 12 SE +/- 0.37, N = 12 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 SE +/- 0.21, N = 3 SE +/- 0.23, N = 3 SE +/- 0.49, N = 3 SE +/- 0.45, N = 3 SE +/- 0.29, N = 3 SE +/- 0.52, N = 3 SE +/- 0.04, N = 3 SE +/- 0.62, N = 3 SE +/- 0.76, N = 3 SE +/- 0.52, N = 3 SE +/- 0.64, N = 3 13.11 14.67 16.22 16.97 17.41 26.82 27.78 30.86 33.30 33.68 34.90 34.90 36.97 37.44 37.91 41.45 41.68 48.89 51.56 52.97 54.84 63.60
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 EPYC 9684X 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X EPYC 9754 EPYC 9654 Xeon Max 9480 Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.0752 0.1504 0.2256 0.3008 0.376 0.040 0.044 0.045 0.045 0.048 0.066 0.073 0.077 0.082 0.113 0.150 0.176 0.179 0.189 0.194 0.194 0.197 0.218 0.235 0.293 0.305 0.334
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 193.43 / Avg: 577.93 / Max: 636.86 Min: 201.49 / Avg: 569.91 / Max: 625.34 Min: 72.64 / Avg: 507.69 / Max: 575.72 Min: 165.22 / Avg: 486.52 / Max: 567.17 Min: 61.35 / Avg: 419.25 / Max: 473.7 Min: 55.56 / Avg: 365.56 / Max: 407.37 Min: 108.2 / Avg: 363.82 / Max: 389.75 Min: 101.92 / Avg: 326.58 / Max: 422.87 Min: 105.49 / Avg: 325.94 / Max: 350.34 Min: 40.16 / Avg: 300.12 / Max: 342.36 Min: 89.32 / Avg: 273.3 / Max: 321.11 Min: 75.38 / Avg: 268.45 / Max: 310.8 Min: 61.04 / Avg: 251.84 / Max: 296.62 Min: 32.73 / Avg: 232.73 / Max: 262.5 Min: 18.63 / Avg: 215.65 / Max: 294.3 Min: 55.01 / Avg: 207.81 / Max: 238.76 Min: 30.18 / Avg: 194.95 / Max: 219.41 Min: 43.38 / Avg: 159.18 / Max: 178.76 Min: 21.47 / Avg: 157.48 / Max: 175.9 Min: 43.68 / Avg: 138.47 / Max: 152.75 Min: 19.91 / Avg: 110.56 / Max: 125.45 Min: 17.28 / Avg: 99.64 / Max: 110.85
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9754 EPYC 9654 Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 40 80 120 160 200 SE +/- 0.23, N = 3 SE +/- 0.63, N = 3 SE +/- 0.37, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 SE +/- 0.50, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 SE +/- 0.46, N = 3 SE +/- 0.57, N = 3 SE +/- 0.30, N = 3 SE +/- 0.93, N = 3 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.43, N = 3 204.21 187.03 176.87 160.56 146.03 140.43 135.56 128.74 114.29 110.56 107.36 106.54 100.24 100.00 94.76 90.85 85.89 79.42
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2023.09.15 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 65.3 / Avg: 702.37 / Max: 819.28 Min: 204.9 / Avg: 661.11 / Max: 752.72 Min: 215.12 / Avg: 658.11 / Max: 751.86 Min: 175.02 / Avg: 647.82 / Max: 749.74 Min: 67.07 / Avg: 633.7 / Max: 776.53 Min: 57.91 / Avg: 595.98 / Max: 703.76 Min: 41.48 / Avg: 554.53 / Max: 680.58 Min: 99.13 / Avg: 505.66 / Max: 581.63 Min: 34.68 / Avg: 370.43 / Max: 409.62 Min: 72.45 / Avg: 335.98 / Max: 368.12 Min: 75.87 / Avg: 334.64 / Max: 374.39 Min: 60.99 / Avg: 331.72 / Max: 375.56 Min: 23.22 / Avg: 328.15 / Max: 377.07 Min: 27.14 / Avg: 303.45 / Max: 345.2 Min: 21.72 / Avg: 297.41 / Max: 340.37 Min: 52.13 / Avg: 259.44 / Max: 290.81 Min: 18.75 / Avg: 147.36 / Max: 159.1 Min: 18.08 / Avg: 129.32 / Max: 137.09
QMCPACK QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. QMCPACK is an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids. QMCPACK is supported by the U.S. Department of Energy. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: Li2_STO_ae Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P EPYC 9754 Xeon Platinum 8490H EPYC 9654 Xeon Max 9480 2P Xeon Platinum 8592+ EPYC 9654 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9684X 2P 40 80 120 160 200 SE +/- 1.47, N = 7 SE +/- 0.40, N = 3 SE +/- 1.13, N = 3 SE +/- 0.50, N = 3 SE +/- 1.20, N = 3 SE +/- 1.04, N = 3 SE +/- 0.42, N = 3 SE +/- 0.63, N = 3 SE +/- 0.89, N = 3 SE +/- 0.54, N = 3 SE +/- 1.11, N = 5 SE +/- 1.03, N = 3 SE +/- 0.23, N = 3 SE +/- 0.88, N = 3 SE +/- 1.11, N = 3 SE +/- 0.93, N = 3 SE +/- 1.06, N = 3 SE +/- 0.06, N = 3 163.75 151.27 137.23 131.37 121.19 117.81 111.15 110.80 109.30 108.02 106.27 105.98 102.98 102.12 101.63 97.91 97.00 91.97 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better QMCPACK 3.17.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9468 EPYC 9754 EPYC 9654 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 66.83 / Avg: 767.28 / Max: 818.97 Min: 206.85 / Avg: 676.4 / Max: 753.87 Min: 208.9 / Avg: 673.9 / Max: 748.46 Min: 169.74 / Avg: 670.52 / Max: 753.5 Min: 63.82 / Avg: 660.86 / Max: 753.6 Min: 54.02 / Avg: 635.44 / Max: 688.42 Min: 44.37 / Avg: 628.81 / Max: 690.2 Min: 104.4 / Avg: 524.73 / Max: 581.03 Min: 33.88 / Avg: 391.36 / Max: 409.49 Min: 80.16 / Avg: 338.77 / Max: 371.37 Min: 59.34 / Avg: 337.54 / Max: 376.68 Min: 23.78 / Avg: 335.13 / Max: 377.2 Min: 75.52 / Avg: 323.64 / Max: 364.79 Min: 21.99 / Avg: 319.33 / Max: 338.99 Min: 28.38 / Avg: 316.1 / Max: 334.43 Min: 53.73 / Avg: 263.86 / Max: 290.45 Min: 17.96 / Avg: 154.43 / Max: 159.92 Min: 17.04 / Avg: 132.24 / Max: 137.56
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 9654 Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Max 9480 2P Xeon Max 9468 2P EPYC 8534PN EPYC 9754 2P EPYC 8534P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P EPYC 9754 Xeon Platinum 8592+ 300 600 900 1200 1500 SE +/- 1.59, N = 3 SE +/- 19.12, N = 12 SE +/- 13.72, N = 15 SE +/- 9.04, N = 12 SE +/- 6.08, N = 15 SE +/- 3.30, N = 3 SE +/- 0.61, N = 3 SE +/- 0.63, N = 3 SE +/- 6.06, N = 3 SE +/- 5.57, N = 13 SE +/- 3.59, N = 15 SE +/- 5.48, N = 3 SE +/- 3.54, N = 3 SE +/- 2.21, N = 3 SE +/- 1.73, N = 3 SE +/- 2.55, N = 3 SE +/- 0.96, N = 3 SE +/- 2.36, N = 15 SE +/- 0.94, N = 3 SE +/- 4.07, N = 3 SE +/- 1.91, N = 3 SE +/- 0.74, N = 3 1165.93 1094.26 801.96 800.23 608.09 587.00 562.40 515.08 475.25 460.67 443.96 397.43 388.74 382.11 380.90 363.35 352.74 345.94 329.04 327.88 319.35 302.27 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 66.22 / Avg: 538.69 / Max: 582.15 Min: 57.08 / Avg: 475.82 / Max: 514.33 Min: 99.33 / Avg: 452.18 / Max: 484 Min: 40.33 / Avg: 426.23 / Max: 461.75 Min: 109.34 / Avg: 411.87 / Max: 447.93 Min: 107.09 / Avg: 366.41 / Max: 399.46 Min: 33.01 / Avg: 268.04 / Max: 290.06 Min: 53.76 / Avg: 239.05 / Max: 256.78 Min: 26.58 / Avg: 226.63 / Max: 248.05 Min: 22.2 / Avg: 210.78 / Max: 229.48 Min: 43.63 / Avg: 190.5 / Max: 207.06 Min: 43.69 / Avg: 159.26 / Max: 172.23 Min: 19.36 / Avg: 129.39 / Max: 140.24 Min: 15.82 / Avg: 105.18 / Max: 117.88
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel EPYC 9684X 2P EPYC 9654 2P EPYC 9654 EPYC 9684X Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Max 9480 2P Xeon Max 9468 2P EPYC 8534PN EPYC 9754 2P EPYC 8534P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P EPYC 9754 Xeon Platinum 8592+ 0.7444 1.4888 2.2332 2.9776 3.722 SE +/- 0.001170, N = 3 SE +/- 0.016597, N = 12 SE +/- 0.013875, N = 12 SE +/- 0.020352, N = 15 SE +/- 0.016386, N = 15 SE +/- 0.009611, N = 3 SE +/- 0.001935, N = 3 SE +/- 0.002384, N = 3 SE +/- 0.026516, N = 3 SE +/- 0.027020, N = 13 SE +/- 0.018603, N = 15 SE +/- 0.034519, N = 3 SE +/- 0.023203, N = 3 SE +/- 0.015170, N = 3 SE +/- 0.011894, N = 3 SE +/- 0.019473, N = 3 SE +/- 0.007683, N = 3 SE +/- 0.019617, N = 15 SE +/- 0.008707, N = 3 SE +/- 0.038257, N = 3 SE +/- 0.018814, N = 3 SE +/- 0.008053, N = 3 0.857685 0.917043 1.251350 1.251790 1.646740 1.703650 1.778090 1.941440 2.104800 2.174630 2.254530 2.517090 2.572780 2.617210 2.625440 2.752420 2.834980 2.892530 3.039220 3.050850 3.131560 3.308360 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 9654 Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Max 9480 2P Xeon Max 9468 2P EPYC 8534PN EPYC 9754 2P EPYC 8534P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P EPYC 9754 Xeon Platinum 8592+ 300 600 900 1200 1500 SE +/- 1.59, N = 3 SE +/- 19.12, N = 12 SE +/- 13.72, N = 15 SE +/- 9.04, N = 12 SE +/- 6.08, N = 15 SE +/- 3.30, N = 3 SE +/- 0.61, N = 3 SE +/- 0.63, N = 3 SE +/- 6.06, N = 3 SE +/- 5.57, N = 13 SE +/- 3.59, N = 15 SE +/- 5.48, N = 3 SE +/- 3.54, N = 3 SE +/- 2.21, N = 3 SE +/- 1.73, N = 3 SE +/- 2.55, N = 3 SE +/- 0.96, N = 3 SE +/- 2.36, N = 15 SE +/- 0.94, N = 3 SE +/- 4.07, N = 3 SE +/- 1.91, N = 3 SE +/- 0.74, N = 3 1165.93 1094.26 801.96 800.23 608.09 587.00 562.40 515.08 475.25 460.67 443.96 397.43 388.74 382.11 380.90 363.35 352.74 345.94 329.04 327.88 319.35 302.27 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 Xeon Max 9480 2P Xeon Max 9468 2P EPYC 8534P EPYC 8534PN Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.07940, N = 3 SE +/- 0.11179, N = 3 SE +/- 0.04869, N = 15 SE +/- 0.04327, N = 3 SE +/- 0.03210, N = 15 SE +/- 0.04200, N = 3 SE +/- 0.02296, N = 15 SE +/- 0.01454, N = 15 SE +/- 0.00871, N = 3 SE +/- 0.00720, N = 3 SE +/- 0.00301, N = 3 SE +/- 0.01684, N = 6 SE +/- 0.01492, N = 3 SE +/- 0.01428, N = 15 SE +/- 0.01586, N = 15 SE +/- 0.00701, N = 3 SE +/- 0.00943, N = 3 SE +/- 0.01053, N = 3 SE +/- 0.00884, N = 3 SE +/- 0.00184, N = 3 SE +/- 0.00936, N = 3 SE +/- 0.01491, N = 4 12.30210 12.12680 5.66426 5.24051 3.69602 3.21781 3.17064 2.21020 2.08780 2.02659 1.82443 1.80573 1.76353 1.70579 1.69307 1.64919 1.55821 1.47249 1.45280 1.30173 1.27368 1.20298 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 66.9 / Avg: 542.3 / Max: 581.73 Min: 57.19 / Avg: 475.21 / Max: 509.74 Min: 98.39 / Avg: 431.89 / Max: 460.51 Min: 39.85 / Avg: 399.31 / Max: 425.54 Min: 108.06 / Avg: 346.02 / Max: 366.29 Min: 104.72 / Avg: 302.14 / Max: 319.15 Min: 35.49 / Avg: 275.71 / Max: 296 Min: 53.65 / Avg: 232.18 / Max: 246.53 Min: 25.06 / Avg: 230.17 / Max: 246.35 Min: 19.98 / Avg: 184.69 / Max: 197.9 Min: 43.54 / Avg: 166.24 / Max: 176.01 Min: 43.72 / Avg: 141.66 / Max: 149.72 Min: 16.81 / Avg: 122.1 / Max: 130.96 Min: 17.47 / Avg: 111.54 / Max: 119.32
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 Xeon Max 9480 2P Xeon Max 9468 2P EPYC 8534P EPYC 8534PN Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 200 400 600 800 1000 SE +/- 0.53, N = 3 SE +/- 0.77, N = 3 SE +/- 1.50, N = 15 SE +/- 1.57, N = 3 SE +/- 2.41, N = 15 SE +/- 4.10, N = 3 SE +/- 2.35, N = 15 SE +/- 3.02, N = 15 SE +/- 1.98, N = 3 SE +/- 1.77, N = 3 SE +/- 0.91, N = 3 SE +/- 5.34, N = 6 SE +/- 4.81, N = 3 SE +/- 4.99, N = 15 SE +/- 5.53, N = 15 SE +/- 2.57, N = 3 SE +/- 3.90, N = 3 SE +/- 4.87, N = 3 SE +/- 4.16, N = 3 SE +/- 1.09, N = 3 SE +/- 5.72, N = 3 SE +/- 10.06, N = 4 81.26 82.44 176.64 190.78 270.63 310.59 315.36 452.32 478.47 492.89 547.52 553.47 566.38 586.18 590.71 605.59 641.00 678.48 687.67 767.48 784.30 830.73 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: CaffeNet 12-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 Xeon Max 9480 2P Xeon Max 9468 2P EPYC 8534P EPYC 8534PN Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.07940, N = 3 SE +/- 0.11179, N = 3 SE +/- 0.04869, N = 15 SE +/- 0.04327, N = 3 SE +/- 0.03210, N = 15 SE +/- 0.04200, N = 3 SE +/- 0.02296, N = 15 SE +/- 0.01454, N = 15 SE +/- 0.00871, N = 3 SE +/- 0.00720, N = 3 SE +/- 0.00301, N = 3 SE +/- 0.01684, N = 6 SE +/- 0.01492, N = 3 SE +/- 0.01428, N = 15 SE +/- 0.01586, N = 15 SE +/- 0.00701, N = 3 SE +/- 0.00943, N = 3 SE +/- 0.01053, N = 3 SE +/- 0.00884, N = 3 SE +/- 0.00184, N = 3 SE +/- 0.00936, N = 3 SE +/- 0.01491, N = 4 12.30210 12.12680 5.66426 5.24051 3.69602 3.21781 3.17064 2.21020 2.08780 2.02659 1.82443 1.80573 1.76353 1.70579 1.69307 1.64919 1.55821 1.47249 1.45280 1.30173 1.27368 1.20298 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 Xeon 6766E 2P EPYC 9654 2P Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P Xeon 6766E Xeon 6780E 2P Xeon Max 9480 Xeon 6780E Xeon Max 9468 EPYC 9684X 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2 4 6 8 10 SE +/- 0.06404, N = 13 SE +/- 0.03354, N = 3 SE +/- 0.07124, N = 3 SE +/- 0.06745, N = 3 SE +/- 0.56391, N = 15 SE +/- 0.06624, N = 3 SE +/- 0.02608, N = 3 SE +/- 0.03084, N = 3 SE +/- 0.03283, N = 3 SE +/- 0.00782, N = 3 SE +/- 0.02282, N = 3 SE +/- 0.01103, N = 3 SE +/- 0.00392, N = 3 SE +/- 0.08827, N = 15 SE +/- 0.06302, N = 15 SE +/- 0.01718, N = 3 SE +/- 0.00316, N = 3 SE +/- 0.06148, N = 15 SE +/- 0.03065, N = 15 SE +/- 0.02371, N = 3 SE +/- 0.00659, N = 3 SE +/- 0.00472, N = 3 7.87325 7.86015 7.84065 7.63337 6.14327 5.98436 5.39123 5.34656 5.02267 4.80725 4.74859 4.64757 4.59703 4.57581 3.80792 3.57543 3.46571 3.43125 3.34966 2.80263 2.79694 2.16966 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 60 120 180 240 300 Min: 99.68 / Avg: 289.97 / Max: 319.08 Min: 34.94 / Avg: 287.83 / Max: 306.6 Min: 58.06 / Avg: 256.93 / Max: 271.34 Min: 40.98 / Avg: 208.45 / Max: 223.35 Min: 52.27 / Avg: 202.48 / Max: 217.49 Min: 75.92 / Avg: 152.85 / Max: 173.61 Min: 105.79 / Avg: 152.81 / Max: 159.65 Min: 34.63 / Avg: 146.68 / Max: 155.53 Min: 26.07 / Avg: 125.08 / Max: 132.3 Min: 20.82 / Avg: 94.1 / Max: 99.49 Min: 43.39 / Avg: 88.68 / Max: 93.08 Min: 43.7 / Avg: 85.81 / Max: 89.61 Min: 16.9 / Avg: 70.5 / Max: 76.74 Min: 15.64 / Avg: 68.55 / Max: 73.08
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 EPYC 9654 2P Xeon 6766E 2P Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P Xeon 6766E Xeon 6780E 2P Xeon Max 9480 Xeon 6780E Xeon Max 9468 EPYC 9684X 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ 100 200 300 400 500 SE +/- 0.98, N = 13 SE +/- 0.54, N = 3 SE +/- 1.15, N = 3 SE +/- 1.16, N = 3 SE +/- 1.86, N = 3 SE +/- 11.98, N = 15 SE +/- 0.89, N = 3 SE +/- 1.08, N = 3 SE +/- 1.31, N = 3 SE +/- 0.35, N = 3 SE +/- 1.00, N = 3 SE +/- 0.51, N = 3 SE +/- 0.17, N = 3 SE +/- 3.95, N = 15 SE +/- 4.17, N = 15 SE +/- 1.35, N = 3 SE +/- 0.26, N = 3 SE +/- 4.93, N = 15 SE +/- 2.62, N = 15 SE +/- 3.01, N = 3 SE +/- 0.84, N = 3 SE +/- 1.00, N = 3 127.09 127.21 127.54 131.00 167.11 178.11 185.46 187.01 199.08 207.94 210.37 215.13 217.45 219.53 263.52 279.64 288.47 292.52 298.67 356.76 357.36 460.78 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Standard EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 Xeon 6766E 2P EPYC 9654 2P Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P Xeon 6766E Xeon 6780E 2P Xeon Max 9480 Xeon 6780E Xeon Max 9468 EPYC 9684X 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2 4 6 8 10 SE +/- 0.06404, N = 13 SE +/- 0.03354, N = 3 SE +/- 0.07124, N = 3 SE +/- 0.06745, N = 3 SE +/- 0.56391, N = 15 SE +/- 0.06624, N = 3 SE +/- 0.02608, N = 3 SE +/- 0.03084, N = 3 SE +/- 0.03283, N = 3 SE +/- 0.00782, N = 3 SE +/- 0.02282, N = 3 SE +/- 0.01103, N = 3 SE +/- 0.00392, N = 3 SE +/- 0.08827, N = 15 SE +/- 0.06302, N = 15 SE +/- 0.01718, N = 3 SE +/- 0.00316, N = 3 SE +/- 0.06148, N = 15 SE +/- 0.03065, N = 15 SE +/- 0.02371, N = 3 SE +/- 0.00659, N = 3 SE +/- 0.00472, N = 3 7.87325 7.86015 7.84065 7.63337 6.14327 5.98436 5.39123 5.34656 5.02267 4.80725 4.74859 4.64757 4.59703 4.57581 3.80792 3.57543 3.46571 3.43125 3.34966 2.80263 2.79694 2.16966 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 EPYC 9754 EPYC 8534P EPYC 9654 EPYC 8534PN Xeon Platinum 8380 2P EPYC 9684X Xeon Platinum 8490H EPYC 9754 2P Xeon Max 9480 2P EPYC 9654 2P Xeon Max 9480 Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Platinum 8592+ 60 120 180 240 300 SE +/- 0.07, N = 3 SE +/- 0.25, N = 3 SE +/- 0.34, N = 3 SE +/- 0.15, N = 3 SE +/- 0.92, N = 3 SE +/- 6.97, N = 15 SE +/- 0.19, N = 3 SE +/- 2.90, N = 15 SE +/- 0.41, N = 3 SE +/- 0.14, N = 3 SE +/- 1.22, N = 15 SE +/- 0.01, N = 3 SE +/- 1.90, N = 15 SE +/- 0.06, N = 3 SE +/- 0.44, N = 15 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 293.02 283.83 274.52 266.91 236.81 230.24 161.48 157.45 156.59 113.70 110.91 100.39 85.86 64.91 63.98 59.69 45.78 43.77 43.41 42.16 41.93 39.62 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8592+ 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 69.94 / Avg: 750.87 / Max: 819.03 Min: 197.25 / Avg: 664.45 / Max: 750.81 Min: 198.61 / Avg: 661.77 / Max: 760.61 Min: 166.26 / Avg: 657.43 / Max: 746.56 Min: 55.49 / Avg: 628.28 / Max: 705.07 Min: 40.79 / Avg: 578.55 / Max: 688.18 Min: 83.28 / Avg: 525.5 / Max: 710.63 Min: 106.87 / Avg: 515.24 / Max: 592.9 Min: 101.92 / Avg: 505.26 / Max: 553.92 Min: 104.28 / Avg: 438.97 / Max: 506.66 Min: 34.13 / Avg: 363.03 / Max: 408.76 Min: 74.3 / Avg: 331.92 / Max: 379.36 Min: 75.73 / Avg: 330.51 / Max: 371.12 Min: 59.06 / Avg: 327.33 / Max: 376.83 Min: 28.22 / Avg: 304.28 / Max: 347.63 Min: 20.51 / Avg: 267.71 / Max: 344.82 Min: 43.59 / Avg: 263.16 / Max: 290.9 Min: 51.68 / Avg: 253.57 / Max: 279.32 Min: 43.7 / Avg: 221.35 / Max: 243.97 Min: 34.28 / Avg: 219.81 / Max: 297.36 Min: 19.75 / Avg: 155.49 / Max: 170.23 Min: 16.08 / Avg: 138.77 / Max: 151.09
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P EPYC 8534P EPYC 8534PN Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 EPYC 9654 Xeon Platinum 8592+ EPYC 9684X Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 200 400 600 800 1000 SE +/- 0.34, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.23, N = 3 SE +/- 0.25, N = 3 SE +/- 0.56, N = 3 SE +/- 0.07, N = 3 SE +/- 0.34, N = 3 SE +/- 13.40, N = 15 SE +/- 1.23, N = 3 SE +/- 0.04, N = 3 SE +/- 0.52, N = 3 SE +/- 7.13, N = 15 SE +/- 0.95, N = 3 SE +/- 5.20, N = 15 SE +/- 1.28, N = 3 SE +/- 0.55, N = 3 SE +/- 0.69, N = 3 SE +/- 1.42, N = 3 SE +/- 5.47, N = 15 SE +/- 20.94, N = 15 SE +/- 2.17, N = 3 84.30 126.64 134.77 175.72 197.91 204.05 245.27 261.64 283.18 285.95 298.56 301.30 306.27 403.20 433.06 568.81 569.60 654.84 736.23 750.11 750.96 1095.79 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard EPYC 9754 2P EPYC 8534PN EPYC 8534P EPYC 9754 Xeon 6780E 2P EPYC 9654 2P EPYC 9654 Xeon Max 9480 2P Xeon 6766E 2P Xeon 6766E Xeon Max 9468 2P Xeon 6780E EPYC 9684X 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.20120, N = 15 SE +/- 0.07964, N = 3 SE +/- 0.03478, N = 3 SE +/- 0.01807, N = 3 SE +/- 0.80628, N = 15 SE +/- 0.01221, N = 3 SE +/- 0.08751, N = 5 SE +/- 0.06105, N = 3 SE +/- 0.02533, N = 3 SE +/- 0.02403, N = 3 SE +/- 0.02902, N = 3 SE +/- 0.02008, N = 3 SE +/- 0.01742, N = 3 SE +/- 0.02661, N = 3 SE +/- 0.06620, N = 3 SE +/- 0.06596, N = 15 SE +/- 0.03218, N = 3 SE +/- 0.08423, N = 15 SE +/- 0.04594, N = 3 SE +/- 0.03075, N = 3 SE +/- 0.15083, N = 15 SE +/- 0.01631, N = 3 11.57740 11.28640 11.20470 11.13920 10.58571 9.74614 7.88584 7.53259 7.32610 7.16440 7.04111 6.74630 6.17190 6.16668 5.91961 5.67700 5.55101 5.16480 4.80418 4.49976 4.29531 3.69649 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 60 120 180 240 300 Min: 97.22 / Avg: 292.43 / Max: 327.64 Min: 65.9 / Avg: 291.34 / Max: 308.52 Min: 55.76 / Avg: 257.41 / Max: 272.32 Min: 39.34 / Avg: 208.62 / Max: 222.38 Min: 52.71 / Avg: 203.23 / Max: 218.58 Min: 105.25 / Avg: 166.09 / Max: 183.4 Min: 34.75 / Avg: 149.45 / Max: 159.93 Min: 103.86 / Avg: 148.82 / Max: 155.68 Min: 27.83 / Avg: 127.32 / Max: 135.72 Min: 20.73 / Avg: 94.62 / Max: 100.76 Min: 43.54 / Avg: 90.3 / Max: 95.5 Min: 43.72 / Avg: 86.91 / Max: 91.46 Min: 16.03 / Avg: 72.08 / Max: 76.76 Min: 15.72 / Avg: 69.12 / Max: 74.02
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard EPYC 9754 2P EPYC 8534PN EPYC 8534P EPYC 9754 EPYC 9654 2P Xeon 6780E 2P EPYC 9654 Xeon Max 9480 2P Xeon 6766E 2P Xeon 6766E Xeon Max 9468 2P Xeon 6780E EPYC 9684X 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 60 120 180 240 300 SE +/- 1.43, N = 15 SE +/- 0.63, N = 3 SE +/- 0.28, N = 3 SE +/- 0.15, N = 3 SE +/- 0.13, N = 3 SE +/- 8.91, N = 15 SE +/- 1.37, N = 5 SE +/- 1.08, N = 3 SE +/- 0.47, N = 3 SE +/- 0.47, N = 3 SE +/- 0.58, N = 3 SE +/- 0.44, N = 3 SE +/- 0.46, N = 3 SE +/- 0.70, N = 3 SE +/- 1.88, N = 3 SE +/- 2.01, N = 15 SE +/- 1.05, N = 3 SE +/- 3.16, N = 15 SE +/- 1.97, N = 3 SE +/- 1.50, N = 3 SE +/- 8.14, N = 15 SE +/- 1.19, N = 3 86.69 88.57 89.21 89.74 102.57 103.89 126.82 132.71 136.39 139.45 141.95 148.11 161.95 162.09 168.86 176.33 180.03 194.15 207.93 222.03 236.65 270.33 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Standard EPYC 9754 2P EPYC 8534PN EPYC 8534P EPYC 9754 Xeon 6780E 2P EPYC 9654 2P EPYC 9654 Xeon Max 9480 2P Xeon 6766E 2P Xeon 6766E Xeon Max 9468 2P Xeon 6780E EPYC 9684X 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.20120, N = 15 SE +/- 0.07964, N = 3 SE +/- 0.03478, N = 3 SE +/- 0.01807, N = 3 SE +/- 0.80628, N = 15 SE +/- 0.01221, N = 3 SE +/- 0.08751, N = 5 SE +/- 0.06105, N = 3 SE +/- 0.02533, N = 3 SE +/- 0.02403, N = 3 SE +/- 0.02902, N = 3 SE +/- 0.02008, N = 3 SE +/- 0.01742, N = 3 SE +/- 0.02661, N = 3 SE +/- 0.06620, N = 3 SE +/- 0.06596, N = 15 SE +/- 0.03218, N = 3 SE +/- 0.08423, N = 15 SE +/- 0.04594, N = 3 SE +/- 0.03075, N = 3 SE +/- 0.15083, N = 15 SE +/- 0.01631, N = 3 11.57740 11.28640 11.20470 11.13920 10.58571 9.74614 7.88584 7.53259 7.32610 7.16440 7.04111 6.74630 6.17190 6.16668 5.91961 5.67700 5.55101 5.16480 4.80418 4.49976 4.29531 3.69649 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: GoogLeNet Xeon 6766E Xeon 6780E EPYC 8534PN Xeon Platinum 8380 Xeon 6766E 2P EPYC 8534P Xeon 6780E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Platinum 8592+ Xeon Max 9468 2P EPYC 9654 Xeon Platinum 8490H Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 110 220 330 440 550 SE +/- 0.31, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.16, N = 3 SE +/- 3.73, N = 4 SE +/- 0.04, N = 3 SE +/- 2.49, N = 3 SE +/- 1.67, N = 3 SE +/- 1.91, N = 3 SE +/- 0.51, N = 3 SE +/- 1.11, N = 3 SE +/- 1.02, N = 3 SE +/- 0.69, N = 3 SE +/- 2.76, N = 15 SE +/- 2.30, N = 3 SE +/- 2.29, N = 3 SE +/- 3.87, N = 15 SE +/- 0.24, N = 3 SE +/- 4.80, N = 3 SE +/- 10.93, N = 12 SE +/- 2.68, N = 3 SE +/- 4.87, N = 3 260.83 281.62 287.42 290.27 301.46 308.46 335.38 375.73 386.00 391.40 397.44 401.84 402.78 406.58 423.59 447.50 447.61 448.46 449.91 462.79 501.39 528.93
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: GoogLeNet EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P EPYC 9754 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Max 9468 Xeon 6780E Xeon Max 9480 Xeon 6766E EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.5108 1.0216 1.5324 2.0432 2.554 0.666 0.684 0.690 0.726 0.743 0.775 0.832 0.833 0.932 0.936 1.138 1.141 1.147 1.170 1.298 1.305 1.385 1.503 1.620 1.896 2.115 2.270
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 201.04 / Avg: 653.82 / Max: 709.07 Min: 201.04 / Avg: 651.98 / Max: 714.73 Min: 161.35 / Avg: 635.04 / Max: 705.2 Min: 65.43 / Avg: 587.49 / Max: 655.55 Min: 82.2 / Avg: 535.58 / Max: 613.03 Min: 57.21 / Avg: 518.78 / Max: 576.81 Min: 103.67 / Avg: 483.98 / Max: 536.18 Min: 107.92 / Avg: 461.73 / Max: 537.33 Min: 40.92 / Avg: 426.33 / Max: 487.57 Min: 105.28 / Avg: 405.89 / Max: 469.79 Min: 79.85 / Avg: 329.98 / Max: 363.65 Min: 73.87 / Avg: 329.22 / Max: 366.78 Min: 58.65 / Avg: 323.79 / Max: 362.41 Min: 30.3 / Avg: 311.48 / Max: 350.99 Min: 33.46 / Avg: 281.92 / Max: 317.12 Min: 27.68 / Avg: 276.32 / Max: 312.83 Min: 53.8 / Avg: 255 / Max: 274.03 Min: 43.42 / Avg: 245.54 / Max: 272.59 Min: 21.26 / Avg: 244.09 / Max: 296.43 Min: 43.66 / Avg: 200.89 / Max: 222.56 Min: 18.95 / Avg: 145.84 / Max: 158.71 Min: 17.59 / Avg: 126.6 / Max: 137.81
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon Platinum 8380 2P EPYC 8534P Xeon Max 9480 Xeon 6766E Xeon 6780E Xeon Platinum 8490H EPYC 9654 Xeon Max 9468 2P Xeon Platinum 8592+ EPYC 9684X Xeon 6766E 2P Xeon Max 9480 2P EPYC 9754 Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P 13 26 39 52 65 SE +/- 0.05948, N = 3 SE +/- 0.03513, N = 3 SE +/- 0.04390, N = 3 SE +/- 0.03319, N = 3 SE +/- 0.02190, N = 3 SE +/- 0.01050, N = 3 SE +/- 0.02488, N = 3 SE +/- 0.01225, N = 3 SE +/- 0.00975, N = 3 SE +/- 0.01424, N = 3 SE +/- 0.01945, N = 3 SE +/- 0.01144, N = 3 SE +/- 0.01754, N = 3 SE +/- 0.03817, N = 3 SE +/- 0.00297, N = 3 SE +/- 0.03039, N = 3 SE +/- 0.03595, N = 3 SE +/- 0.02269, N = 3 SE +/- 0.01406, N = 3 SE +/- 0.07203, N = 3 SE +/- 0.02899, N = 3 SE +/- 0.01800, N = 3 9.77764 16.05020 16.45040 17.82690 17.96680 18.55330 19.51590 21.62220 21.93240 28.09560 29.50180 30.84040 32.51880 32.96630 33.11250 35.24610 36.50430 38.22350 47.61430 54.11950 55.33820 56.69360
Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8592+ 2P EPYC 9684X Xeon 6766E 2P Xeon Platinum 8592+ Xeon 6780E EPYC 9754 2P EPYC 9654 Xeon 6766E EPYC 9754 EPYC 8534P EPYC 8534PN 0.029 0.058 0.087 0.116 0.145 0.034 0.037 0.043 0.049 0.056 0.056 0.060 0.065 0.072 0.079 0.079 0.080 0.085 0.087 0.091 0.092 0.095 0.096 0.107 0.114 0.121 0.129
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 3.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9480 EPYC 9754 EPYC 9654 Xeon Max 9468 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 61.93 / Avg: 764.28 / Max: 797.27 Min: 200.34 / Avg: 682.67 / Max: 705.07 Min: 176.11 / Avg: 681.46 / Max: 714.09 Min: 195.3 / Avg: 681.19 / Max: 725.09 Min: 77.58 / Avg: 677.36 / Max: 715.65 Min: 60.35 / Avg: 600.41 / Max: 624.73 Min: 42.49 / Avg: 596.49 / Max: 627.65 Min: 103.11 / Avg: 521.41 / Max: 554.74 Min: 108.67 / Avg: 463.55 / Max: 488.13 Min: 36.05 / Avg: 383.1 / Max: 399.03 Min: 106.01 / Avg: 377.24 / Max: 400.35 Min: 35 / Avg: 338.48 / Max: 364.64 Min: 59.83 / Avg: 336.31 / Max: 366.79 Min: 78.47 / Avg: 334.1 / Max: 367.59 Min: 23.11 / Avg: 308.84 / Max: 321.58 Min: 28.62 / Avg: 291.85 / Max: 303.75 Min: 74.5 / Avg: 268.43 / Max: 329.84 Min: 53.36 / Avg: 261.49 / Max: 284.07 Min: 43.56 / Avg: 235.42 / Max: 250.81 Min: 43.7 / Avg: 183.09 / Max: 194.2 Min: 17.75 / Avg: 148.12 / Max: 155.49 Min: 16.71 / Avg: 127.12 / Max: 134.69
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ 30 60 90 120 150 SE +/- 1.03, N = 3 SE +/- 2.08, N = 3 SE +/- 1.60, N = 3 SE +/- 1.08, N = 3 SE +/- 0.25, N = 3 SE +/- 0.77, N = 3 SE +/- 1.32, N = 5 SE +/- 1.36, N = 4 SE +/- 1.34, N = 3 SE +/- 0.88, N = 8 SE +/- 0.37, N = 3 SE +/- 0.51, N = 3 SE +/- 1.43, N = 15 SE +/- 0.47, N = 14 SE +/- 0.28, N = 3 SE +/- 0.25, N = 3 SE +/- 0.55, N = 15 SE +/- 0.35, N = 3 SE +/- 0.55, N = 15 SE +/- 0.12, N = 3 SE +/- 0.38, N = 3 SE +/- 0.10, N = 3 155.96 148.21 137.99 133.36 122.75 120.56 114.31 112.73 102.73 101.47 78.73 72.31 69.45 69.20 64.29 60.93 59.18 58.94 54.96 50.35 49.39 43.54 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 67.43 / Avg: 546.46 / Max: 595.03 Min: 60.04 / Avg: 479.74 / Max: 516.86 Min: 98.37 / Avg: 446.63 / Max: 480.06 Min: 40.24 / Avg: 404.21 / Max: 436.31 Min: 105.31 / Avg: 380 / Max: 411.37 Min: 103.87 / Avg: 332.75 / Max: 361.02 Min: 34.28 / Avg: 276.26 / Max: 300.81 Min: 48.27 / Avg: 242.83 / Max: 266.43 Min: 25.1 / Avg: 234.83 / Max: 253.99 Min: 43.43 / Avg: 192.41 / Max: 207.48 Min: 20.25 / Avg: 189.72 / Max: 207.12 Min: 43.64 / Avg: 163.17 / Max: 174.94 Min: 18.9 / Avg: 123.51 / Max: 135.75 Min: 16.87 / Avg: 112.11 / Max: 123.24
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon 6766E Xeon 6780E Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ 6 12 18 24 30 SE +/- 0.04207, N = 3 SE +/- 0.09575, N = 3 SE +/- 0.08454, N = 3 SE +/- 0.06011, N = 3 SE +/- 0.01654, N = 3 SE +/- 0.05314, N = 3 SE +/- 0.09781, N = 5 SE +/- 0.10588, N = 4 SE +/- 0.12519, N = 3 SE +/- 0.08554, N = 8 SE +/- 0.05969, N = 3 SE +/- 0.09768, N = 3 SE +/- 0.09595, N = 14 SE +/- 0.29451, N = 15 SE +/- 0.06825, N = 3 SE +/- 0.06818, N = 3 SE +/- 0.15263, N = 15 SE +/- 0.09991, N = 3 SE +/- 0.16821, N = 15 SE +/- 0.04802, N = 3 SE +/- 0.15605, N = 3 SE +/- 0.05084, N = 3 6.41229 6.74977 7.24869 7.49940 8.14615 8.29533 8.75233 8.87446 9.73685 9.86018 12.70150 13.82950 14.45830 14.48310 15.55550 16.41230 16.91660 16.96720 18.21790 19.85930 20.24950 22.96890 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Standard EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ 30 60 90 120 150 SE +/- 1.03, N = 3 SE +/- 2.08, N = 3 SE +/- 1.60, N = 3 SE +/- 1.08, N = 3 SE +/- 0.25, N = 3 SE +/- 0.77, N = 3 SE +/- 1.32, N = 5 SE +/- 1.36, N = 4 SE +/- 1.34, N = 3 SE +/- 0.88, N = 8 SE +/- 0.37, N = 3 SE +/- 0.51, N = 3 SE +/- 1.43, N = 15 SE +/- 0.47, N = 14 SE +/- 0.28, N = 3 SE +/- 0.25, N = 3 SE +/- 0.55, N = 15 SE +/- 0.35, N = 3 SE +/- 0.55, N = 15 SE +/- 0.12, N = 3 SE +/- 0.38, N = 3 SE +/- 0.10, N = 3 155.96 148.21 137.99 133.36 122.75 120.56 114.31 112.73 102.73 101.47 78.73 72.31 69.45 69.20 64.29 60.93 59.18 58.94 54.96 50.35 49.39 43.54 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Xeon 6766E Xeon 6766E 2P Xeon 6780E 2P Xeon 6780E EPYC 9654 2P EPYC 9754 2P EPYC 8534PN EPYC 9754 EPYC 8534P EPYC 9684X 2P EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4 8 12 16 20 SE +/- 0.08782, N = 3 SE +/- 0.07602, N = 3 SE +/- 0.14238, N = 15 SE +/- 0.07241, N = 3 SE +/- 0.06617, N = 3 SE +/- 0.26893, N = 15 SE +/- 0.02847, N = 3 SE +/- 0.02331, N = 3 SE +/- 0.02616, N = 3 SE +/- 0.18371, N = 12 SE +/- 0.04482, N = 3 SE +/- 0.03798, N = 3 SE +/- 0.28946, N = 12 SE +/- 0.04501, N = 3 SE +/- 0.02558, N = 3 SE +/- 0.05347, N = 4 SE +/- 0.10855, N = 15 SE +/- 0.00532, N = 3 SE +/- 0.00187, N = 3 SE +/- 0.00313, N = 3 SE +/- 0.05342, N = 3 SE +/- 0.00044, N = 3 16.86310 16.80620 15.12740 15.10570 10.43440 10.23106 9.71131 9.42177 9.38681 8.39969 8.15092 8.13326 5.29844 5.05427 5.00222 4.85818 4.72530 4.67269 4.58912 4.39649 3.98013 3.85774 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 EPYC 9754 2P EPYC 9684X EPYC 9654 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 60 120 180 240 300 Min: 98.64 / Avg: 328.39 / Max: 359.38 Min: 62.01 / Avg: 306.76 / Max: 325.52 Min: 57.88 / Avg: 270.43 / Max: 286.65 Min: 51.72 / Avg: 236.59 / Max: 257.65 Min: 40.2 / Avg: 219.21 / Max: 234.95 Min: 28.38 / Avg: 160.26 / Max: 175.87 Min: 27.15 / Avg: 144.22 / Max: 153.32 Min: 104.68 / Avg: 138.22 / Max: 146.78 Min: 103.86 / Avg: 127.8 / Max: 131.15 Min: 21.68 / Avg: 106.78 / Max: 113.35 Min: 18.73 / Avg: 83.53 / Max: 88.8 Min: 16.93 / Avg: 76.89 / Max: 81.74 Min: 43.48 / Avg: 72.93 / Max: 75.76 Min: 33.7 / Avg: 65.57 / Max: 67.97
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Xeon 6766E Xeon 6766E 2P Xeon 6780E 2P Xeon 6780E EPYC 9654 2P EPYC 9754 2P EPYC 8534PN EPYC 9754 EPYC 8534P EPYC 9684X 2P EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 60 120 180 240 300 SE +/- 0.31, N = 3 SE +/- 0.27, N = 3 SE +/- 0.60, N = 15 SE +/- 0.32, N = 3 SE +/- 0.61, N = 3 SE +/- 2.46, N = 15 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 SE +/- 0.30, N = 3 SE +/- 2.15, N = 12 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 6.83, N = 12 SE +/- 1.75, N = 3 SE +/- 1.02, N = 3 SE +/- 2.30, N = 4 SE +/- 4.15, N = 15 SE +/- 0.25, N = 3 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 SE +/- 3.39, N = 3 SE +/- 0.03, N = 3 59.30 59.50 66.18 66.20 95.84 98.64 102.97 106.13 106.53 119.56 122.68 122.95 192.81 197.85 199.90 205.89 212.92 213.99 217.88 227.42 251.31 259.19 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Standard Xeon 6766E Xeon 6766E 2P Xeon 6780E 2P Xeon 6780E EPYC 9654 2P EPYC 9754 2P EPYC 8534PN EPYC 9754 EPYC 8534P EPYC 9684X 2P EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4 8 12 16 20 SE +/- 0.08782, N = 3 SE +/- 0.07602, N = 3 SE +/- 0.14238, N = 15 SE +/- 0.07241, N = 3 SE +/- 0.06617, N = 3 SE +/- 0.26893, N = 15 SE +/- 0.02847, N = 3 SE +/- 0.02331, N = 3 SE +/- 0.02616, N = 3 SE +/- 0.18371, N = 12 SE +/- 0.04482, N = 3 SE +/- 0.03798, N = 3 SE +/- 0.28946, N = 12 SE +/- 0.04501, N = 3 SE +/- 0.02558, N = 3 SE +/- 0.05347, N = 4 SE +/- 0.10855, N = 15 SE +/- 0.00532, N = 3 SE +/- 0.00187, N = 3 SE +/- 0.00313, N = 3 SE +/- 0.05342, N = 3 SE +/- 0.00044, N = 3 16.86310 16.80620 15.12740 15.10570 10.43440 10.23106 9.71131 9.42177 9.38681 8.39969 8.15092 8.13326 5.29844 5.05427 5.00222 4.85818 4.72530 4.67269 4.58912 4.39649 3.98013 3.85774 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 20K 40K 60K 80K 100K SE +/- 175.68, N = 3 SE +/- 541.85, N = 3 SE +/- 424.84, N = 3 SE +/- 346.19, N = 3 SE +/- 172.59, N = 3 SE +/- 134.33, N = 3 SE +/- 64.91, N = 3 SE +/- 739.02, N = 15 SE +/- 102.40, N = 3 SE +/- 605.82, N = 15 SE +/- 152.29, N = 3 SE +/- 90.37, N = 3 SE +/- 42.05, N = 3 SE +/- 37.55, N = 3 SE +/- 193.23, N = 3 SE +/- 312.83, N = 12 SE +/- 13.86, N = 3 SE +/- 64.24, N = 3 SE +/- 16.05, N = 3 SE +/- 109.43, N = 3 SE +/- 14.62, N = 3 SE +/- 47.34, N = 3 103461 88579 81003 78093 72051 68973 62540 62449 58026 56082 55247 50798 43290 38926 38645 37383 36179 33411 24249 20750 17855 16960
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 2P Xeon Platinum 8490H 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 69.54 / Avg: 653.11 / Max: 822.49 Min: 79.71 / Avg: 606.49 / Max: 752.52 Min: 213.26 / Avg: 577.01 / Max: 753.84 Min: 197.25 / Avg: 571.94 / Max: 754.03 Min: 60.75 / Avg: 559.19 / Max: 686.72 Min: 168.48 / Avg: 535.88 / Max: 754.67 Min: 42.88 / Avg: 522.41 / Max: 691.8 Min: 102.98 / Avg: 432.31 / Max: 581.57 Min: 107.48 / Avg: 352.84 / Max: 587.47 Min: 104.78 / Avg: 311.45 / Max: 486.78 Min: 69.88 / Avg: 308.64 / Max: 375.21 Min: 78.44 / Avg: 306.37 / Max: 375.68 Min: 60.65 / Avg: 292.18 / Max: 377.6 Min: 30.5 / Avg: 290.44 / Max: 410.63 Min: 35.11 / Avg: 281.84 / Max: 376.97 Min: 30.06 / Avg: 244.64 / Max: 330.87 Min: 54.98 / Avg: 238.47 / Max: 291.29 Min: 21.62 / Avg: 219.88 / Max: 335.09 Min: 43.57 / Avg: 204.48 / Max: 283.69 Min: 43.65 / Avg: 164.56 / Max: 223.84 Min: 17.98 / Avg: 135.52 / Max: 167.31 Min: 17.4 / Avg: 117.68 / Max: 142.04
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 30K 60K 90K 120K 150K SE +/- 623.29, N = 3 SE +/- 365.52, N = 3 SE +/- 189.03, N = 3 SE +/- 13.58, N = 3 SE +/- 29.36, N = 3 SE +/- 41.33, N = 3 SE +/- 65.97, N = 3 SE +/- 900.17, N = 15 SE +/- 58.68, N = 3 SE +/- 176.25, N = 3 SE +/- 32.38, N = 3 SE +/- 162.52, N = 3 SE +/- 231.95, N = 3 SE +/- 155.80, N = 3 SE +/- 89.57, N = 3 SE +/- 50.97, N = 3 SE +/- 141.04, N = 3 SE +/- 125.33, N = 3 SE +/- 47.16, N = 3 SE +/- 756.08, N = 15 SE +/- 27.74, N = 3 SE +/- 28.11, N = 3 121734 101444 92175 91643 84261 80742 73366 71583 68006 66487 64188 59522 50019 45211 44349 42945 41971 38813 33391 27943 20893 20071
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 68.36 / Avg: 672.33 / Max: 821.45 Min: 204.64 / Avg: 589.92 / Max: 755.25 Min: 194.1 / Avg: 583.5 / Max: 754.71 Min: 167.48 / Avg: 554.33 / Max: 756.36 Min: 43.47 / Avg: 541.66 / Max: 691.2 Min: 60.79 / Avg: 534.58 / Max: 678.46 Min: 81.52 / Avg: 518.28 / Max: 753.01 Min: 105.22 / Avg: 444.93 / Max: 582.81 Min: 107.91 / Avg: 369.36 / Max: 547.58 Min: 56.05 / Avg: 325.96 / Max: 489.46 Min: 69.72 / Avg: 313.73 / Max: 377.15 Min: 74.4 / Avg: 312.09 / Max: 377.67 Min: 34.85 / Avg: 304.67 / Max: 411.05 Min: 59.95 / Avg: 299.76 / Max: 377.1 Min: 34.02 / Avg: 290.6 / Max: 377.55 Min: 27.71 / Avg: 254.04 / Max: 331.67 Min: 52.23 / Avg: 243.3 / Max: 290.85 Min: 21.87 / Avg: 229.47 / Max: 334.93 Min: 43.57 / Avg: 212.15 / Max: 289.98 Min: 43.64 / Avg: 170.07 / Max: 223.38 Min: 18.47 / Avg: 138.95 / Max: 167.41 Min: 16.93 / Avg: 120.39 / Max: 142.49
Zstd Compression This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 2P EPYC 8534P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P EPYC 9754 EPYC 8534PN Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9654 2P EPYC 9684X EPYC 9654 EPYC 9684X 2P 300 600 900 1200 1500 SE +/- 5.06, N = 3 SE +/- 2.22, N = 3 SE +/- 2.25, N = 3 SE +/- 5.13, N = 3 SE +/- 1.74, N = 4 SE +/- 4.96, N = 3 SE +/- 4.45, N = 3 SE +/- 1.75, N = 3 SE +/- 0.65, N = 15 SE +/- 0.66, N = 15 SE +/- 21.23, N = 3 SE +/- 2.12, N = 3 SE +/- 1.08, N = 15 SE +/- 1.83, N = 3 SE +/- 0.83, N = 3 SE +/- 1.58, N = 3 SE +/- 1.88, N = 3 SE +/- 3.01, N = 4 SE +/- 2.20, N = 3 SE +/- 7.31, N = 3 SE +/- 0.46, N = 3 SE +/- 1.73, N = 3 721.4 743.5 774.4 816.7 900.5 963.6 1032.0 1032.4 1039.2 1040.2 1118.8 1126.4 1127.5 1139.0 1139.9 1144.8 1165.8 1221.8 1382.1 1385.3 1388.9 1392.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
MB/s Per Watt
OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon Max 9480 Xeon Max 9468 EPYC 9654 2P Xeon 6766E 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X Xeon 6766E EPYC 9654 Xeon 6780E EPYC 9754 EPYC 8534P EPYC 8534PN 5 10 15 20 25 2.506 2.520 2.828 4.008 4.454 5.292 5.548 5.616 5.818 5.845 5.875 6.162 6.465 8.705 9.439 11.711 12.746 13.308 13.679 14.065 19.698 20.546
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression 1.5.4 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Platinum 8380 2P Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 80 160 240 320 400 Min: 203.74 / Avg: 415.14 / Max: 451.39 Min: 197.43 / Avg: 412.33 / Max: 448.69 Min: 170.25 / Avg: 340.73 / Max: 371.6 Min: 76.44 / Avg: 290.84 / Max: 334.48 Min: 60.19 / Avg: 263.13 / Max: 287.32 Min: 59.25 / Avg: 237.56 / Max: 259.24 Min: 75.37 / Avg: 203.22 / Max: 228.29 Min: 98.06 / Avg: 202.2 / Max: 229.76 Min: 73.69 / Avg: 200.55 / Max: 225.84 Min: 38.29 / Avg: 193.87 / Max: 209.99 Min: 61.06 / Avg: 159.64 / Max: 183.39 Min: 33.62 / Avg: 140.35 / Max: 172.45 Min: 104.87 / Avg: 125.62 / Max: 159.28 Min: 103.62 / Avg: 123.42 / Max: 157.28 Min: 33.68 / Avg: 118.29 / Max: 136.36 Min: 50.67 / Avg: 109.38 / Max: 135.43 Min: 27.93 / Avg: 104.36 / Max: 120.51 Min: 21.5 / Avg: 81.05 / Max: 92.77 Min: 43.45 / Avg: 59.7 / Max: 75.66 Min: 43.62 / Avg: 58.33 / Max: 74.24 Min: 16.44 / Avg: 56.8 / Max: 67.51 Min: 16.36 / Avg: 55.72 / Max: 65.47
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed Xeon 6766E 2P Xeon 6766E Xeon 6780E Xeon 6780E 2P Xeon Max 9480 2P Xeon Platinum 8380 EPYC 9754 2P Xeon Max 9468 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 9654 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 15 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 15 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.17, N = 4 SE +/- 0.15, N = 3 SE +/- 0.11, N = 15 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.22, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.21, N = 4 10.6 10.6 11.5 11.6 13.3 13.7 13.7 13.8 13.8 13.8 13.9 14.3 14.4 14.5 14.6 15.2 16.8 17.0 17.2 17.2 17.8 18.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
Speedb Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Read Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon Max 9480 Xeon Platinum 8380 2P EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 Xeon 6766E Xeon 6780E EPYC 9654 2P EPYC 9684X 2P Xeon 6766E 2P EPYC 9754 2P Xeon 6780E 2P 300M 600M 900M 1200M 1500M SE +/- 232538.80, N = 3 SE +/- 3698537.65, N = 15 SE +/- 70537.88, N = 3 SE +/- 2763560.64, N = 13 SE +/- 706582.63, N = 3 SE +/- 109015.29, N = 3 SE +/- 168680.90, N = 3 SE +/- 242146.75, N = 3 SE +/- 8491098.40, N = 15 SE +/- 66268.38, N = 3 SE +/- 2955608.21, N = 3 SE +/- 205170.43, N = 3 SE +/- 5393159.45, N = 3 SE +/- 5399265.88, N = 15 SE +/- 1606748.01, N = 3 SE +/- 998087.60, N = 3 SE +/- 1322733.50, N = 3 SE +/- 955915.20, N = 3 SE +/- 5954964.38, N = 3 SE +/- 1272758.30, N = 3 SE +/- 2399164.12, N = 3 SE +/- 2674444.99, N = 3 130359145 211457048 242940110 244070674 259136466 274091778 276179617 315178381 419943570 428557054 497907490 537633034 551286958 586147871 589951070 596955494 673159217 857687179 1059546533 1158496546 1169947385 1324163340 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Op/s Per Watt
OpenBenchmarking.org Op/s Per Watt, More Is Better Speedb 2.7 Test: Random Read Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 8534PN Xeon 6780E 2P Xeon 6780E Xeon 6766E 2P Xeon 6766E 500K 1000K 1500K 2000K 2500K 506592.64 509439.26 644065.87 680456.82 744809.12 747196.35 834394.35 834970.47 894980.08 962315.70 1380809.63 1404496.49 1511464.50 1563545.14 1818446.43 1962564.72 1991742.68 2023204.53 2130388.24 2159153.28 2449964.81 2531402.05
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Speedb 2.7 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8490H Xeon Max 9480 Xeon Platinum 8592+ Xeon 6780E Xeon Max 9468 EPYC 9754 EPYC 9654 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 69.56 / Avg: 767.34 / Max: 822.12 Min: 196.64 / Avg: 666.37 / Max: 752.39 Min: 168.96 / Avg: 660.7 / Max: 755.23 Min: 68.16 / Avg: 654.93 / Max: 718.87 Min: 185.93 / Avg: 652.02 / Max: 753.16 Min: 107.84 / Avg: 621.56 / Max: 712.89 Min: 40.77 / Avg: 596.13 / Max: 648.34 Min: 60.4 / Avg: 567.45 / Max: 609.28 Min: 103.26 / Avg: 511.53 / Max: 582.64 Min: 105.77 / Avg: 472.86 / Max: 540.08 Min: 33.89 / Avg: 382.79 / Max: 411.07 Min: 54.25 / Avg: 330.77 / Max: 378.66 Min: 70.78 / Avg: 327.7 / Max: 377.13 Min: 27.16 / Avg: 327.52 / Max: 377.21 Min: 43.47 / Avg: 311.77 / Max: 356.67 Min: 71.79 / Avg: 310.76 / Max: 333.42 Min: 22.11 / Avg: 296.2 / Max: 318.84 Min: 29.2 / Avg: 274.09 / Max: 293.61 Min: 54.55 / Avg: 255.89 / Max: 290.77 Min: 43.69 / Avg: 235.82 / Max: 270.43 Min: 18.42 / Avg: 150.73 / Max: 161.26 Min: 18.13 / Avg: 120.08 / Max: 129.07
VVenC VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Fast Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN Xeon Max 9468 2P Xeon Max 9480 2P EPYC 8534P Xeon Max 9468 EPYC 9754 Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9684X 2 4 6 8 10 SE +/- 0.008, N = 3 SE +/- 0.007, N = 3 SE +/- 0.010, N = 3 SE +/- 0.028, N = 3 SE +/- 0.041, N = 3 SE +/- 0.081, N = 3 SE +/- 0.043, N = 15 SE +/- 0.038, N = 3 SE +/- 0.010, N = 3 SE +/- 0.045, N = 3 SE +/- 0.047, N = 3 SE +/- 0.033, N = 3 SE +/- 0.022, N = 3 SE +/- 0.038, N = 3 SE +/- 0.023, N = 3 SE +/- 0.048, N = 3 SE +/- 0.057, N = 3 4.052 4.440 5.583 5.877 6.000 6.023 6.077 6.118 6.324 6.465 6.480 6.501 6.719 6.960 7.392 7.431 7.547 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Fast Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 0.0151 0.0302 0.0453 0.0604 0.0755 0.012 0.012 0.015 0.017 0.018 0.023 0.023 0.028 0.028 0.032 0.037 0.042 0.048 0.050 0.052 0.062 0.067
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better VVenC 1.11 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 110 220 330 440 550 Min: 193.59 / Avg: 516.46 / Max: 637.28 Min: 218.19 / Avg: 515.79 / Max: 625.23 Min: 154.77 / Avg: 444.48 / Max: 576.57 Min: 77.27 / Avg: 413.94 / Max: 550.57 Min: 100.2 / Avg: 328.02 / Max: 463.25 Min: 84.83 / Avg: 277.48 / Max: 349.11 Min: 71.41 / Avg: 273.3 / Max: 339.11 Min: 59.59 / Avg: 242.83 / Max: 330.87 Min: 26.5 / Avg: 232.82 / Max: 325.56 Min: 31.5 / Avg: 204.88 / Max: 302.64 Min: 52.86 / Avg: 196.6 / Max: 265.58 Min: 27.21 / Avg: 177.95 / Max: 263.84 Min: 20.88 / Avg: 134.72 / Max: 195.13 Min: 16.24 / Avg: 99.45 / Max: 145.04 Min: 15.3 / Avg: 89.82 / Max: 125.64 Min: 43.46 / Avg: 89.13 / Max: 146.7 Min: 43.59 / Avg: 78.47 / Max: 122.17
Video Input: Bosphorus 4K - Video Preset: Fast
EPYC 9684X 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
EPYC 9654 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
EPYC 9754 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Xeon 6766E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Xeon 6780E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Zstd Compression This test measures the time needed to compress/decompress a sample file (silesia.tar) using Zstd (Zstandard) compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H EPYC 8534PN EPYC 8534P EPYC 9754 EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 9654 300 600 900 1200 1500 SE +/- 4.61, N = 3 SE +/- 3.99, N = 3 SE +/- 1.54, N = 3 SE +/- 1.05, N = 3 SE +/- 0.30, N = 3 SE +/- 3.69, N = 3 SE +/- 4.15, N = 3 SE +/- 1.00, N = 3 SE +/- 1.78, N = 15 SE +/- 0.43, N = 3 SE +/- 0.92, N = 3 SE +/- 2.09, N = 3 SE +/- 1.95, N = 3 SE +/- 0.19, N = 3 SE +/- 0.56, N = 3 SE +/- 1.45, N = 3 SE +/- 1.60, N = 3 SE +/- 0.84, N = 3 SE +/- 2.93, N = 3 SE +/- 1.87, N = 3 SE +/- 1.99, N = 3 SE +/- 1.17, N = 3 701.2 739.1 753.2 797.7 912.9 992.1 1018.3 1041.8 1046.0 1069.1 1096.5 1101.4 1102.2 1104.2 1131.1 1133.3 1189.7 1242.6 1321.4 1324.6 1324.9 1328.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
MB/s Per Watt
OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 5 10 15 20 25 2.512 2.539 2.956 4.173 4.675 5.089 5.643 5.674 5.787 5.816 6.001 6.333 6.931 9.241 9.833 11.661 13.268 14.042 14.311 15.034 20.514 20.797
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression 1.5.4 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 2P EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P Xeon 6780E EPYC 8534PN Xeon 6766E 80 160 240 320 400 Min: 208.83 / Avg: 414.8 / Max: 438.11 Min: 201.8 / Avg: 412.05 / Max: 436.43 Min: 172.05 / Avg: 335.67 / Max: 356.47 Min: 75.89 / Avg: 285.1 / Max: 313.97 Min: 64.16 / Avg: 259.66 / Max: 276.36 Min: 57.79 / Avg: 234.74 / Max: 249.39 Min: 82.48 / Avg: 199.75 / Max: 214.36 Min: 73.9 / Avg: 195.37 / Max: 210.14 Min: 96.44 / Avg: 195.29 / Max: 212.05 Min: 39.89 / Avg: 189.86 / Max: 203.51 Min: 61.25 / Avg: 154.25 / Max: 170.09 Min: 33.99 / Avg: 134.46 / Max: 153.43 Min: 105.69 / Avg: 118.94 / Max: 149.49 Min: 103.71 / Avg: 116.84 / Max: 150.87 Min: 33.27 / Avg: 113.62 / Max: 124.55 Min: 49.33 / Avg: 103.56 / Max: 117.6 Min: 28.35 / Avg: 100.13 / Max: 109.97 Min: 18.92 / Avg: 78.5 / Max: 87.36 Min: 17.05 / Avg: 53.69 / Max: 60.18 Min: 43.37 / Avg: 53.06 / Max: 71.35 Min: 15.43 / Avg: 52.72 / Max: 59.1 Min: 43.63 / Avg: 51.65 / Max: 69.7
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E EPYC 9754 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Max 9480 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 15 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 5.60 5.65 6.10 6.19 6.64 6.68 6.74 6.76 7.46 7.52 7.62 7.72 7.76 7.83 7.94 8.16 8.30 8.38 8.42 8.45 9.67 9.80 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon 6766E Xeon 6780E Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 EPYC 8534PN Xeon Platinum 8380 EPYC 8534P Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8592+ 2P EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8490H EPYC 9754 2P Xeon Max 9480 EPYC 9654 2P EPYC 9684X 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P 0.306 0.612 0.918 1.224 1.53 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 9 SE +/- 0.01, N = 3 SE +/- 0.00, N = 15 SE +/- 0.00, N = 7 SE +/- 0.00, N = 3 SE +/- 0.00, N = 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.36 1.25 1.20 1.09 0.73 0.60 0.56 0.53 0.49 0.48 0.46 0.45 0.45 0.43 0.41 0.37 0.35 0.35 0.33 0.30 0.29 0.28 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9654 EPYC 9754 Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 Xeon 6780E Xeon Platinum 8592+ Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 201.96 / Avg: 633.47 / Max: 674.77 Min: 200.92 / Avg: 627.67 / Max: 669.86 Min: 36.23 / Avg: 623.56 / Max: 689.59 Min: 169.81 / Avg: 585.54 / Max: 631.87 Min: 57.78 / Avg: 545.61 / Max: 614.54 Min: 104.06 / Avg: 507.52 / Max: 580.05 Min: 81.83 / Avg: 472.9 / Max: 559.21 Min: 40.6 / Avg: 436.99 / Max: 487.81 Min: 34.06 / Avg: 367.01 / Max: 400.16 Min: 83.36 / Avg: 331.78 / Max: 377.93 Min: 73.52 / Avg: 330.72 / Max: 377.05 Min: 59.31 / Avg: 328.19 / Max: 373.29 Min: 26.97 / Avg: 310.58 / Max: 341.7 Min: 21.53 / Avg: 310.47 / Max: 338.08 Min: 107.98 / Avg: 302.19 / Max: 331.56 Min: 104.83 / Avg: 274.08 / Max: 295.37 Min: 51.57 / Avg: 255.35 / Max: 290.92 Min: 43.63 / Avg: 241.33 / Max: 263.98 Min: 33.52 / Avg: 235.56 / Max: 293.33 Min: 43.65 / Avg: 203.6 / Max: 221.29 Min: 19.35 / Avg: 152.78 / Max: 164.84 Min: 16.42 / Avg: 129.12 / Max: 139.81
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon Platinum 8380 Xeon 6766E 2P Xeon 6780E 2P EPYC 8534PN Xeon Platinum 8592+ Xeon 6766E EPYC 8534P Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ 2P EPYC 9754 EPYC 9654 Xeon Max 9468 EPYC 9684X Xeon Max 9480 Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9654 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8490H 2P 40K 80K 120K 160K 200K SE +/- 95.54, N = 3 SE +/- 1048.23, N = 3 SE +/- 1067.91, N = 3 SE +/- 55.52, N = 3 SE +/- 988.12, N = 3 SE +/- 68.06, N = 3 SE +/- 86.99, N = 3 SE +/- 100.17, N = 3 SE +/- 75.30, N = 3 SE +/- 1158.60, N = 3 SE +/- 89.35, N = 3 SE +/- 205.87, N = 3 SE +/- 383.22, N = 3 SE +/- 162.47, N = 3 SE +/- 1761.33, N = 3 SE +/- 696.52, N = 3 SE +/- 1374.23, N = 9 SE +/- 1922.38, N = 15 SE +/- 18.38, N = 3 SE +/- 1422.88, N = 15 SE +/- 1640.61, N = 7 SE +/- 2494.14, N = 3 61956.93 75761.50 76895.29 78334.92 81279.79 84584.13 87511.11 91273.02 115106.30 128566.81 132973.43 133779.62 135075.07 138605.52 140144.01 151627.42 166151.42 172688.50 174862.56 176900.32 178488.03 189893.31 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Xeon Platinum 8380 Xeon 6766E EPYC 8534PN Xeon 6780E EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon 6780E 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 700 1400 2100 2800 3500 SE +/- 4.62, N = 3 SE +/- 7.84, N = 3 SE +/- 1.20, N = 3 SE +/- 11.06, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 21.79, N = 12 SE +/- 0.88, N = 3 SE +/- 24.01, N = 12 SE +/- 0.58, N = 3 SE +/- 1.76, N = 3 SE +/- 1.15, N = 3 SE +/- 0.58, N = 3 SE +/- 1.20, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 0.58, N = 3 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 3052 2318 2240 2090 2043 1988 1792 1657 1553 1497 1441 1342 1180 1049 1037 961 954 894 759 661 561 531
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 62.5 / Avg: 640.62 / Max: 822.3 Min: 203.09 / Avg: 603.55 / Max: 753.72 Min: 198.09 / Avg: 602.84 / Max: 752.6 Min: 171.28 / Avg: 584.71 / Max: 751.6 Min: 81.36 / Avg: 571.36 / Max: 749.47 Min: 57.88 / Avg: 533.99 / Max: 677.83 Min: 41.9 / Avg: 518.09 / Max: 690.69 Min: 104.51 / Avg: 436.59 / Max: 581.52 Min: 108 / Avg: 365.31 / Max: 571.25 Min: 34.89 / Avg: 319.28 / Max: 410.78 Min: 56.57 / Avg: 313.79 / Max: 485.54 Min: 74.38 / Avg: 304.87 / Max: 378.48 Min: 75.94 / Avg: 303.61 / Max: 375.87 Min: 60.62 / Avg: 292.35 / Max: 377.02 Min: 35.06 / Avg: 288.94 / Max: 377.45 Min: 29.72 / Avg: 259.52 / Max: 331.33 Min: 22.93 / Avg: 248.39 / Max: 335.61 Min: 52 / Avg: 225.09 / Max: 290.77 Min: 43.56 / Avg: 188.73 / Max: 285.39 Min: 43.68 / Avg: 147 / Max: 223.13 Min: 18.36 / Avg: 131.28 / Max: 167.17 Min: 16.85 / Avg: 112.81 / Max: 142.09
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P EPYC 9754 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Platinum 8380 4 8 12 16 20 SE +/- 0.01, N = 15 SE +/- 0.02, N = 3 SE +/- 0.03, N = 15 SE +/- 0.06, N = 15 SE +/- 0.03, N = 15 SE +/- 0.01, N = 3 SE +/- 0.04, N = 15 SE +/- 0.06, N = 15 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 15 SE +/- 0.05, N = 9 SE +/- 0.09, N = 15 SE +/- 0.01, N = 4 SE +/- 0.13, N = 15 SE +/- 0.10, N = 4 SE +/- 0.05, N = 4 SE +/- 0.08, N = 15 SE +/- 0.08, N = 15 SE +/- 0.09, N = 4 SE +/- 0.08, N = 5 1.76 1.99 2.47 3.66 3.85 3.92 4.37 4.39 4.67 5.02 5.11 6.19 6.43 8.96 9.01 9.13 9.99 10.53 10.70 10.79 11.29 17.82
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 Xeon Max 9480 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Max 9480 EPYC 9754 EPYC 9684X Xeon Max 9468 Xeon Platinum 8490H EPYC 9654 Xeon 6780E Xeon 6766E Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 0.0315 0.063 0.0945 0.126 0.1575 0.009 0.009 0.009 0.009 0.010 0.010 0.010 0.011 0.011 0.032 0.042 0.045 0.048 0.050 0.053 0.056 0.057 0.060 0.062 0.130 0.132 0.140
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8490H EPYC 9684X EPYC 9654 Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9754 Xeon 6780E EPYC 8534P EPYC 8534PN Xeon 6766E 100 200 300 400 500 Min: 193.89 / Avg: 495.88 / Max: 584.14 Min: 196.38 / Avg: 479.87 / Max: 557.8 Min: 139.48 / Avg: 455.97 / Max: 550.2 Min: 64.93 / Avg: 389.7 / Max: 463.09 Min: 55.24 / Avg: 357.87 / Max: 424.3 Min: 77.73 / Avg: 351.48 / Max: 431.04 Min: 39.45 / Avg: 288.27 / Max: 343.12 Min: 98.96 / Avg: 285.87 / Max: 395.19 Min: 74.4 / Avg: 220.35 / Max: 283.28 Min: 74.86 / Avg: 214.64 / Max: 277.01 Min: 104.65 / Avg: 212.41 / Max: 239.17 Min: 103.83 / Avg: 203.64 / Max: 238.14 Min: 59.45 / Avg: 188.55 / Max: 248.97 Min: 32.53 / Avg: 179.99 / Max: 250.99 Min: 29.81 / Avg: 157.26 / Max: 218.19 Min: 26.03 / Avg: 152.5 / Max: 203.99 Min: 49.72 / Avg: 137.42 / Max: 216.79 Min: 20.21 / Avg: 128.28 / Max: 166.19 Min: 43.51 / Avg: 83.13 / Max: 101.84 Min: 16.58 / Avg: 81.51 / Max: 118.9 Min: 15.23 / Avg: 76.32 / Max: 109.67 Min: 43.57 / Avg: 74.94 / Max: 90.44
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 Xeon 6766E 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 9654 2P EPYC 9684X 2P EPYC 8534P Xeon Platinum 8380 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Max 9468 EPYC 9684X EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 9654 Xeon Platinum 8490H 2P Xeon Platinum 8490H 30 60 90 120 150 SE +/- 0.56, N = 3 SE +/- 0.88, N = 3 SE +/- 0.76, N = 3 SE +/- 0.04, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.91, N = 5 SE +/- 1.04, N = 4 SE +/- 0.05, N = 3 SE +/- 0.36, N = 3 SE +/- 0.50, N = 3 SE +/- 0.70, N = 3 SE +/- 0.93, N = 3 SE +/- 0.13, N = 3 SE +/- 0.08, N = 3 SE +/- 0.60, N = 3 SE +/- 1.28, N = 3 SE +/- 1.42, N = 3 SE +/- 0.39, N = 3 SE +/- 0.64, N = 3 SE +/- 1.12, N = 3 SE +/- 0.04, N = 3 61.48 67.08 68.52 71.41 76.37 80.86 82.94 86.08 87.31 90.72 91.51 94.66 103.56 104.23 104.52 106.14 107.30 108.32 111.71 114.63 115.47 120.93
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 2P EPYC 9754 2P Xeon Max 9468 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9684X Xeon Platinum 8380 Xeon 6780E Xeon Platinum 8592+ Xeon Platinum 8490H Xeon 6766E EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.1472 0.2944 0.4416 0.5888 0.736 0.159 0.170 0.178 0.179 0.186 0.186 0.188 0.202 0.202 0.236 0.326 0.330 0.354 0.362 0.378 0.382 0.398 0.423 0.448 0.477 0.610 0.654
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X EPYC 9654 Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 193.17 / Avg: 603.74 / Max: 661.05 Min: 206.91 / Avg: 601.85 / Max: 661.69 Min: 158.09 / Avg: 571.99 / Max: 633.85 Min: 66.65 / Avg: 542.07 / Max: 602.63 Min: 53.67 / Avg: 487.46 / Max: 539.03 Min: 81.35 / Avg: 469.58 / Max: 533.37 Min: 104.27 / Avg: 458.39 / Max: 515.43 Min: 40.87 / Avg: 375.57 / Max: 410.97 Min: 53.44 / Avg: 364.61 / Max: 411.61 Min: 104.2 / Avg: 330.36 / Max: 365.9 Min: 75.88 / Avg: 317.98 / Max: 346.3 Min: 73.44 / Avg: 315.74 / Max: 344.17 Min: 57.29 / Avg: 303.56 / Max: 335.19 Min: 33.94 / Avg: 295.36 / Max: 331.29 Min: 28.64 / Avg: 256.02 / Max: 290.14 Min: 51.52 / Avg: 250.55 / Max: 277.16 Min: 35.02 / Avg: 239.37 / Max: 274.93 Min: 19.21 / Avg: 222.65 / Max: 256.54 Min: 43.53 / Avg: 201.8 / Max: 232.09 Min: 43.68 / Avg: 168.94 / Max: 189.35 Min: 17.24 / Avg: 143.22 / Max: 160.51 Min: 15.94 / Avg: 123.62 / Max: 139.7
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8380 EPYC 8534PN EPYC 9754 EPYC 8534P EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8490H EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 60 120 180 240 300 SE +/- 2.84, N = 15 SE +/- 3.14, N = 3 SE +/- 0.48, N = 3 SE +/- 0.06, N = 3 SE +/- 0.39, N = 3 SE +/- 0.05, N = 3 SE +/- 1.05, N = 5 SE +/- 0.13, N = 3 SE +/- 0.77, N = 7 SE +/- 0.60, N = 11 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.59, N = 3 SE +/- 0.44, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.34, N = 3 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 294.69 271.14 259.66 240.38 127.89 109.00 102.84 100.67 91.16 83.11 70.95 62.46 56.73 48.43 43.17 41.57 38.50 37.58 29.98 28.73 28.17 26.85 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8490H EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 69.87 / Avg: 750.94 / Max: 819.6 Min: 196.83 / Avg: 663.81 / Max: 748.85 Min: 203.57 / Avg: 662.79 / Max: 751.8 Min: 167.2 / Avg: 656.03 / Max: 736.45 Min: 86.44 / Avg: 651.59 / Max: 748.25 Min: 52.92 / Avg: 645.83 / Max: 711.68 Min: 39.45 / Avg: 607.43 / Max: 679.21 Min: 108.68 / Avg: 553.41 / Max: 653.25 Min: 102.32 / Avg: 507.36 / Max: 566.08 Min: 106.93 / Avg: 441.51 / Max: 532 Min: 31.03 / Avg: 374.75 / Max: 410.94 Min: 70.61 / Avg: 331.05 / Max: 366.72 Min: 74.79 / Avg: 330.98 / Max: 373.36 Min: 34.43 / Avg: 325.81 / Max: 362.26 Min: 29.13 / Avg: 323.9 / Max: 362.47 Min: 59.14 / Avg: 321.95 / Max: 371.05 Min: 20.94 / Avg: 299.63 / Max: 344.93 Min: 43.55 / Avg: 296.98 / Max: 325.95 Min: 50.83 / Avg: 254.14 / Max: 284.65 Min: 43.66 / Avg: 230.17 / Max: 253.31 Min: 18.55 / Avg: 159.63 / Max: 174.23 Min: 17.99 / Avg: 135.1 / Max: 150.13
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9654 EPYC 9684X Xeon Platinum 8592+ EPYC 9754 Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P Xeon Platinum 8592+ 2P 200 400 600 800 1000 SE +/- 0.25, N = 3 SE +/- 0.03, N = 3 SE +/- 0.45, N = 3 SE +/- 2.30, N = 15 SE +/- 3.00, N = 3 SE +/- 0.17, N = 3 SE +/- 0.13, N = 3 SE +/- 0.39, N = 3 SE +/- 1.21, N = 3 SE +/- 4.09, N = 3 SE +/- 0.17, N = 3 SE +/- 4.59, N = 7 SE +/- 4.29, N = 11 SE +/- 0.54, N = 3 SE +/- 6.34, N = 5 SE +/- 3.48, N = 3 SE +/- 1.99, N = 3 SE +/- 1.13, N = 3 SE +/- 8.96, N = 3 SE +/- 0.37, N = 3 SE +/- 11.78, N = 3 SE +/- 0.85, N = 3 138.53 149.63 156.13 243.76 264.66 281.36 293.07 317.38 415.96 467.08 477.77 525.88 576.98 592.20 621.42 793.64 795.63 889.18 990.16 1110.49 1127.05 1128.78 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9684X EPYC 9654 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 Xeon Max 9468 8 16 24 32 40 SE +/- 0.34399, N = 3 SE +/- 0.32730, N = 6 SE +/- 0.08701, N = 3 SE +/- 0.07856, N = 3 SE +/- 0.08457, N = 3 SE +/- 0.05293, N = 3 SE +/- 0.05309, N = 3 SE +/- 0.02258, N = 3 SE +/- 0.03080, N = 3 SE +/- 0.06875, N = 3 SE +/- 0.02968, N = 3 SE +/- 0.01680, N = 3 SE +/- 0.04669, N = 3 SE +/- 0.06505, N = 4 SE +/- 0.03509, N = 3 SE +/- 0.03633, N = 15 SE +/- 0.03641, N = 15 SE +/- 0.03023, N = 3 SE +/- 0.02630, N = 3 SE +/- 0.00544, N = 3 SE +/- 0.01736, N = 3 SE +/- 0.01698, N = 3 36.40090 35.22660 17.90000 15.58560 11.31480 9.96245 9.95245 6.52367 6.51744 6.49693 6.39031 6.00525 5.59491 5.25321 5.18070 4.92653 4.82506 3.32030 3.23780 3.19298 3.17360 3.13366 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 64.35 / Avg: 547.96 / Max: 588.36 Min: 51.2 / Avg: 478.17 / Max: 512.01 Min: 101.46 / Avg: 445.87 / Max: 473.79 Min: 42.14 / Avg: 407.23 / Max: 436.3 Min: 108.09 / Avg: 347.86 / Max: 369.84 Min: 104.68 / Avg: 302.86 / Max: 321.76 Min: 36.05 / Avg: 285.19 / Max: 306.51 Min: 28.74 / Avg: 240.91 / Max: 259.49 Min: 53.36 / Avg: 238.84 / Max: 254.78 Min: 21.2 / Avg: 199.22 / Max: 213.69 Min: 43.63 / Avg: 170.55 / Max: 180.89 Min: 43.72 / Avg: 144.55 / Max: 152.6 Min: 18.11 / Avg: 126.52 / Max: 135.68 Min: 16.2 / Avg: 115 / Max: 124.26
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9684X EPYC 9654 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 Xeon Max 9468 70 140 210 280 350 SE +/- 0.26, N = 3 SE +/- 0.27, N = 6 SE +/- 0.27, N = 3 SE +/- 0.32, N = 3 SE +/- 0.66, N = 3 SE +/- 0.54, N = 3 SE +/- 0.54, N = 3 SE +/- 0.53, N = 3 SE +/- 0.73, N = 3 SE +/- 1.63, N = 3 SE +/- 0.73, N = 3 SE +/- 0.47, N = 3 SE +/- 1.50, N = 3 SE +/- 2.31, N = 4 SE +/- 1.30, N = 3 SE +/- 1.50, N = 15 SE +/- 1.54, N = 15 SE +/- 2.72, N = 3 SE +/- 2.50, N = 3 SE +/- 0.53, N = 3 SE +/- 1.73, N = 3 SE +/- 1.74, N = 3 27.47 28.40 55.86 64.16 88.37 100.36 100.46 153.25 153.41 153.92 156.46 166.49 178.70 190.38 192.99 203.06 207.34 301.14 308.80 313.10 315.03 319.04 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ResNet50 v1-12-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9684X EPYC 9654 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 Xeon Max 9468 8 16 24 32 40 SE +/- 0.34399, N = 3 SE +/- 0.32730, N = 6 SE +/- 0.08701, N = 3 SE +/- 0.07856, N = 3 SE +/- 0.08457, N = 3 SE +/- 0.05293, N = 3 SE +/- 0.05309, N = 3 SE +/- 0.02258, N = 3 SE +/- 0.03080, N = 3 SE +/- 0.06875, N = 3 SE +/- 0.02968, N = 3 SE +/- 0.01680, N = 3 SE +/- 0.04669, N = 3 SE +/- 0.06505, N = 4 SE +/- 0.03509, N = 3 SE +/- 0.03633, N = 15 SE +/- 0.03641, N = 15 SE +/- 0.03023, N = 3 SE +/- 0.02630, N = 3 SE +/- 0.00544, N = 3 SE +/- 0.01736, N = 3 SE +/- 0.01698, N = 3 36.40090 35.22660 17.90000 15.58560 11.31480 9.96245 9.95245 6.52367 6.51744 6.49693 6.39031 6.00525 5.59491 5.25321 5.18070 4.92653 4.82506 3.32030 3.23780 3.19298 3.17360 3.13366 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9654 2P EPYC 9754 EPYC 9684X 2P Xeon Max 9480 2P EPYC 8534PN EPYC 8534P Xeon Max 9468 2P EPYC 9654 Xeon Platinum 8490H 2P Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ 70 140 210 280 350 SE +/- 4.48, N = 3 SE +/- 0.86, N = 3 SE +/- 0.66, N = 3 SE +/- 0.65, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.45, N = 12 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 14 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 340.26 293.36 82.12 75.22 28.10 26.33 25.91 23.12 22.67 22.20 18.72 18.49 17.30 17.15 16.32 15.96 13.95 13.52 13.15 12.72 11.37 9.40 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon 6766E 2P EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.53 / Avg: 716.78 / Max: 816.61 Min: 205.34 / Avg: 657.37 / Max: 743.06 Min: 204.87 / Avg: 656.57 / Max: 725.7 Min: 171.01 / Avg: 649.04 / Max: 743.64 Min: 43.35 / Avg: 637.42 / Max: 766.05 Min: 61.14 / Avg: 581.56 / Max: 658.32 Min: 103.92 / Avg: 501.31 / Max: 570.17 Min: 41.91 / Avg: 488.86 / Max: 570.14 Min: 34.79 / Avg: 374.52 / Max: 409.97 Min: 108.4 / Avg: 354.62 / Max: 434.65 Min: 85.86 / Avg: 330.63 / Max: 384.53 Min: 73.68 / Avg: 329.15 / Max: 372.33 Min: 60.51 / Avg: 327.19 / Max: 379.48 Min: 34.54 / Avg: 324.07 / Max: 405.42 Min: 29.75 / Avg: 315.18 / Max: 357.38 Min: 105.02 / Avg: 307.84 / Max: 385.97 Min: 20.78 / Avg: 292.63 / Max: 342.23 Min: 51.5 / Avg: 253.93 / Max: 289.36 Min: 43.5 / Avg: 248.78 / Max: 279.12 Min: 43.71 / Avg: 207.06 / Max: 230.09 Min: 17.46 / Avg: 161.25 / Max: 175.66 Min: 17.49 / Avg: 137.08 / Max: 149.27
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 EPYC 9754 Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9754 2P Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 2K 4K 6K 8K 10K SE +/- 11.12, N = 3 SE +/- 2.88, N = 3 SE +/- 1.70, N = 3 SE +/- 13.67, N = 3 SE +/- 16.46, N = 3 SE +/- 6.96, N = 3 SE +/- 3.67, N = 3 SE +/- 0.64, N = 3 SE +/- 15.13, N = 3 SE +/- 1.87, N = 3 SE +/- 7.60, N = 3 SE +/- 139.41, N = 12 SE +/- 37.79, N = 3 SE +/- 67.22, N = 14 SE +/- 28.98, N = 3 SE +/- 27.90, N = 3 SE +/- 10.14, N = 3 SE +/- 1.84, N = 3 SE +/- 13.31, N = 3 SE +/- 77.59, N = 3 SE +/- 59.51, N = 3 SE +/- 24.76, N = 3 843.92 978.46 1525.57 1747.50 1906.99 2963.82 3405.94 3636.33 4208.49 4209.10 4386.48 5310.07 5565.23 5697.51 5933.65 6513.36 6757.26 6963.31 7356.63 7810.65 8231.72 9360.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 0 Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN Xeon Max 9468 EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P 30 60 90 120 150 SE +/- 0.22, N = 3 SE +/- 0.03, N = 3 SE +/- 0.18, N = 3 SE +/- 0.12, N = 3 SE +/- 0.52, N = 3 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 SE +/- 0.15, N = 3 SE +/- 0.19, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.22, N = 3 SE +/- 0.32, N = 3 SE +/- 0.29, N = 3 SE +/- 0.32, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 143.80 140.86 129.91 126.97 100.46 88.07 78.24 76.92 75.86 74.69 73.27 73.06 69.93 69.65 68.44 67.38 64.48 63.40 62.89 61.99 61.63 60.53 1. (CXX) g++ options: -O3 -fPIC -lm
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 1.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 130 260 390 520 650 Min: 205.63 / Avg: 494.12 / Max: 704.89 Min: 208.88 / Avg: 485.4 / Max: 727.55 Min: 152.89 / Avg: 425.04 / Max: 708.08 Min: 77.6 / Avg: 391.09 / Max: 728.04 Min: 62.98 / Avg: 324.3 / Max: 548.71 Min: 58.14 / Avg: 295.3 / Max: 499.26 Min: 96.24 / Avg: 285.14 / Max: 552.25 Min: 75.95 / Avg: 254.61 / Max: 372.81 Min: 69.59 / Avg: 253.47 / Max: 376.81 Min: 39.64 / Avg: 234.99 / Max: 370.06 Min: 61.27 / Avg: 218.41 / Max: 375.95 Min: 34.78 / Avg: 197.77 / Max: 373.2 Min: 30.24 / Avg: 180.87 / Max: 389.03 Min: 49.17 / Avg: 165.96 / Max: 290.88 Min: 29.48 / Avg: 156.52 / Max: 318.36 Min: 105.44 / Avg: 139.04 / Max: 263.97 Min: 104.01 / Avg: 131.11 / Max: 231.48 Min: 19.55 / Avg: 121.7 / Max: 248.44 Min: 17.01 / Avg: 85.23 / Max: 156.74 Min: 16.02 / Avg: 77.61 / Max: 131.52 Min: 43.39 / Avg: 72.37 / Max: 182.54 Min: 43.56 / Avg: 65.01 / Max: 148.96
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 2P EPYC 8534PN EPYC 8534P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8380 EPYC 9754 Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.12596, N = 3 SE +/- 0.14331, N = 3 SE +/- 0.01143, N = 3 SE +/- 0.01135, N = 3 SE +/- 0.04801, N = 3 SE +/- 0.04072, N = 3 SE +/- 0.01782, N = 3 SE +/- 0.01019, N = 3 SE +/- 0.02633, N = 15 SE +/- 0.02993, N = 3 SE +/- 0.03399, N = 3 SE +/- 0.03309, N = 3 SE +/- 0.00852, N = 3 SE +/- 0.02857, N = 3 SE +/- 0.02990, N = 3 SE +/- 0.00807, N = 3 SE +/- 0.03338, N = 15 SE +/- 0.01443, N = 3 SE +/- 0.01381, N = 3 SE +/- 0.00389, N = 3 SE +/- 0.01812, N = 3 SE +/- 0.01801, N = 3 10.80660 10.58830 4.20355 4.06272 4.05881 4.05270 4.00675 3.98735 3.95819 3.92455 3.91006 3.68001 3.61792 3.54242 3.12904 3.06500 2.97094 2.88734 2.81739 2.66711 2.23922 2.15980 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 60 120 180 240 300 Min: 99.27 / Avg: 314.65 / Max: 333.57 Min: 64.84 / Avg: 297.41 / Max: 317.19 Min: 57.25 / Avg: 267.87 / Max: 282.78 Min: 40.04 / Avg: 220.47 / Max: 233.47 Min: 52.52 / Avg: 218.31 / Max: 234.43 Min: 105.65 / Avg: 182.76 / Max: 192.69 Min: 103.76 / Avg: 180.19 / Max: 189.22 Min: 33.5 / Avg: 163.65 / Max: 174.8 Min: 29.55 / Avg: 141.28 / Max: 150.78 Min: 21.09 / Avg: 108.61 / Max: 116.43 Min: 43.42 / Avg: 105.34 / Max: 111.27 Min: 43.59 / Avg: 101.11 / Max: 106.64 Min: 17.28 / Avg: 82.81 / Max: 89.26 Min: 15.18 / Avg: 80.15 / Max: 85.73
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 2P EPYC 8534PN EPYC 8534P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8380 EPYC 9754 Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 100 200 300 400 500 SE +/- 1.08, N = 3 SE +/- 1.28, N = 3 SE +/- 0.65, N = 3 SE +/- 0.69, N = 3 SE +/- 2.94, N = 3 SE +/- 2.44, N = 3 SE +/- 1.11, N = 3 SE +/- 0.64, N = 3 SE +/- 1.67, N = 15 SE +/- 1.96, N = 3 SE +/- 2.24, N = 3 SE +/- 2.43, N = 3 SE +/- 0.65, N = 3 SE +/- 2.25, N = 3 SE +/- 3.02, N = 3 SE +/- 0.86, N = 3 SE +/- 3.48, N = 15 SE +/- 1.74, N = 3 SE +/- 1.73, N = 3 SE +/- 0.55, N = 3 SE +/- 3.58, N = 3 SE +/- 3.84, N = 3 92.51 94.42 237.80 246.04 246.34 246.68 249.48 250.63 252.67 254.73 255.67 271.62 276.21 282.25 319.45 326.14 337.00 346.21 354.75 374.75 446.30 462.86 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: T5 Encoder - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 2P EPYC 8534PN EPYC 8534P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8380 EPYC 9754 Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.12596, N = 3 SE +/- 0.14331, N = 3 SE +/- 0.01143, N = 3 SE +/- 0.01135, N = 3 SE +/- 0.04801, N = 3 SE +/- 0.04072, N = 3 SE +/- 0.01782, N = 3 SE +/- 0.01019, N = 3 SE +/- 0.02633, N = 15 SE +/- 0.02993, N = 3 SE +/- 0.03399, N = 3 SE +/- 0.03309, N = 3 SE +/- 0.00852, N = 3 SE +/- 0.02857, N = 3 SE +/- 0.02990, N = 3 SE +/- 0.00807, N = 3 SE +/- 0.03338, N = 15 SE +/- 0.01443, N = 3 SE +/- 0.01381, N = 3 SE +/- 0.00389, N = 3 SE +/- 0.01812, N = 3 SE +/- 0.01801, N = 3 10.80660 10.58830 4.20355 4.06272 4.05881 4.05270 4.00675 3.98735 3.95819 3.92455 3.91006 3.68001 3.61792 3.54242 3.12904 3.06500 2.97094 2.88734 2.81739 2.66711 2.23922 2.15980 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
ASKAP ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9654 2P EPYC 9684X 2P 30K 60K 90K 120K 150K SE +/- 47.29, N = 3 SE +/- 46.25, N = 3 SE +/- 0.00, N = 3 SE +/- 86.77, N = 3 SE +/- 76.67, N = 3 SE +/- 99.83, N = 3 SE +/- 0.00, N = 3 SE +/- 685.49, N = 12 SE +/- 219.20, N = 3 SE +/- 412.68, N = 4 SE +/- 194.30, N = 3 SE +/- 802.88, N = 3 SE +/- 1853.72, N = 3 SE +/- 1180.69, N = 14 SE +/- 1080.03, N = 3 SE +/- 581.17, N = 3 SE +/- 2386.93, N = 4 SE +/- 19579.11, N = 3 9623.77 14497.30 16399.70 16573.20 21314.20 21766.50 23250.20 28854.30 37265.90 41773.00 42939.20 45195.10 46233.70 54066.00 72004.00 74389.00 86757.70 121976.90 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Mpix/sec Per Watt
OpenBenchmarking.org Mpix/sec Per Watt, More Is Better ASKAP 1.0 Test: tConvolve MPI - Gridding Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 8534P EPYC 9754 EPYC 8534PN EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X 50 100 150 200 250 29.22 38.76 66.72 67.77 67.85 69.96 70.87 75.14 109.74 125.14 128.04 130.96 134.70 142.12 167.00 188.14 199.37 247.30
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASKAP 1.0 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 196.89 / Avg: 637.73 / Max: 729.76 Min: 196.26 / Avg: 633.57 / Max: 720.17 Min: 163.2 / Avg: 626.07 / Max: 724.87 Min: 64.2 / Avg: 611.81 / Max: 819.12 Min: 74.42 / Avg: 562.35 / Max: 727.39 Min: 57.21 / Avg: 519.5 / Max: 681.6 Min: 97.93 / Avg: 496.22 / Max: 563.93 Min: 37.58 / Avg: 492.69 / Max: 670.56 Min: 57.81 / Avg: 314.14 / Max: 357.36 Min: 74.39 / Avg: 311.12 / Max: 354.1 Min: 73.2 / Avg: 309.44 / Max: 360.17 Min: 31.29 / Avg: 300.8 / Max: 409.34 Min: 24.59 / Avg: 297.8 / Max: 352.67 Min: 52.74 / Avg: 248.29 / Max: 286.59 Min: 29.47 / Avg: 245.74 / Max: 336.85 Min: 20.61 / Avg: 214.21 / Max: 327.89 Min: 19.03 / Avg: 126.56 / Max: 161.28 Min: 16.5 / Avg: 115.4 / Max: 136.82
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9654 2P EPYC 9684X 2P 30K 60K 90K 120K 150K SE +/- 64.71, N = 3 SE +/- 62.13, N = 3 SE +/- 69.57, N = 3 SE +/- 44.43, N = 3 SE +/- 93.91, N = 3 SE +/- 0.00, N = 3 SE +/- 76.47, N = 3 SE +/- 598.81, N = 12 SE +/- 153.57, N = 3 SE +/- 378.22, N = 4 SE +/- 143.60, N = 3 SE +/- 0.00, N = 3 SE +/- 189.10, N = 3 SE +/- 1077.92, N = 14 SE +/- 480.95, N = 3 SE +/- 0.00, N = 3 SE +/- 882.91, N = 4 SE +/- 0.00, N = 3 8429.13 12800.40 15903.40 16704.40 17891.60 18522.00 20561.40 28476.60 31177.20 34614.10 36900.50 40368.60 42172.40 52639.50 59139.20 64260.20 81025.80 123480.00 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
Helsing Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon 6766E Xeon Max 9480 EPYC 8534P Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 9654 Xeon 6766E 2P Xeon Max 9480 2P EPYC 9684X Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9754 Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.53, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.27, N = 3 SE +/- 0.10, N = 3 SE +/- 0.26, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.42, N = 3 SE +/- 0.14, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.38, N = 5 SE +/- 0.42, N = 3 SE +/- 0.32, N = 3 165.79 123.83 120.56 115.46 107.24 105.68 103.86 93.35 89.07 82.96 65.03 62.17 58.96 58.25 56.91 53.02 50.83 48.85 48.09 33.68 30.69 26.78 1. (CC) gcc options: -O2 -pthread
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Helsing 1.0-beta CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 150 300 450 600 750 Min: 67.93 / Avg: 711.96 / Max: 830.1 Min: 210.37 / Avg: 664.49 / Max: 742.91 Min: 203.6 / Avg: 662.24 / Max: 747.53 Min: 173.59 / Avg: 654.95 / Max: 756.78 Min: 74.95 / Avg: 643.2 / Max: 755.25 Min: 58.49 / Avg: 624.24 / Max: 716.4 Min: 41.44 / Avg: 591.29 / Max: 696.59 Min: 107.47 / Avg: 552.92 / Max: 634.15 Min: 102.73 / Avg: 517.9 / Max: 581.32 Min: 105.07 / Avg: 444.27 / Max: 495.95 Min: 34.66 / Avg: 378.16 / Max: 412.26 Min: 73.73 / Avg: 338.57 / Max: 364.52 Min: 87.46 / Avg: 338.48 / Max: 364.16 Min: 56.9 / Avg: 336.32 / Max: 376.98 Min: 32.85 / Avg: 334.81 / Max: 377.7 Min: 28.89 / Avg: 322.19 / Max: 348.84 Min: 21.32 / Avg: 315.34 / Max: 347.42 Min: 43.52 / Avg: 283.2 / Max: 302.38 Min: 52.7 / Avg: 264.22 / Max: 291.17 Min: 43.76 / Avg: 217.84 / Max: 231.94 Min: 18.11 / Avg: 166.23 / Max: 176.55 Min: 17.86 / Avg: 131.19 / Max: 137.88
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P Xeon 6766E 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 12K 24K 36K 48K 60K SE +/- 148.46, N = 3 SE +/- 199.93, N = 3 SE +/- 371.33, N = 3 SE +/- 31.02, N = 3 SE +/- 250.73, N = 3 SE +/- 409.89, N = 15 SE +/- 28.06, N = 3 SE +/- 429.71, N = 4 SE +/- 83.47, N = 3 SE +/- 62.46, N = 3 SE +/- 53.03, N = 3 SE +/- 37.49, N = 3 SE +/- 44.33, N = 3 SE +/- 72.42, N = 3 SE +/- 39.30, N = 3 SE +/- 51.39, N = 3 SE +/- 33.33, N = 3 SE +/- 34.10, N = 3 SE +/- 7.13, N = 3 SE +/- 32.74, N = 3 SE +/- 17.16, N = 3 SE +/- 12.34, N = 3 54456 52083 46875 42513 38811 38228 37055 35081 33790 31380 30442 23125 18896 16645 16603 15357 15286 14138 12124 10428 8916 8413
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Platinum 8592+ Xeon Max 9468 Xeon Max 9480 Xeon 6780E 2P EPYC 9654 Xeon Platinum 8490H Xeon 6766E 2P EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 66.57 / Avg: 696.59 / Max: 822.15 Min: 175.84 / Avg: 622.79 / Max: 756.66 Min: 210.55 / Avg: 606.6 / Max: 753.89 Min: 201.01 / Avg: 599.93 / Max: 754.22 Min: 78.22 / Avg: 573.74 / Max: 753.21 Min: 41.91 / Avg: 564.91 / Max: 692.23 Min: 61.04 / Avg: 548.32 / Max: 683.37 Min: 95.78 / Avg: 375.01 / Max: 583.47 Min: 35.54 / Avg: 320.39 / Max: 411.05 Min: 35.35 / Avg: 299.63 / Max: 376.51 Min: 74.46 / Avg: 283.63 / Max: 375.94 Min: 78.1 / Avg: 281.43 / Max: 376.32 Min: 107.79 / Avg: 277.62 / Max: 555.46 Min: 29.03 / Avg: 265.51 / Max: 331.71 Min: 61.9 / Avg: 259.12 / Max: 377.23 Min: 105.3 / Avg: 248.8 / Max: 487.82 Min: 21.92 / Avg: 245.02 / Max: 336.36 Min: 53.95 / Avg: 217.25 / Max: 291.65 Min: 43.51 / Avg: 165.73 / Max: 285.29 Min: 43.63 / Avg: 134.74 / Max: 219.04 Min: 17.86 / Avg: 118.24 / Max: 166.58 Min: 17.28 / Avg: 103.3 / Max: 141.73
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P Xeon 6766E 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 14K 28K 42K 56K 70K SE +/- 62.75, N = 3 SE +/- 500.31, N = 3 SE +/- 26.58, N = 3 SE +/- 197.99, N = 3 SE +/- 111.72, N = 3 SE +/- 51.90, N = 3 SE +/- 36.47, N = 3 SE +/- 301.00, N = 12 SE +/- 74.33, N = 3 SE +/- 61.20, N = 3 SE +/- 28.75, N = 3 SE +/- 26.00, N = 3 SE +/- 5.55, N = 3 SE +/- 25.12, N = 3 SE +/- 24.66, N = 3 SE +/- 21.05, N = 3 SE +/- 10.97, N = 3 SE +/- 29.96, N = 3 SE +/- 8.00, N = 3 SE +/- 27.79, N = 3 SE +/- 32.79, N = 3 SE +/- 16.90, N = 3 63035 57657 52501 48844 45377 43906 42837 39283 39238 36649 34866 31993 22305 19701 19535 18129 18111 16837 14358 12427 10514 10015
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon 6780E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9654 Xeon Platinum 8490H Xeon 6766E 2P EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 63.78 / Avg: 623.33 / Max: 822.16 Min: 78.39 / Avg: 616.75 / Max: 753.89 Min: 210.27 / Avg: 614.16 / Max: 754.39 Min: 199.93 / Avg: 609.51 / Max: 752.77 Min: 175.58 / Avg: 588.27 / Max: 757.42 Min: 63.21 / Avg: 573.82 / Max: 678.02 Min: 42.24 / Avg: 558.27 / Max: 695.79 Min: 106.2 / Avg: 388.48 / Max: 582.9 Min: 35.75 / Avg: 329.8 / Max: 411.04 Min: 107.96 / Avg: 295.44 / Max: 567.47 Min: 68.84 / Avg: 291.26 / Max: 378.07 Min: 76.02 / Avg: 287.68 / Max: 377.28 Min: 27.99 / Avg: 273.01 / Max: 332.14 Min: 59.63 / Avg: 268.15 / Max: 377.52 Min: 105.47 / Avg: 265.24 / Max: 464.47 Min: 22.55 / Avg: 256.1 / Max: 337.04 Min: 26.59 / Avg: 252.77 / Max: 377.16 Min: 53.28 / Avg: 223.15 / Max: 291.09 Min: 43.5 / Avg: 175.23 / Max: 284.38 Min: 43.65 / Avg: 142.62 / Max: 223.55 Min: 17.33 / Avg: 121.97 / Max: 166.66 Min: 17.31 / Avg: 107.81 / Max: 142.82
CloverLeaf CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf 1.3 Input: clover_bm64_short Xeon Platinum 8380 EPYC 8534PN EPYC 8534P EPYC 9754 EPYC 9654 Xeon Max 9480 EPYC 9684X Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E Xeon 6766E Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon Platinum 8490H 2P EPYC 9684X 2P 14 28 42 56 70 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 2.07, N = 12 SE +/- 2.15, N = 15 SE +/- 0.17, N = 3 SE +/- 1.81, N = 15 SE +/- 0.15, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.31, N = 3 SE +/- 0.40, N = 4 SE +/- 0.31, N = 15 SE +/- 0.45, N = 3 SE +/- 1.11, N = 12 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.30, N = 3 SE +/- 0.24, N = 3 SE +/- 0.23, N = 3 60.89 57.54 57.38 48.36 46.50 42.22 42.17 41.43 39.48 39.38 38.01 38.01 35.29 32.44 32.25 31.90 30.05 28.99 28.92 27.74 26.58 22.83 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better CloverLeaf 1.3 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 199.64 / Avg: 627.92 / Max: 713.69 Min: 195.63 / Avg: 623.99 / Max: 717.07 Min: 166.73 / Avg: 611.92 / Max: 712.51 Min: 75.65 / Avg: 552.24 / Max: 662.73 Min: 68.07 / Avg: 499.33 / Max: 638.11 Min: 102.86 / Avg: 479 / Max: 543.07 Min: 56.35 / Avg: 437.97 / Max: 551.54 Min: 107.36 / Avg: 389.09 / Max: 472.12 Min: 42.14 / Avg: 366.92 / Max: 461.67 Min: 104.9 / Avg: 364.67 / Max: 444.64 Min: 76.4 / Avg: 324.2 / Max: 367.03 Min: 74.72 / Avg: 323.64 / Max: 372.82 Min: 57.26 / Avg: 320.54 / Max: 366.56 Min: 32.08 / Avg: 299.62 / Max: 336.85 Min: 33.05 / Avg: 264.63 / Max: 353.22 Min: 53.35 / Avg: 254.93 / Max: 281.37 Min: 25.91 / Avg: 223.18 / Max: 288.87 Min: 43.45 / Avg: 184.14 / Max: 204.33 Min: 19.77 / Avg: 183.89 / Max: 245.13 Min: 43.65 / Avg: 168.7 / Max: 186.26 Min: 19.22 / Avg: 132.55 / Max: 146.42 Min: 17.1 / Avg: 122.03 / Max: 133.14
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU Xeon Platinum 8380 Xeon 6766E EPYC 8534PN Xeon 6780E EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon 6780E 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 800 1600 2400 3200 4000 SE +/- 3.79, N = 3 SE +/- 6.23, N = 3 SE +/- 3.06, N = 3 SE +/- 3.51, N = 3 SE +/- 1.00, N = 3 SE +/- 1.20, N = 3 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 SE +/- 2.73, N = 3 SE +/- 4.67, N = 3 SE +/- 1.45, N = 3 SE +/- 16.65, N = 5 SE +/- 1.00, N = 3 SE +/- 2.65, N = 3 SE +/- 1.53, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 0.00, N = 3 SE +/- 0.58, N = 3 SE +/- 1.45, N = 3 SE +/- 0.67, N = 3 3616 2731 2649 2472 2421 2357 2123 1977 1833 1832 1709 1631 1391 1237 1225 1143 1130 1063 898 780 660 630
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.19 / Avg: 642.74 / Max: 821.11 Min: 208.56 / Avg: 606.68 / Max: 753.95 Min: 204.32 / Avg: 605.57 / Max: 755.38 Min: 179.12 / Avg: 588.21 / Max: 753.37 Min: 79.09 / Avg: 574.5 / Max: 751.34 Min: 59.99 / Avg: 534.76 / Max: 676.92 Min: 42.39 / Avg: 515 / Max: 688.22 Min: 103.42 / Avg: 440.54 / Max: 582.66 Min: 108.07 / Avg: 363.45 / Max: 555.01 Min: 30.75 / Avg: 323.21 / Max: 411.04 Min: 105.7 / Avg: 310.43 / Max: 465.96 Min: 71.66 / Avg: 307.39 / Max: 377.12 Min: 74.64 / Avg: 306.2 / Max: 376.48 Min: 61.31 / Avg: 293.93 / Max: 377.6 Min: 26.01 / Avg: 290.77 / Max: 377.76 Min: 31.26 / Avg: 263.32 / Max: 331.82 Min: 22.69 / Avg: 249.28 / Max: 335.5 Min: 54.18 / Avg: 227.88 / Max: 291.87 Min: 43.6 / Avg: 190.51 / Max: 286.01 Min: 43.67 / Avg: 146.96 / Max: 222.56 Min: 18.61 / Avg: 131.5 / Max: 167.12 Min: 17.17 / Avg: 114.16 / Max: 142.74
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8592+ Xeon 6766E 2P Xeon 6766E EPYC 9754 Xeon 6780E 2P Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Platinum 8380 EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 15 30 45 60 75 SE +/- 0.03, N = 3 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.28, N = 3 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.26, N = 15 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 65.02 62.53 62.11 57.13 56.71 55.99 55.74 55.07 41.50 38.87 38.21 37.17 35.30 34.76 31.99 31.05 27.46 21.63 16.84 15.84 14.30 11.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon 6780E EPYC 9754 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.8 / Avg: 760.09 / Max: 819.06 Min: 201 / Avg: 659.95 / Max: 753.12 Min: 200.42 / Avg: 659.67 / Max: 754.38 Min: 168.6 / Avg: 652.87 / Max: 754.8 Min: 81.23 / Avg: 641.35 / Max: 755.31 Min: 60.61 / Avg: 599.17 / Max: 650.25 Min: 40.64 / Avg: 591.23 / Max: 648.1 Min: 109.15 / Avg: 564.61 / Max: 636.36 Min: 99.46 / Avg: 509.59 / Max: 578.94 Min: 106.85 / Avg: 458.61 / Max: 523.13 Min: 33.63 / Avg: 370.93 / Max: 400.44 Min: 74.41 / Avg: 330.18 / Max: 376.61 Min: 84.64 / Avg: 330.18 / Max: 380.81 Min: 59.15 / Avg: 327.9 / Max: 376.83 Min: 34.63 / Avg: 325.47 / Max: 376.24 Min: 30.63 / Avg: 302.4 / Max: 328.21 Min: 43.56 / Avg: 269.61 / Max: 298.84 Min: 21.36 / Avg: 269.44 / Max: 322.88 Min: 50.28 / Avg: 253.24 / Max: 288.06 Min: 43.66 / Avg: 218.36 / Max: 239.94 Min: 16.37 / Avg: 152.34 / Max: 164.44 Min: 17.95 / Avg: 130.31 / Max: 141.74
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon 6766E EPYC 8534P Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 2P EPYC 9754 Xeon Max 9468 2P Xeon 6766E 2P EPYC 9654 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon 6780E 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 900 1800 2700 3600 4500 SE +/- 0.62, N = 3 SE +/- 2.29, N = 3 SE +/- 2.94, N = 3 SE +/- 0.81, N = 3 SE +/- 2.69, N = 3 SE +/- 0.65, N = 3 SE +/- 2.82, N = 3 SE +/- 2.65, N = 3 SE +/- 0.47, N = 3 SE +/- 3.75, N = 3 SE +/- 11.41, N = 15 SE +/- 1.56, N = 3 SE +/- 2.08, N = 3 SE +/- 6.85, N = 3 SE +/- 1.74, N = 3 SE +/- 0.66, N = 3 SE +/- 2.23, N = 3 SE +/- 1.09, N = 3 SE +/- 11.53, N = 3 SE +/- 3.90, N = 3 SE +/- 5.33, N = 3 SE +/- 5.40, N = 3 642.44 860.64 894.87 918.53 924.90 998.09 1018.18 1068.43 1159.66 1186.24 1671.23 1691.79 1731.50 1743.49 1801.89 1843.61 1933.08 2212.41 2237.69 3353.73 4013.96 4032.66 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 60 120 180 240 300 SE +/- 3.87, N = 3 SE +/- 1.74, N = 15 SE +/- 0.84, N = 3 SE +/- 0.89, N = 3 SE +/- 0.45, N = 3 SE +/- 0.25, N = 3 SE +/- 0.22, N = 3 SE +/- 0.13, N = 3 SE +/- 0.35, N = 3 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.28, N = 3 SE +/- 0.11, N = 3 SE +/- 0.37, N = 3 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 285.99 266.10 160.13 146.78 83.77 66.63 66.44 40.63 38.10 36.61 34.31 34.25 34.16 33.50 31.79 30.47 25.98 24.55 23.66 22.59 21.34 16.55 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 62.47 / Avg: 550.79 / Max: 593.02 Min: 55.89 / Avg: 483.5 / Max: 517.8 Min: 102.55 / Avg: 456.44 / Max: 489.76 Min: 35.54 / Avg: 404.89 / Max: 435.36 Min: 107.98 / Avg: 351.03 / Max: 380.24 Min: 104.82 / Avg: 306.33 / Max: 331.18 Min: 34.21 / Avg: 290.09 / Max: 313.77 Min: 51.87 / Avg: 247.61 / Max: 266.6 Min: 30.05 / Avg: 245.24 / Max: 265.47 Min: 21.46 / Avg: 198.94 / Max: 215.69 Min: 43.59 / Avg: 175.34 / Max: 190.81 Min: 43.73 / Avg: 146.66 / Max: 157.5 Min: 19.18 / Avg: 133.31 / Max: 143.64 Min: 16.96 / Avg: 119.46 / Max: 129.05
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 14 28 42 56 70 SE +/- 0.04782, N = 3 SE +/- 0.02474, N = 15 SE +/- 0.03255, N = 3 SE +/- 0.04131, N = 3 SE +/- 0.06474, N = 3 SE +/- 0.05569, N = 3 SE +/- 0.05013, N = 3 SE +/- 0.07716, N = 3 SE +/- 0.23936, N = 3 SE +/- 0.12474, N = 3 SE +/- 0.09239, N = 3 SE +/- 0.11212, N = 3 SE +/- 0.03174, N = 3 SE +/- 0.04145, N = 3 SE +/- 0.27122, N = 3 SE +/- 0.11901, N = 3 SE +/- 0.55506, N = 3 SE +/- 0.27882, N = 3 SE +/- 0.20934, N = 3 SE +/- 0.10899, N = 3 SE +/- 0.09731, N = 3 SE +/- 0.27014, N = 3 3.49785 3.76003 6.24521 6.81330 11.93820 15.00820 15.05160 24.60950 26.24750 27.31280 29.14870 29.19550 29.26900 29.84930 31.45890 32.81410 38.50250 40.72890 42.27110 44.27480 46.84910 60.40940 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: ArcFace ResNet-100 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 60 120 180 240 300 SE +/- 3.87, N = 3 SE +/- 1.74, N = 15 SE +/- 0.84, N = 3 SE +/- 0.89, N = 3 SE +/- 0.45, N = 3 SE +/- 0.25, N = 3 SE +/- 0.22, N = 3 SE +/- 0.13, N = 3 SE +/- 0.35, N = 3 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.28, N = 3 SE +/- 0.11, N = 3 SE +/- 0.37, N = 3 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 285.99 266.10 160.13 146.78 83.77 66.63 66.44 40.63 38.10 36.61 34.31 34.25 34.16 33.50 31.79 30.47 25.98 24.55 23.66 22.59 21.34 16.55 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 9654 2P Xeon Platinum 8490H EPYC 9654 EPYC 9684X 2P EPYC 9684X Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 2P Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 40 80 120 160 200 SE +/- 0.13, N = 3 SE +/- 0.34, N = 3 SE +/- 0.33, N = 3 SE +/- 0.10, N = 3 SE +/- 0.46, N = 3 SE +/- 0.45, N = 15 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 180.29 172.72 157.28 153.76 62.64 60.90 45.71 41.38 39.86 38.85 36.90 36.20 34.92 33.18 32.00 25.72 25.12 24.94 24.00 23.12 22.96 21.87 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9754 Xeon Platinum 8592+ Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.9 / Avg: 760.8 / Max: 819.21 Min: 208.68 / Avg: 665.43 / Max: 751.81 Min: 200.26 / Avg: 664.69 / Max: 755.11 Min: 175.49 / Avg: 660.59 / Max: 741.22 Min: 79.4 / Avg: 653.57 / Max: 770.7 Min: 59.67 / Avg: 652.58 / Max: 705.65 Min: 42.75 / Avg: 632.45 / Max: 690.87 Min: 108.82 / Avg: 608.93 / Max: 712.7 Min: 102.66 / Avg: 511.4 / Max: 581.89 Min: 106.76 / Avg: 462.61 / Max: 540.57 Min: 31.71 / Avg: 382.65 / Max: 411.13 Min: 30.45 / Avg: 333.47 / Max: 360.29 Min: 87.21 / Avg: 332.74 / Max: 375.71 Min: 75.49 / Avg: 331.88 / Max: 373.56 Min: 59.81 / Avg: 328.72 / Max: 377.28 Min: 23.52 / Avg: 323.53 / Max: 352.29 Min: 24.83 / Avg: 318.97 / Max: 381.52 Min: 43.62 / Avg: 308.92 / Max: 356.46 Min: 49.49 / Avg: 255.74 / Max: 292.14 Min: 43.65 / Avg: 235.17 / Max: 270.9 Min: 17.94 / Avg: 165.08 / Max: 177.71 Min: 16.48 / Avg: 135.3 / Max: 146.77
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon 6766E 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9654 Xeon Platinum 8592+ EPYC 9684X EPYC 9754 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P 1400 2800 4200 5600 7000 SE +/- 4.60, N = 3 SE +/- 1.73, N = 3 SE +/- 0.61, N = 3 SE +/- 9.58, N = 15 SE +/- 0.47, N = 3 SE +/- 3.51, N = 3 SE +/- 1.20, N = 3 SE +/- 1.46, N = 3 SE +/- 3.81, N = 3 SE +/- 3.41, N = 3 SE +/- 4.55, N = 3 SE +/- 4.84, N = 3 SE +/- 0.73, N = 3 SE +/- 4.06, N = 3 SE +/- 7.27, N = 3 SE +/- 1.09, N = 3 SE +/- 2.81, N = 3 SE +/- 2.46, N = 3 SE +/- 9.83, N = 3 SE +/- 3.43, N = 3 SE +/- 13.59, N = 3 SE +/- 14.68, N = 3 637.76 832.29 934.97 1313.39 1396.78 1542.61 1593.88 1643.43 1826.82 2074.30 2243.84 2739.01 2924.66 2986.33 3280.25 3998.02 4351.59 4744.05 5178.29 5570.63 5766.62 6400.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9468 Xeon 6766E 2P Xeon 6766E Xeon Platinum 8592+ 2P Xeon 6780E 2P Xeon 6780E Xeon Platinum 8592+ EPYC 8534PN EPYC 9754 EPYC 8534P Xeon Platinum 8380 EPYC 9654 EPYC 9684X EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9684X 2P 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 21.73 20.24 19.44 17.84 17.19 16.33 16.28 15.11 14.67 14.30 14.01 13.73 11.48 10.97 10.78 9.26 8.58 7.85 5.00 4.54 4.46 4.08 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9654 EPYC 9754 Xeon Platinum 8592+ Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 68.28 / Avg: 749.07 / Max: 815.77 Min: 203.39 / Avg: 666.38 / Max: 758.84 Min: 209.95 / Avg: 663.67 / Max: 754.1 Min: 169.19 / Avg: 657.97 / Max: 750.83 Min: 85.37 / Avg: 650.24 / Max: 758.93 Min: 60.42 / Avg: 615.26 / Max: 666.72 Min: 43.09 / Avg: 614.49 / Max: 665.93 Min: 110.43 / Avg: 596.74 / Max: 654.1 Min: 100.89 / Avg: 510.45 / Max: 581 Min: 107.07 / Avg: 468.4 / Max: 537.67 Min: 34.99 / Avg: 371.14 / Max: 399.65 Min: 75.87 / Avg: 332.1 / Max: 380.66 Min: 71.96 / Avg: 331 / Max: 377.8 Min: 59.46 / Avg: 330.49 / Max: 383.24 Min: 29.58 / Avg: 315.71 / Max: 340.19 Min: 21.25 / Avg: 305.35 / Max: 334.91 Min: 33.71 / Avg: 302.37 / Max: 379.73 Min: 43.53 / Avg: 284.95 / Max: 316.24 Min: 49.67 / Avg: 255.11 / Max: 289.85 Min: 43.79 / Avg: 234.55 / Max: 257.28 Min: 17.62 / Avg: 156.89 / Max: 169.02 Min: 17.95 / Avg: 132.64 / Max: 143.89
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 8534PN Xeon Max 9480 Xeon Max 9468 EPYC 8534P Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9654 Xeon Max 9468 2P EPYC 9754 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 3K 6K 9K 12K 15K SE +/- 1.06, N = 3 SE +/- 1.12, N = 3 SE +/- 2.61, N = 3 SE +/- 2.89, N = 3 SE +/- 5.68, N = 3 SE +/- 8.09, N = 3 SE +/- 2.22, N = 3 SE +/- 0.81, N = 3 SE +/- 8.74, N = 3 SE +/- 2.84, N = 3 SE +/- 0.73, N = 3 SE +/- 5.08, N = 3 SE +/- 11.51, N = 3 SE +/- 8.70, N = 3 SE +/- 8.39, N = 3 SE +/- 4.11, N = 3 SE +/- 66.33, N = 15 SE +/- 3.54, N = 3 SE +/- 6.25, N = 3 SE +/- 4.21, N = 3 SE +/- 4.04, N = 3 SE +/- 1.24, N = 3 2120.33 2366.83 2553.55 2763.48 2877.32 2935.47 2943.08 3325.90 4376.09 4390.81 4656.92 4992.78 5483.81 5525.56 5528.15 5576.86 5778.51 6017.19 8719.37 10708.91 11735.42 12750.59 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E EPYC 9754 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 EPYC 9684X EPYC 9654 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ 13 26 39 52 65 SE +/- 0.71, N = 3 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.32, N = 3 SE +/- 0.55, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.35, N = 7 SE +/- 0.43, N = 4 SE +/- 0.33, N = 3 SE +/- 0.18, N = 3 SE +/- 0.30, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.22, N = 3 SE +/- 0.41, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 56.77 54.25 42.90 41.57 40.52 40.45 39.02 38.52 38.42 38.00 36.45 35.88 35.79 35.60 35.11 35.07 34.81 33.52 33.29 31.53 30.92 29.96 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 80 160 240 320 400 Min: 65.93 / Avg: 426.21 / Max: 468.57 Min: 58.29 / Avg: 391.03 / Max: 427.27 Min: 101.44 / Avg: 386.17 / Max: 431.52 Min: 41.16 / Avg: 302.54 / Max: 329.11 Min: 106.52 / Avg: 256.16 / Max: 280.65 Min: 104.02 / Avg: 236.43 / Max: 258.12 Min: 33.52 / Avg: 227.41 / Max: 249.95 Min: 53.88 / Avg: 210.59 / Max: 230.53 Min: 29.71 / Avg: 198.61 / Max: 217.44 Min: 21.43 / Avg: 160.48 / Max: 176.89 Min: 43.46 / Avg: 155.26 / Max: 169.97 Min: 43.71 / Avg: 132.85 / Max: 145.13 Min: 17.92 / Avg: 105.97 / Max: 115.61 Min: 16.17 / Avg: 95.68 / Max: 104.17
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E EPYC 9754 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 EPYC 9684X EPYC 9654 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ 8 16 24 32 40 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.19, N = 3 SE +/- 0.34, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.24, N = 7 SE +/- 0.33, N = 4 SE +/- 0.25, N = 3 SE +/- 0.14, N = 3 SE +/- 0.24, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 SE +/- 0.36, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 17.62 18.43 23.31 24.05 24.68 24.73 25.63 25.96 26.03 26.33 27.45 27.87 27.94 28.09 28.48 28.52 28.73 29.84 30.04 31.71 32.34 33.38 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E EPYC 9754 2P EPYC 9754 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 EPYC 9684X EPYC 9654 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ 13 26 39 52 65 SE +/- 0.71, N = 3 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.32, N = 3 SE +/- 0.55, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.35, N = 7 SE +/- 0.43, N = 4 SE +/- 0.33, N = 3 SE +/- 0.18, N = 3 SE +/- 0.30, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.22, N = 3 SE +/- 0.41, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 56.77 54.25 42.90 41.57 40.52 40.45 39.02 38.52 38.42 38.00 36.45 35.88 35.79 35.60 35.11 35.07 34.81 33.52 33.29 31.53 30.92 29.96 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: AlexNet Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon 6766E 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Max 9468 2P EPYC 9754 Xeon Max 9480 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 400 800 1200 1600 2000 SE +/- 2.03, N = 3 SE +/- 0.86, N = 3 SE +/- 0.57, N = 3 SE +/- 0.35, N = 3 SE +/- 1.47, N = 3 SE +/- 20.10, N = 12 SE +/- 3.89, N = 3 SE +/- 38.99, N = 12 SE +/- 5.13, N = 3 SE +/- 0.51, N = 3 SE +/- 0.67, N = 3 SE +/- 0.49, N = 3 SE +/- 5.91, N = 3 SE +/- 1.84, N = 3 SE +/- 17.88, N = 4 SE +/- 4.07, N = 3 SE +/- 8.55, N = 3 SE +/- 12.71, N = 3 SE +/- 7.97, N = 3 SE +/- 23.15, N = 4 SE +/- 18.52, N = 3 SE +/- 19.23, N = 3 677.40 732.79 796.82 875.23 883.00 979.89 1047.96 1064.18 1108.95 1278.45 1363.33 1392.91 1470.46 1486.12 1604.11 1620.53 1677.62 1862.79 1876.66 1897.64 1899.64 2039.63
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: AlexNet Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon 6766E Xeon Platinum 8380 EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H EPYC 9754 2P EPYC 9684X Xeon Platinum 8592+ EPYC 9654 EPYC 8534P EPYC 9754 EPYC 8534PN 2 4 6 8 10 2.310 2.406 2.537 2.674 3.050 3.101 3.147 3.220 3.409 3.502 3.517 3.526 3.853 3.903 4.426 4.569 4.675 4.861 5.294 6.494 6.899 6.990
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8490H EPYC 9654 Xeon Platinum 8380 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 200.65 / Avg: 632.22 / Max: 705.95 Min: 209.29 / Avg: 625.4 / Max: 706.28 Min: 161.55 / Avg: 603.65 / Max: 700.57 Min: 64.96 / Avg: 538.13 / Max: 644.98 Min: 84.88 / Avg: 522.57 / Max: 631.68 Min: 59.19 / Avg: 483.44 / Max: 576.3 Min: 99.17 / Avg: 474.18 / Max: 540.4 Min: 108.97 / Avg: 460.62 / Max: 565.85 Min: 42.21 / Avg: 410.73 / Max: 503.82 Min: 105.98 / Avg: 407.31 / Max: 478.77 Min: 73.05 / Avg: 325.43 / Max: 363.64 Min: 83.71 / Avg: 325.32 / Max: 365.52 Min: 33.58 / Avg: 305.73 / Max: 353.3 Min: 32.89 / Avg: 297.93 / Max: 351.95 Min: 60.6 / Avg: 288.85 / Max: 359.42 Min: 29.56 / Avg: 257.54 / Max: 304.86 Min: 53.82 / Avg: 251.06 / Max: 280.69 Min: 43.52 / Avg: 240.23 / Max: 284.38 Min: 21.12 / Avg: 234.91 / Max: 276.8 Min: 43.65 / Avg: 193.42 / Max: 225.02 Min: 19.53 / Avg: 134.77 / Max: 159.36 Min: 17.15 / Avg: 114 / Max: 136.39
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon Max 9480 EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6766E Xeon 6780E Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P EPYC 9754 Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 160K 320K 480K 640K 800K SE +/- 395.04, N = 3 SE +/- 155.19, N = 3 SE +/- 86.28, N = 3 SE +/- 40.48, N = 3 SE +/- 82.80, N = 3 SE +/- 105.60, N = 3 SE +/- 457.00, N = 3 SE +/- 63.14, N = 3 SE +/- 306.14, N = 3 SE +/- 846.02, N = 3 SE +/- 286.86, N = 3 SE +/- 86.78, N = 3 SE +/- 160.59, N = 3 SE +/- 412.72, N = 3 SE +/- 362.38, N = 3 SE +/- 156.35, N = 3 SE +/- 248.00, N = 3 SE +/- 1610.78, N = 3 SE +/- 1647.70, N = 3 SE +/- 713.18, N = 3 SE +/- 1065.76, N = 3 SE +/- 804.57, N = 3 91036.5 143755.3 153920.8 162727.4 172566.8 179647.5 182366.9 195648.8 233836.3 262432.6 288129.1 294183.2 316359.2 319827.2 350187.5 374413.5 380867.5 456271.0 519392.2 593246.9 644091.0 759922.1 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
MFLOPS Per Watt
OpenBenchmarking.org MFLOPS Per Watt, More Is Better QuantLib 1.32 Configuration: Multi-Threaded Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X EPYC 9684X 2P EPYC 9654 2P EPYC 9654 Xeon 6780E 2P Xeon 6780E Xeon 6766E 2P EPYC 8534P Xeon 6766E EPYC 9754 2P EPYC 9754 EPYC 8534PN 300 600 900 1200 1500 358.69 359.31 436.19 447.64 477.83 495.61 537.18 552.74 585.75 605.78 864.58 881.58 921.01 930.70 956.27 960.37 1089.21 1092.36 1113.28 1200.40 1200.71 1202.80
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better QuantLib 1.32 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9468 EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 65.34 / Avg: 730.61 / Max: 822.15 Min: 203.63 / Avg: 662.07 / Max: 755.13 Min: 205.33 / Avg: 660.57 / Max: 754.82 Min: 167.37 / Avg: 651.9 / Max: 756.65 Min: 77.95 / Avg: 650.23 / Max: 756.48 Min: 55.66 / Avg: 644.13 / Max: 715.22 Min: 40.73 / Avg: 633.06 / Max: 715.84 Min: 104.62 / Avg: 543.14 / Max: 713.12 Min: 100.73 / Avg: 507.54 / Max: 581.6 Min: 103.76 / Avg: 418.9 / Max: 541.48 Min: 33.64 / Avg: 369.92 / Max: 411.04 Min: 83.08 / Avg: 328.34 / Max: 376.88 Min: 58.59 / Avg: 325.01 / Max: 377.73 Min: 31.57 / Avg: 322.97 / Max: 378.63 Min: 72.72 / Avg: 321.14 / Max: 375.61 Min: 28.93 / Avg: 316.09 / Max: 352.6 Min: 21.13 / Avg: 311.83 / Max: 350.73 Min: 43.42 / Avg: 273.26 / Max: 357.57 Min: 49.64 / Avg: 253.81 / Max: 290.36 Min: 43.59 / Avg: 210.04 / Max: 270.15 Min: 17.59 / Avg: 157.98 / Max: 175.08 Min: 16.19 / Avg: 127.97 / Max: 140.32
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Xeon 6766E 2P Xeon 6766E EPYC 8534PN Xeon 6780E 2P Xeon 6780E EPYC 8534P EPYC 9754 EPYC 9654 EPYC 9684X Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 2P EPYC 9654 2P Xeon Max 9468 Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8592+ Xeon Platinum 8380 2P 160 320 480 640 800 SE +/- 1.58, N = 3 SE +/- 0.99, N = 3 SE +/- 0.12, N = 3 SE +/- 1.63, N = 3 SE +/- 1.47, N = 3 SE +/- 0.18, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.43, N = 3 SE +/- 3.13, N = 3 SE +/- 0.28, N = 3 SE +/- 0.00, N = 3 SE +/- 0.35, N = 3 SE +/- 0.03, N = 3 SE +/- 0.47, N = 3 SE +/- 0.40, N = 3 SE +/- 0.02, N = 3 SE +/- 0.15, N = 3 SE +/- 0.33, N = 3 SE +/- 0.43, N = 3 SE +/- 0.69, N = 3 SE +/- 0.22, N = 3 719.83 692.79 654.83 630.23 618.97 592.22 551.07 510.10 471.98 415.89 356.38 283.11 278.52 275.53 257.50 256.63 253.63 236.52 234.24 233.63 224.64 207.84 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon 6780E EPYC 9754 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.22 / Avg: 740.61 / Max: 819.79 Min: 204.33 / Avg: 649.97 / Max: 743.7 Min: 200.71 / Avg: 649.1 / Max: 748.61 Min: 166.52 / Avg: 639.29 / Max: 750.58 Min: 53.33 / Avg: 629.45 / Max: 695.56 Min: 74.99 / Avg: 625.11 / Max: 757.77 Min: 42.88 / Avg: 582.16 / Max: 663.93 Min: 107.91 / Avg: 568.65 / Max: 711.11 Min: 102.18 / Avg: 501.41 / Max: 578.17 Min: 105.04 / Avg: 434 / Max: 540.8 Min: 35.31 / Avg: 374.05 / Max: 411.15 Min: 82.85 / Avg: 327.08 / Max: 376.47 Min: 73.05 / Avg: 326.77 / Max: 376.97 Min: 58.75 / Avg: 323.68 / Max: 377.26 Min: 35.2 / Avg: 319.39 / Max: 384.58 Min: 28.86 / Avg: 317.58 / Max: 349.47 Min: 43.45 / Avg: 297.23 / Max: 353.99 Min: 20.35 / Avg: 295.9 / Max: 332.78 Min: 50.07 / Avg: 251.32 / Max: 290.45 Min: 43.56 / Avg: 225.98 / Max: 269.62 Min: 18.22 / Avg: 153 / Max: 168.49 Min: 17.81 / Avg: 126.81 / Max: 139.78
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU Xeon Platinum 8380 EPYC 8534PN Xeon 6766E EPYC 8534P Xeon 6780E EPYC 9654 Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon 6780E 2P EPYC 9754 Xeon Platinum 8490H EPYC 9654 2P Xeon Max 9468 EPYC 9684X 2P Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 120 240 360 480 600 SE +/- 0.36, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 SE +/- 0.12, N = 3 SE +/- 0.18, N = 3 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 SE +/- 0.41, N = 3 SE +/- 0.41, N = 3 SE +/- 0.04, N = 3 SE +/- 0.69, N = 3 SE +/- 0.58, N = 3 SE +/- 0.54, N = 3 SE +/- 0.01, N = 3 SE +/- 0.77, N = 3 47.99 48.73 51.85 53.89 58.06 93.99 96.08 99.72 101.51 113.68 115.78 167.83 188.74 202.59 205.03 217.11 231.83 284.64 373.50 401.45 423.18 545.21 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Xeon Platinum 8380 Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon 6766E 2P Xeon Max 9480 Xeon Platinum 8380 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9684X Xeon Max 9468 2P EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 14 28 42 56 70 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.23, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 SE +/- 0.05, N = 3 11.86 12.17 13.40 16.92 18.47 19.91 21.22 22.36 22.51 23.12 24.64 27.10 30.61 34.64 35.93 37.74 39.34 42.82 48.76 52.67 60.37 63.85
Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon 6780E 2P Xeon Max 9480 2P Xeon 6766E 2P Xeon Max 9468 Xeon Platinum 8490H 2P Xeon 6780E Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon 6766E EPYC 9684X 2P Xeon Platinum 8592+ EPYC 9654 2P EPYC 9684X EPYC 9754 2P EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.032 0.064 0.096 0.128 0.16 0.047 0.049 0.055 0.058 0.060 0.061 0.063 0.068 0.069 0.070 0.077 0.079 0.079 0.084 0.088 0.091 0.094 0.111 0.112 0.130 0.135 0.142
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 3.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 65.72 / Avg: 718.49 / Max: 821.14 Min: 206.3 / Avg: 652.41 / Max: 753.05 Min: 207.37 / Avg: 650.92 / Max: 752.3 Min: 174.41 / Avg: 631.92 / Max: 708.59 Min: 77.1 / Avg: 630.9 / Max: 750.84 Min: 60.47 / Avg: 577.89 / Max: 656.09 Min: 42.2 / Avg: 573.28 / Max: 670.75 Min: 100.97 / Avg: 476.45 / Max: 565.54 Min: 107.82 / Avg: 395.24 / Max: 502.47 Min: 35.77 / Avg: 367.12 / Max: 410.2 Min: 105.18 / Avg: 346.87 / Max: 441 Min: 78.8 / Avg: 318.09 / Max: 375.14 Min: 76.02 / Avg: 317.76 / Max: 373.98 Min: 61.9 / Avg: 311.6 / Max: 375.6 Min: 26.13 / Avg: 308.08 / Max: 376.91 Min: 23.6 / Avg: 289.58 / Max: 332.39 Min: 29.59 / Avg: 273.92 / Max: 319.11 Min: 53.09 / Avg: 241.12 / Max: 287.29 Min: 43.52 / Avg: 195.57 / Max: 243.19 Min: 43.64 / Avg: 154.91 / Max: 191.69 Min: 18.46 / Avg: 136.83 / Max: 158.83 Min: 16.8 / Avg: 119.14 / Max: 138.68
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Pabellon Barcelona - Compute: CPU-Only Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 30 60 90 120 150 SE +/- 0.15, N = 3 SE +/- 0.31, N = 3 SE +/- 0.44, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.16, N = 3 SE +/- 0.09, N = 3 SE +/- 0.26, N = 3 SE +/- 0.13, N = 3 SE +/- 0.25, N = 3 SE +/- 0.08, N = 3 SE +/- 0.20, N = 3 SE +/- 0.04, N = 3 SE +/- 0.26, N = 3 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.29, N = 3 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 150.39 106.96 97.80 94.41 87.92 85.12 80.29 76.10 65.67 60.11 55.26 51.29 48.88 46.38 44.87 41.85 39.83 35.11 31.28 26.35 23.84 21.66
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 65.23 / Avg: 677.05 / Max: 822.1 Min: 211.91 / Avg: 656.12 / Max: 755.31 Min: 208.34 / Avg: 654.26 / Max: 753.55 Min: 172.77 / Avg: 638.84 / Max: 757.46 Min: 77.37 / Avg: 624.76 / Max: 738.53 Min: 58.1 / Avg: 592.5 / Max: 710.39 Min: 108.3 / Avg: 523.16 / Max: 632.46 Min: 98.03 / Avg: 509.42 / Max: 580.91 Min: 41.28 / Avg: 465.54 / Max: 700.45 Min: 105.22 / Avg: 415.82 / Max: 498.21 Min: 31.38 / Avg: 370.95 / Max: 410.68 Min: 76.38 / Avg: 337.24 / Max: 375.65 Min: 76.03 / Avg: 336.64 / Max: 376.9 Min: 60.61 / Avg: 332.25 / Max: 377.75 Min: 34.2 / Avg: 330.4 / Max: 377.77 Min: 30.54 / Avg: 312.47 / Max: 346.36 Min: 21.64 / Avg: 304.63 / Max: 348.18 Min: 43.58 / Avg: 280.84 / Max: 315.47 Min: 52.51 / Avg: 261.74 / Max: 291.09 Min: 43.71 / Avg: 217.74 / Max: 239.54 Min: 19.07 / Avg: 163.93 / Max: 175 Min: 17.1 / Avg: 133.17 / Max: 140.81
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 2P EPYC 8534PN Xeon Max 9468 Xeon Platinum 8592+ 2P EPYC 9754 EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8380 2P EPYC 9654 EPYC 9684X EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 26.12 25.33 24.24 23.49 18.08 16.50 15.04 14.42 13.59 13.34 12.67 12.54 11.69 11.35 11.22 11.17 9.82 9.47 8.48 6.27 5.20 4.91 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 70.55 / Avg: 710.38 / Max: 794.96 Min: 206.04 / Avg: 658.8 / Max: 752.52 Min: 204.78 / Avg: 655.73 / Max: 753.37 Min: 174.42 / Avg: 651.12 / Max: 753.13 Min: 84.22 / Avg: 639.31 / Max: 759.19 Min: 35.7 / Avg: 634.64 / Max: 688.41 Min: 43.98 / Avg: 604.36 / Max: 672.48 Min: 110.24 / Avg: 513.09 / Max: 584.23 Min: 101.65 / Avg: 506.94 / Max: 559.01 Min: 107.91 / Avg: 444.05 / Max: 496.43 Min: 34.6 / Avg: 368.08 / Max: 403.09 Min: 83.78 / Avg: 329.87 / Max: 374.74 Min: 60.78 / Avg: 328.2 / Max: 380.56 Min: 73.58 / Avg: 327.03 / Max: 377.73 Min: 33.49 / Avg: 325.49 / Max: 379.56 Min: 29.5 / Avg: 315.59 / Max: 344.89 Min: 22.15 / Avg: 293.51 / Max: 329.03 Min: 43.7 / Avg: 257.32 / Max: 280.77 Min: 50.78 / Avg: 254.29 / Max: 289.74 Min: 43.71 / Avg: 214.7 / Max: 232.23 Min: 18.03 / Avg: 158.07 / Max: 171.2 Min: 15.14 / Avg: 128.27 / Max: 140.82
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P EPYC 8534PN Xeon 6766E 2P EPYC 8534P Xeon 6780E 2P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 EPYC 9654 EPYC 9754 EPYC 9684X Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P Xeon Platinum 8592+ 2P 2K 4K 6K 8K 10K SE +/- 0.24, N = 3 SE +/- 2.55, N = 3 SE +/- 2.87, N = 3 SE +/- 1.00, N = 3 SE +/- 3.87, N = 3 SE +/- 5.02, N = 3 SE +/- 2.97, N = 3 SE +/- 3.86, N = 3 SE +/- 4.52, N = 3 SE +/- 7.17, N = 3 SE +/- 9.37, N = 3 SE +/- 25.68, N = 3 SE +/- 54.09, N = 3 SE +/- 18.02, N = 3 SE +/- 4.97, N = 3 SE +/- 4.05, N = 3 SE +/- 3.66, N = 3 SE +/- 8.98, N = 3 SE +/- 6.56, N = 3 SE +/- 10.88, N = 3 SE +/- 4.91, N = 3 SE +/- 3.37, N = 3 1100.18 1414.86 1525.26 2030.97 2506.10 2743.39 2830.12 2957.69 3606.12 3802.61 4093.73 5024.32 5594.81 5608.07 5725.03 7127.28 7689.32 7862.58 9203.19 9752.89 10182.16 10934.17 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E EPYC 9684X 2P EPYC 9654 2P EPYC 8534PN Xeon 6780E EPYC 9754 EPYC 8534P EPYC 9654 EPYC 9684X Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8592+ 30 60 90 120 150 SE +/- 0.90, N = 3 SE +/- 0.21, N = 3 SE +/- 0.30, N = 3 SE +/- 0.10, N = 3 SE +/- 0.60, N = 3 SE +/- 0.65, N = 3 SE +/- 1.29, N = 4 SE +/- 0.31, N = 3 SE +/- 0.60, N = 3 SE +/- 1.08, N = 3 SE +/- 0.60, N = 3 SE +/- 0.57, N = 3 SE +/- 0.23, N = 3 SE +/- 0.50, N = 3 SE +/- 0.11, N = 3 SE +/- 0.56, N = 3 SE +/- 0.12, N = 3 SE +/- 0.31, N = 3 SE +/- 0.18, N = 3 SE +/- 0.23, N = 3 SE +/- 0.49, N = 3 SE +/- 0.57, N = 3 149.99 140.07 125.24 116.64 114.16 113.52 112.76 105.22 103.60 102.05 81.60 81.43 73.97 72.80 68.83 66.91 64.79 63.54 62.13 61.25 59.94 50.83 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 90 180 270 360 450 Min: 68.13 / Avg: 462.27 / Max: 495 Min: 103.61 / Avg: 436.17 / Max: 466.43 Min: 58.35 / Avg: 411.86 / Max: 441.41 Min: 105.38 / Avg: 317.3 / Max: 341.18 Min: 40.61 / Avg: 307.67 / Max: 327.17 Min: 104.24 / Avg: 292.81 / Max: 313.39 Min: 33.93 / Avg: 264.24 / Max: 286.38 Min: 53.86 / Avg: 240.25 / Max: 259.56 Min: 30.08 / Avg: 223.68 / Max: 241.02 Min: 20.48 / Avg: 190.15 / Max: 204.22 Min: 43.61 / Avg: 168.62 / Max: 180.75 Min: 43.69 / Avg: 144.23 / Max: 154.04 Min: 18.28 / Avg: 121.13 / Max: 131.61 Min: 16.6 / Avg: 99.26 / Max: 116.55
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E EPYC 9684X 2P EPYC 9654 2P EPYC 8534PN Xeon 6780E EPYC 9754 EPYC 8534P EPYC 9654 EPYC 9684X Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8592+ 5 10 15 20 25 SE +/- 0.03979, N = 3 SE +/- 0.01071, N = 3 SE +/- 0.01907, N = 3 SE +/- 0.00728, N = 3 SE +/- 0.04604, N = 3 SE +/- 0.05052, N = 3 SE +/- 0.10146, N = 4 SE +/- 0.02804, N = 3 SE +/- 0.05587, N = 3 SE +/- 0.10485, N = 3 SE +/- 0.09004, N = 3 SE +/- 0.08493, N = 3 SE +/- 0.04124, N = 3 SE +/- 0.09371, N = 3 SE +/- 0.02421, N = 3 SE +/- 0.12404, N = 3 SE +/- 0.02832, N = 3 SE +/- 0.07567, N = 3 SE +/- 0.04566, N = 3 SE +/- 0.06023, N = 3 SE +/- 0.13407, N = 3 SE +/- 0.21736, N = 3 6.66718 7.13917 7.98402 8.57286 8.75971 8.80930 8.87144 9.50353 9.65296 9.80090 12.25490 12.28070 13.51900 13.73660 14.52800 14.94600 15.43410 15.73940 16.09560 16.32510 16.68630 19.67730 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: bertsquad-12 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E EPYC 9684X 2P EPYC 9654 2P EPYC 8534PN Xeon 6780E EPYC 9754 EPYC 8534P EPYC 9654 EPYC 9684X Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8592+ 30 60 90 120 150 SE +/- 0.90, N = 3 SE +/- 0.21, N = 3 SE +/- 0.30, N = 3 SE +/- 0.10, N = 3 SE +/- 0.60, N = 3 SE +/- 0.65, N = 3 SE +/- 1.29, N = 4 SE +/- 0.31, N = 3 SE +/- 0.60, N = 3 SE +/- 1.08, N = 3 SE +/- 0.60, N = 3 SE +/- 0.57, N = 3 SE +/- 0.23, N = 3 SE +/- 0.50, N = 3 SE +/- 0.11, N = 3 SE +/- 0.56, N = 3 SE +/- 0.12, N = 3 SE +/- 0.31, N = 3 SE +/- 0.18, N = 3 SE +/- 0.23, N = 3 SE +/- 0.49, N = 3 SE +/- 0.57, N = 3 149.99 140.07 125.24 116.64 114.16 113.52 112.76 105.22 103.60 102.05 81.60 81.43 73.97 72.80 68.83 66.91 64.79 63.54 62.13 61.25 59.94 50.83 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8490H EPYC 8534PN EPYC 8534P EPYC 9754 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9654 Xeon Max 9468 Xeon Platinum 8592+ 2P EPYC 9684X Xeon Platinum 8592+ EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 24.39 23.25 18.75 17.81 16.73 16.36 9.79 9.46 8.59 8.03 7.97 7.76 7.72 7.32 7.23 7.13 6.95 6.93 6.72 4.37 3.98 3.78 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 64.76 / Avg: 750.99 / Max: 819.5 Min: 209.53 / Avg: 660.24 / Max: 754.29 Min: 198.29 / Avg: 659.86 / Max: 754.53 Min: 172.39 / Avg: 651.14 / Max: 755.22 Min: 60.33 / Avg: 641.88 / Max: 698.45 Min: 84.79 / Avg: 638.38 / Max: 770.92 Min: 41.99 / Avg: 631.93 / Max: 700.82 Min: 110.7 / Avg: 588.97 / Max: 656.55 Min: 101.18 / Avg: 504.36 / Max: 573.33 Min: 107.09 / Avg: 456.74 / Max: 515.82 Min: 33.67 / Avg: 380.02 / Max: 410.65 Min: 29.57 / Avg: 331.39 / Max: 358.09 Min: 83.77 / Avg: 330.51 / Max: 377.23 Min: 73.88 / Avg: 330.38 / Max: 377.07 Min: 57.71 / Avg: 328.31 / Max: 374.69 Min: 34.07 / Avg: 323.98 / Max: 378.14 Min: 23.26 / Avg: 322.4 / Max: 353.88 Min: 43.64 / Avg: 297.75 / Max: 328.7 Min: 49.85 / Avg: 255.01 / Max: 291.18 Min: 43.82 / Avg: 230.25 / Max: 249.52 Min: 18.98 / Avg: 159.92 / Max: 172.73 Min: 18.47 / Avg: 133.6 / Max: 149.13
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H EPYC 9654 Xeon Max 9468 EPYC 9684X Xeon Max 9480 EPYC 9754 Xeon Platinum 8592+ EPYC 9654 2P EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 4K 8K 12K 16K 20K SE +/- 1.47, N = 3 SE +/- 20.57, N = 3 SE +/- 11.75, N = 3 SE +/- 2.06, N = 3 SE +/- 1.89, N = 3 SE +/- 3.18, N = 3 SE +/- 6.55, N = 3 SE +/- 4.90, N = 3 SE +/- 3.97, N = 3 SE +/- 4.14, N = 3 SE +/- 3.72, N = 3 SE +/- 4.58, N = 3 SE +/- 0.46, N = 3 SE +/- 4.98, N = 3 SE +/- 5.57, N = 3 SE +/- 7.03, N = 3 SE +/- 7.99, N = 3 SE +/- 3.67, N = 3 SE +/- 7.22, N = 3 SE +/- 10.13, N = 3 SE +/- 4.14, N = 3 SE +/- 7.74, N = 3 1698.05 2006.00 2179.99 3263.03 3355.73 3692.67 3787.94 4259.99 5943.66 6554.12 6717.65 6846.79 7207.74 7862.65 9515.86 12024.18 12665.62 13102.28 14033.94 14601.52 15519.92 18375.63 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
PyTorch This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 Xeon 6766E Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon 6780E EPYC 9654 EPYC 8534PN EPYC 8534P EPYC 9684X Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.20, N = 3 SE +/- 0.22, N = 4 SE +/- 0.28, N = 15 SE +/- 0.37, N = 12 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 SE +/- 0.44, N = 3 SE +/- 0.49, N = 3 SE +/- 0.45, N = 4 SE +/- 0.15, N = 3 SE +/- 0.30, N = 3 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 SE +/- 0.20, N = 3 SE +/- 0.52, N = 3 SE +/- 0.38, N = 8 SE +/- 0.36, N = 3 SE +/- 0.28, N = 3 SE +/- 0.03, N = 3 SE +/- 0.22, N = 3 SE +/- 0.16, N = 3 14.90 16.45 17.91 19.34 19.84 31.62 32.45 35.46 35.53 35.85 40.45 40.97 41.11 41.17 42.64 45.69 46.49 48.59 50.99 51.46 61.32 77.52
batches/sec Per Watt
OpenBenchmarking.org batches/sec Per Watt, More Is Better PyTorch 2.2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 EPYC 9684X 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P EPYC 9654 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9684X Xeon Max 9468 EPYC 9754 EPYC 9654 Xeon Platinum 8490H Xeon 6780E Xeon 6766E Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 0.1026 0.2052 0.3078 0.4104 0.513 0.052 0.052 0.053 0.053 0.056 0.066 0.083 0.088 0.102 0.155 0.193 0.200 0.214 0.221 0.231 0.234 0.251 0.258 0.346 0.377 0.435 0.456
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyTorch 2.2.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 199.22 / Avg: 540.93 / Max: 610.22 Min: 204.28 / Avg: 527.85 / Max: 604.75 Min: 81.45 / Avg: 450.14 / Max: 553.23 Min: 160.89 / Avg: 425.75 / Max: 563.56 Min: 62.51 / Avg: 384.75 / Max: 433.08 Min: 58.39 / Avg: 343.94 / Max: 402.47 Min: 108.69 / Avg: 341.29 / Max: 380.81 Min: 105.53 / Avg: 307.69 / Max: 344.16 Min: 41.67 / Avg: 279.95 / Max: 308.17 Min: 101.16 / Avg: 274.76 / Max: 317.28 Min: 78.78 / Avg: 251.12 / Max: 295.23 Min: 73.83 / Avg: 237.82 / Max: 286.68 Min: 58.92 / Avg: 219.54 / Max: 264.14 Min: 33.48 / Avg: 206.21 / Max: 246.32 Min: 33.19 / Avg: 205.45 / Max: 273.87 Min: 52.57 / Avg: 177.33 / Max: 220.98 Min: 30.07 / Avg: 174.93 / Max: 206.71 Min: 21.5 / Avg: 143.05 / Max: 166.54 Min: 43.45 / Avg: 142.9 / Max: 169.81 Min: 43.63 / Avg: 125.95 / Max: 146.47 Min: 17.99 / Avg: 94.53 / Max: 112.2 Min: 16.55 / Avg: 89.88 / Max: 106.44
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 9654 2P EPYC 9654 EPYC 9684X EPYC 9684X 2P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 2P Xeon Max 9468 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 7 14 21 28 35 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 28.24 27.01 24.77 24.25 13.11 11.78 11.20 10.92 10.17 10.09 9.42 9.25 8.58 8.27 3.58 2.79 2.67 2.53 2.50 2.50 2.48 2.36 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon 6780E EPYC 9754 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 68.11 / Avg: 762.39 / Max: 819.68 Min: 206.25 / Avg: 666.2 / Max: 754.51 Min: 208.01 / Avg: 666.11 / Max: 753.96 Min: 168.91 / Avg: 662.23 / Max: 753.52 Min: 83.6 / Avg: 652.57 / Max: 760.35 Min: 59.07 / Avg: 649.54 / Max: 702.57 Min: 40.68 / Avg: 615.84 / Max: 667.35 Min: 108.97 / Avg: 612 / Max: 711.29 Min: 100.48 / Avg: 510.62 / Max: 581.76 Min: 106.03 / Avg: 466.01 / Max: 540.12 Min: 34.9 / Avg: 384.48 / Max: 410.25 Min: 83.9 / Avg: 332.66 / Max: 375.98 Min: 73.64 / Avg: 331.47 / Max: 377.08 Min: 58.8 / Avg: 329.61 / Max: 364.22 Min: 34.78 / Avg: 327.29 / Max: 381.26 Min: 28.34 / Avg: 326.4 / Max: 351.05 Min: 43.61 / Avg: 309.55 / Max: 356.77 Min: 21.95 / Avg: 308.04 / Max: 333.19 Min: 50.92 / Avg: 255.35 / Max: 288.21 Min: 43.68 / Avg: 235.37 / Max: 270.07 Min: 18.69 / Avg: 156.99 / Max: 167.88 Min: 17.61 / Avg: 128.88 / Max: 137.57
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU Xeon Platinum 8380 EPYC 8534PN Xeon 6766E EPYC 8534P Xeon 6780E EPYC 9654 Xeon Platinum 8380 2P EPYC 9684X Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 Xeon Platinum 8490H EPYC 9654 2P Xeon Max 9468 EPYC 9684X 2P Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 10K 20K 30K 40K 50K SE +/- 5.62, N = 3 SE +/- 1.69, N = 3 SE +/- 7.59, N = 3 SE +/- 0.41, N = 3 SE +/- 6.61, N = 3 SE +/- 4.46, N = 3 SE +/- 6.41, N = 3 SE +/- 11.71, N = 3 SE +/- 12.93, N = 3 SE +/- 19.55, N = 3 SE +/- 5.50, N = 3 SE +/- 2.71, N = 3 SE +/- 147.69, N = 3 SE +/- 234.43, N = 4 SE +/- 110.20, N = 3 SE +/- 21.27, N = 3 SE +/- 11.27, N = 3 SE +/- 47.41, N = 3 SE +/- 80.58, N = 3 SE +/- 233.95, N = 3 SE +/- 53.98, N = 3 SE +/- 39.08, N = 3 4502.74 4830.01 5278.46 5366.79 5866.63 9356.71 9657.08 9997.89 10020.91 11390.04 11508.19 15943.17 18666.16 19183.83 20550.93 20910.53 22499.03 26943.42 37710.60 40032.81 47654.95 48122.16 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 8534P EPYC 8534PN Xeon 6766E Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9754 Xeon 6780E Xeon Platinum 8490H 2P Xeon Platinum 8380 2P EPYC 9654 EPYC 9684X Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4 8 12 16 20 SE +/- 0.11771, N = 3 SE +/- 0.01174, N = 3 SE +/- 0.01997, N = 3 SE +/- 0.02885, N = 3 SE +/- 0.03939, N = 3 SE +/- 0.03809, N = 3 SE +/- 0.02580, N = 3 SE +/- 0.00515, N = 3 SE +/- 0.08283, N = 3 SE +/- 0.01417, N = 3 SE +/- 0.00921, N = 3 SE +/- 0.01181, N = 3 SE +/- 0.03717, N = 3 SE +/- 0.06784, N = 3 SE +/- 0.00351, N = 3 SE +/- 0.02436, N = 3 SE +/- 0.01980, N = 3 SE +/- 0.07483, N = 3 SE +/- 0.02823, N = 3 SE +/- 0.01428, N = 3 SE +/- 0.02114, N = 3 SE +/- 0.00434, N = 3 17.05530 16.54180 10.06660 9.12452 9.06607 7.74521 7.70511 7.59589 7.34848 7.30822 7.28087 7.13535 6.90619 6.50747 6.37780 6.18478 5.54379 5.29027 5.22781 5.21520 5.10948 4.01687 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 60 120 180 240 300 Min: 97.1 / Avg: 306.05 / Max: 325.94 Min: 61.69 / Avg: 290.82 / Max: 309 Min: 57.53 / Avg: 262.4 / Max: 276.96 Min: 40 / Avg: 213.81 / Max: 226.08 Min: 53.03 / Avg: 204.41 / Max: 224.2 Min: 94.92 / Avg: 183.21 / Max: 193.59 Min: 103.68 / Avg: 180.17 / Max: 191.33 Min: 35.03 / Avg: 153.85 / Max: 164.75 Min: 27.22 / Avg: 134.62 / Max: 143.75 Min: 19.44 / Avg: 102.38 / Max: 109.98 Min: 43.53 / Avg: 101.74 / Max: 108.09 Min: 43.73 / Avg: 95.8 / Max: 101.7 Min: 16.21 / Avg: 79.24 / Max: 84.5 Min: 15.83 / Avg: 75.69 / Max: 81.06
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 8534P EPYC 8534PN Xeon 6766E Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9754 Xeon 6780E Xeon Platinum 8490H 2P Xeon Platinum 8380 2P EPYC 9654 EPYC 9684X Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 50 100 150 200 250 SE +/- 0.40, N = 3 SE +/- 0.04, N = 3 SE +/- 0.19, N = 3 SE +/- 0.35, N = 3 SE +/- 0.48, N = 3 SE +/- 0.64, N = 3 SE +/- 0.43, N = 3 SE +/- 0.09, N = 3 SE +/- 1.53, N = 3 SE +/- 0.26, N = 3 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 SE +/- 0.78, N = 3 SE +/- 1.59, N = 3 SE +/- 0.08, N = 3 SE +/- 0.64, N = 3 SE +/- 0.64, N = 3 SE +/- 2.63, N = 3 SE +/- 1.04, N = 3 SE +/- 0.53, N = 3 SE +/- 0.81, N = 3 SE +/- 0.27, N = 3 58.58 60.39 99.22 109.46 110.17 128.98 129.65 131.54 135.98 136.69 137.19 140.03 144.64 153.54 156.61 161.50 180.23 188.93 191.11 191.56 195.45 248.68 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: GPT-2 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 8534P EPYC 8534PN Xeon 6766E Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9754 Xeon 6780E Xeon Platinum 8490H 2P Xeon Platinum 8380 2P EPYC 9654 EPYC 9684X Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4 8 12 16 20 SE +/- 0.11771, N = 3 SE +/- 0.01174, N = 3 SE +/- 0.01997, N = 3 SE +/- 0.02885, N = 3 SE +/- 0.03939, N = 3 SE +/- 0.03809, N = 3 SE +/- 0.02580, N = 3 SE +/- 0.00515, N = 3 SE +/- 0.08283, N = 3 SE +/- 0.01417, N = 3 SE +/- 0.00921, N = 3 SE +/- 0.01181, N = 3 SE +/- 0.03717, N = 3 SE +/- 0.06784, N = 3 SE +/- 0.00351, N = 3 SE +/- 0.02436, N = 3 SE +/- 0.01980, N = 3 SE +/- 0.07483, N = 3 SE +/- 0.02823, N = 3 SE +/- 0.01428, N = 3 SE +/- 0.02114, N = 3 SE +/- 0.00434, N = 3 17.05530 16.54180 10.06660 9.12452 9.06607 7.74521 7.70511 7.59589 7.34848 7.30822 7.28087 7.13535 6.90619 6.50747 6.37780 6.18478 5.54379 5.29027 5.22781 5.21520 5.10948 4.01687 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E EPYC 8534PN EPYC 8534P EPYC 9754 2P Xeon Platinum 8380 Xeon Platinum 8490H EPYC 9754 Xeon Max 9480 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9654 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9684X EPYC 9684X 2P Xeon Max 9468 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 19.23 18.20 16.98 16.41 7.60 6.77 6.60 6.56 6.43 6.25 6.02 5.98 5.93 5.85 5.77 5.72 5.55 5.41 5.34 5.27 5.19 5.18 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 65.72 / Avg: 754.92 / Max: 818.94 Min: 196.21 / Avg: 665.03 / Max: 748.66 Min: 203.86 / Avg: 663.32 / Max: 752.94 Min: 165.34 / Avg: 658.39 / Max: 751.53 Min: 83.99 / Avg: 648.24 / Max: 768.1 Min: 59.24 / Avg: 612.41 / Max: 670.98 Min: 39.66 / Avg: 604.27 / Max: 668.8 Min: 108.98 / Avg: 585.34 / Max: 658.24 Min: 100.5 / Avg: 510.02 / Max: 582.06 Min: 105.68 / Avg: 456.22 / Max: 521.95 Min: 30.34 / Avg: 377.27 / Max: 406.75 Min: 77.72 / Avg: 331.34 / Max: 373.94 Min: 72.13 / Avg: 330.52 / Max: 368.64 Min: 58.3 / Avg: 329.39 / Max: 378.11 Min: 35.16 / Avg: 326.91 / Max: 374.78 Min: 31.29 / Avg: 316.48 / Max: 340.73 Min: 21 / Avg: 311.43 / Max: 339.91 Min: 43.59 / Avg: 299.29 / Max: 327.76 Min: 49.75 / Avg: 255.45 / Max: 289.44 Min: 43.67 / Avg: 229.66 / Max: 249.94 Min: 18.15 / Avg: 159.45 / Max: 171.38 Min: 16.94 / Avg: 130.25 / Max: 140.67
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU Xeon Platinum 8380 Xeon 6766E EPYC 8534PN Xeon 6780E Xeon Platinum 8490H Xeon Max 9468 EPYC 8534P Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9654 Xeon 6780E 2P EPYC 9684X Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 8K 16K 24K 32K 40K SE +/- 15.90, N = 3 SE +/- 2.54, N = 3 SE +/- 7.49, N = 3 SE +/- 0.67, N = 3 SE +/- 5.45, N = 3 SE +/- 18.13, N = 3 SE +/- 2.45, N = 3 SE +/- 7.39, N = 3 SE +/- 4.30, N = 3 SE +/- 16.45, N = 3 SE +/- 30.29, N = 3 SE +/- 2.59, N = 3 SE +/- 41.98, N = 3 SE +/- 7.70, N = 3 SE +/- 12.64, N = 3 SE +/- 3.89, N = 3 SE +/- 8.57, N = 3 SE +/- 12.64, N = 3 SE +/- 17.69, N = 3 SE +/- 46.87, N = 3 SE +/- 15.46, N = 3 SE +/- 10.72, N = 3 5913.04 7721.00 8279.63 8536.39 9004.23 9087.12 9256.11 9686.39 12317.94 13467.28 14551.12 16038.90 16394.06 17230.35 17252.27 18561.91 19917.54 20937.58 24676.86 31974.88 35809.59 38546.66 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 9754 EPYC 8534P EPYC 9654 EPYC 9684X Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 50 100 150 200 250 SE +/- 1.41, N = 3 SE +/- 2.49, N = 3 SE +/- 2.38, N = 3 SE +/- 0.15, N = 3 SE +/- 0.61, N = 3 SE +/- 0.91, N = 3 SE +/- 0.52, N = 3 SE +/- 0.53, N = 3 SE +/- 0.20, N = 3 SE +/- 0.01, N = 3 SE +/- 0.20, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.74, N = 3 SE +/- 0.57, N = 3 SE +/- 0.46, N = 3 SE +/- 0.22, N = 3 SE +/- 0.01, N = 3 SE +/- 0.36, N = 3 SE +/- 0.05, N = 3 SE +/- 0.30, N = 3 219.17 217.93 179.99 158.27 157.51 140.14 129.94 118.02 115.79 114.17 102.19 102.04 79.38 78.40 76.42 70.44 70.34 61.83 61.01 56.58 55.12 47.90 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 67.07 / Avg: 552.04 / Max: 595.99 Min: 59.75 / Avg: 482.18 / Max: 521.5 Min: 103.81 / Avg: 450.11 / Max: 482.7 Min: 39.89 / Avg: 406.34 / Max: 438.62 Min: 108.42 / Avg: 392.56 / Max: 431.32 Min: 104.75 / Avg: 350.62 / Max: 384.9 Min: 33.83 / Avg: 279.27 / Max: 303.77 Min: 53.1 / Avg: 243.23 / Max: 261.05 Min: 29.58 / Avg: 236.8 / Max: 255.65 Min: 21.66 / Avg: 192.93 / Max: 209.55 Min: 43.53 / Avg: 179.64 / Max: 193.29 Min: 43.74 / Avg: 152.65 / Max: 163.54 Min: 19.76 / Avg: 124.93 / Max: 135 Min: 18.05 / Avg: 113.49 / Max: 122.89
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 9754 EPYC 8534P EPYC 9654 EPYC 9684X Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 5 10 15 20 25 SE +/- 0.02942, N = 3 SE +/- 0.05214, N = 3 SE +/- 0.07368, N = 3 SE +/- 0.00606, N = 3 SE +/- 0.02467, N = 3 SE +/- 0.04609, N = 3 SE +/- 0.03075, N = 3 SE +/- 0.03807, N = 3 SE +/- 0.01474, N = 3 SE +/- 0.00112, N = 3 SE +/- 0.01934, N = 3 SE +/- 0.00491, N = 3 SE +/- 0.02010, N = 3 SE +/- 0.01439, N = 3 SE +/- 0.12795, N = 3 SE +/- 0.11392, N = 3 SE +/- 0.09305, N = 3 SE +/- 0.05802, N = 3 SE +/- 0.00279, N = 3 SE +/- 0.11211, N = 3 SE +/- 0.01672, N = 3 SE +/- 0.13074, N = 3 4.56278 4.58960 5.55767 6.31828 6.34891 7.13587 7.69583 8.47283 8.63594 8.75814 9.78516 9.80008 12.59740 12.75460 13.08690 14.19800 14.21690 16.17420 16.38980 17.67470 18.14130 20.87950 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: yolov4 - Device: CPU - Executor: Parallel Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 9754 EPYC 8534P EPYC 9654 EPYC 9684X Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 50 100 150 200 250 SE +/- 1.41, N = 3 SE +/- 2.49, N = 3 SE +/- 2.38, N = 3 SE +/- 0.15, N = 3 SE +/- 0.61, N = 3 SE +/- 0.91, N = 3 SE +/- 0.52, N = 3 SE +/- 0.53, N = 3 SE +/- 0.20, N = 3 SE +/- 0.01, N = 3 SE +/- 0.20, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.74, N = 3 SE +/- 0.57, N = 3 SE +/- 0.46, N = 3 SE +/- 0.22, N = 3 SE +/- 0.01, N = 3 SE +/- 0.36, N = 3 SE +/- 0.05, N = 3 SE +/- 0.30, N = 3 219.17 217.93 179.99 158.27 157.51 140.14 129.94 118.02 115.79 114.17 102.19 102.04 79.38 78.40 76.42 70.44 70.34 61.83 61.01 56.58 55.12 47.90 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian Xeon 6766E 2P EPYC 8534PN Xeon Platinum 8380 EPYC 8534P Xeon 6780E 2P Xeon 6766E Xeon Max 9468 Xeon Max 9468 2P EPYC 9754 Xeon Platinum 8380 2P Xeon 6780E Xeon Platinum 8490H Xeon Max 9480 EPYC 9654 Xeon Max 9480 2P EPYC 9754 2P EPYC 9684X Xeon Platinum 8592+ EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 1.44, N = 4 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 1.15, N = 3 SE +/- 0.88, N = 3 118 120 121 123 126 145 150 150 151 153 155 158 158 160 164 164 165 171 178 179 182 194 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Max 9468 EPYC 9654 2P Xeon Max 9480 Xeon Platinum 8380 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P EPYC 8534PN Xeon 6766E 0.3443 0.6886 1.0329 1.3772 1.7215 0.308 0.345 0.467 0.482 0.540 0.544 0.552 0.597 0.614 0.620 0.674 0.716 0.729 0.740 0.778 0.932 1.041 1.226 1.417 1.420 1.507 1.530
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.43 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 90 180 270 360 450 Min: 203.35 / Avg: 486.24 / Max: 527.71 Min: 196.74 / Avg: 476 / Max: 507.38 Min: 160.72 / Avg: 389.84 / Max: 423.25 Min: 82.86 / Avg: 356.85 / Max: 403.74 Min: 66.05 / Avg: 331.54 / Max: 359.49 Min: 99.29 / Avg: 317.68 / Max: 360.97 Min: 59.18 / Avg: 297.92 / Max: 323.55 Min: 74.91 / Avg: 271.55 / Max: 302.98 Min: 75.67 / Avg: 257.27 / Max: 283.18 Min: 39.77 / Avg: 243.28 / Max: 272.18 Min: 59.26 / Avg: 220.76 / Max: 250.24 Min: 34.53 / Avg: 219.79 / Max: 241.79 Min: 53.3 / Avg: 195.01 / Max: 207.9 Min: 33.85 / Avg: 176.95 / Max: 194.06 Min: 98.17 / Avg: 172.89 / Max: 203.08 Min: 104.1 / Avg: 159.54 / Max: 190.88 Min: 29.47 / Avg: 153.63 / Max: 171.14 Min: 21.53 / Avg: 123.19 / Max: 140.7 Min: 43.47 / Avg: 109.4 / Max: 130.3 Min: 43.66 / Avg: 94.78 / Max: 111.52 Min: 17.9 / Avg: 86.65 / Max: 95.02 Min: 16.29 / Avg: 79.6 / Max: 84.69
GPAW GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Max 9480 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9754 EPYC 9684X EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.60, N = 3 SE +/- 0.24, N = 3 SE +/- 0.27, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.55, N = 3 SE +/- 0.10, N = 3 SE +/- 0.21, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.18, N = 3 SE +/- 0.29, N = 15 SE +/- 0.30, N = 15 76.18 66.71 63.80 54.38 48.49 48.45 47.78 43.91 43.05 42.87 41.56 38.05 34.87 33.12 30.00 27.15 25.84 24.13 1. (CC) gcc options: -shared -lxc -lblas -lmpi
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GPAW 23.6 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 65.21 / Avg: 641.29 / Max: 819.6 Min: 213.42 / Avg: 622.05 / Max: 746.91 Min: 203.73 / Avg: 621.08 / Max: 746.35 Min: 153.52 / Avg: 606.84 / Max: 749.04 Min: 80.11 / Avg: 568.78 / Max: 750.58 Min: 57.4 / Avg: 562.66 / Max: 711.92 Min: 43.78 / Avg: 513.29 / Max: 700.14 Min: 103.43 / Avg: 497.52 / Max: 576.52 Min: 34.27 / Avg: 353.01 / Max: 409.6 Min: 72.36 / Avg: 327.19 / Max: 373.7 Min: 75.93 / Avg: 324.94 / Max: 375.46 Min: 59.13 / Avg: 322.66 / Max: 373.01 Min: 24.08 / Avg: 314.73 / Max: 374.48 Min: 28.47 / Avg: 300.58 / Max: 350.83 Min: 23.61 / Avg: 293.6 / Max: 347.81 Min: 53.47 / Avg: 257.77 / Max: 289.43 Min: 18.71 / Avg: 154.54 / Max: 175.1 Min: 18.16 / Avg: 136.93 / Max: 153.06
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X EPYC 9754 Xeon Max 9480 2P Xeon 6766E EPYC 9654 2P Xeon Platinum 8490H 2P Xeon 6780E Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P 80 160 240 320 400 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 1.20, N = 3 SE +/- 1.67, N = 3 SE +/- 0.00, N = 3 SE +/- 1.67, N = 3 SE +/- 0.88, N = 3 SE +/- 3.00, N = 3 SE +/- 0.88, N = 3 SE +/- 0.67, N = 3 79 105 112 114 130 144 157 167 173 199 201 207 227 253 262 265 281 284 297 310 336 381 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H EPYC 9684X 2P Xeon Platinum 8592+ EPYC 9654 2P EPYC 9684X EPYC 9654 EPYC 9754 2P EPYC 9754 EPYC 8534P Xeon 6780E 2P EPYC 8534PN Xeon 6766E 2P Xeon 6780E Xeon 6766E 0.2781 0.5562 0.8343 1.1124 1.3905 0.285 0.301 0.310 0.343 0.345 0.405 0.419 0.453 0.476 0.492 0.512 0.544 0.589 0.674 0.690 0.838 0.881 0.894 0.904 0.965 1.074 1.236
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.43 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9480 Xeon 6780E EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 206.23 / Avg: 662.12 / Max: 708.79 Min: 197.85 / Avg: 660.39 / Max: 706.79 Min: 148.52 / Avg: 632.93 / Max: 684.15 Min: 74.46 / Avg: 627.19 / Max: 683.79 Min: 65.27 / Avg: 603.16 / Max: 655.4 Min: 102.73 / Avg: 504.87 / Max: 544.93 Min: 59.05 / Avg: 481.76 / Max: 531.74 Min: 38.07 / Avg: 448.99 / Max: 494.64 Min: 107.76 / Avg: 425.97 / Max: 469.34 Min: 104.82 / Avg: 348.18 / Max: 384.37 Min: 34.61 / Avg: 341.04 / Max: 370.17 Min: 74.41 / Avg: 330.11 / Max: 353.01 Min: 62.29 / Avg: 329.54 / Max: 363.35 Min: 26.5 / Avg: 326.08 / Max: 362.61 Min: 74.28 / Avg: 321.22 / Max: 366.4 Min: 43.66 / Avg: 261.59 / Max: 286.06 Min: 28.8 / Avg: 256.57 / Max: 278.61 Min: 53.14 / Avg: 254.91 / Max: 285.61 Min: 22 / Avg: 247.13 / Max: 273.84 Min: 43.7 / Avg: 204.72 / Max: 219.13 Min: 17.43 / Avg: 127.19 / Max: 145.11 Min: 15.82 / Avg: 116.15 / Max: 127.18
Timed Linux Kernel Compilation This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: defconfig Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon 6766E Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P EPYC 9754 Xeon 6780E Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9684X Xeon 6780E 2P Xeon Max 9468 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 13 26 39 52 65 SE +/- 0.33, N = 3 SE +/- 0.54, N = 4 SE +/- 0.50, N = 4 SE +/- 0.59, N = 3 SE +/- 0.39, N = 6 SE +/- 0.57, N = 3 SE +/- 0.55, N = 3 SE +/- 0.42, N = 5 SE +/- 0.44, N = 3 SE +/- 0.37, N = 6 SE +/- 0.22, N = 14 SE +/- 0.39, N = 4 SE +/- 0.43, N = 3 SE +/- 0.46, N = 3 SE +/- 0.28, N = 8 SE +/- 0.40, N = 4 SE +/- 0.28, N = 7 SE +/- 0.31, N = 5 SE +/- 0.43, N = 3 SE +/- 0.33, N = 3 SE +/- 0.17, N = 13 SE +/- 0.23, N = 7 55.74 46.35 44.28 43.42 41.10 40.50 39.45 39.41 38.53 37.64 35.55 34.59 34.57 32.89 32.66 32.14 30.68 30.53 29.98 27.68 25.87 25.87
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Linux Kernel Compilation 6.8 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon 6780E 2P Xeon Platinum 8380 Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 189.61 / Avg: 492.26 / Max: 752.95 Min: 176.87 / Avg: 486.28 / Max: 754.8 Min: 150.36 / Avg: 425.97 / Max: 755.88 Min: 73.91 / Avg: 384.63 / Max: 756.99 Min: 62.86 / Avg: 375.56 / Max: 824.56 Min: 98.92 / Avg: 340.2 / Max: 582.62 Min: 52.83 / Avg: 317.6 / Max: 662.66 Min: 38.17 / Avg: 283.46 / Max: 659.24 Min: 73.73 / Avg: 265.23 / Max: 376.52 Min: 69.92 / Avg: 260.34 / Max: 376.76 Min: 60.49 / Avg: 234.11 / Max: 377.45 Min: 26.35 / Avg: 214.95 / Max: 377.53 Min: 32.62 / Avg: 210.93 / Max: 409.9 Min: 106.91 / Avg: 202.81 / Max: 628.9 Min: 48.64 / Avg: 197.71 / Max: 290.64 Min: 104.46 / Avg: 183.63 / Max: 516.23 Min: 27.91 / Avg: 175.53 / Max: 322.12 Min: 20.78 / Avg: 155.1 / Max: 328.08 Min: 21.97 / Avg: 123.43 / Max: 312.29 Min: 43.51 / Avg: 106.04 / Max: 250.64 Min: 16.1 / Avg: 97.22 / Max: 163.42 Min: 14.06 / Avg: 87.28 / Max: 138.54
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P Xeon 6766E Xeon 6780E EPYC 9684X Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon 6766E 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9684X 2P 90 180 270 360 450 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 1.45, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 2.60, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.20, N = 3 SE +/- 1.15, N = 3 SE +/- 1.53, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 123 160 163 172 181 215 216 228 264 269 270 299 300 301 304 342 350 368 374 389 403 408 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P EPYC 9684X Xeon 6780E 2P EPYC 9754 2P EPYC 9654 Xeon 6766E 2P Xeon 6780E EPYC 9754 EPYC 8534P Xeon 6766E EPYC 8534PN 0.3308 0.6616 0.9924 1.3232 1.654 0.410 0.435 0.466 0.484 0.484 0.549 0.568 0.614 0.656 0.696 0.742 0.815 0.935 0.999 1.014 1.067 1.086 1.211 1.342 1.348 1.391 1.470
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.43 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 198.68 / Avg: 656.05 / Max: 702.16 Min: 202.79 / Avg: 645.53 / Max: 683.28 Min: 74.15 / Avg: 608.66 / Max: 666.76 Min: 161.82 / Avg: 601.76 / Max: 650.47 Min: 64.84 / Avg: 549.68 / Max: 597.34 Min: 101.45 / Avg: 493.87 / Max: 534.32 Min: 59.43 / Avg: 451.41 / Max: 489.55 Min: 40.42 / Avg: 397.41 / Max: 433.85 Min: 105.4 / Avg: 389.46 / Max: 429.53 Min: 73.74 / Avg: 330.74 / Max: 355.56 Min: 75.94 / Avg: 329.68 / Max: 362.6 Min: 61.03 / Avg: 329.43 / Max: 359.83 Min: 28.79 / Avg: 327.64 / Max: 359.97 Min: 104.13 / Avg: 322.39 / Max: 344.94 Min: 33.82 / Avg: 320.71 / Max: 343.53 Min: 52.22 / Avg: 254.21 / Max: 282.55 Min: 26.64 / Avg: 247.53 / Max: 267.87 Min: 43.55 / Avg: 246.9 / Max: 265.73 Min: 20.16 / Avg: 226.47 / Max: 243.63 Min: 43.58 / Avg: 194.07 / Max: 209.22 Min: 18.4 / Avg: 127.55 / Max: 140 Min: 16.93 / Avg: 110.88 / Max: 122.16
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4 8 12 16 20 SE +/- 0.06373, N = 3 SE +/- 0.02665, N = 3 SE +/- 0.00867, N = 3 SE +/- 0.00657, N = 3 SE +/- 0.13507, N = 3 SE +/- 0.06993, N = 3 SE +/- 0.05412, N = 3 SE +/- 0.02898, N = 3 SE +/- 0.07856, N = 3 SE +/- 0.05765, N = 3 SE +/- 0.08338, N = 3 SE +/- 0.03015, N = 3 SE +/- 0.02155, N = 3 SE +/- 0.03854, N = 3 SE +/- 0.01290, N = 3 SE +/- 0.02822, N = 3 SE +/- 0.02062, N = 3 SE +/- 0.01694, N = 3 SE +/- 0.02534, N = 3 SE +/- 0.05586, N = 3 SE +/- 0.02988, N = 3 SE +/- 0.03569, N = 3 16.58280 15.27840 14.47610 13.17890 12.80930 11.50240 11.45800 10.55370 10.39770 10.30260 9.18524 9.08955 5.88628 5.74921 5.67175 5.59763 5.29287 5.26075 5.10914 4.86604 4.65431 4.26352 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ONNX Runtime 1.17 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 EPYC 9754 2P EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P EPYC 8534PN Xeon 6766E 60 120 180 240 300 Min: 102.14 / Avg: 339.94 / Max: 362.78 Min: 64.69 / Avg: 300.88 / Max: 323.81 Min: 58.04 / Avg: 272.09 / Max: 288.97 Min: 50.48 / Avg: 227.45 / Max: 243.02 Min: 40.67 / Avg: 218.35 / Max: 232.79 Min: 34.49 / Avg: 165.58 / Max: 176.42 Min: 84.94 / Avg: 161.97 / Max: 179.97 Min: 103.7 / Avg: 151.35 / Max: 165.49 Min: 29.43 / Avg: 145.22 / Max: 154.34 Min: 20.2 / Avg: 107.51 / Max: 113.85 Min: 43.53 / Avg: 86.18 / Max: 89.75 Min: 17.58 / Avg: 85.08 / Max: 90.86 Min: 16.21 / Avg: 80.29 / Max: 85.38 Min: 43.65 / Avg: 75.71 / Max: 78.31
Result
OpenBenchmarking.org Inferences Per Second, More Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 50 100 150 200 250 SE +/- 0.23, N = 3 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.83, N = 3 SE +/- 0.53, N = 3 SE +/- 0.41, N = 3 SE +/- 0.26, N = 3 SE +/- 0.72, N = 3 SE +/- 0.54, N = 3 SE +/- 0.99, N = 3 SE +/- 0.36, N = 3 SE +/- 0.62, N = 3 SE +/- 1.17, N = 3 SE +/- 0.40, N = 3 SE +/- 0.90, N = 3 SE +/- 0.74, N = 3 SE +/- 0.61, N = 3 SE +/- 0.98, N = 3 SE +/- 2.34, N = 3 SE +/- 1.38, N = 3 SE +/- 1.98, N = 3 60.29 65.43 69.07 75.87 78.07 86.92 87.26 94.74 96.17 97.05 108.87 110.00 169.85 173.91 176.29 178.62 188.89 190.06 195.71 205.53 214.81 234.54 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
Inference Time Cost (ms)
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.17 Model: super-resolution-10 - Device: CPU - Executor: Parallel Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 EPYC 8534PN EPYC 8534P EPYC 9684X EPYC 9654 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4 8 12 16 20 SE +/- 0.06373, N = 3 SE +/- 0.02665, N = 3 SE +/- 0.00867, N = 3 SE +/- 0.00657, N = 3 SE +/- 0.13507, N = 3 SE +/- 0.06993, N = 3 SE +/- 0.05412, N = 3 SE +/- 0.02898, N = 3 SE +/- 0.07856, N = 3 SE +/- 0.05765, N = 3 SE +/- 0.08338, N = 3 SE +/- 0.03015, N = 3 SE +/- 0.02155, N = 3 SE +/- 0.03854, N = 3 SE +/- 0.01290, N = 3 SE +/- 0.02822, N = 3 SE +/- 0.02062, N = 3 SE +/- 0.01694, N = 3 SE +/- 0.02534, N = 3 SE +/- 0.05586, N = 3 SE +/- 0.02988, N = 3 SE +/- 0.03569, N = 3 16.58280 15.27840 14.47610 13.17890 12.80930 11.50240 11.45800 10.55370 10.39770 10.30260 9.18524 9.08955 5.88628 5.74921 5.67175 5.59763 5.29287 5.26075 5.10914 4.86604 4.65431 4.26352 1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Swirl Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H Xeon 6766E Xeon Max 9468 2P EPYC 9654 Xeon 6780E 2P Xeon Platinum 8592+ EPYC 9754 EPYC 9684X EPYC 9654 2P Xeon Max 9480 2P Xeon 6780E EPYC 9754 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 150 300 450 600 750 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 4.41, N = 3 SE +/- 0.67, N = 3 SE +/- 2.33, N = 3 SE +/- 1.15, N = 3 SE +/- 4.91, N = 3 SE +/- 1.33, N = 3 SE +/- 0.33, N = 3 SE +/- 3.00, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 1.15, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 1.76, N = 3 SE +/- 0.58, N = 3 278 363 379 394 403 432 474 502 504 509 511 517 529 535 546 553 558 566 567 583 617 689 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.43 Operation: Swirl Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9468 EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Max 9480 EPYC 9654 2P Xeon Platinum 8490H EPYC 9754 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 0.7398 1.4796 2.2194 2.9592 3.699 0.851 0.943 0.964 1.097 1.137 1.193 1.298 1.307 1.341 1.445 1.617 1.710 1.724 1.872 1.923 2.036 2.290 2.779 2.944 3.093 3.279 3.288
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.43 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E 2P EPYC 9684X Xeon Platinum 8380 Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 110 220 330 440 550 Min: 191.82 / Avg: 598.34 / Max: 636.3 Min: 192.72 / Avg: 578.67 / Max: 624.15 Min: 159.26 / Avg: 542.66 / Max: 585.44 Min: 80.88 / Avg: 527.29 / Max: 574.8 Min: 62.97 / Avg: 449.12 / Max: 484.89 Min: 104.89 / Avg: 427.21 / Max: 467.28 Min: 56.5 / Avg: 382.8 / Max: 426.76 Min: 40.54 / Avg: 331.64 / Max: 362.33 Min: 72.86 / Avg: 330.14 / Max: 351.19 Min: 70.83 / Avg: 322.19 / Max: 348.63 Min: 59.04 / Avg: 310.53 / Max: 334.67 Min: 25.3 / Avg: 306.84 / Max: 336.43 Min: 107.08 / Avg: 276.13 / Max: 303.23 Min: 34.46 / Avg: 268.23 / Max: 288.18 Min: 52.31 / Avg: 253.3 / Max: 271.57 Min: 104.8 / Avg: 246.46 / Max: 265.1 Min: 30.38 / Avg: 223.17 / Max: 243.96 Min: 21.51 / Avg: 192.51 / Max: 206.12 Min: 43.48 / Avg: 192.24 / Max: 208.39 Min: 43.71 / Avg: 153.73 / Max: 166.75 Min: 18.54 / Avg: 122.54 / Max: 132.44 Min: 17.2 / Avg: 110.39 / Max: 118.71
RocksDB This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8380 2P Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P EPYC 9754 Xeon 6766E Xeon Platinum 8592+ 2P Xeon 6780E EPYC 9654 2P EPYC 9684X 2P Xeon 6766E 2P EPYC 9754 2P Xeon 6780E 2P 300M 600M 900M 1200M 1500M SE +/- 744772.41, N = 3 SE +/- 81327.78, N = 3 SE +/- 86315.43, N = 3 SE +/- 211259.57, N = 3 SE +/- 704022.38, N = 3 SE +/- 3338569.32, N = 3 SE +/- 206014.27, N = 3 SE +/- 1119855.47, N = 3 SE +/- 1120857.00, N = 3 SE +/- 610621.13, N = 3 SE +/- 785893.13, N = 3 SE +/- 326038.01, N = 3 SE +/- 1411218.60, N = 3 SE +/- 153963.59, N = 3 SE +/- 1336933.52, N = 3 SE +/- 82996.27, N = 3 SE +/- 2130676.22, N = 3 SE +/- 599126.55, N = 3 SE +/- 2927744.32, N = 3 SE +/- 4448269.22, N = 3 SE +/- 1154820.73, N = 3 SE +/- 1897433.73, N = 3 125584953 205346154 234469939 234992636 251234103 265366170 266186537 297517946 405533173 409272949 473755946 523310091 525049998 573235452 574749552 578392800 645309483 815145110 1031209151 1115720742 1135206564 1272907561 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
Op/s Per Watt
OpenBenchmarking.org Op/s Per Watt, More Is Better RocksDB 9.0 Test: Random Read Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 8534PN Xeon 6780E 2P Xeon 6780E Xeon 6766E 2P Xeon 6766E 500K 1000K 1500K 2000K 2500K 489869.48 490897.23 608125.97 663946.02 704496.50 709419.37 791368.94 802721.25 878232.54 904750.01 1341710.00 1362651.04 1477897.34 1523041.95 1780768.80 1907427.82 1957165.94 1972313.57 2038972.60 2069916.27 2359232.60 2436056.02
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RocksDB 9.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E Xeon Max 9468 EPYC 9754 EPYC 9654 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 61.31 / Avg: 768.58 / Max: 822.92 Min: 195.53 / Avg: 667.81 / Max: 755.48 Min: 186.94 / Avg: 666.86 / Max: 752.6 Min: 145.71 / Avg: 663.47 / Max: 754.3 Min: 63.13 / Avg: 658.59 / Max: 754.12 Min: 107.45 / Avg: 624.29 / Max: 712.89 Min: 40.42 / Avg: 595.15 / Max: 641.39 Min: 53.06 / Avg: 551.56 / Max: 593.87 Min: 100.64 / Avg: 512.86 / Max: 581.28 Min: 104.97 / Avg: 472.92 / Max: 541.33 Min: 33.04 / Avg: 384.04 / Max: 411.06 Min: 77.85 / Avg: 332.82 / Max: 365.47 Min: 54.21 / Avg: 330.58 / Max: 378.42 Min: 25.38 / Avg: 328.84 / Max: 377.98 Min: 43.52 / Avg: 311.76 / Max: 357.69 Min: 73.12 / Avg: 309.28 / Max: 327.48 Min: 21.45 / Avg: 292.89 / Max: 315.65 Min: 24.72 / Avg: 268.72 / Max: 291.05 Min: 53.91 / Avg: 255.83 / Max: 291.63 Min: 43.66 / Avg: 235.93 / Max: 270.68 Min: 19.07 / Avg: 149.48 / Max: 159.86 Min: 18.15 / Avg: 119.15 / Max: 127.37
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 70 140 210 280 350 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.11, N = 3 SE +/- 0.31, N = 3 SE +/- 0.96, N = 4 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.31, N = 3 SE +/- 0.75, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 1.48, N = 3 SE +/- 0.93, N = 3 SE +/- 0.99, N = 3 SE +/- 0.93, N = 3 SE +/- 1.71, N = 3 SE +/- 1.93, N = 15 SE +/- 0.01, N = 3 SE +/- 3.85, N = 3 SE +/- 0.08, N = 3 SE +/- 2.28, N = 3 39.35 43.73 49.20 70.21 78.11 78.24 86.88 86.97 97.08 97.98 107.72 108.12 127.85 133.99 140.83 171.77 187.68 191.82 232.75 288.54 291.28 309.22 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Billion Interactions/s Per Watt
OpenBenchmarking.org Billion Interactions/s Per Watt, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon Platinum 8380 Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6766E 2P Xeon 6766E Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9754 0.1906 0.3812 0.5718 0.7624 0.953 0.191 0.195 0.196 0.196 0.211 0.215 0.216 0.225 0.244 0.245 0.248 0.275 0.319 0.334 0.532 0.551 0.588 0.605 0.669 0.746 0.789 0.847
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better miniBUDE 20210901 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9468 EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 203.67 / Avg: 621.91 / Max: 746.15 Min: 193.86 / Avg: 605.49 / Max: 719.24 Min: 63.99 / Avg: 600.52 / Max: 754.84 Min: 68.45 / Avg: 581.3 / Max: 795.09 Min: 173.4 / Avg: 578.13 / Max: 755.42 Min: 59.15 / Avg: 495.6 / Max: 654.49 Min: 104.71 / Avg: 494.9 / Max: 576.68 Min: 107.71 / Avg: 444.54 / Max: 472.65 Min: 42.31 / Avg: 431.39 / Max: 620.63 Min: 105.16 / Avg: 361.96 / Max: 383.12 Min: 33.63 / Avg: 340.93 / Max: 409.44 Min: 23.61 / Avg: 323.61 / Max: 376.85 Min: 62.05 / Avg: 316.19 / Max: 372.81 Min: 75.23 / Avg: 314.81 / Max: 352.37 Min: 72.43 / Avg: 286.83 / Max: 306.63 Min: 28.02 / Avg: 283.82 / Max: 328.33 Min: 20.19 / Avg: 274.94 / Max: 327 Min: 52.78 / Avg: 257.94 / Max: 287.95 Min: 43.56 / Avg: 223.09 / Max: 250.29 Min: 43.66 / Avg: 174.56 / Max: 194.55 Min: 18.74 / Avg: 144.45 / Max: 156.43 Min: 16.52 / Avg: 124.23 / Max: 135.64
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 1700 3400 5100 6800 8500 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 2.69, N = 3 SE +/- 7.81, N = 3 SE +/- 23.93, N = 4 SE +/- 0.82, N = 3 SE +/- 1.96, N = 3 SE +/- 7.77, N = 3 SE +/- 18.66, N = 3 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 SE +/- 0.70, N = 3 SE +/- 36.96, N = 3 SE +/- 23.14, N = 3 SE +/- 24.63, N = 3 SE +/- 23.15, N = 3 SE +/- 42.85, N = 3 SE +/- 48.20, N = 15 SE +/- 0.20, N = 3 SE +/- 96.25, N = 3 SE +/- 2.03, N = 3 SE +/- 57.10, N = 3 983.71 1093.21 1230.08 1755.33 1952.61 1955.88 2172.10 2174.19 2426.88 2449.45 2692.87 2703.09 3196.12 3349.76 3520.71 4294.28 4692.11 4795.46 5818.74 7213.43 7281.96 7730.47 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Coremark This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon 6766E Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6780E Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X EPYC 9754 Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 2M 4M 6M 8M 10M SE +/- 927.64, N = 3 SE +/- 1747.99, N = 3 SE +/- 30163.42, N = 15 SE +/- 5202.86, N = 3 SE +/- 11678.22, N = 3 SE +/- 9256.47, N = 3 SE +/- 1374.66, N = 3 SE +/- 4635.95, N = 3 SE +/- 10294.77, N = 3 SE +/- 7219.73, N = 3 SE +/- 20649.43, N = 3 SE +/- 40214.40, N = 15 SE +/- 12743.41, N = 3 SE +/- 10132.66, N = 3 SE +/- 54326.71, N = 3 SE +/- 4775.53, N = 3 SE +/- 9700.21, N = 3 SE +/- 9906.84, N = 3 SE +/- 7619.10, N = 3 SE +/- 2306.54, N = 3 SE +/- 54771.53, N = 3 SE +/- 76743.24, N = 3 1218453.34 1614763.70 1839444.40 1855135.33 2069432.53 2194630.60 2274636.13 2369998.36 2915609.75 2993136.60 3279262.53 3340274.03 3902076.24 3926265.28 4152864.88 4525288.00 4966250.78 6575205.54 7302247.14 7975907.45 8171241.71 8448083.73 1. (CC) gcc options: -O2 -lrt" -lrt
Iterations/Sec Per Watt
OpenBenchmarking.org Iterations/Sec Per Watt, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9654 EPYC 9684X 2P EPYC 9654 2P Xeon 6780E EPYC 8534P EPYC 9754 2P EPYC 9754 EPYC 8534PN Xeon 6766E Xeon 6780E 2P Xeon 6766E 2P 5K 10K 15K 20K 25K 4373.42 5016.56 5763.20 5880.62 6163.40 6571.62 7118.47 7477.77 7555.56 8414.46 12144.31 13254.14 13681.18 14883.36 15612.90 15712.09 16699.88 16764.47 16836.69 18400.49 18406.92 21799.95
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Coremark 1.0 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Max 9468 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9654 Xeon Platinum 8490H Xeon Max 9480 EPYC 9754 Xeon Max 9468 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 68.03 / Avg: 617.5 / Max: 820.53 Min: 73.47 / Avg: 590.2 / Max: 753.92 Min: 206.68 / Avg: 557.64 / Max: 672.47 Min: 163.01 / Avg: 548.16 / Max: 709.21 Min: 57.24 / Avg: 535.89 / Max: 711.09 Min: 188.96 / Avg: 519.35 / Max: 613.18 Min: 42.53 / Avg: 489.3 / Max: 675.15 Min: 100.85 / Avg: 420.6 / Max: 582.07 Min: 106.84 / Avg: 396.71 / Max: 563.32 Min: 32.2 / Avg: 341.96 / Max: 411.86 Min: 34.34 / Avg: 313.68 / Max: 378.24 Min: 104.32 / Avg: 301.62 / Max: 446.07 Min: 26.88 / Avg: 296.23 / Max: 351.89 Min: 54.25 / Avg: 293.49 / Max: 341.26 Min: 77.43 / Avg: 282.3 / Max: 314.07 Min: 21.14 / Avg: 269.93 / Max: 353.42 Min: 76.41 / Avg: 261.99 / Max: 288.93 Min: 50.82 / Avg: 242.89 / Max: 290.97 Min: 21.83 / Avg: 213.94 / Max: 282.7 Min: 43.57 / Avg: 158.45 / Max: 217.13 Min: 16.44 / Avg: 144.77 / Max: 164.64 Min: 14.91 / Avg: 122.91 / Max: 138.78
srsRAN Project srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Total Xeon Max 9480 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Platinum 8380 2P EPYC 8534P EPYC 8534PN Xeon Max 9468 EPYC 9654 2P Xeon Platinum 8490H EPYC 9754 EPYC 9684X 2P Xeon Platinum 8592+ Xeon 6766E EPYC 9654 EPYC 9684X Xeon 6780E EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P 7K 14K 21K 28K 35K SE +/- 490.54, N = 15 SE +/- 44.42, N = 3 SE +/- 281.72, N = 15 SE +/- 308.01, N = 15 SE +/- 207.19, N = 5 SE +/- 58.21, N = 3 SE +/- 938.95, N = 15 SE +/- 526.01, N = 15 SE +/- 236.27, N = 4 SE +/- 237.63, N = 3 SE +/- 343.97, N = 3 SE +/- 298.34, N = 15 SE +/- 150.02, N = 4 SE +/- 357.13, N = 12 SE +/- 348.28, N = 4 SE +/- 134.28, N = 4 SE +/- 2115.57, N = 15 SE +/- 312.17, N = 3 SE +/- 175.78, N = 4 SE +/- 356.81, N = 15 SE +/- 319.61, N = 3 SE +/- 242.64, N = 3 11866.7 13537.7 15081.0 18943.6 19375.9 19485.8 21286.6 22931.8 24688.5 25194.6 25977.4 26378.1 27281.9 27695.2 29384.9 29804.4 29877.1 30108.7 30236.0 30547.6 31677.2 33010.5 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
Mbps Per Watt
OpenBenchmarking.org Mbps Per Watt, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Total Xeon Max 9480 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9684X 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Platinum 8380 Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X EPYC 9754 Xeon Platinum 8592+ EPYC 9654 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 40 80 120 160 200 19.21 40.31 40.98 41.07 49.98 51.12 52.16 56.88 58.04 58.87 64.73 74.22 75.68 87.21 91.42 96.52 98.83 100.26 121.16 133.01 141.87 165.23
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN Project 23.10.1-20240325 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 EPYC 9654 Xeon Platinum 8592+ EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 65.52 / Avg: 632.5 / Max: 723.62 Min: 189.97 / Avg: 617.8 / Max: 721.97 Min: 195.95 / Avg: 604.92 / Max: 745.23 Min: 148.45 / Avg: 589.02 / Max: 721.35 Min: 55.25 / Avg: 559.64 / Max: 633.66 Min: 68.27 / Avg: 537.03 / Max: 710 Min: 41.23 / Avg: 514.74 / Max: 612.62 Min: 104.56 / Avg: 509.97 / Max: 630.46 Min: 100.98 / Avg: 470 / Max: 560.27 Min: 103.72 / Avg: 426.81 / Max: 506.19 Min: 32.26 / Avg: 321.41 / Max: 408.75 Min: 74.87 / Avg: 289.12 / Max: 373.87 Min: 60.24 / Avg: 283.1 / Max: 369.61 Min: 74.5 / Avg: 281.29 / Max: 379.76 Min: 28.12 / Avg: 276.24 / Max: 341.73 Min: 25.9 / Avg: 266.9 / Max: 379.06 Min: 21.57 / Avg: 261.04 / Max: 306.84 Min: 43.52 / Avg: 245.99 / Max: 312.37 Min: 51.25 / Avg: 229.96 / Max: 288.72 Min: 43.55 / Avg: 205.11 / Max: 263.97 Min: 17.85 / Avg: 136.58 / Max: 166.81 Min: 16.71 / Avg: 117.93 / Max: 142.26
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Classroom - Compute: CPU-Only Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 30 60 90 120 150 SE +/- 0.38, N = 3 SE +/- 0.20, N = 3 SE +/- 0.40, N = 3 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.67, N = 3 SE +/- 0.38, N = 3 SE +/- 0.25, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 124.63 86.67 76.87 75.26 68.61 67.67 63.61 62.54 52.47 48.07 44.71 40.38 40.26 35.91 35.66 33.61 31.65 27.41 24.61 21.12 18.67 16.82
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 62.19 / Avg: 671.43 / Max: 821.27 Min: 203.45 / Avg: 652.82 / Max: 753.03 Min: 210.08 / Avg: 648.81 / Max: 752.1 Min: 168.91 / Avg: 636.73 / Max: 754.11 Min: 80.44 / Avg: 621.31 / Max: 724.97 Min: 59.51 / Avg: 570.92 / Max: 684.42 Min: 41.08 / Avg: 534.08 / Max: 683.35 Min: 101.27 / Avg: 509.54 / Max: 580.93 Min: 108.2 / Avg: 509.44 / Max: 619.2 Min: 105.51 / Avg: 410.34 / Max: 487.07 Min: 32.63 / Avg: 365.01 / Max: 410.63 Min: 77.77 / Avg: 335.02 / Max: 376.96 Min: 77.25 / Avg: 334.43 / Max: 376.17 Min: 60.22 / Avg: 330.03 / Max: 377.07 Min: 24.56 / Avg: 326.8 / Max: 368.75 Min: 31.02 / Avg: 300.94 / Max: 333.76 Min: 21.92 / Avg: 295.34 / Max: 341.6 Min: 43.65 / Avg: 273.8 / Max: 305.54 Min: 52.8 / Avg: 262.14 / Max: 290.33 Min: 43.66 / Avg: 214.19 / Max: 233.43 Min: 16.44 / Avg: 159.04 / Max: 169.83 Min: 17.21 / Avg: 130.93 / Max: 139.49
Aircrack-ng Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.7 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 8534P Xeon Platinum 8380 2P EPYC 9754 EPYC 9654 EPYC 9684X 40K 80K 120K 160K 200K SE +/- 1197.41, N = 15 SE +/- 773.70, N = 3 SE +/- 1131.21, N = 15 SE +/- 1027.07, N = 15 SE +/- 728.55, N = 3 SE +/- 1379.58, N = 4 SE +/- 888.98, N = 3 SE +/- 36.42, N = 3 SE +/- 122.31, N = 3 SE +/- 319.60, N = 3 SE +/- 1953.08, N = 3 SE +/- 840.59, N = 3 SE +/- 338.71, N = 3 SE +/- 1234.47, N = 15 SE +/- 714.86, N = 3 SE +/- 207.11, N = 3 SE +/- 1622.56, N = 3 53914.93 64181.29 65663.82 83665.76 101665.47 114715.79 116716.40 117588.99 134048.96 141831.78 147469.33 153584.20 153818.03 159709.75 177989.89 186675.43 206619.29 1. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread
k/s Per Watt
OpenBenchmarking.org k/s Per Watt, More Is Better Aircrack-ng 1.7 Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon 6780E EPYC 9654 Xeon 6766E EPYC 9754 EPYC 8534P EPYC 8534PN 300 600 900 1200 1500 97.52 112.13 128.68 142.86 333.67 377.96 424.59 433.27 479.36 507.73 585.84 609.64 702.97 725.96 763.99 1057.15 1173.57
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Aircrack-ng 1.7 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 195.2 / Avg: 585.65 / Max: 659.01 Min: 193.67 / Avg: 585.6 / Max: 670.08 Min: 160.46 / Avg: 552.88 / Max: 630.35 Min: 78.32 / Avg: 498.75 / Max: 586.29 Min: 97.38 / Avg: 478.65 / Max: 580.33 Min: 34.08 / Avg: 352.69 / Max: 410.53 Min: 73.18 / Avg: 311.12 / Max: 377.22 Min: 77.17 / Avg: 309.39 / Max: 375.45 Min: 55.34 / Avg: 307.64 / Max: 375.71 Min: 25.19 / Avg: 302.49 / Max: 376.59 Min: 29.99 / Avg: 265.55 / Max: 307.89 Min: 53.68 / Avg: 239.45 / Max: 291.67 Min: 10.09 / Avg: 232.97 / Max: 273.01 Min: 43.53 / Avg: 191.45 / Max: 221.34 Min: 43.62 / Avg: 158.02 / Max: 182.75 Min: 17.23 / Avg: 145.5 / Max: 168.72 Min: 15.46 / Avg: 120.86 / Max: 145.49
EPYC 9684X 2P: The test run did not produce a result.
EPYC 9654 2P: The test run did not produce a result.
EPYC 9754 2P: The test run did not produce a result.
Xeon 6766E 2P: The test run did not produce a result.
Xeon 6780E 2P: The test run did not produce a result.
WebP Image Encode This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E EPYC 9754 EPYC 9754 2P EPYC 8534P EPYC 8534PN Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X 2P EPYC 9684X EPYC 9654 EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 0.135 0.27 0.405 0.54 0.675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.35 0.35 0.38 0.39 0.48 0.48 0.48 0.48 0.49 0.50 0.51 0.52 0.54 0.54 0.55 0.55 0.56 0.57 0.57 0.57 0.59 0.60 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
MP/s Per Watt
OpenBenchmarking.org MP/s Per Watt, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 0.002 0.004 0.006 0.008 0.01 0.001 0.001 0.002 0.002 0.002 0.003 0.003 0.003 0.003 0.003 0.003 0.003 0.004 0.005 0.005 0.005 0.006 0.006 0.007 0.008 0.009 0.009
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better WebP Image Encode 1.2.4 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9754 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 80 160 240 320 400 Min: 205.48 / Avg: 407.7 / Max: 432.16 Min: 205.98 / Avg: 397.44 / Max: 422.1 Min: 150.62 / Avg: 324.76 / Max: 344.8 Min: 79.69 / Avg: 274 / Max: 299.87 Min: 61.65 / Avg: 249.88 / Max: 268.66 Min: 57.93 / Avg: 225.88 / Max: 245.29 Min: 97.01 / Avg: 192.53 / Max: 212.04 Min: 83.4 / Avg: 190.72 / Max: 207.25 Min: 39.58 / Avg: 186.91 / Max: 199.67 Min: 80.95 / Avg: 184.91 / Max: 202.94 Min: 60.77 / Avg: 148.44 / Max: 161.11 Min: 34.5 / Avg: 128.71 / Max: 144.36 Min: 105.36 / Avg: 121.62 / Max: 143.58 Min: 104.05 / Avg: 111.28 / Max: 129.11 Min: 30.35 / Avg: 109.81 / Max: 119.47 Min: 50.06 / Avg: 101.4 / Max: 108.28 Min: 27.22 / Avg: 96.75 / Max: 105.57 Min: 20.24 / Avg: 77.06 / Max: 83.97 Min: 15.79 / Avg: 53.42 / Max: 58.48 Min: 15.76 / Avg: 52.31 / Max: 56.63 Min: 43.35 / Avg: 51.07 / Max: 67.23 Min: 43.65 / Avg: 50.5 / Max: 67.21
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 2 Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN EPYC 9754 2P EPYC 8534P Xeon Max 9468 EPYC 9754 Xeon Max 9480 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.41, N = 3 SE +/- 0.04, N = 3 SE +/- 0.25, N = 3 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.31, N = 3 SE +/- 0.22, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.43, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 79.20 76.47 71.97 69.34 52.23 47.51 42.61 41.92 41.66 41.13 40.35 39.88 38.65 38.14 37.75 37.31 35.40 35.32 34.79 34.15 34.04 33.65 1. (CXX) g++ options: -O3 -fPIC -lm
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 1.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 130 260 390 520 650 Min: 207.34 / Avg: 461.85 / Max: 707.44 Min: 195.24 / Avg: 458.52 / Max: 733.31 Min: 149.52 / Avg: 390.93 / Max: 714.36 Min: 77.42 / Avg: 350.42 / Max: 724.52 Min: 63.92 / Avg: 296.47 / Max: 540.97 Min: 57.84 / Avg: 267.46 / Max: 494.12 Min: 97.78 / Avg: 258.88 / Max: 544.31 Min: 80.19 / Avg: 235.72 / Max: 375.98 Min: 71.37 / Avg: 235.53 / Max: 369.9 Min: 39.83 / Avg: 217.6 / Max: 369.6 Min: 58.97 / Avg: 196.29 / Max: 374.92 Min: 34.19 / Avg: 161.32 / Max: 375.73 Min: 32.31 / Avg: 157.68 / Max: 383.9 Min: 50.37 / Avg: 150.68 / Max: 290.84 Min: 28.7 / Avg: 137.31 / Max: 316.42 Min: 105.72 / Avg: 131.77 / Max: 264.67 Min: 103.94 / Avg: 125.3 / Max: 229.12 Min: 20.27 / Avg: 107.23 / Max: 247.8 Min: 16.88 / Avg: 75.22 / Max: 155.11 Min: 14.11 / Avg: 69.45 / Max: 130.44 Min: 43.42 / Avg: 65.19 / Max: 183.13 Min: 43.58 / Avg: 59.56 / Max: 150.24
srsRAN Project srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Total Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 8534PN Xeon 6766E 2P Xeon Platinum 8592+ EPYC 8534P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 2K 4K 6K 8K 10K SE +/- 0.07, N = 3 SE +/- 8.17, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 18.30, N = 3 SE +/- 18.43, N = 3 SE +/- 19.02, N = 13 SE +/- 36.60, N = 3 SE +/- 18.09, N = 3 SE +/- 25.25, N = 3 SE +/- 0.17, N = 3 SE +/- 14.40, N = 3 SE +/- 26.47, N = 3 SE +/- 0.15, N = 3 SE +/- 47.68, N = 6 SE +/- 0.20, N = 3 SE +/- 0.12, N = 3 SE +/- 55.17, N = 3 SE +/- 63.64, N = 5 SE +/- 74.95, N = 4 SE +/- 2.29, N = 3 SE +/- 76.45, N = 3 1770.0 1953.1 2118.6 2170.7 2514.0 2616.9 2818.5 3067.0 3088.7 3193.0 3288.4 3414.2 3787.0 4386.6 4853.6 5239.6 5493.4 5656.9 5973.8 6835.7 6999.7 8396.7 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
Mbps Per Watt
OpenBenchmarking.org Mbps Per Watt, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Total Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9480 Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8490H EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8592+ Xeon 6780E Xeon 6766E EPYC 9754 2P EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 6 12 18 24 30 6.643 7.535 7.552 7.971 7.989 8.808 8.854 9.756 9.956 10.299 10.725 10.976 12.702 13.247 14.180 15.533 16.197 18.052 20.666 23.406 24.996 26.846
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN Project 23.10.1-20240325 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 Xeon Platinum 8490H EPYC 9654 Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 140 280 420 560 700 Min: 67.45 / Avg: 652.65 / Max: 788.02 Min: 196.65 / Avg: 580.82 / Max: 660.22 Min: 206.4 / Avg: 570.06 / Max: 634.71 Min: 156.44 / Avg: 551.02 / Max: 636.6 Min: 60.3 / Avg: 538.17 / Max: 621.29 Min: 37.54 / Avg: 518.41 / Max: 623.41 Min: 82.2 / Avg: 500.5 / Max: 584.22 Min: 104.84 / Avg: 436.41 / Max: 487.66 Min: 108.83 / Avg: 349.96 / Max: 395.95 Min: 31.36 / Avg: 313.37 / Max: 378.12 Min: 106.26 / Avg: 308.05 / Max: 384.76 Min: 73.76 / Avg: 283.68 / Max: 318.07 Min: 74.32 / Avg: 272.33 / Max: 304.79 Min: 21.5 / Avg: 255.23 / Max: 297.3 Min: 62.91 / Avg: 254.1 / Max: 294.51 Min: 27.31 / Avg: 253.54 / Max: 296.82 Min: 25.89 / Avg: 233.17 / Max: 276.77 Min: 53.15 / Avg: 221.57 / Max: 249.62 Min: 43.57 / Avg: 149.41 / Max: 169.56 Min: 18.17 / Avg: 127.74 / Max: 148.29 Min: 43.71 / Avg: 125.74 / Max: 140.92 Min: 14.51 / Avg: 104.99 / Max: 125.17
Llamafile Mozilla's Llamafile allows distributing and running large language models (LLMs) as a single file. Llamafile aims to make open-source LLMs more accessible to developers and users. Llamafile supports a variety of models, CPUs and GPUs, and other options. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Tokens Per Second, More Is Better Llamafile 0.7 Test: llava-v1.5-7b-q4 - Acceleration: CPU Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon 6766E Xeon 6780E Xeon Platinum 8490H 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9754 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P EPYC 9684X EPYC 9654 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 1.08, N = 12 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.30, N = 15 SE +/- 0.09, N = 15 SE +/- 0.08, N = 4 SE +/- 0.10, N = 15 SE +/- 0.02, N = 4 SE +/- 0.07, N = 4 SE +/- 0.17, N = 4 SE +/- 0.11, N = 3 SE +/- 0.05, N = 4 SE +/- 0.07, N = 4 SE +/- 0.15, N = 4 SE +/- 0.11, N = 4 SE +/- 0.10, N = 5 SE +/- 0.02, N = 5 2.83 2.99 7.26 7.49 7.67 7.77 8.13 8.56 9.60 10.44 10.94 12.29 14.29 14.47 16.61 19.11 20.64 20.65 20.95 21.00 25.38 25.75
Tokens Per Second Per Watt
OpenBenchmarking.org Tokens Per Second Per Watt, More Is Better Llamafile 0.7 Test: llava-v1.5-7b-q4 - Acceleration: CPU Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9754 2P EPYC 9654 2P Xeon 6780E Xeon 6766E Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9684X EPYC 9754 EPYC 9654 EPYC 8534P EPYC 8534PN 0.0502 0.1004 0.1506 0.2008 0.251 0.007 0.007 0.013 0.014 0.015 0.019 0.027 0.028 0.030 0.031 0.032 0.037 0.056 0.061 0.068 0.080 0.089 0.110 0.126 0.138 0.202 0.223
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Llamafile 0.7 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon 6766E 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 191.45 / Avg: 566.01 / Max: 704.67 Min: 205.99 / Avg: 559.87 / Max: 716.53 Min: 152.91 / Avg: 537.58 / Max: 745.57 Min: 81.53 / Avg: 512.88 / Max: 707.9 Min: 62.86 / Avg: 462.55 / Max: 790.45 Min: 106.56 / Avg: 429.62 / Max: 646.38 Min: 95.32 / Avg: 409.62 / Max: 565.75 Min: 57.8 / Avg: 388.15 / Max: 621.67 Min: 103.86 / Avg: 385.26 / Max: 509.52 Min: 40.53 / Avg: 343.52 / Max: 619.26 Min: 72.54 / Avg: 288.22 / Max: 376.39 Min: 72.53 / Avg: 283.07 / Max: 370.83 Min: 56.03 / Avg: 262.55 / Max: 376.09 Min: 34.18 / Avg: 244.07 / Max: 354.9 Min: 32.28 / Avg: 231.13 / Max: 402.04 Min: 51.28 / Avg: 215.58 / Max: 284.94 Min: 28.61 / Avg: 186.7 / Max: 318.2 Min: 43.49 / Avg: 172.82 / Max: 332.78 Min: 20.15 / Avg: 163.65 / Max: 315.47 Min: 43.72 / Avg: 139.67 / Max: 256.22 Min: 17.78 / Avg: 104.22 / Max: 157.47 Min: 14.6 / Avg: 92.71 / Max: 131.37
LULESH LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Max 9468 EPYC 9754 Xeon Max 9480 Xeon 6766E EPYC 9654 Xeon 6780E EPYC 9684X Xeon Platinum 8592+ Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 15K 30K 45K 60K 75K SE +/- 373.78, N = 12 SE +/- 372.63, N = 12 SE +/- 53.94, N = 5 SE +/- 188.07, N = 8 SE +/- 182.38, N = 15 SE +/- 211.12, N = 6 SE +/- 244.17, N = 3 SE +/- 217.67, N = 6 SE +/- 254.25, N = 6 SE +/- 372.12, N = 3 SE +/- 314.85, N = 4 SE +/- 194.65, N = 15 SE +/- 437.51, N = 4 SE +/- 55.60, N = 3 SE +/- 272.44, N = 4 SE +/- 91.45, N = 3 SE +/- 427.75, N = 3 SE +/- 349.39, N = 15 SE +/- 206.20, N = 5 SE +/- 207.54, N = 5 SE +/- 675.87, N = 3 SE +/- 359.29, N = 3 16855.89 16949.59 17348.43 21389.82 23072.30 23848.54 24218.83 25831.84 26024.60 26082.71 26864.11 27287.26 38433.97 42946.26 43724.06 44136.53 46126.08 48760.82 52102.67 53269.47 54678.49 70826.73 1. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
z/s Per Watt
OpenBenchmarking.org z/s Per Watt, More Is Better LULESH 2.0.3 Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X EPYC 9754 Xeon 6780E 2P EPYC 9654 Xeon Platinum 8592+ 2P Xeon 6766E 2P EPYC 8534P Xeon 6780E Xeon Platinum 8592+ EPYC 8534PN Xeon 6766E 40 80 120 160 200 50.91 84.83 88.38 97.72 100.20 100.41 103.89 105.60 122.54 122.60 123.49 130.21 134.50 134.87 143.77 143.95 144.08 149.38 153.17 155.84 162.52 167.31
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LULESH 2.0.3 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 Xeon Platinum 8592+ Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 198.01 / Avg: 533.2 / Max: 722.21 Min: 194.87 / Avg: 531.65 / Max: 728.1 Min: 165.01 / Avg: 494.73 / Max: 717.17 Min: 69.2 / Avg: 492.01 / Max: 729.97 Min: 68.15 / Avg: 446.2 / Max: 721.49 Min: 100.66 / Avg: 420.13 / Max: 555.76 Min: 55.4 / Avg: 394.86 / Max: 598.6 Min: 41.83 / Avg: 376.23 / Max: 647.63 Min: 107.92 / Avg: 327.25 / Max: 513.74 Min: 105.26 / Avg: 298.06 / Max: 439.37 Min: 73.96 / Avg: 248.64 / Max: 365.61 Min: 22.84 / Avg: 246.63 / Max: 365.09 Min: 73.71 / Avg: 237.51 / Max: 333.91 Min: 50.79 / Avg: 218.49 / Max: 329.56 Min: 31.6 / Avg: 209.57 / Max: 345.61 Min: 53.1 / Avg: 204.51 / Max: 281.83 Min: 27.74 / Avg: 181.42 / Max: 285.77 Min: 21.79 / Avg: 180.07 / Max: 311.6 Min: 43.51 / Avg: 175.39 / Max: 270.27 Min: 43.63 / Avg: 155.54 / Max: 229.09 Min: 19.22 / Avg: 113.47 / Max: 157.81 Min: 17.36 / Avg: 103.72 / Max: 135.92
7-Zip Compression This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 8534PN Xeon Platinum 8380 2P EPYC 8534P Xeon Max 9468 2P Xeon 6766E Xeon 6780E Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X Xeon 6766E 2P EPYC 9754 Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 300K 600K 900K 1200K 1500K SE +/- 309.57, N = 3 SE +/- 916.22, N = 3 SE +/- 374.59, N = 3 SE +/- 61.74, N = 3 SE +/- 119.21, N = 3 SE +/- 81.21, N = 3 SE +/- 559.82, N = 3 SE +/- 120.28, N = 3 SE +/- 2598.93, N = 3 SE +/- 343.82, N = 3 SE +/- 258.19, N = 3 SE +/- 6276.88, N = 3 SE +/- 185.14, N = 3 SE +/- 28320.74, N = 3 SE +/- 111.53, N = 3 SE +/- 1085.99, N = 3 SE +/- 2333.15, N = 3 SE +/- 291.68, N = 3 SE +/- 903.01, N = 3 SE +/- 15794.26, N = 3 SE +/- 38431.24, N = 3 SE +/- 14188.09, N = 3 188345 207738 243347 287862 338146 338355 366534 367989 401707 421063 463768 469131 557054 573410 642626 716065 767313 780871 846335 1033277 1116465 1340226 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
MIPS Per Watt
OpenBenchmarking.org MIPS Per Watt, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon 6780E 2P EPYC 9684X 2P Xeon 6766E 2P EPYC 9654 2P Xeon 6780E Xeon 6766E EPYC 9684X EPYC 9654 EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 700 1400 2100 2800 3500 637.01 663.36 746.10 773.01 775.27 777.16 908.47 934.34 986.76 1119.86 1861.55 1928.99 1954.73 2011.14 2052.50 2265.09 2281.23 2434.84 2768.54 2828.90 2852.08 3140.68
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better 7-Zip Compression 22.01 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 EPYC 9684X Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 205.27 / Avg: 630.61 / Max: 754.38 Min: 198.7 / Avg: 628.77 / Max: 756.25 Min: 170.4 / Avg: 613.18 / Max: 756.05 Min: 77.81 / Avg: 581.11 / Max: 756.45 Min: 68.73 / Avg: 578.78 / Max: 823.64 Min: 60.89 / Avg: 513.78 / Max: 716.51 Min: 101.47 / Avg: 471.63 / Max: 582.19 Min: 42.06 / Avg: 469.91 / Max: 704.89 Min: 108.05 / Avg: 454.64 / Max: 642.86 Min: 105.13 / Avg: 392.54 / Max: 530.11 Min: 74.78 / Avg: 314.81 / Max: 375.55 Min: 33.61 / Avg: 313.89 / Max: 411.35 Min: 70.41 / Avg: 313.16 / Max: 376.07 Min: 60.14 / Avg: 308.09 / Max: 375.76 Min: 34.7 / Avg: 301.96 / Max: 375.99 Min: 27.34 / Avg: 263.93 / Max: 352.58 Min: 22.44 / Avg: 248.63 / Max: 349.11 Min: 52.56 / Avg: 242.94 / Max: 291.38 Min: 43.58 / Avg: 225.95 / Max: 302.95 Min: 43.69 / Avg: 185.89 / Max: 235.27 Min: 19.72 / Avg: 132.92 / Max: 171.37 Min: 18.26 / Avg: 119.61 / Max: 153.19
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon 6766E Xeon 6780E Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 EPYC 9754 EPYC 9684X Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon 6780E 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P 170K 340K 510K 680K 850K SE +/- 248.73, N = 3 SE +/- 1836.55, N = 3 SE +/- 206.69, N = 3 SE +/- 268.94, N = 3 SE +/- 2258.81, N = 3 SE +/- 1535.53, N = 3 SE +/- 1785.84, N = 3 SE +/- 610.46, N = 3 SE +/- 933.46, N = 3 SE +/- 1982.97, N = 3 SE +/- 5127.15, N = 3 SE +/- 3924.87, N = 3 SE +/- 719.89, N = 3 SE +/- 1188.96, N = 3 SE +/- 1520.59, N = 3 SE +/- 7384.79, N = 3 SE +/- 4200.62, N = 3 SE +/- 1102.28, N = 3 SE +/- 709.87, N = 3 SE +/- 3075.95, N = 3 SE +/- 6869.20, N = 3 SE +/- 2500.52, N = 3 243732 314716 319094 331357 342363 388190 391719 413851 438048 441636 491729 525514 549500 575440 579112 591835 592729 611200 674239 741366 761734 776968 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Algebraic Multi-Grid Benchmark AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark 1.2 Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 9654 EPYC 9684X EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P 1000M 2000M 3000M 4000M 5000M SE +/- 467864.03, N = 3 SE +/- 971797.70, N = 3 SE +/- 291866.98, N = 3 SE +/- 2902028.33, N = 3 SE +/- 3359086.30, N = 3 SE +/- 1778769.08, N = 3 SE +/- 468935.32, N = 3 SE +/- 4000850.45, N = 3 SE +/- 433397.56, N = 3 SE +/- 1066998.75, N = 3 SE +/- 4963892.66, N = 3 SE +/- 235140242.43, N = 12 SE +/- 2438223.49, N = 3 SE +/- 7233468.75, N = 3 SE +/- 9164253.67, N = 3 SE +/- 9014927.20, N = 3 SE +/- 8808919.44, N = 3 SE +/- 6340323.98, N = 3 723153533 1073627667 1147108000 1150052667 1588496667 1597993333 1605097000 1814760000 2275352667 2282802000 2376149000 2783039083 3124402667 3156261667 3205161000 3609646333 4324930333 4467281333 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
Figure Of Merit Per Watt
OpenBenchmarking.org Figure Of Merit Per Watt, More Is Better Algebraic Multi-Grid Benchmark 1.2 Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9754 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 8534P EPYC 9654 EPYC 8534PN EPYC 9754 2M 4M 6M 8M 10M 1552824.49 4622831.26 5278683.30 5320019.08 5337195.71 5363427.41 5380716.03 5415151.06 5533330.98 6349445.21 6520382.60 7422966.05 8293777.78 8578578.70 9344903.38 9442032.07 10387087.22 10610537.82
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Algebraic Multi-Grid Benchmark 1.2 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 63.8 / Avg: 601.82 / Max: 781.06 Min: 186.85 / Avg: 600.53 / Max: 731.72 Min: 189.38 / Avg: 593.28 / Max: 741.95 Min: 164.81 / Avg: 591.89 / Max: 729.05 Min: 67.59 / Avg: 553.59 / Max: 733.88 Min: 58.67 / Avg: 504.15 / Max: 640.85 Min: 42.41 / Avg: 502.96 / Max: 635.91 Min: 98.75 / Avg: 465.7 / Max: 552.2 Min: 59.54 / Avg: 297.94 / Max: 371.37 Min: 58.01 / Avg: 296.41 / Max: 368.28 Min: 75.43 / Avg: 295.22 / Max: 373.47 Min: 27.09 / Avg: 286.5 / Max: 375.22 Min: 25.82 / Avg: 285.81 / Max: 370.88 Min: 23.58 / Avg: 241.77 / Max: 304.95 Min: 51.21 / Avg: 232.24 / Max: 283.34 Min: 20 / Avg: 214.44 / Max: 294.78 Min: 17.02 / Avg: 123.07 / Max: 150.22 Min: 16.12 / Avg: 110.44 / Max: 131.86
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E EPYC 9754 EPYC 8534PN EPYC 9754 2P EPYC 8534P EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 2P Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 4M 8M 12M 16M 20M SE +/- 33.33, N = 3 SE +/- 115.47, N = 3 SE +/- 133.33, N = 3 SE +/- 88.19, N = 3 SE +/- 120841.84, N = 4 SE +/- 31571.79, N = 3 SE +/- 11050.39, N = 3 SE +/- 3464.10, N = 3 SE +/- 234395.65, N = 15 SE +/- 134727.30, N = 3 SE +/- 124115.99, N = 3 SE +/- 121304.48, N = 3 SE +/- 11150.49, N = 3 SE +/- 18478.22, N = 3 SE +/- 38670.98, N = 3 SE +/- 8685.88, N = 3 SE +/- 7571.88, N = 3 SE +/- 30179.10, N = 3 SE +/- 17457.89, N = 3 SE +/- 5238.74, N = 3 SE +/- 162096.41, N = 15 SE +/- 9492.69, N = 3 6280767 6284300 6969967 6983933 11174500 11236333 11273667 11290000 13083133 13387333 13390667 13394667 13599000 13608333 16843333 16882333 16884000 16885333 16904667 16906333 18200533 18774333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 EPYC 9684X 2P Xeon 6766E 2P Xeon Max 9480 2P EPYC 9654 2P Xeon Max 9468 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X Xeon Max 9480 Xeon 6766E Xeon Max 9468 Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8490H EPYC 8534P EPYC 8534PN Xeon Platinum 8592+ 50K 100K 150K 200K 250K 54322.93 59249.32 60089.56 61154.45 61488.83 63241.27 64666.31 72744.48 75252.11 92062.08 129024.51 136523.06 143435.84 144779.82 145590.23 146784.94 155096.20 158555.72 186991.46 229953.45 232185.74 234762.36
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 60 120 180 240 300 Min: 214.89 / Avg: 280.98 / Max: 313.66 Min: 202.94 / Avg: 274.92 / Max: 318.53 Min: 58.81 / Avg: 240.84 / Max: 263.72 Min: 161.66 / Avg: 231.54 / Max: 318.27 Min: 58.4 / Avg: 218.96 / Max: 238.65 Min: 80.57 / Avg: 197.7 / Max: 288.51 Min: 100.48 / Avg: 180.71 / Max: 198.88 Min: 39.35 / Avg: 178.26 / Max: 197.4 Min: 87.22 / Avg: 123.68 / Max: 135.23 Min: 76.32 / Avg: 116.77 / Max: 126.02 Min: 105.16 / Avg: 107.78 / Max: 109.29 Min: 103.81 / Avg: 106.01 / Max: 108.94 Min: 33.62 / Avg: 103.76 / Max: 113.64 Min: 48.5 / Avg: 93.47 / Max: 100.4 Min: 27.87 / Avg: 91.25 / Max: 99.85 Min: 64.97 / Avg: 90.28 / Max: 123.68 Min: 34.71 / Avg: 79.97 / Max: 86.36 Min: 20.45 / Avg: 72.05 / Max: 78.73 Min: 16.02 / Avg: 49.1 / Max: 53.74 Min: 15.14 / Avg: 48.39 / Max: 52.91 Min: 43.37 / Avg: 44.05 / Max: 45.52 Min: 43.55 / Avg: 43.81 / Max: 45.6
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 2P EPYC 9654 Xeon Max 9468 2P EPYC 9684X EPYC 9754 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 5K 10K 15K 20K 25K SE +/- 13.82, N = 3 SE +/- 155.10, N = 12 SE +/- 50.01, N = 8 SE +/- 14.68, N = 3 SE +/- 6.53, N = 3 SE +/- 6.77, N = 3 SE +/- 22.33, N = 3 SE +/- 17.53, N = 3 SE +/- 122.47, N = 15 SE +/- 4.83, N = 4 SE +/- 309.03, N = 15 SE +/- 367.88, N = 12 SE +/- 10.93, N = 4 SE +/- 100.23, N = 4 SE +/- 30.19, N = 4 SE +/- 530.31, N = 15 SE +/- 1274.85, N = 12 SE +/- 602.37, N = 15 4479.28 5366.69 5745.04 6416.34 6445.09 7562.80 8089.14 8880.82 10652.03 10970.45 11424.05 12575.30 12793.01 14946.76 16004.07 19414.94 22017.75 22166.60 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9654 EPYC 9684X 2P EPYC 9654 2P EPYC 8534P EPYC 8534PN EPYC 9754 EPYC 9754 2P 13 26 39 52 65 18.48 20.17 20.39 21.07 22.77 23.86 25.96 28.72 29.24 33.93 37.12 43.86 44.72 46.56 49.71 50.72 53.74 58.09
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9480 Xeon Max 9468 EPYC 9654 Xeon Platinum 8380 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 196.31 / Avg: 561.84 / Max: 754.16 Min: 200.97 / Avg: 537.97 / Max: 722.6 Min: 155.56 / Avg: 520.43 / Max: 752.57 Min: 65.8 / Avg: 495.73 / Max: 819.01 Min: 68.69 / Avg: 471.7 / Max: 753.27 Min: 100.12 / Avg: 440.29 / Max: 581.61 Min: 56.44 / Avg: 416.97 / Max: 683.16 Min: 40.5 / Avg: 379.03 / Max: 677.9 Min: 31.93 / Avg: 307.77 / Max: 409.54 Min: 57.58 / Avg: 291.31 / Max: 376.98 Min: 26.35 / Avg: 276.68 / Max: 375.06 Min: 76.21 / Avg: 270.13 / Max: 345.76 Min: 73.35 / Avg: 254.67 / Max: 351.04 Min: 26.47 / Avg: 242.89 / Max: 334.43 Min: 51.37 / Avg: 242.36 / Max: 290.59 Min: 21.19 / Avg: 234.01 / Max: 336.9 Min: 18.8 / Avg: 129.08 / Max: 158.73 Min: 17.1 / Avg: 113.27 / Max: 135.62
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Very Thorough Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 EPYC 8534PN EPYC 8534P Xeon 6766E Xeon Max 9480 Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9480 2P EPYC 9754 Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 5 10 15 20 25 SE +/- 0.0075, N = 3 SE +/- 0.0026, N = 3 SE +/- 0.0016, N = 3 SE +/- 0.0012, N = 3 SE +/- 0.0007, N = 3 SE +/- 0.0005, N = 3 SE +/- 0.0016, N = 3 SE +/- 0.0005, N = 3 SE +/- 0.0054, N = 3 SE +/- 0.0294, N = 3 SE +/- 0.0006, N = 3 SE +/- 0.0055, N = 3 SE +/- 0.0254, N = 3 SE +/- 0.0386, N = 3 SE +/- 0.0022, N = 3 SE +/- 0.0006, N = 3 SE +/- 0.0314, N = 3 SE +/- 0.0379, N = 3 SE +/- 0.0007, N = 3 SE +/- 0.1965, N = 3 SE +/- 0.1284, N = 3 SE +/- 0.1961, N = 15 2.1596 4.2935 5.1342 5.2406 5.7420 5.8632 5.9702 6.5166 7.0885 7.6240 9.1844 10.2051 10.3224 11.3573 11.8875 12.3187 12.6220 13.7518 14.6334 17.0098 19.4052 22.0023 1. (CXX) g++ options: -O3 -flto -pthread
MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.7 Preset: Very Thorough Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon 6780E Xeon Platinum 8592+ 2P Xeon 6766E Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 EPYC 9684X 2P EPYC 9654 2P EPYC 8534P EPYC 8534PN EPYC 9754 EPYC 9754 2P 0.0117 0.0234 0.0351 0.0468 0.0585 0.008 0.009 0.016 0.017 0.019 0.020 0.023 0.025 0.026 0.026 0.028 0.030 0.030 0.032 0.033 0.034 0.036 0.036 0.038 0.041 0.047 0.052
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.7 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 205.14 / Avg: 590.21 / Max: 754.13 Min: 200.66 / Avg: 582.09 / Max: 758.49 Min: 154.33 / Avg: 550 / Max: 755.26 Min: 64.98 / Avg: 538.44 / Max: 820.03 Min: 71.14 / Avg: 526.63 / Max: 753.88 Min: 97.89 / Avg: 488.29 / Max: 581.33 Min: 58.13 / Avg: 474.96 / Max: 673.2 Min: 106.83 / Avg: 422.58 / Max: 617.03 Min: 39.19 / Avg: 421.17 / Max: 704.37 Min: 104.49 / Avg: 346.65 / Max: 485.81 Min: 33 / Avg: 322.42 / Max: 410.63 Min: 74.02 / Avg: 315.87 / Max: 377.36 Min: 87.45 / Avg: 313.77 / Max: 375.54 Min: 61.31 / Avg: 301.81 / Max: 376.57 Min: 35.19 / Avg: 294.16 / Max: 378.5 Min: 25.96 / Avg: 270.94 / Max: 337.98 Min: 21.13 / Avg: 262.17 / Max: 365.71 Min: 53.27 / Avg: 255.32 / Max: 291.21 Min: 43.52 / Avg: 249.37 / Max: 311.61 Min: 43.59 / Avg: 194.13 / Max: 235.38 Min: 18.13 / Avg: 151.45 / Max: 177.27 Min: 15.84 / Avg: 128.4 / Max: 151.19
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: AlexNet Xeon 6766E Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon 6766E 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9684X Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9754 Xeon Max 9468 2P EPYC 9654 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 400 800 1200 1600 2000 SE +/- 1.03, N = 3 SE +/- 2.12, N = 3 SE +/- 0.41, N = 3 SE +/- 0.99, N = 3 SE +/- 1.28, N = 3 SE +/- 19.06, N = 15 SE +/- 1.21, N = 3 SE +/- 10.51, N = 4 SE +/- 6.82, N = 3 SE +/- 0.54, N = 3 SE +/- 4.27, N = 3 SE +/- 2.58, N = 3 SE +/- 1.54, N = 3 SE +/- 3.03, N = 3 SE +/- 10.23, N = 15 SE +/- 4.01, N = 3 SE +/- 1.15, N = 3 SE +/- 6.01, N = 3 SE +/- 5.81, N = 3 SE +/- 15.82, N = 3 SE +/- 1.86, N = 3 SE +/- 5.06, N = 3 609.67 668.33 771.47 843.63 852.14 857.20 986.04 1010.93 1058.99 1205.30 1277.46 1278.58 1301.26 1340.34 1403.46 1454.71 1479.53 1524.74 1528.41 1560.56 1681.44 1730.25
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: AlexNet Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Max 9468 EPYC 9684X 2P Xeon Max 9480 Xeon 6766E EPYC 9654 2P Xeon Platinum 8380 Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 8534P EPYC 9754 EPYC 8534PN 2 4 6 8 10 2.368 2.456 2.515 2.593 3.122 3.126 3.127 3.205 3.248 3.444 3.524 3.535 3.591 3.635 3.829 4.146 4.749 4.808 5.419 6.684 6.976 7.144
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 196.2 / Avg: 589.54 / Max: 703.42 Min: 206.23 / Avg: 588.17 / Max: 702.19 Min: 155.31 / Avg: 554.16 / Max: 691.31 Min: 69.6 / Avg: 480.42 / Max: 618.89 Min: 79.54 / Avg: 462.52 / Max: 594.2 Min: 102.12 / Avg: 428.69 / Max: 526.9 Min: 54.66 / Avg: 428.39 / Max: 556.88 Min: 108.29 / Avg: 411.57 / Max: 512.05 Min: 40.95 / Avg: 366.52 / Max: 481.87 Min: 105.44 / Avg: 362.01 / Max: 449.07 Min: 71.72 / Avg: 307.61 / Max: 356.17 Min: 83.56 / Avg: 307.45 / Max: 358.74 Min: 58.81 / Avg: 290.68 / Max: 351.63 Min: 33.53 / Avg: 270.65 / Max: 335.43 Min: 33.64 / Avg: 268.97 / Max: 332.41 Min: 53.46 / Avg: 237.33 / Max: 279.61 Min: 26.89 / Avg: 235.94 / Max: 296.09 Min: 43.57 / Avg: 213.83 / Max: 263.13 Min: 22.22 / Avg: 206.77 / Max: 269.72 Min: 43.66 / Avg: 173.02 / Max: 210.79 Min: 17.24 / Avg: 126.21 / Max: 154.11 Min: 18.12 / Avg: 108 / Max: 132.76
miniFE MiniFE Finite Element is an application for unstructured implicit finite element codes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small Xeon Max 9480 Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Platinum 8380 EPYC 8534P EPYC 8534PN Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon 6766E Xeon 6780E EPYC 9754 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8490H 2P EPYC 9754 EPYC 9654 EPYC 9684X EPYC 9684X 2P 13K 26K 39K 52K 65K SE +/- 572.00, N = 12 SE +/- 1097.75, N = 15 SE +/- 601.03, N = 12 SE +/- 283.44, N = 3 SE +/- 54.57, N = 4 SE +/- 49.20, N = 4 SE +/- 42.17, N = 4 SE +/- 366.08, N = 4 SE +/- 135.77, N = 4 SE +/- 11.14, N = 4 SE +/- 712.94, N = 12 SE +/- 1039.71, N = 15 SE +/- 19.87, N = 4 SE +/- 8.42, N = 4 SE +/- 2087.13, N = 15 SE +/- 1633.92, N = 15 SE +/- 1510.37, N = 15 SE +/- 467.78, N = 4 SE +/- 53.07, N = 5 SE +/- 42.89, N = 5 SE +/- 92.04, N = 5 SE +/- 2182.93, N = 15 18621.2 19876.5 20091.1 21583.2 22957.3 24526.0 24548.8 31046.5 31830.2 35230.1 37461.1 39580.9 40441.0 40626.4 42113.5 42114.6 43531.0 46877.5 50139.9 50909.6 53167.8 59466.6 1. (CXX) g++ options: -O3 -fopenmp -lmpi_cxx -lmpi
CG Mflops Per Watt
OpenBenchmarking.org CG Mflops Per Watt, More Is Better miniFE 2.2 Problem Size: Small Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 EPYC 9654 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 2P Xeon 6780E 2P EPYC 9684X 2P Xeon 6766E 2P EPYC 8534P EPYC 8534PN EPYC 9684X EPYC 9654 Xeon 6780E Xeon 6766E EPYC 9754 90 180 270 360 450 39.85 43.11 71.52 79.24 95.00 110.48 114.81 120.52 140.84 156.59 160.18 162.67 165.96 179.90 183.43 254.52 282.72 298.90 334.41 340.56 373.28 392.87
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better miniFE 2.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 EPYC 9754 2P Xeon Max 9468 Xeon 6780E 2P Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 199.32 / Avg: 500.61 / Max: 723.88 Min: 189.32 / Avg: 498.77 / Max: 730.29 Min: 168.8 / Avg: 424.3 / Max: 732.03 Min: 73.08 / Avg: 366.83 / Max: 700.4 Min: 63.04 / Avg: 330.55 / Max: 718.24 Min: 99.06 / Avg: 326.82 / Max: 539.95 Min: 53.09 / Avg: 309.09 / Max: 579.88 Min: 73.91 / Avg: 260.35 / Max: 366.7 Min: 40.05 / Avg: 258.88 / Max: 518.97 Min: 75.77 / Avg: 253.53 / Max: 365.64 Min: 106.66 / Avg: 225.73 / Max: 522.28 Min: 61.92 / Avg: 224.98 / Max: 377.92 Min: 104.71 / Avg: 215.79 / Max: 487.65 Min: 31.62 / Avg: 198.71 / Max: 331.13 Min: 53.33 / Avg: 190.48 / Max: 282.32 Min: 33.7 / Avg: 177.88 / Max: 364.34 Min: 28.79 / Avg: 152.24 / Max: 300.13 Min: 21.36 / Avg: 127.63 / Max: 261.53 Min: 43.53 / Avg: 119.29 / Max: 232.16 Min: 43.59 / Avg: 108.34 / Max: 211.25 Min: 19.07 / Avg: 96.36 / Max: 147.72 Min: 15.16 / Avg: 86.83 / Max: 132.07
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Cell Phone Drop Test Xeon Platinum 8380 EPYC 8534PN Xeon Max 9468 EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ EPYC 9754 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P EPYC 9754 EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X 10 20 30 40 50 SE +/- 0.21, N = 3 SE +/- 0.35, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.32, N = 3 SE +/- 0.26, N = 3 SE +/- 0.05, N = 3 SE +/- 0.26, N = 3 SE +/- 0.05, N = 3 SE +/- 0.19, N = 3 43.45 35.95 33.75 33.23 31.92 31.49 31.17 28.22 27.90 27.86 27.63 27.51 26.88 23.69 23.53 22.53 22.52 20.45
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2023.09.15 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 206.26 / Avg: 572.24 / Max: 749.99 Min: 199.37 / Avg: 570.84 / Max: 753.68 Min: 172.03 / Avg: 545.45 / Max: 745.98 Min: 71.17 / Avg: 504.55 / Max: 754.24 Min: 60.04 / Avg: 493.1 / Max: 819.11 Min: 58.09 / Avg: 439.02 / Max: 706.97 Min: 97.57 / Avg: 424.07 / Max: 583.23 Min: 41.04 / Avg: 357.25 / Max: 670.96 Min: 76.63 / Avg: 302.43 / Max: 377 Min: 77.53 / Avg: 297.92 / Max: 375.01 Min: 59.2 / Avg: 289.5 / Max: 374.11 Min: 33.62 / Avg: 276.69 / Max: 409.57 Min: 34.28 / Avg: 272.03 / Max: 374.83 Min: 30.24 / Avg: 238.37 / Max: 343.81 Min: 52.02 / Avg: 232.77 / Max: 290.08 Min: 19.86 / Avg: 210.23 / Max: 333.55 Min: 19.07 / Avg: 127.55 / Max: 161.94 Min: 18.07 / Avg: 113.05 / Max: 140.62
VVenC VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Faster Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8592+ 2P EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 EPYC 9754 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9684X 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.16, N = 3 SE +/- 0.13, N = 6 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 10.39 11.18 11.90 11.97 12.54 13.02 13.10 13.26 13.61 13.97 14.10 14.36 14.79 15.06 15.97 16.73 17.02 1. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better VVenC 1.11 Video Input: Bosphorus 4K - Video Preset: Faster Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 0.0322 0.0644 0.0966 0.1288 0.161 0.023 0.023 0.028 0.031 0.038 0.051 0.051 0.060 0.062 0.068 0.080 0.090 0.106 0.108 0.114 0.130 0.143
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better VVenC 1.11 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P Xeon 6780E EPYC 8534PN Xeon 6766E 110 220 330 440 550 Min: 209.37 / Avg: 521.79 / Max: 619.75 Min: 204.58 / Avg: 521.13 / Max: 631.04 Min: 149.66 / Avg: 449.44 / Max: 572.09 Min: 77.34 / Avg: 425.45 / Max: 535.49 Min: 100.84 / Avg: 347.13 / Max: 466.54 Min: 73.18 / Avg: 282.13 / Max: 350.27 Min: 74.46 / Avg: 275.77 / Max: 340.06 Min: 60.17 / Avg: 250.97 / Max: 326.74 Min: 34.91 / Avg: 235.39 / Max: 320.85 Min: 34.49 / Avg: 211.98 / Max: 303.77 Min: 54.24 / Avg: 210.37 / Max: 275.5 Min: 29.27 / Avg: 185.29 / Max: 257.81 Min: 20.86 / Avg: 139.36 / Max: 195.74 Min: 18.52 / Avg: 107.71 / Max: 147.66 Min: 43.51 / Avg: 103.62 / Max: 147.39 Min: 17.01 / Avg: 95.43 / Max: 126.76 Min: 43.53 / Avg: 90.8 / Max: 124.66
Video Input: Bosphorus 4K - Video Preset: Faster
EPYC 9684X 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
EPYC 9654 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
EPYC 9754 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Xeon 6766E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Xeon 6780E 2P: The test quit with a non-zero exit status. E: Parameter Check Error: Number of threads out of range (-1
Primesieve Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e13 Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E EPYC 8534PN Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 8534P Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon 6780E 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 20 40 60 80 100 SE +/- 0.25, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 4 SE +/- 0.02, N = 4 SE +/- 0.01, N = 4 81.36 67.32 58.16 57.71 54.39 52.07 51.82 48.41 45.95 40.44 33.92 30.20 29.39 27.11 26.46 25.02 24.24 23.27 21.76 12.63 12.13 11.56 1. (CXX) g++ options: -O3
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Primesieve 12.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 198.12 / Avg: 644.29 / Max: 754.21 Min: 195.98 / Avg: 641.65 / Max: 754.11 Min: 169.87 / Avg: 623.11 / Max: 754.26 Min: 60.51 / Avg: 618.54 / Max: 821.49 Min: 72.85 / Avg: 610.7 / Max: 755.46 Min: 38.5 / Avg: 568.09 / Max: 750.08 Min: 105.22 / Avg: 507.66 / Max: 599.09 Min: 41.03 / Avg: 500.8 / Max: 682.66 Min: 103.1 / Avg: 498.66 / Max: 583 Min: 104.03 / Avg: 414.77 / Max: 479.6 Min: 34.15 / Avg: 347.93 / Max: 410.94 Min: 74.26 / Avg: 333.11 / Max: 377.38 Min: 74.48 / Avg: 332.68 / Max: 375.62 Min: 54.67 / Avg: 328.05 / Max: 377.53 Min: 21.47 / Avg: 325.15 / Max: 377.46 Min: 28.63 / Avg: 313.43 / Max: 370.81 Min: 21.63 / Avg: 274.16 / Max: 334.73 Min: 43.4 / Avg: 266.63 / Max: 294.13 Min: 52.11 / Avg: 258.9 / Max: 290.98 Min: 43.71 / Avg: 208.57 / Max: 226.96 Min: 17.27 / Avg: 151.7 / Max: 165.81 Min: 15.99 / Avg: 116.97 / Max: 130.2
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 5 10 15 20 25 SE +/- 0.018, N = 3 SE +/- 0.004, N = 3 SE +/- 0.004, N = 3 SE +/- 0.019, N = 3 SE +/- 0.007, N = 3 SE +/- 0.010, N = 3 SE +/- 0.036, N = 3 SE +/- 0.009, N = 3 SE +/- 0.034, N = 3 SE +/- 0.032, N = 3 SE +/- 0.025, N = 3 SE +/- 0.032, N = 3 SE +/- 0.052, N = 3 SE +/- 0.019, N = 3 SE +/- 0.046, N = 3 SE +/- 0.189, N = 6 SE +/- 0.067, N = 3 SE +/- 0.224, N = 14 4.813 6.246 6.499 7.545 8.282 8.762 8.964 10.477 12.514 13.242 13.392 14.127 15.222 15.450 18.540 20.234 21.305 22.525 1. (CXX) g++ options: -O3 -lm
Ns Per Day Per Watt
OpenBenchmarking.org Ns Per Day Per Watt, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P EPYC 8534P EPYC 9684X EPYC 9654 EPYC 8534PN EPYC 9754 0.0119 0.0238 0.0357 0.0476 0.0595 0.019 0.019 0.022 0.023 0.024 0.026 0.027 0.029 0.035 0.036 0.037 0.040 0.047 0.047 0.048 0.048 0.052 0.053
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GROMACS 2024 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 205.45 / Avg: 603.46 / Max: 753.72 Min: 201.3 / Avg: 602.79 / Max: 753.69 Min: 65.5 / Avg: 601.18 / Max: 820.89 Min: 166.32 / Avg: 584.52 / Max: 753.32 Min: 75.68 / Avg: 535.3 / Max: 753.28 Min: 56.1 / Avg: 505.98 / Max: 708.92 Min: 104.75 / Avg: 474.08 / Max: 581.34 Min: 40.72 / Avg: 455.51 / Max: 701.31 Min: 33.95 / Avg: 317.95 / Max: 409.49 Min: 76.31 / Avg: 314 / Max: 374.89 Min: 75.59 / Avg: 311.94 / Max: 375.77 Min: 54.7 / Avg: 306.77 / Max: 376.19 Min: 24.97 / Avg: 289.21 / Max: 376.32 Min: 27.69 / Avg: 260.21 / Max: 348.03 Min: 22.18 / Avg: 250.1 / Max: 348.03 Min: 53.31 / Avg: 248.51 / Max: 290.81 Min: 18.05 / Avg: 137.24 / Max: 164.83 Min: 16.45 / Avg: 120.24 / Max: 142.62
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Exhaustive Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon 6766E Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon 6766E 2P Xeon Max 9480 2P EPYC 9754 Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 4 8 12 16 20 SE +/- 0.0016, N = 3 SE +/- 0.0029, N = 3 SE +/- 0.0003, N = 3 SE +/- 0.0006, N = 3 SE +/- 0.0010, N = 3 SE +/- 0.0011, N = 3 SE +/- 0.0007, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0024, N = 3 SE +/- 0.0072, N = 3 SE +/- 0.0002, N = 3 SE +/- 0.0033, N = 3 SE +/- 0.0086, N = 3 SE +/- 0.0040, N = 3 SE +/- 0.0016, N = 3 SE +/- 0.0025, N = 3 SE +/- 0.0118, N = 3 SE +/- 0.0164, N = 3 SE +/- 0.0157, N = 3 SE +/- 0.0218, N = 3 SE +/- 0.0170, N = 3 SE +/- 0.1160, N = 3 1.3319 2.6471 3.1204 3.1993 3.5146 3.6276 3.6505 4.0574 4.2689 4.6303 5.6301 6.2126 6.3027 7.1291 7.2075 7.5573 7.9060 8.3701 8.9091 10.6018 11.9107 14.1038 1. (CXX) g++ options: -O3 -flto -pthread
MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.7 Preset: Exhaustive Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ Xeon 6780E Xeon Platinum 8592+ 2P Xeon 6766E Xeon 6780E 2P EPYC 9684X EPYC 9684X 2P EPYC 9654 Xeon 6766E 2P EPYC 9654 2P EPYC 8534P EPYC 8534PN EPYC 9754 EPYC 9754 2P 0.0074 0.0148 0.0222 0.0296 0.037 0.005 0.005 0.010 0.011 0.012 0.012 0.014 0.015 0.016 0.016 0.017 0.019 0.019 0.020 0.021 0.021 0.021 0.023 0.023 0.025 0.029 0.033
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.7 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 207.97 / Avg: 591.29 / Max: 755.19 Min: 207.67 / Avg: 586.49 / Max: 753.26 Min: 65.5 / Avg: 555.22 / Max: 820.52 Min: 152.83 / Avg: 551.93 / Max: 753.4 Min: 80.68 / Avg: 525.87 / Max: 752.74 Min: 103.02 / Avg: 483.56 / Max: 581.87 Min: 58.38 / Avg: 469.68 / Max: 682.7 Min: 41.13 / Avg: 424.16 / Max: 725.4 Min: 107.83 / Avg: 422.73 / Max: 622.38 Min: 105.14 / Avg: 347.52 / Max: 490.12 Min: 35.44 / Avg: 322.22 / Max: 410.64 Min: 74.57 / Avg: 315.36 / Max: 378.01 Min: 82.06 / Avg: 312.54 / Max: 376.01 Min: 57.84 / Avg: 300.87 / Max: 376.96 Min: 36.03 / Avg: 293.73 / Max: 378.6 Min: 29.24 / Avg: 271.69 / Max: 338.26 Min: 22.1 / Avg: 264.41 / Max: 366.28 Min: 54.67 / Avg: 254.82 / Max: 291.9 Min: 43.55 / Avg: 250.35 / Max: 311.8 Min: 43.7 / Avg: 193.71 / Max: 235.48 Min: 18.31 / Avg: 151.62 / Max: 177.01 Min: 15.2 / Avg: 129.53 / Max: 151.58
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Xeon Platinum 8380 Xeon Max 9468 Xeon 6766E Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6780E EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon 6766E 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9754 EPYC 9684X EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 10 20 30 40 50 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.23, N = 5 SE +/- 0.03, N = 3 SE +/- 0.16, N = 15 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.28, N = 11 SE +/- 0.23, N = 4 SE +/- 0.46, N = 4 12.56 15.17 15.65 15.68 16.19 16.64 17.29 17.80 17.85 19.25 22.03 22.25 22.59 24.65 27.65 30.37 31.44 32.44 32.74 38.12 42.03 45.26
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9684X 2P Xeon 6780E 2P EPYC 9654 2P Xeon 6766E 2P EPYC 9684X EPYC 9754 2P Xeon 6780E Xeon 6766E EPYC 9754 EPYC 8534P EPYC 9654 EPYC 8534PN 0.0374 0.0748 0.1122 0.1496 0.187 0.038 0.039 0.042 0.051 0.051 0.051 0.051 0.057 0.059 0.062 0.086 0.087 0.090 0.094 0.105 0.105 0.124 0.134 0.145 0.148 0.150 0.166
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E 2P Xeon Platinum 8380 Xeon 6766E 2P EPYC 9754 EPYC 9654 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 130 260 390 520 650 Min: 190.07 / Avg: 582.58 / Max: 673.85 Min: 208.68 / Avg: 571.96 / Max: 640.22 Min: 168.73 / Avg: 543.59 / Max: 642.52 Min: 76.25 / Avg: 536.26 / Max: 744.89 Min: 66.05 / Avg: 527.19 / Max: 710.22 Min: 56.62 / Avg: 464.69 / Max: 608.77 Min: 103.64 / Avg: 425.24 / Max: 481.28 Min: 40.54 / Avg: 362.19 / Max: 493.12 Min: 34.79 / Avg: 310.62 / Max: 383.33 Min: 74.3 / Avg: 306.72 / Max: 336.87 Min: 76.55 / Avg: 299.38 / Max: 332.83 Min: 60.4 / Avg: 287.16 / Max: 327.69 Min: 26.08 / Avg: 283.27 / Max: 364.78 Min: 107.22 / Avg: 259.74 / Max: 308.25 Min: 52.84 / Avg: 248.57 / Max: 274.13 Min: 104.75 / Avg: 234.71 / Max: 274.07 Min: 22.31 / Avg: 224.13 / Max: 286.22 Min: 29.07 / Avg: 209.83 / Max: 311.67 Min: 43.45 / Avg: 138.99 / Max: 161.82 Min: 18.2 / Avg: 130.37 / Max: 151.17 Min: 43.61 / Avg: 116.67 / Max: 128.84 Min: 16.52 / Avg: 107.55 / Max: 128.61
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: WPA PSK Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon 6766E 2P EPYC 8534P Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 300K 600K 900K 1200K 1500K SE +/- 30.00, N = 3 SE +/- 66.16, N = 3 SE +/- 177.03, N = 3 SE +/- 987.33, N = 3 SE +/- 1274.00, N = 3 SE +/- 79.20, N = 3 SE +/- 187.67, N = 3 SE +/- 321.00, N = 3 SE +/- 1599.31, N = 3 SE +/- 394.40, N = 3 SE +/- 864.17, N = 3 SE +/- 1491.72, N = 3 SE +/- 5122.51, N = 3 SE +/- 921.74, N = 3 SE +/- 788.50, N = 3 SE +/- 2683.36, N = 3 SE +/- 2519.00, N = 3 SE +/- 15579.94, N = 15 SE +/- 478.70, N = 3 SE +/- 1333.33, N = 3 SE +/- 5291.50, N = 3 SE +/- 4358.90, N = 3 188925 209803 248066 286552 334076 339998 367657 386212 401278 407256 428116 491583 562875 643475 657889 671322 793253 797093 803187 1253333 1294000 1551000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Real C/S Per Watt
OpenBenchmarking.org Real C/S Per Watt, More Is Better John The Ripper 2023.03.14 Test: WPA PSK Xeon 6780E 2P Xeon 6780E Xeon 6766E 2P Xeon 6766E Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 9754 2P EPYC 9754 EPYC 8534P EPYC 8534PN 600 1200 1800 2400 3000 784.52 815.37 881.55 953.29 1004.94 1017.12 1057.22 1100.83 1133.97 1204.61 1261.48 1285.88 1347.41 1374.72 1799.50 1853.75 1941.48 2017.72 2253.10 2304.83 2414.27 2563.93
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better John The Ripper 2023.03.14 CPU Power Consumption Monitor EPYC 9684X 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9684X EPYC 9754 EPYC 9654 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9480 Xeon 6780E Xeon Max 9468 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.44 / Avg: 719.09 / Max: 821.15 Min: 43.51 / Avg: 688.39 / Max: 796.51 Min: 59 / Avg: 645.56 / Max: 737.44 Min: 165.05 / Avg: 628.83 / Max: 743.61 Min: 64.41 / Avg: 619.88 / Max: 753.08 Min: 193.96 / Avg: 597.63 / Max: 753.44 Min: 186.18 / Avg: 532.41 / Max: 591.91 Min: 109.89 / Avg: 519.11 / Max: 586.15 Min: 99.22 / Avg: 489.17 / Max: 579.96 Min: 108.35 / Avg: 417.06 / Max: 466.57 Min: 33.28 / Avg: 362.14 / Max: 411.02 Min: 22.59 / Avg: 348.48 / Max: 397.44 Min: 29.6 / Avg: 318.91 / Max: 365.41 Min: 23.24 / Avg: 311.42 / Max: 376.46 Min: 56.65 / Avg: 297.81 / Max: 364.7 Min: 76.35 / Avg: 277.33 / Max: 310.37 Min: 43.57 / Avg: 257.31 / Max: 292.39 Min: 66.96 / Avg: 252.7 / Max: 281.63 Min: 53.04 / Avg: 243.89 / Max: 290.93 Min: 43.68 / Avg: 198.18 / Max: 221.69 Min: 18.24 / Avg: 159.97 / Max: 182.75 Min: 17.08 / Avg: 132.61 / Max: 150.07
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: GoogLeNet Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon 6780E Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9654 Xeon Platinum 8490H EPYC 9684X Xeon Max 9468 EPYC 8534PN EPYC 8534P Xeon Platinum 8380 12 24 36 48 60 SE +/- 0.05, N = 7 SE +/- 0.06, N = 9 SE +/- 0.04, N = 3 SE +/- 0.04, N = 4 SE +/- 0.14, N = 15 SE +/- 0.12, N = 6 SE +/- 0.17, N = 15 SE +/- 0.09, N = 4 SE +/- 0.23, N = 15 SE +/- 0.23, N = 12 SE +/- 0.20, N = 15 SE +/- 0.27, N = 15 SE +/- 0.21, N = 6 SE +/- 0.34, N = 15 SE +/- 0.27, N = 6 SE +/- 0.41, N = 15 SE +/- 0.19, N = 6 SE +/- 0.33, N = 15 SE +/- 0.27, N = 7 SE +/- 0.14, N = 6 SE +/- 0.30, N = 15 SE +/- 0.24, N = 7 5.88 6.72 8.10 12.40 12.42 12.69 12.83 13.14 13.50 14.67 18.24 21.00 21.67 29.18 31.47 32.80 33.56 34.20 36.13 36.48 36.66 53.38
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: GoogLeNet Xeon 6766E 2P EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon 6780E Xeon Platinum 8592+ Xeon 6766E Xeon Max 9468 EPYC 9754 Xeon Platinum 8490H EPYC 9684X EPYC 9654 Xeon Platinum 8380 EPYC 8534P EPYC 8534PN 0.1458 0.2916 0.4374 0.5832 0.729 0.030 0.031 0.032 0.034 0.034 0.038 0.041 0.041 0.043 0.127 0.171 0.172 0.174 0.177 0.204 0.207 0.217 0.261 0.283 0.496 0.607 0.648
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 191.38 / Avg: 433 / Max: 578.39 Min: 186.6 / Avg: 423.67 / Max: 565.69 Min: 148.89 / Avg: 402.29 / Max: 545.86 Min: 61.13 / Avg: 340.38 / Max: 500.24 Min: 73.56 / Avg: 313.09 / Max: 440.43 Min: 57.14 / Avg: 306.45 / Max: 450.83 Min: 39.52 / Avg: 262.36 / Max: 352.55 Min: 98.2 / Avg: 229.87 / Max: 381.04 Min: 105.84 / Avg: 207.14 / Max: 268.89 Min: 104.02 / Avg: 195.59 / Max: 247.83 Min: 71.73 / Avg: 183.7 / Max: 287.38 Min: 74.34 / Avg: 177.15 / Max: 279.76 Min: 57.88 / Avg: 154.91 / Max: 259.01 Min: 30.18 / Avg: 131.02 / Max: 261.02 Min: 26.58 / Avg: 124.36 / Max: 199.6 Min: 27.18 / Avg: 115.93 / Max: 228.86 Min: 50.23 / Avg: 107.65 / Max: 211.46 Min: 20.13 / Avg: 101.49 / Max: 176.75 Min: 43.43 / Avg: 76.44 / Max: 108.57 Min: 43.55 / Avg: 69.97 / Max: 94.67 Min: 14.4 / Avg: 60.4 / Max: 120.48 Min: 15.28 / Avg: 56.3 / Max: 109.74
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9654 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 16M 32M 48M 64M 80M SE +/- 2185.81, N = 3 SE +/- 20835.33, N = 3 SE +/- 11392.00, N = 3 SE +/- 5206.83, N = 3 SE +/- 393224.42, N = 3 SE +/- 4807.40, N = 3 SE +/- 8089.77, N = 3 SE +/- 7937.25, N = 3 SE +/- 178712.37, N = 3 SE +/- 15982.63, N = 3 SE +/- 486361.09, N = 3 SE +/- 34724.31, N = 3 SE +/- 12719.19, N = 3 SE +/- 7423.69, N = 3 SE +/- 822374.71, N = 4 SE +/- 3844.19, N = 3 SE +/- 4163.33, N = 3 SE +/- 666.67, N = 3 SE +/- 5364.49, N = 3 SE +/- 4910.31, N = 3 SE +/- 68119.99, N = 3 SE +/- 599433.09, N = 9 33439333 33444667 37121333 37195667 45486333 46210667 46229667 46270000 53930333 54089667 54954667 55415667 55425333 55455333 66266000 66991333 67064000 67074667 67127667 67130333 70499000 73140667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 57 EPYC 9684X 2P Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X Xeon Max 9480 Xeon Platinum 8380 Xeon Max 9468 EPYC 9654 EPYC 9754 Xeon Platinum 8490H Xeon 6766E Xeon 6780E Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 200K 400K 600K 800K 1000K 229312.07 235014.31 243752.92 250729.15 256852.19 287557.79 295293.25 310526.31 315271.07 344751.30 529757.56 539196.73 572291.34 575880.01 604481.01 633663.71 741692.03 764093.38 845147.04 859261.41 919805.49 924272.74
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 60 120 180 240 300 Min: 203.12 / Avg: 281.97 / Max: 319.46 Min: 206.29 / Avg: 275.13 / Max: 324.32 Min: 64.49 / Avg: 241.66 / Max: 264.36 Min: 162.53 / Avg: 232.97 / Max: 292.63 Min: 79.82 / Avg: 227.03 / Max: 288.68 Min: 56.89 / Avg: 219.18 / Max: 239.46 Min: 97.63 / Avg: 182.63 / Max: 203.03 Min: 40.07 / Avg: 179.99 / Max: 198.16 Min: 84.47 / Avg: 124.5 / Max: 135.18 Min: 75.77 / Avg: 116.57 / Max: 125.17 Min: 104.74 / Avg: 107.68 / Max: 108.89 Min: 103.81 / Avg: 106.07 / Max: 107.92 Min: 31.94 / Avg: 104.68 / Max: 114.13 Min: 50.3 / Avg: 94.51 / Max: 101.21 Min: 26.34 / Avg: 91.69 / Max: 100.53 Min: 62.53 / Avg: 90.43 / Max: 122.85 Min: 33.42 / Avg: 85.12 / Max: 133.8 Min: 21.28 / Avg: 73.02 / Max: 80.63 Min: 17.35 / Avg: 50.24 / Max: 54.91 Min: 16 / Avg: 49.21 / Max: 54.17 Min: 43.3 / Avg: 44.01 / Max: 45.17 Min: 43.57 / Avg: 43.77 / Max: 45.58
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 9754 2P EPYC 8534PN EPYC 8534P EPYC 9754 EPYC 9654 2P EPYC 9654 EPYC 9684X EPYC 9684X 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 800 1600 2400 3200 4000 SE +/- 4.34, N = 3 SE +/- 4.87, N = 3 SE +/- 7.35, N = 3 SE +/- 6.88, N = 3 SE +/- 14.88, N = 3 SE +/- 2.82, N = 3 SE +/- 19.30, N = 3 SE +/- 14.40, N = 3 SE +/- 18.64, N = 3 SE +/- 14.83, N = 3 SE +/- 19.83, N = 3 SE +/- 24.27, N = 3 SE +/- 22.39, N = 3 SE +/- 1.14, N = 3 SE +/- 28.11, N = 3 SE +/- 28.42, N = 3 SE +/- 25.40, N = 3 SE +/- 28.57, N = 3 SE +/- 22.17, N = 3 SE +/- 25.35, N = 3 SE +/- 30.36, N = 12 SE +/- 33.58, N = 3 1760.8 1765.6 1954.2 1960.7 2534.5 2558.6 2590.8 2593.0 2593.3 2596.1 3098.5 3105.9 3114.2 3125.4 3207.0 3209.6 3210.1 3222.8 3225.7 3229.1 3586.3 3600.5 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
MFLOPS Per Watt
OpenBenchmarking.org MFLOPS Per Watt, More Is Better QuantLib 1.32 Configuration: Single-Threaded Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 EPYC 9684X Xeon Platinum 8490H EPYC 9654 EPYC 9754 Xeon 6766E Xeon 6780E Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN 11 22 33 44 55 11.01 11.15 12.80 13.29 13.92 14.07 14.23 15.01 16.48 18.09 24.92 26.68 27.32 29.60 31.94 33.74 34.81 40.30 43.87 45.35 49.12 50.14
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better QuantLib 1.32 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9654 Xeon Platinum 8592+ EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 70 140 210 280 350 Min: 208.95 / Avg: 292.75 / Max: 399.59 Min: 202.91 / Avg: 287.73 / Max: 404.53 Min: 66.1 / Avg: 244.1 / Max: 269.19 Min: 161.45 / Avg: 241.52 / Max: 334.35 Min: 75.25 / Avg: 238.94 / Max: 292.83 Min: 57.57 / Avg: 217.74 / Max: 241.62 Min: 40.16 / Avg: 184.09 / Max: 202.33 Min: 100.96 / Avg: 183.87 / Max: 210.8 Min: 80.8 / Avg: 129.58 / Max: 191.82 Min: 69.08 / Avg: 120.93 / Max: 183.43 Min: 104.5 / Avg: 108.03 / Max: 111.66 Min: 52.85 / Avg: 106.82 / Max: 109.76 Min: 32.36 / Avg: 105.22 / Max: 115.88 Min: 55.04 / Avg: 100.48 / Max: 155.72 Min: 47.97 / Avg: 92.78 / Max: 99.62 Min: 29.32 / Avg: 92.05 / Max: 101.3 Min: 31.58 / Avg: 79.4 / Max: 103.91 Min: 20.77 / Avg: 74.58 / Max: 81.84 Min: 17.54 / Avg: 52.79 / Max: 57.91 Min: 17.21 / Avg: 51.72 / Max: 57.08 Min: 43.37 / Avg: 44.69 / Max: 46.71 Min: 43.57 / Avg: 43.81 / Max: 45.53
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 EPYC 8534PN Xeon Max 9468 EPYC 8534P Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9754 2P EPYC 9754 Xeon Max 9468 2P Xeon Platinum 8490H Xeon Max 9480 2P Xeon Platinum 8592+ Xeon Platinum 8490H 2P EPYC 9654 EPYC 9654 2P EPYC 9684X 2P EPYC 9684X Xeon Platinum 8592+ 2P 200M 400M 600M 800M 1000M SE +/- 584646.14, N = 3 SE +/- 271682.00, N = 3 SE +/- 3610015.39, N = 3 SE +/- 124677.36, N = 3 SE +/- 147685.85, N = 3 SE +/- 2292977.20, N = 3 SE +/- 1611276.24, N = 3 SE +/- 822739.33, N = 3 SE +/- 749718.47, N = 3 SE +/- 1289603.73, N = 3 SE +/- 958772.36, N = 3 SE +/- 673003.22, N = 3 SE +/- 4432294.36, N = 3 SE +/- 940265.92, N = 3 SE +/- 6141471.96, N = 3 SE +/- 1515552.70, N = 3 SE +/- 3717554.45, N = 3 SE +/- 1678355.68, N = 3 SE +/- 2261241.06, N = 3 SE +/- 3039034.93, N = 3 SE +/- 752558.60, N = 3 SE +/- 7562646.32, N = 8 349746667 359576667 384406667 398566667 503253333 577263333 632396667 633860000 646513333 689003333 709393333 709650000 732560000 744410000 757176667 783770000 799496667 811373333 824583333 849340000 850586667 883701250 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 512 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X 2P Xeon Max 9468 Xeon Platinum 8380 EPYC 9654 2P Xeon Max 9480 Xeon Platinum 8490H EPYC 9754 2P Xeon 6780E Xeon Platinum 8592+ EPYC 9684X Xeon 6766E EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 1.2M 2.4M 3.6M 4.8M 6M 1151612.89 1184768.10 1510160.81 1519282.71 1705499.35 1718163.34 1767425.56 1904459.88 1991130.78 2067133.31 2172222.16 2174337.88 2362548.08 2394875.44 2545869.67 2577646.65 2753902.96 2885618.69 3317050.16 3748079.60 5046791.28 5458880.22
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9754 2P EPYC 9654 Xeon Platinum 8380 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 130 260 390 520 650 Min: 148.91 / Avg: 639.09 / Max: 734.49 Min: 195.75 / Avg: 636.12 / Max: 707.28 Min: 164.45 / Avg: 526.23 / Max: 645.98 Min: 67.01 / Avg: 518.15 / Max: 711.65 Min: 65.79 / Avg: 445.97 / Max: 506.44 Min: 103.26 / Avg: 428.11 / Max: 542.37 Min: 59.09 / Avg: 379.6 / Max: 439.61 Min: 79.61 / Avg: 317.61 / Max: 374.24 Min: 80.39 / Avg: 316.88 / Max: 376.81 Min: 61.24 / Avg: 315.09 / Max: 375.37 Min: 34.73 / Avg: 308.87 / Max: 353.22 Min: 26.5 / Avg: 304.06 / Max: 370.78 Min: 39.32 / Avg: 296.21 / Max: 332.18 Min: 28.29 / Avg: 244.61 / Max: 277.01 Min: 52.9 / Avg: 243.45 / Max: 291.14 Min: 107.13 / Avg: 223.73 / Max: 248.1 Min: 104.54 / Avg: 197.88 / Max: 220.13 Min: 18.89 / Avg: 189.34 / Max: 213.55 Min: 43.52 / Avg: 156.55 / Max: 174.71 Min: 17.47 / Avg: 125.6 / Max: 142.49 Min: 43.66 / Avg: 124.61 / Max: 137.3 Min: 16.94 / Avg: 105.75 / Max: 120.76
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H 2P EPYC 9754 2P EPYC 8534P EPYC 9684X 2P Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 EPYC 9654 2P EPYC 9654 Xeon Platinum 8592+ 40 80 120 160 200 SE +/- 0.80, N = 15 SE +/- 1.01, N = 8 SE +/- 1.79, N = 15 SE +/- 1.63, N = 15 SE +/- 1.67, N = 15 SE +/- 1.12, N = 7 SE +/- 1.11, N = 15 SE +/- 3.34, N = 15 SE +/- 1.44, N = 15 SE +/- 1.62, N = 15 SE +/- 3.84, N = 15 SE +/- 2.18, N = 15 SE +/- 4.46, N = 15 SE +/- 4.25, N = 15 SE +/- 1.54, N = 15 SE +/- 2.31, N = 15 SE +/- 3.81, N = 15 SE +/- 2.84, N = 15 SE +/- 4.48, N = 15 SE +/- 4.23, N = 15 SE +/- 4.38, N = 15 SE +/- 2.83, N = 15 108.29 114.54 116.62 122.62 124.26 124.60 133.19 138.72 144.70 150.00 153.42 154.50 159.75 160.79 161.34 162.47 162.48 162.98 163.41 167.22 172.88 174.83 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Max 9468 Xeon Max 9480 EPYC 9654 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon 6766E Xeon 6780E EPYC 9754 EPYC 8534P EPYC 8534PN 0.6239 1.2478 1.8717 2.4956 3.1195 0.308 0.310 0.486 0.632 0.659 0.698 0.773 0.801 0.808 0.821 0.824 0.933 1.033 1.042 1.334 1.366 1.644 1.660 1.691 1.942 2.657 2.773
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 2.0 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 193.69 / Avg: 401.02 / Max: 565.3 Min: 196.97 / Avg: 398.41 / Max: 555.31 Min: 160.44 / Avg: 317.58 / Max: 460.42 Min: 70.69 / Avg: 247.31 / Max: 459.08 Min: 60.69 / Avg: 231.16 / Max: 380.35 Min: 96.21 / Avg: 219.64 / Max: 381.28 Min: 56.44 / Avg: 206.94 / Max: 347.98 Min: 73.18 / Avg: 187.24 / Max: 299.74 Min: 69.14 / Avg: 187.17 / Max: 307.31 Min: 38.31 / Avg: 171.31 / Max: 283.81 Min: 59.06 / Avg: 155.98 / Max: 273.08 Min: 106.17 / Avg: 142.03 / Max: 219.81 Min: 104.02 / Avg: 131.43 / Max: 193.79 Min: 26.49 / Avg: 131.08 / Max: 275.44 Min: 49.33 / Avg: 128.89 / Max: 223.87 Min: 31.67 / Avg: 118.98 / Max: 227.28 Min: 25.79 / Avg: 105.15 / Max: 208.71 Min: 19.23 / Avg: 84.14 / Max: 169.24 Min: 43.43 / Avg: 73.7 / Max: 142.81 Min: 43.57 / Avg: 69.02 / Max: 130.57 Min: 16.06 / Avg: 60.52 / Max: 126.9 Min: 14.1 / Avg: 55.32 / Max: 107.14
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Xeon Platinum 8380 Xeon Max 9468 Xeon 6766E Xeon Platinum 8380 2P Xeon Max 9480 Xeon 6780E Xeon Platinum 8490H EPYC 8534PN Xeon Platinum 8592+ EPYC 8534P Xeon Max 9468 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9754 EPYC 9684X EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 10 20 30 40 50 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.23, N = 4 SE +/- 0.21, N = 4 SE +/- 0.12, N = 4 10.93 13.36 13.77 13.79 13.89 15.24 15.71 15.77 16.06 17.04 19.75 20.46 21.63 22.14 24.71 27.11 28.01 29.00 29.18 37.13 40.96 43.39
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X 2P Xeon 6780E 2P EPYC 9654 2P Xeon 6766E 2P EPYC 9684X EPYC 9754 2P EPYC 9654 Xeon 6780E Xeon 6766E EPYC 9754 EPYC 8534P EPYC 8534PN 0.0331 0.0662 0.0993 0.1324 0.1655 0.033 0.034 0.038 0.044 0.044 0.045 0.045 0.049 0.054 0.055 0.080 0.081 0.086 0.086 0.092 0.099 0.108 0.109 0.117 0.127 0.130 0.147
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon 6780E 2P EPYC 9654 Xeon Platinum 8380 Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 130 260 390 520 650 Min: 181.76 / Avg: 590.16 / Max: 673.18 Min: 196.37 / Avg: 575.73 / Max: 648.93 Min: 75.78 / Avg: 550.27 / Max: 756.12 Min: 171.75 / Avg: 547.66 / Max: 641.35 Min: 66.68 / Avg: 543.26 / Max: 734.77 Min: 57.99 / Avg: 473.23 / Max: 616.87 Min: 102.97 / Avg: 423.75 / Max: 489.52 Min: 40.4 / Avg: 375.03 / Max: 518.77 Min: 32.45 / Avg: 317.42 / Max: 382.18 Min: 38.16 / Avg: 306.83 / Max: 339.09 Min: 76.03 / Avg: 301.55 / Max: 333.2 Min: 26.18 / Avg: 291.45 / Max: 378.34 Min: 61.29 / Avg: 289.12 / Max: 322.82 Min: 106.34 / Avg: 267.41 / Max: 316.34 Min: 28.73 / Avg: 258.29 / Max: 311.87 Min: 53.14 / Avg: 249.24 / Max: 277.94 Min: 104.27 / Avg: 238.73 / Max: 273.18 Min: 21.98 / Avg: 227.72 / Max: 282.74 Min: 43.49 / Avg: 139.76 / Max: 158.94 Min: 18.85 / Avg: 130.95 / Max: 149.92 Min: 43.62 / Avg: 117.38 / Max: 135.39 Min: 16.27 / Avg: 107.27 / Max: 124.79
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 EPYC 9754 2P EPYC 8534PN EPYC 8534P EPYC 9754 Xeon 6766E 2P Xeon 6766E Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon 6780E 2P Xeon 6780E EPYC 9654 2P EPYC 9684X 2P EPYC 9684X EPYC 9654 Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 9M 18M 27M 36M 45M SE +/- 2185.81, N = 3 SE +/- 881.92, N = 3 SE +/- 2333.33, N = 3 SE +/- 6984.11, N = 3 SE +/- 881.92, N = 3 SE +/- 0.00, N = 3 SE +/- 577.35, N = 3 SE +/- 1000.00, N = 3 SE +/- 881.92, N = 3 SE +/- 1527.53, N = 3 SE +/- 13503.09, N = 3 SE +/- 19139.84, N = 3 SE +/- 7023.77, N = 3 SE +/- 7753.14, N = 3 SE +/- 1154.70, N = 3 SE +/- 1201.85, N = 3 SE +/- 1527.53, N = 3 SE +/- 1452.97, N = 3 SE +/- 1666.67, N = 3 SE +/- 3000.00, N = 3 SE +/- 419600.12, N = 5 SE +/- 417042.80, N = 5 29893333 29899333 29899667 29907333 31705667 31726000 31992000 31995000 35190667 35259000 36033000 36040000 36066000 36068333 36461000 36497667 36506000 36521333 36537667 36539000 38950600 40244000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon 6766E 2P Xeon Max 9468 Xeon 6780E 2P Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 8534P EPYC 8534PN Xeon 6766E Xeon 6780E 200K 400K 600K 800K 1000K 130400.41 133630.14 148995.98 158420.27 165061.92 166453.31 175115.57 215045.22 300054.21 300148.32 318611.94 326342.24 340868.75 344631.62 393460.52 410323.62 411972.01 509090.21 588721.27 596676.31 725751.19 803665.72
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 60 120 180 240 300 Min: 204.92 / Avg: 280.07 / Max: 323.05 Min: 199.94 / Avg: 273.12 / Max: 314.88 Min: 62.85 / Avg: 241.89 / Max: 266.07 Min: 163.87 / Avg: 230.15 / Max: 297.76 Min: 55.79 / Avg: 218.3 / Max: 239.44 Min: 96.06 / Avg: 182.69 / Max: 203.89 Min: 81.91 / Avg: 181.13 / Max: 198.07 Min: 37.62 / Avg: 179.59 / Max: 198.37 Min: 84.78 / Avg: 121.77 / Max: 132.95 Min: 72.3 / Avg: 114.68 / Max: 123.65 Min: 104.44 / Avg: 107.83 / Max: 110.44 Min: 103.77 / Avg: 105.63 / Max: 107.48 Min: 33.02 / Avg: 104.65 / Max: 115.43 Min: 51.12 / Avg: 93.86 / Max: 101.44 Min: 29.58 / Avg: 91.67 / Max: 100.42 Min: 61.4 / Avg: 88.61 / Max: 120.23 Min: 33.18 / Avg: 79.05 / Max: 85.63 Min: 20.11 / Avg: 72.89 / Max: 80.63 Min: 17.38 / Avg: 50.79 / Max: 56.16 Min: 16.61 / Avg: 50.11 / Max: 55.4 Min: 43.37 / Avg: 43.87 / Max: 45.94 Min: 43.55 / Avg: 43.71 / Max: 45.4
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: GoogLeNet Xeon 6766E 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E EPYC 9654 2P Xeon 6780E EPYC 9684X 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon Platinum 8592+ 2P Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Max 9468 2P Xeon Platinum 8380 2P EPYC 9654 Xeon Platinum 8490H 80 160 240 320 400 SE +/- 2.29, N = 3 SE +/- 1.18, N = 3 SE +/- 0.21, N = 3 SE +/- 0.29, N = 3 SE +/- 2.41, N = 3 SE +/- 0.64, N = 3 SE +/- 2.47, N = 3 SE +/- 0.44, N = 3 SE +/- 0.30, N = 3 SE +/- 0.49, N = 3 SE +/- 0.21, N = 3 SE +/- 2.38, N = 3 SE +/- 3.84, N = 4 SE +/- 1.12, N = 3 SE +/- 1.66, N = 3 SE +/- 2.37, N = 3 SE +/- 1.94, N = 3 SE +/- 0.83, N = 3 SE +/- 3.52, N = 5 SE +/- 1.42, N = 3 SE +/- 4.22, N = 3 SE +/- 1.62, N = 3 168.10 176.00 190.80 214.14 227.22 232.51 248.03 256.79 276.93 282.50 291.37 308.95 314.67 319.76 330.26 331.76 333.73 335.58 341.51 347.72 354.59 380.14
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: GoogLeNet EPYC 9754 2P EPYC 9684X 2P EPYC 9654 2P Xeon 6766E 2P Xeon Max 9480 2P Xeon 6780E 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon 6780E Xeon Platinum 8380 EPYC 9684X Xeon 6766E Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.5164 1.0328 1.5492 2.0656 2.582 0.502 0.503 0.513 0.550 0.553 0.565 0.606 0.633 0.683 0.853 1.142 1.153 1.240 1.261 1.274 1.360 1.378 1.411 1.568 1.603 2.169 2.295
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 207.32 / Avg: 563.45 / Max: 671.04 Min: 188.75 / Avg: 558.65 / Max: 667.23 Min: 157.05 / Avg: 524.23 / Max: 643.88 Min: 65.57 / Avg: 493.46 / Max: 594.88 Min: 60.41 / Avg: 443.22 / Max: 530.84 Min: 83.13 / Avg: 426.33 / Max: 534.67 Min: 98.08 / Avg: 407.6 / Max: 516.03 Min: 41.18 / Avg: 350.5 / Max: 413.71 Min: 105.79 / Avg: 337.98 / Max: 420.56 Min: 104.39 / Avg: 305.84 / Max: 369.61 Min: 77.16 / Avg: 292.25 / Max: 352.1 Min: 76.86 / Avg: 291.07 / Max: 351.95 Min: 60.91 / Avg: 275.93 / Max: 349.1 Min: 33.26 / Avg: 259.15 / Max: 327.64 Min: 33.87 / Avg: 226.63 / Max: 286.57 Min: 26.86 / Avg: 226.08 / Max: 291.32 Min: 52.71 / Avg: 224.1 / Max: 274.4 Min: 21.15 / Avg: 196.33 / Max: 257.11 Min: 43.56 / Avg: 187.52 / Max: 236.56 Min: 43.67 / Avg: 157.46 / Max: 196.46 Min: 19.2 / Avg: 127.66 / Max: 158.33 Min: 17.15 / Avg: 111.89 / Max: 138.4
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 Xeon 6766E 2P Xeon 6766E Xeon Platinum 8380 2P EPYC 8534PN Xeon 6780E 2P Xeon 6780E Xeon Max 9468 EPYC 8534P Xeon Max 9480 EPYC 9754 2P EPYC 9754 Xeon Platinum 8592+ Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X 600M 1200M 1800M 2400M 3000M SE +/- 4885465.97, N = 3 SE +/- 4223873.95, N = 3 SE +/- 1953913.45, N = 3 SE +/- 25737283.81, N = 3 SE +/- 7776531.65, N = 3 SE +/- 7523814.04, N = 3 SE +/- 1361779.88, N = 3 SE +/- 2629533.12, N = 3 SE +/- 4914717.13, N = 3 SE +/- 5493127.02, N = 3 SE +/- 17457503.96, N = 3 SE +/- 8567444.84, N = 3 SE +/- 11426868.92, N = 3 SE +/- 27382304.50, N = 5 SE +/- 28812627.44, N = 4 SE +/- 7076957.92, N = 3 SE +/- 32405829.38, N = 3 SE +/- 28500058.48, N = 3 SE +/- 10590929.03, N = 3 SE +/- 8732315.46, N = 3 SE +/- 3786085.64, N = 3 SE +/- 8476044.68, N = 3 1469166667 1852366667 1906266667 1999266667 2026333333 2036733333 2099033333 2138766667 2186833333 2308966667 2374766667 2444933333 2475500000 2491340000 2494050000 2539200000 2620066667 2655500000 2730233333 2772800000 2859833333 2862000000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 EPYC 9684X 2P Xeon Max 9468 EPYC 9654 2P Xeon Max 9480 Xeon Platinum 8592+ EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 4M 8M 12M 16M 20M 3870621.21 3917514.64 4681614.53 4994066.82 5119414.53 5987302.63 6245758.05 6748464.67 6982683.34 7252530.07 8044246.29 8048978.36 8050132.03 8820935.85 9063033.04 9250164.53 10813033.93 12777153.28 12897729.09 14237235.02 16817799.69 18884627.20
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ EPYC 9754 2P EPYC 9654 Xeon Platinum 8380 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 206.33 / Avg: 643.65 / Max: 732.46 Min: 203.4 / Avg: 636.64 / Max: 709.85 Min: 154.62 / Avg: 531.73 / Max: 660.07 Min: 67.62 / Avg: 511.79 / Max: 675.09 Min: 64 / Avg: 443.95 / Max: 498.34 Min: 101.13 / Avg: 427.05 / Max: 542.12 Min: 54.92 / Avg: 391 / Max: 447.88 Min: 76.69 / Avg: 318.37 / Max: 376.42 Min: 74.72 / Avg: 316.93 / Max: 377.16 Min: 60.17 / Avg: 315.42 / Max: 375.58 Min: 32.57 / Avg: 309.4 / Max: 348.95 Min: 27.41 / Avg: 307.74 / Max: 373.74 Min: 37.21 / Avg: 295.04 / Max: 331.11 Min: 27.79 / Avg: 264.48 / Max: 300.86 Min: 52.59 / Avg: 245.38 / Max: 291.79 Min: 107.02 / Avg: 230.9 / Max: 255.6 Min: 104.16 / Avg: 204.39 / Max: 225.35 Min: 18.99 / Avg: 191.35 / Max: 215.83 Min: 43.55 / Avg: 162.74 / Max: 182.74 Min: 43.66 / Avg: 133.68 / Max: 150 Min: 17.61 / Avg: 130.03 / Max: 147.65 Min: 16.16 / Avg: 107.3 / Max: 126.15
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 512 Xeon Platinum 8380 Xeon 6766E 2P Xeon 6766E EPYC 8534PN Xeon 6780E 2P Xeon 6780E Xeon Max 9468 EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9654 2P Xeon Max 9480 2P EPYC 9754 2P EPYC 9684X EPYC 9754 EPYC 9684X 2P Xeon Platinum 8592+ 2P 300M 600M 900M 1200M 1500M SE +/- 912164.70, N = 3 SE +/- 1072572.19, N = 3 SE +/- 305632.31, N = 3 SE +/- 431058.13, N = 3 SE +/- 866544.86, N = 3 SE +/- 287923.60, N = 3 SE +/- 681281.47, N = 3 SE +/- 390953.25, N = 3 SE +/- 1345523.44, N = 3 SE +/- 1740596.96, N = 3 SE +/- 8061118.62, N = 3 SE +/- 11560043.25, N = 5 SE +/- 6842108.19, N = 3 SE +/- 2313246.88, N = 3 SE +/- 1047748.91, N = 3 SE +/- 2338327.99, N = 3 SE +/- 2123152.79, N = 3 SE +/- 503322.30, N = 3 SE +/- 2412697.89, N = 3 SE +/- 814452.78, N = 3 SE +/- 3901424.24, N = 3 SE +/- 4790383.89, N = 3 539226667 707053333 719626667 731756667 777940000 796340000 800186667 809916667 882200000 918566667 981090000 1091460000 1126466667 1152933333 1158166667 1199966667 1206066667 1349800000 1368733333 1369800000 1394733333 1493833333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 512 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8592+ 2P Xeon 6780E 2P Xeon Max 9468 Xeon 6766E 2P Xeon Max 9480 EPYC 9684X 2P Xeon Platinum 8490H EPYC 9654 2P Xeon 6780E Xeon 6766E EPYC 9754 2P Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 1.4M 2.8M 4.2M 5.6M 7M 1702250.87 1899608.97 1966021.92 2021740.47 2212405.84 2443783.02 2466244.28 2528910.04 2621658.59 2800439.16 2805690.78 2929507.99 2957086.75 3117578.50 3673478.12 3727692.53 3740373.11 3778092.65 4367851.07 5183635.11 5867538.62 6364836.35
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9684X EPYC 9754 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 197.48 / Avg: 641.19 / Max: 750.61 Min: 206.37 / Avg: 634.9 / Max: 748.44 Min: 70.15 / Avg: 611.28 / Max: 739.63 Min: 168.69 / Avg: 572.97 / Max: 696.31 Min: 65.97 / Avg: 497.11 / Max: 585.32 Min: 102.29 / Avg: 485.27 / Max: 581.46 Min: 53.51 / Avg: 405.79 / Max: 476.68 Min: 32.21 / Avg: 362.28 / Max: 409.42 Min: 40.86 / Avg: 362.1 / Max: 421.05 Min: 77.21 / Avg: 316.42 / Max: 377.29 Min: 107.89 / Avg: 315.44 / Max: 358.75 Min: 75.73 / Avg: 315.02 / Max: 376.2 Min: 60 / Avg: 313.56 / Max: 376 Min: 27.09 / Avg: 308.24 / Max: 376.57 Min: 104.69 / Avg: 269.7 / Max: 304.35 Min: 26.08 / Avg: 265.16 / Max: 303.52 Min: 21.47 / Avg: 264.25 / Max: 302.73 Min: 43.62 / Avg: 255.44 / Max: 293.66 Min: 52.09 / Avg: 243.73 / Max: 291.23 Min: 43.64 / Avg: 195.9 / Max: 223.9 Min: 18.57 / Avg: 138.03 / Max: 156.97 Min: 16.09 / Avg: 114.97 / Max: 130.99
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 512 Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon 6766E Xeon 6780E Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9654 Xeon 6780E 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P EPYC 9754 2P EPYC 9754 Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P 500M 1000M 1500M 2000M 2500M SE +/- 4629652.01, N = 3 SE +/- 170391.71, N = 3 SE +/- 776881.23, N = 3 SE +/- 569766.03, N = 3 SE +/- 320537.74, N = 3 SE +/- 409267.64, N = 3 SE +/- 740202.67, N = 3 SE +/- 1722723.94, N = 3 SE +/- 11053858.05, N = 3 SE +/- 240370.09, N = 3 SE +/- 2198737.01, N = 3 SE +/- 520683.31, N = 3 SE +/- 6411708.04, N = 3 SE +/- 4238841.56, N = 3 SE +/- 6728628.72, N = 3 SE +/- 2676440.42, N = 3 SE +/- 5630373.98, N = 3 SE +/- 1650252.51, N = 3 SE +/- 1300000.00, N = 3 SE +/- 14465476.14, N = 3 SE +/- 11753202.87, N = 3 SE +/- 14870701.99, N = 3 542606667 741740000 821013333 838530000 848376667 940270000 944550000 1020833333 1061033333 1178766667 1306733333 1362166667 1437100000 1444066667 1518933333 1570400000 1616966667 1734800000 1744700000 2027000000 2129533333 2394333333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 512 Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon 6780E EPYC 9684X 2P Xeon Platinum 8592+ Xeon 6766E EPYC 9654 2P EPYC 9684X EPYC 9754 2P EPYC 9654 EPYC 8534P EPYC 9754 EPYC 8534PN 1.4M 2.8M 4.2M 5.6M 7M 2190947.55 2257184.32 2269719.80 2388645.74 2571656.77 2666847.49 2808259.47 2982249.17 3182607.79 3267678.46 3272343.49 3349035.56 3603186.16 3805850.46 3974344.33 4001237.14 4387111.54 4657018.09 4853033.94 5998206.24 6413920.52 6532499.05
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9754 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 67.21 / Avg: 664.5 / Max: 779.27 Min: 210.59 / Avg: 636.23 / Max: 755.25 Min: 198.99 / Avg: 635.9 / Max: 752.9 Min: 157.59 / Avg: 628.76 / Max: 754.2 Min: 70.53 / Avg: 619.43 / Max: 752.7 Min: 53.43 / Avg: 532.22 / Max: 613.02 Min: 109.82 / Avg: 511.74 / Max: 621.27 Min: 104.84 / Avg: 484.28 / Max: 583.22 Min: 108.01 / Avg: 410.59 / Max: 495.66 Min: 40.06 / Avg: 372.51 / Max: 431.46 Min: 35.59 / Avg: 357.96 / Max: 411.45 Min: 77.34 / Avg: 316.72 / Max: 376.86 Min: 74.44 / Avg: 314.43 / Max: 376.72 Min: 60.01 / Avg: 312.4 / Max: 376.93 Min: 25.3 / Avg: 309.72 / Max: 376.79 Min: 43.73 / Avg: 280.76 / Max: 332.63 Min: 29.69 / Avg: 280.68 / Max: 320.8 Min: 20.69 / Avg: 272.02 / Max: 314.58 Min: 53.55 / Avg: 240.39 / Max: 291.06 Min: 43.63 / Avg: 213.46 / Max: 250.49 Min: 17.86 / Avg: 136.88 / Max: 157.55 Min: 17.93 / Avg: 113.55 / Max: 130.59
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: bcrypt Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H 2P Xeon 6766E EPYC 9684X Xeon Platinum 8592+ 2P Xeon 6780E EPYC 9754 EPYC 9654 2P Xeon 6766E 2P EPYC 9684X 2P Xeon 6780E 2P EPYC 9754 2P 90K 180K 270K 360K 450K SE +/- 6.33, N = 3 SE +/- 8.84, N = 3 SE +/- 8.67, N = 3 SE +/- 0.00, N = 3 SE +/- 10.67, N = 3 SE +/- 22.28, N = 3 SE +/- 46.28, N = 3 SE +/- 12.67, N = 3 SE +/- 866.68, N = 3 SE +/- 576.80, N = 3 SE +/- 20.00, N = 3 SE +/- 292.24, N = 3 SE +/- 32.84, N = 3 SE +/- 154.46, N = 3 SE +/- 288.38, N = 3 SE +/- 87.49, N = 3 SE +/- 1.33, N = 3 SE +/- 710.46, N = 3 SE +/- 801.76, N = 3 SE +/- 1315.55, N = 3 SE +/- 2096.39, N = 3 SE +/- 4958.68, N = 4 56939 67875 79144 93472 94551 102222 105781 113219 133866 155959 166541 183603 190058 192898 206778 211311 220188 320527 363133 376268 402275 412723 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Real C/S Per Watt
OpenBenchmarking.org Real C/S Per Watt, More Is Better John The Ripper 2023.03.14 Test: bcrypt Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 9754 2P Xeon 6780E 2P Xeon 6780E EPYC 8534P EPYC 9754 Xeon 6766E 2P Xeon 6766E EPYC 8534PN 200 400 600 800 1000 231.51 233.71 241.56 256.35 256.68 273.70 292.69 305.82 334.53 342.68 523.96 531.63 573.89 606.47 705.60 712.79 746.76 749.17 759.60 816.03 885.93 920.41
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon Platinum 8380 2P Xeon Max 9480 EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9468 2P Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon 6766E Xeon Max 9480 2P Xeon 6780E 2P Xeon 6780E EPYC 9654 EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9754 EPYC 9684X EPYC 9684X 2P 1000M 2000M 3000M 4000M 5000M SE +/- 1549551.91, N = 3 SE +/- 2030052.00, N = 3 SE +/- 6398003.16, N = 3 SE +/- 11686221.71, N = 3 SE +/- 3119294.79, N = 3 SE +/- 3527510.93, N = 3 SE +/- 3116800.35, N = 3 SE +/- 5260228.13, N = 3 SE +/- 25888414.40, N = 3 SE +/- 2709448.49, N = 3 SE +/- 13655808.69, N = 3 SE +/- 6887912.12, N = 3 SE +/- 14772609.79, N = 3 SE +/- 13354940.83, N = 3 SE +/- 1909915.65, N = 3 SE +/- 20120967.50, N = 3 SE +/- 4098915.85, N = 3 SE +/- 51282832.98, N = 4 SE +/- 14606429.33, N = 3 SE +/- 18691531.06, N = 3 SE +/- 6778479.02, N = 3 SE +/- 11892621.43, N = 3 1554666667 2670033333 2687066667 2689033333 2972400000 2982800000 3181266667 3503200000 3596400000 3712133333 3723666667 3736300000 3896500000 4068666667 4136766667 4256300000 4280933333 4450525000 4626566667 4714500000 4755333333 4759366667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X 2P Xeon Platinum 8490H EPYC 9654 2P Xeon Platinum 8592+ EPYC 9754 2P Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 5M 10M 15M 20M 25M 5516263.53 5639264.93 6058163.97 6364402.84 6447021.00 7209189.04 8437038.99 9312055.82 9563226.72 10089438.81 10089896.41 11273487.11 12234041.51 12284401.92 13085490.53 13110978.99 14722432.57 15275772.40 16705633.01 17916149.91 20620501.38 22733164.52
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon 6766E 2P EPYC 9754 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 195.26 / Avg: 643.18 / Max: 753.46 Min: 204.5 / Avg: 637.74 / Max: 753.77 Min: 69.61 / Avg: 617.34 / Max: 730.41 Min: 158.24 / Avg: 577.58 / Max: 700.7 Min: 60.6 / Avg: 497.67 / Max: 581.47 Min: 101.61 / Avg: 487.47 / Max: 581.03 Min: 57.66 / Avg: 424.28 / Max: 495.38 Min: 40.47 / Avg: 378.17 / Max: 438.15 Min: 35.08 / Avg: 363.41 / Max: 409.45 Min: 107.77 / Avg: 331.21 / Max: 370.24 Min: 79.18 / Avg: 319.2 / Max: 376.38 Min: 75.83 / Avg: 316.47 / Max: 376.18 Min: 32.16 / Avg: 315.31 / Max: 376.7 Min: 24.5 / Avg: 310.75 / Max: 376.14 Min: 29.04 / Avg: 289.1 / Max: 326.36 Min: 104.64 / Avg: 283.13 / Max: 314.71 Min: 21.64 / Avg: 282.21 / Max: 320.93 Min: 43.58 / Avg: 270.81 / Max: 310.28 Min: 51.05 / Avg: 244.28 / Max: 290.35 Min: 43.75 / Avg: 208.54 / Max: 241.22 Min: 17.85 / Avg: 144.65 / Max: 162.72 Min: 17.47 / Avg: 118.2 / Max: 136.58
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P EPYC 8534PN EPYC 8534P Xeon Platinum 8490H EPYC 9754 2P EPYC 9754 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9654 2P EPYC 9654 EPYC 9684X 2P EPYC 9684X 2 4 6 8 10 SE +/- 0.023, N = 3 SE +/- 0.002, N = 3 SE +/- 0.041, N = 3 SE +/- 0.003, N = 3 SE +/- 0.014, N = 3 SE +/- 0.014, N = 3 SE +/- 0.015, N = 3 SE +/- 0.042, N = 3 SE +/- 0.027, N = 3 SE +/- 0.047, N = 3 SE +/- 0.049, N = 3 SE +/- 0.015, N = 3 SE +/- 0.007, N = 3 SE +/- 0.030, N = 3 SE +/- 0.004, N = 3 SE +/- 0.024, N = 3 SE +/- 0.044, N = 3 SE +/- 0.005, N = 3 SE +/- 0.046, N = 3 SE +/- 0.019, N = 3 SE +/- 0.040, N = 3 SE +/- 0.021, N = 3 3.710 3.972 4.040 4.350 5.437 5.438 5.991 6.052 6.490 6.572 6.698 6.727 6.939 7.061 7.153 7.283 7.360 7.876 8.349 8.422 8.513 8.595 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P Xeon Platinum 8380 EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon 6780E Xeon 6766E EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.0205 0.041 0.0615 0.082 0.1025 0.013 0.013 0.018 0.021 0.022 0.027 0.027 0.027 0.028 0.029 0.031 0.032 0.033 0.034 0.040 0.054 0.055 0.056 0.060 0.067 0.084 0.091
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 2.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X Xeon 6780E 2P EPYC 9654 Xeon 6766E 2P EPYC 9754 EPYC 8534P Xeon 6780E EPYC 8534PN Xeon 6766E 110 220 330 440 550 Min: 198.73 / Avg: 457.13 / Max: 618.95 Min: 209.94 / Avg: 456.54 / Max: 621.56 Min: 168.49 / Avg: 378.27 / Max: 506.21 Min: 78.08 / Avg: 333.26 / Max: 452.51 Min: 64.63 / Avg: 294.39 / Max: 468.18 Min: 57.39 / Avg: 264.94 / Max: 394.93 Min: 97.29 / Avg: 264.19 / Max: 369.25 Min: 73.14 / Avg: 245.81 / Max: 351.66 Min: 73.83 / Avg: 242.37 / Max: 350.93 Min: 40.1 / Avg: 214.15 / Max: 316.2 Min: 59.43 / Avg: 204.79 / Max: 319.21 Min: 34.17 / Avg: 196.16 / Max: 355 Min: 52.81 / Avg: 173.53 / Max: 276.87 Min: 33.04 / Avg: 159.73 / Max: 314.08 Min: 105.45 / Avg: 146.79 / Max: 227.06 Min: 26.67 / Avg: 140.24 / Max: 261.59 Min: 104.17 / Avg: 135.78 / Max: 199.44 Min: 20.56 / Avg: 108.62 / Max: 213.33 Min: 16.63 / Avg: 82.61 / Max: 136.8 Min: 43.43 / Avg: 78.63 / Max: 157.97 Min: 15.18 / Avg: 74.03 / Max: 115.16 Min: 43.55 / Avg: 71.01 / Max: 131.44
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon 6766E Xeon Platinum 8490H Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon 6766E 2P Xeon Platinum 8490H 2P EPYC 9684X EPYC 9754 Xeon 6780E 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 50 100 150 200 250 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.35, N = 3 SE +/- 0.76, N = 3 SE +/- 0.89, N = 15 SE +/- 0.02, N = 4 SE +/- 0.22, N = 3 SE +/- 0.22, N = 4 SE +/- 0.11, N = 4 SE +/- 0.07, N = 4 SE +/- 0.09, N = 3 SE +/- 0.29, N = 4 SE +/- 1.58, N = 15 SE +/- 3.26, N = 12 SE +/- 1.72, N = 15 47.64 63.34 64.33 64.96 71.83 76.53 79.38 83.73 84.80 97.19 104.84 112.72 113.28 125.11 132.28 133.48 133.93 136.22 173.22 175.60 200.16 210.44
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon 6766E 2P EPYC 8534P Xeon 6780E 2P EPYC 9654 EPYC 8534PN EPYC 9684X Xeon 6780E Xeon 6766E EPYC 9754 2P EPYC 9754 0.2201 0.4402 0.6603 0.8804 1.1005 0.222 0.240 0.261 0.263 0.272 0.291 0.320 0.368 0.523 0.575 0.579 0.602 0.635 0.642 0.643 0.693 0.713 0.716 0.719 0.746 0.759 0.978
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 4.3 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 193.13 / Avg: 472.12 / Max: 755.04 Min: 187.33 / Avg: 469.55 / Max: 757.04 Min: 164.62 / Avg: 413.97 / Max: 758.06 Min: 65.49 / Avg: 349.82 / Max: 819.75 Min: 101.28 / Avg: 312.13 / Max: 580.75 Min: 56.83 / Avg: 305.41 / Max: 649.39 Min: 66.3 / Avg: 299.17 / Max: 755.1 Min: 36.73 / Avg: 263.84 / Max: 656.51 Min: 73.93 / Avg: 247.01 / Max: 377.15 Min: 86.41 / Avg: 246.7 / Max: 376.83 Min: 61.45 / Avg: 215.69 / Max: 377.02 Min: 106.69 / Avg: 211.77 / Max: 566.07 Min: 104.6 / Avg: 197.13 / Max: 492.74 Min: 32.74 / Avg: 186.36 / Max: 410.63 Min: 26.36 / Avg: 185.86 / Max: 375.76 Min: 54.43 / Avg: 182.65 / Max: 290.73 Min: 28.7 / Avg: 163.54 / Max: 333.81 Min: 19.95 / Avg: 136.96 / Max: 327.05 Min: 43.49 / Avg: 116.43 / Max: 260.73 Min: 43.56 / Avg: 102.53 / Max: 218.97 Min: 17.71 / Avg: 100.16 / Max: 169.93 Min: 17.83 / Avg: 88.8 / Max: 143.53
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H 2P Xeon 6766E EPYC 9684X Xeon Platinum 8592+ 2P Xeon 6780E EPYC 9754 EPYC 9654 2P Xeon 6766E 2P EPYC 9684X 2P Xeon 6780E 2P EPYC 9754 2P 90K 180K 270K 360K 450K SE +/- 6.33, N = 3 SE +/- 17.33, N = 3 SE +/- 8.67, N = 3 SE +/- 20.54, N = 3 SE +/- 11.39, N = 3 SE +/- 13.72, N = 3 SE +/- 79.75, N = 3 SE +/- 14.62, N = 3 SE +/- 116.69, N = 3 SE +/- 169.28, N = 3 SE +/- 38.33, N = 3 SE +/- 348.45, N = 3 SE +/- 174.44, N = 3 SE +/- 98.33, N = 3 SE +/- 649.08, N = 3 SE +/- 14.67, N = 3 SE +/- 1.33, N = 3 SE +/- 3455.48, N = 3 SE +/- 353.58, N = 3 SE +/- 454.86, N = 3 SE +/- 482.17, N = 3 SE +/- 2397.15, N = 3 56939 67893 79152 93473 94513 102198 105831 113223 134562 156658 166541 183583 190209 192574 205499 211449 220188 316492 363300 374589 404739 415412 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Real C/S Per Watt
OpenBenchmarking.org Real C/S Per Watt, More Is Better John The Ripper 2023.03.14 Test: Blowfish Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 9754 2P Xeon 6780E 2P Xeon 6780E EPYC 8534P EPYC 9754 EPYC 8534PN Xeon 6766E 2P Xeon 6766E 200 400 600 800 1000 231.64 233.58 243.04 257.14 258.82 274.74 291.56 305.95 332.35 339.84 527.64 531.08 568.71 605.49 711.80 720.56 747.26 753.26 757.83 805.43 818.19 885.52
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better John The Ripper 2023.03.14 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P EPYC 9754 2P Xeon 6780E 2P EPYC 9654 2P Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon 6766E 2P Full Xeon 6766E 2P EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9754 Xeon Max 9480 Xeon 6780E EPYC 9654 Xeon Max 9468 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 63.32 / Avg: 718.13 / Max: 821.91 Min: 161.87 / Avg: 629.66 / Max: 734.18 Min: 64.41 / Avg: 618.33 / Max: 750.74 Min: 196.84 / Avg: 607.6 / Max: 711.09 Min: 41.23 / Avg: 584.92 / Max: 678.42 Min: 109.68 / Avg: 564.37 / Max: 639.35 Min: 57.83 / Avg: 558.52 / Max: 635.56 Min: 194.9 / Avg: 554.18 / Max: 671.99 Min: 103.01 / Avg: 489.04 / Max: 579.68 Min: 107.82 / Avg: 445 / Max: 497.2 Min: 108.45 / Avg: 444.03 / Max: 499.02 Min: 34.3 / Avg: 362.84 / Max: 410.63 Min: 22.7 / Avg: 311.41 / Max: 377.71 Min: 56.54 / Avg: 309.17 / Max: 344.77 Min: 22.18 / Avg: 290.55 / Max: 334.66 Min: 71.78 / Avg: 289.17 / Max: 318.47 Min: 43.56 / Avg: 282.97 / Max: 322.03 Min: 30.41 / Avg: 275.05 / Max: 311.29 Min: 71.89 / Avg: 264.78 / Max: 291.9 Min: 52.31 / Avg: 243.76 / Max: 291.32 Min: 43.56 / Avg: 214.8 / Max: 240.98 Min: 18.94 / Avg: 136.45 / Max: 154.65 Min: 16.41 / Avg: 116.05 / Max: 133.89
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 EPYC 8534PN Xeon Max 9468 Xeon Platinum 8380 2P EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9754 Xeon 6766E 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9684X 2P 2000M 4000M 6000M 8000M 10000M SE +/- 2935605.18, N = 3 SE +/- 4481443.22, N = 3 SE +/- 4088330.28, N = 3 SE +/- 3572580.77, N = 3 SE +/- 1959875.28, N = 3 SE +/- 1976810.00, N = 3 SE +/- 5292237.50, N = 3 SE +/- 3555434.03, N = 3 SE +/- 8015887.00, N = 3 SE +/- 6906036.01, N = 3 SE +/- 17558125.69, N = 3 SE +/- 28453880.81, N = 3 SE +/- 2618735.91, N = 3 SE +/- 2331189.49, N = 3 SE +/- 8144527.82, N = 3 SE +/- 61971606.40, N = 3 SE +/- 8069352.17, N = 3 SE +/- 12739745.33, N = 3 SE +/- 28436830.58, N = 3 SE +/- 60380193.59, N = 3 SE +/- 30821331.00, N = 3 SE +/- 50144890.07, N = 3 1610466667 2793700000 2848933333 3037100000 3116933333 3222533333 3500833333 3806833333 4259433333 4714700000 4825133333 5036000000 5266466667 5361266667 5811900000 6284300000 6316266667 6401366667 6800900000 7411866667 7597566667 8012700000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Platinum 8592+ 2P Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X 2P Xeon Platinum 8592+ EPYC 9654 2P Xeon 6780E 2P Xeon 6766E 2P Xeon 6780E EPYC 9684X EPYC 9754 2P EPYC 9654 Xeon 6766E EPYC 8534P EPYC 9754 EPYC 8534PN 5M 10M 15M 20M 25M 6213581.60 6601048.41 7597124.43 7871904.97 8419315.63 8954185.90 10144378.39 10156047.28 11085612.93 11934150.92 12268330.08 12864302.70 13780225.29 15666459.94 15942975.31 16030850.56 16347865.87 17475938.77 18991058.67 21345877.02 22424548.82 23457026.73
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor EPYC 9684X 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P Xeon 6766E 2P EPYC 9754 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon 6780E EPYC 9754 Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 62.88 / Avg: 671.41 / Max: 791.35 Min: 193.94 / Avg: 639.74 / Max: 752.86 Min: 155.13 / Avg: 636.78 / Max: 752.99 Min: 195.33 / Avg: 635.13 / Max: 752.27 Min: 68.73 / Avg: 619.49 / Max: 754.72 Min: 54.92 / Avg: 576.16 / Max: 661.98 Min: 108.43 / Avg: 551.34 / Max: 625.76 Min: 101.61 / Avg: 488.78 / Max: 580.58 Min: 106.08 / Avg: 434.11 / Max: 495.15 Min: 40.8 / Avg: 386.37 / Max: 445.76 Min: 35.02 / Avg: 362.54 / Max: 411.45 Min: 75.93 / Avg: 318.17 / Max: 376.27 Min: 75.49 / Avg: 317.3 / Max: 376.02 Min: 58.98 / Avg: 315.8 / Max: 377.13 Min: 24.86 / Avg: 310.3 / Max: 377.83 Min: 30.72 / Avg: 301.36 / Max: 345.8 Min: 43.65 / Avg: 295.72 / Max: 355.96 Min: 22.44 / Avg: 285.46 / Max: 328.97 Min: 52.71 / Avg: 243.97 / Max: 290.99 Min: 43.61 / Avg: 224.29 / Max: 267.77 Min: 17.88 / Avg: 146.02 / Max: 166.38 Min: 18.06 / Avg: 119.1 / Max: 135.86
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 32 Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon 6766E Xeon Max 9468 2P Xeon 6780E EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9754 2P EPYC 9754 Xeon 6766E 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9684X 2P 2000M 4000M 6000M 8000M 10000M SE +/- 1266666.67, N = 3 SE +/- 1320353.49, N = 3 SE +/- 1338323.99, N = 3 SE +/- 1928730.15, N = 3 SE +/- 1501110.70, N = 3 SE +/- 2516611.48, N = 3 SE +/- 4021608.30, N = 3 SE +/- 7369833.41, N = 3 SE +/- 821245.67, N = 3 SE +/- 2447674.63, N = 3 SE +/- 2601495.30, N = 3 SE +/- 1419311.26, N = 3 SE +/- 895048.11, N = 3 SE +/- 11426625.83, N = 3 SE +/- 6711433.03, N = 3 SE +/- 10496401.50, N = 3 SE +/- 2936551.27, N = 3 SE +/- 3768731.00, N = 3 SE +/- 32054242.22, N = 3 SE +/- 46730658.51, N = 3 SE +/- 20501246.57, N = 3 SE +/- 34610274.65, N = 3 1823566667 2381800000 2769066667 2789600000 3062200000 3167200000 3243800000 3572233333 4301166667 4670966667 4799133333 5271933333 5367033333 5862466667 6077300000 6116566667 6439000000 6588200000 6821533333 7513333333 7546366667 7935266667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9684X EPYC 9754 2P Xeon 6766E 2P EPYC 9654 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 9754 EPYC 8534PN 5M 10M 15M 20M 25M 7263532.04 7299110.00 7475059.61 8335236.32 8576477.66 9061082.03 9661394.05 9752693.41 10180344.31 10249944.70 12478169.67 13431732.69 15839180.07 16171511.91 16713460.67 17638157.23 17844515.21 18436155.38 21409914.84 21992105.60 22727990.09 23304528.15
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 2P EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9480 EPYC 9654 EPYC 9754 Xeon Max 9468 Xeon 6780E Xeon Platinum 8380 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 204.52 / Avg: 643.9 / Max: 752.56 Min: 186.6 / Avg: 643.07 / Max: 754.55 Min: 65.54 / Avg: 635.93 / Max: 742.68 Min: 160.12 / Avg: 633.09 / Max: 754.38 Min: 70.49 / Avg: 623.14 / Max: 733.57 Min: 59.09 / Avg: 559.37 / Max: 644.46 Min: 101.34 / Avg: 489.41 / Max: 581.58 Min: 107.72 / Avg: 476.44 / Max: 538.02 Min: 104.79 / Avg: 386.75 / Max: 438.06 Min: 40.61 / Avg: 385.26 / Max: 440.96 Min: 34.34 / Avg: 362.52 / Max: 411.45 Min: 59.61 / Avg: 316.47 / Max: 377.01 Min: 25.92 / Avg: 311.11 / Max: 357.53 Min: 78.49 / Avg: 305.6 / Max: 341.63 Min: 30.54 / Avg: 295.44 / Max: 336.72 Min: 21.58 / Avg: 289.87 / Max: 330.19 Min: 74.86 / Avg: 277.71 / Max: 312.01 Min: 43.63 / Avg: 260.31 / Max: 300.33 Min: 52.43 / Avg: 243.95 / Max: 291.4 Min: 43.68 / Avg: 200.9 / Max: 230.57 Min: 18.82 / Avg: 139.24 / Max: 159.66 Min: 16.68 / Avg: 119.7 / Max: 139.58
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 32 Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8380 2P EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P Xeon 6766E 2P Xeon 6766E EPYC 9754 EPYC 9754 2P Xeon 6780E 2P EPYC 9654 EPYC 9654 2P Xeon 6780E EPYC 9684X EPYC 9684X 2P 900M 1800M 2700M 3600M 4500M SE +/- 3178574.10, N = 3 SE +/- 400000.00, N = 3 SE +/- 1342054.81, N = 3 SE +/- 2003607.86, N = 3 SE +/- 3557152.42, N = 3 SE +/- 3138116.92, N = 3 SE +/- 2236316.42, N = 3 SE +/- 1858314.65, N = 3 SE +/- 4598671.31, N = 3 SE +/- 2403700.85, N = 3 SE +/- 13813198.20, N = 3 SE +/- 26633124.74, N = 3 SE +/- 3194265.70, N = 3 SE +/- 920748.49, N = 3 SE +/- 4056818.68, N = 3 SE +/- 384418.75, N = 3 SE +/- 517472.49, N = 3 SE +/- 2714365.08, N = 3 SE +/- 3186603.90, N = 3 SE +/- 2023198.79, N = 3 SE +/- 841295.30, N = 3 SE +/- 4250882.26, N = 3 1797400000 2351900000 2739633333 2767933333 3044700000 3047066667 3148233333 3200600000 3254033333 3337066667 3520766667 3558600000 3607900000 3671966667 3791566667 3794133333 4021033333 4032733333 4063333333 4102200000 4353533333 4407900000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 Xeon Max 9468 EPYC 9684X 2P Xeon Max 9480 EPYC 9654 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 2P EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 5M 10M 15M 20M 25M 5098423.00 5205818.86 6260399.40 6353287.78 6918246.02 7357841.69 8304651.14 8852490.97 8871933.76 9803609.24 10135010.79 10144782.58 10891038.63 11993608.96 13659351.74 14282136.05 14392112.20 15541749.24 17724724.88 20349128.58 21706213.46 23574098.60
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9684X EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Max 9480 Xeon 6780E 2P Xeon Max 9468 EPYC 9654 Xeon 6766E 2P Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 196.59 / Avg: 641.03 / Max: 736.11 Min: 189.62 / Avg: 638.24 / Max: 714.51 Min: 75.15 / Avg: 554.16 / Max: 686.41 Min: 144.18 / Avg: 514.38 / Max: 660.61 Min: 66.83 / Avg: 497.93 / Max: 572.66 Min: 104.18 / Avg: 486.34 / Max: 574.85 Min: 56.36 / Avg: 414.47 / Max: 483.6 Min: 35.34 / Avg: 362.99 / Max: 409.42 Min: 40.25 / Avg: 348.37 / Max: 393.82 Min: 62.65 / Avg: 315.8 / Max: 377.95 Min: 27.32 / Avg: 310.33 / Max: 359.1 Min: 80.13 / Avg: 308.8 / Max: 366.56 Min: 107.24 / Avg: 294.38 / Max: 328.07 Min: 74.4 / Avg: 283.2 / Max: 376.87 Min: 28.95 / Avg: 280.2 / Max: 318.02 Min: 104.22 / Avg: 252.62 / Max: 279.84 Min: 52.85 / Avg: 244.28 / Max: 291.62 Min: 21.67 / Avg: 243.96 / Max: 276.65 Min: 43.44 / Avg: 231.44 / Max: 260.99 Min: 43.66 / Avg: 180.45 / Max: 204.69 Min: 16.53 / Avg: 140.38 / Max: 157.26 Min: 16.54 / Avg: 117.41 / Max: 138.28
Google SynthMark SynthMark is a cross platform tool for benchmarking CPU performance under a variety of real-time audio workloads. It uses a polyphonic synthesizer model to provide standardized tests for latency, jitter and computational throughput. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Voices, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 Xeon 6766E Xeon 6766E 2P Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9754 2P EPYC 8534P EPYC 9754 EPYC 8534PN Xeon Max 9468 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9684X EPYC 9654 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 200 400 600 800 1000 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.06, N = 3 SE +/- 0.18, N = 3 SE +/- 0.53, N = 3 SE +/- 7.09, N = 3 SE +/- 0.88, N = 3 SE +/- 0.14, N = 3 SE +/- 0.45, N = 3 SE +/- 0.60, N = 3 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 SE +/- 0.22, N = 3 SE +/- 0.24, N = 3 SE +/- 0.48, N = 3 SE +/- 1.51, N = 3 SE +/- 0.56, N = 3 SE +/- 0.72, N = 3 SE +/- 0.69, N = 3 SE +/- 0.55, N = 3 SE +/- 0.38, N = 3 SE +/- 0.13, N = 3 494.05 494.38 538.91 540.24 548.36 555.60 655.05 655.24 655.80 656.25 710.92 711.10 711.38 712.01 712.09 712.70 782.32 783.20 783.42 783.78 799.49 799.72 1. (CXX) g++ options: -lm -lpthread -std=c++11 -Ofast
Voices Per Watt
OpenBenchmarking.org Voices Per Watt, More Is Better Google SynthMark 20201109 Test: VoiceMark_100 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8380 Xeon Max 9468 EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 3 6 9 12 15 2.322 2.567 2.986 3.044 3.121 3.246 3.607 3.610 4.640 4.969 5.891 5.954 6.250 7.582 7.626 7.777 8.699 9.006 11.291 12.340 12.984 13.295
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Google SynthMark 20201109 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 70 140 210 280 350 Min: 203.32 / Avg: 306.14 / Max: 413.85 Min: 201.92 / Avg: 277.45 / Max: 348.85 Min: 77.31 / Avg: 256.19 / Max: 292.81 Min: 61.62 / Avg: 241.28 / Max: 266.15 Min: 172.36 / Avg: 234.1 / Max: 329.35 Min: 57.99 / Avg: 216.87 / Max: 238.45 Min: 99.91 / Avg: 183.65 / Max: 205.87 Min: 40.35 / Avg: 181.43 / Max: 200.97 Min: 84.65 / Avg: 120.87 / Max: 129.59 Min: 75.06 / Avg: 113.78 / Max: 122.61 Min: 106.8 / Avg: 108.46 / Max: 112.7 Min: 104.37 / Avg: 106.55 / Max: 109.25 Min: 33.97 / Avg: 103.33 / Max: 113.89 Min: 33.54 / Avg: 102.83 / Max: 128.91 Min: 63.55 / Avg: 93.65 / Max: 130.75 Min: 52.55 / Avg: 93.31 / Max: 100.6 Min: 28.69 / Avg: 90.1 / Max: 99.51 Min: 21.02 / Avg: 72.82 / Max: 80.06 Min: 17.96 / Avg: 50.47 / Max: 55.88 Min: 16.18 / Avg: 49.36 / Max: 54.66 Min: 43.34 / Avg: 43.78 / Max: 45.89 Min: 43.51 / Avg: 43.76 / Max: 45.51
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P EPYC 8534PN Xeon 6766E 2P Xeon 6766E EPYC 8534P Xeon Platinum 8490H EPYC 9754 2P EPYC 9754 Xeon Platinum 8592+ Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon 6780E Xeon Max 9480 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9654 EPYC 9684X 500M 1000M 1500M 2000M 2500M SE +/- 3209534.41, N = 3 SE +/- 688799.28, N = 3 SE +/- 692820.32, N = 3 SE +/- 9052685.30, N = 3 SE +/- 3256958.36, N = 3 SE +/- 1003881.36, N = 3 SE +/- 1379613.47, N = 3 SE +/- 3090487.20, N = 3 SE +/- 3167192.94, N = 3 SE +/- 1462114.15, N = 3 SE +/- 1550627.11, N = 3 SE +/- 27191440.65, N = 3 SE +/- 2206304.10, N = 3 SE +/- 4028647.42, N = 3 SE +/- 3300505.01, N = 3 SE +/- 808290.38, N = 3 SE +/- 3017909.50, N = 3 SE +/- 17236814.61, N = 3 SE +/- 2510644.01, N = 3 SE +/- 1567730.14, N = 3 SE +/- 2810891.52, N = 3 SE +/- 3000185.18, N = 3 1561766667 1640266667 1679700000 1731166667 1776866667 1780533333 1841400000 1871333333 1890566667 1894966667 1898766667 1927766667 1963233333 1989300000 2025000000 2057300000 2090466667 2154633333 2279300000 2282066667 2282766667 2287466667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 64 - Buffer Length: 256 - Filter Length: 32 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9754 2P EPYC 9684X Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 4M 8M 12M 16M 20M 3308597.89 3387722.73 3966847.18 4217240.97 4527054.56 5779445.49 6304024.25 6395094.29 6609424.93 6685402.04 6720931.25 6722664.60 7114576.18 8884551.10 9390076.73 9419289.56 9937920.60 11984070.91 14358014.80 14706486.76 15528502.68 17627091.46
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9754 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 EPYC 9654 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 120 240 360 480 600 Min: 197.41 / Avg: 617.07 / Max: 678.02 Min: 200.67 / Avg: 593.37 / Max: 651.17 Min: 152.44 / Avg: 510.48 / Max: 610.23 Min: 75.17 / Avg: 475.95 / Max: 586.43 Min: 100.23 / Avg: 410.5 / Max: 516.01 Min: 64.31 / Avg: 394.38 / Max: 445.2 Min: 57.58 / Avg: 362 / Max: 403.93 Min: 27.76 / Avg: 286.83 / Max: 364.52 Min: 60.85 / Avg: 281.22 / Max: 356.43 Min: 38.6 / Avg: 266.35 / Max: 296.68 Min: 33.54 / Avg: 257.47 / Max: 292.35 Min: 74.71 / Avg: 254.14 / Max: 326.8 Min: 76.61 / Avg: 245.35 / Max: 268.44 Min: 49.48 / Avg: 244.21 / Max: 290.74 Min: 25.11 / Avg: 229.7 / Max: 257.97 Min: 105.02 / Avg: 211.19 / Max: 235.86 Min: 104.03 / Avg: 189.62 / Max: 209.49 Min: 20.46 / Avg: 158.44 / Max: 178.44 Min: 43.43 / Avg: 143.29 / Max: 159.65 Min: 15.76 / Avg: 127.25 / Max: 146.72 Min: 43.61 / Avg: 118.58 / Max: 131.69 Min: 15.81 / Avg: 100.8 / Max: 114.74
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 Xeon Platinum 8592+ Xeon Max 9468 Xeon Platinum 8380 2P Xeon 6766E Xeon Max 9480 Xeon 6780E Xeon Max 9468 2P EPYC 8534PN EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8490H EPYC 8534P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X 14 28 42 56 70 SE +/- 0.34, N = 15 SE +/- 0.43, N = 15 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 4 SE +/- 0.18, N = 4 SE +/- 0.01, N = 4 SE +/- 0.02, N = 4 SE +/- 0.06, N = 4 SE +/- 0.39, N = 4 SE +/- 0.06, N = 4 SE +/- 0.43, N = 15 SE +/- 0.38, N = 9 SE +/- 0.01, N = 4 SE +/- 0.08, N = 4 SE +/- 0.55, N = 5 SE +/- 0.16, N = 5 SE +/- 0.18, N = 5 SE +/- 0.50, N = 5 SE +/- 0.12, N = 5 SE +/- 0.13, N = 5 SE +/- 0.13, N = 5 27.33 28.43 30.17 35.10 39.56 40.69 40.73 40.82 44.44 44.75 44.92 46.00 46.25 49.42 50.04 53.44 53.66 54.46 54.88 55.05 62.02 62.70
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6780E 2P EPYC 9684X 2P Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8490H EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 0.1087 0.2174 0.3261 0.4348 0.5435 0.090 0.092 0.110 0.121 0.132 0.138 0.147 0.150 0.152 0.154 0.157 0.160 0.167 0.185 0.193 0.269 0.310 0.346 0.369 0.389 0.445 0.483
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9754 2P EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 110 220 330 440 550 Min: 191.29 / Avg: 503.31 / Max: 608.25 Min: 193.43 / Avg: 495.22 / Max: 603.09 Min: 161.1 / Avg: 454.5 / Max: 579.21 Min: 77.02 / Avg: 407.69 / Max: 581.55 Min: 103.41 / Avg: 370.67 / Max: 458.86 Min: 57.76 / Avg: 357.6 / Max: 478.64 Min: 52.01 / Avg: 320.69 / Max: 430.96 Min: 73.99 / Avg: 272.27 / Max: 334.62 Min: 76.83 / Avg: 268.38 / Max: 326.31 Min: 59.83 / Avg: 256.47 / Max: 330.75 Min: 39.54 / Avg: 249.19 / Max: 335.92 Min: 33.4 / Avg: 232.88 / Max: 324.16 Min: 27.1 / Avg: 218.83 / Max: 315.11 Min: 53.16 / Avg: 217.91 / Max: 258.49 Min: 28.57 / Avg: 200.36 / Max: 279.14 Min: 106.09 / Avg: 187.3 / Max: 229.82 Min: 104.1 / Avg: 174.26 / Max: 196.44 Min: 18.78 / Avg: 157.17 / Max: 216.69 Min: 43.47 / Avg: 120.53 / Max: 150.37 Min: 17.76 / Avg: 112.52 / Max: 149.73 Min: 43.61 / Avg: 104.71 / Max: 124.97 Min: 17.16 / Avg: 92.93 / Max: 127.1
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Junkshop - Compute: CPU-Only Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 Xeon 6766E 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 14 28 42 56 70 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.24, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.02, N = 4 SE +/- 0.08, N = 4 SE +/- 0.02, N = 4 61.22 42.85 39.17 38.86 35.96 35.82 33.20 32.08 29.06 26.49 24.99 23.45 21.15 21.02 18.70 18.65 18.31 17.70 16.89 12.87 11.47 11.21
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 208.58 / Avg: 605.47 / Max: 751.55 Min: 206.83 / Avg: 603.68 / Max: 753.22 Min: 169.62 / Avg: 575.47 / Max: 754.28 Min: 63.79 / Avg: 553.98 / Max: 822.05 Min: 77.61 / Avg: 545.55 / Max: 722.02 Min: 59.75 / Avg: 483.45 / Max: 681.8 Min: 105.08 / Avg: 471.81 / Max: 581.38 Min: 39.86 / Avg: 438.61 / Max: 691.32 Min: 107.64 / Avg: 397.69 / Max: 593.53 Min: 106.82 / Avg: 347.76 / Max: 500.93 Min: 75.79 / Avg: 322.02 / Max: 374.53 Min: 85.92 / Avg: 320.19 / Max: 376.39 Min: 35.12 / Avg: 316.57 / Max: 411.05 Min: 59.14 / Avg: 311.52 / Max: 376.21 Min: 24.83 / Avg: 303.23 / Max: 378.56 Min: 16.01 / Avg: 272.23 / Max: 337.39 Min: 22.09 / Avg: 255.66 / Max: 340.71 Min: 51.88 / Avg: 251.6 / Max: 290.8 Min: 43.63 / Avg: 235.7 / Max: 293.05 Min: 43.7 / Avg: 186.05 / Max: 225.88 Min: 18.72 / Avg: 148.28 / Max: 170.5 Min: 18.29 / Avg: 127.16 / Max: 145.93
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Fishy Cat - Compute: CPU-Only Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 8534PN Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 13 26 39 52 65 SE +/- 0.15, N = 3 SE +/- 0.17, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 SE +/- 0.27, N = 3 SE +/- 0.37, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 4 SE +/- 0.05, N = 4 SE +/- 0.02, N = 5 SE +/- 0.04, N = 5 59.15 42.78 38.48 38.04 34.83 34.35 31.91 30.75 29.55 26.52 23.17 21.45 20.15 19.13 18.36 17.29 16.58 16.52 15.16 11.25 10.16 9.71
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Platinum 8380 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 205.55 / Avg: 607.36 / Max: 752.78 Min: 211.08 / Avg: 602.46 / Max: 751.81 Min: 169.36 / Avg: 570.45 / Max: 755.96 Min: 67.56 / Avg: 561.28 / Max: 821.67 Min: 76.09 / Avg: 546.98 / Max: 735.92 Min: 60.34 / Avg: 491.93 / Max: 710.82 Min: 104.59 / Avg: 473.37 / Max: 583.21 Min: 42.38 / Avg: 447.74 / Max: 705.75 Min: 109.2 / Avg: 429.78 / Max: 624.43 Min: 106.69 / Avg: 350.36 / Max: 494.32 Min: 36.44 / Avg: 322.13 / Max: 410.23 Min: 74.34 / Avg: 321.04 / Max: 375.24 Min: 74.14 / Avg: 319.1 / Max: 376.73 Min: 59.73 / Avg: 313.33 / Max: 377.56 Min: 23.46 / Avg: 303.18 / Max: 371.62 Min: 30.77 / Avg: 277.68 / Max: 346.38 Min: 22.97 / Avg: 261.77 / Max: 349.11 Min: 53.1 / Avg: 251.93 / Max: 290.63 Min: 43.69 / Avg: 247.1 / Max: 308.06 Min: 43.64 / Avg: 193.48 / Max: 236.22 Min: 16.84 / Avg: 152.85 / Max: 176.56 Min: 16.69 / Avg: 126.35 / Max: 143.05
Appleseed Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.
Scene: Disney Material
EPYC 9684X 2P: The test run did not produce a result.
EPYC 9654 2P: The test run did not produce a result.
EPYC 9754 2P: The test run did not produce a result.
Xeon 6766E 2P: The test run did not produce a result.
Xeon 6780E 2P: The test run did not produce a result.
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: AlexNet Xeon 6766E Xeon 6766E 2P Xeon 6780E Xeon 6780E 2P EPYC 8534PN EPYC 9754 2P EPYC 8534P Xeon Platinum 8380 EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P EPYC 9684X Xeon Platinum 8380 2P EPYC 9754 Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H Xeon Platinum 8490H 2P 200 400 600 800 1000 SE +/- 0.70, N = 3 SE +/- 5.44, N = 15 SE +/- 0.97, N = 3 SE +/- 5.91, N = 15 SE +/- 0.16, N = 4 SE +/- 7.43, N = 15 SE +/- 0.45, N = 4 SE +/- 0.27, N = 4 SE +/- 8.87, N = 4 SE +/- 7.66, N = 5 SE +/- 6.22, N = 5 SE +/- 1.95, N = 5 SE +/- 2.31, N = 5 SE +/- 2.22, N = 5 SE +/- 1.37, N = 5 SE +/- 3.70, N = 5 SE +/- 2.99, N = 5 SE +/- 6.39, N = 13 SE +/- 7.35, N = 5 SE +/- 1.31, N = 5 SE +/- 0.51, N = 5 SE +/- 7.98, N = 5 443.74 464.80 482.06 520.01 617.03 658.97 673.42 690.09 727.77 738.31 819.89 841.68 852.36 858.84 868.54 904.36 924.80 932.59 940.40 942.19 969.62 996.47
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 64 - Model: AlexNet Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P Xeon 6780E Xeon Max 9468 Xeon 6766E Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8490H EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 2 4 6 8 10 1.740 1.794 1.857 1.898 1.919 2.065 2.236 2.269 2.404 2.677 3.051 3.341 3.355 3.374 3.481 4.145 4.332 4.375 5.439 6.238 6.508 6.664
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 196.31 / Avg: 491.23 / Max: 676.71 Min: 186.67 / Avg: 489.99 / Max: 671.14 Min: 156.12 / Avg: 439.21 / Max: 636.86 Min: 64.28 / Avg: 397.64 / Max: 581.36 Min: 76.02 / Avg: 357.25 / Max: 522.13 Min: 59.14 / Avg: 352.38 / Max: 512.39 Min: 99.68 / Avg: 337.77 / Max: 509.02 Min: 40.23 / Avg: 294.77 / Max: 430.69 Min: 107.28 / Avg: 289.41 / Max: 402.43 Min: 104.81 / Avg: 267.11 / Max: 360.8 Min: 75.5 / Avg: 252.6 / Max: 351.73 Min: 72.44 / Avg: 251.93 / Max: 351.73 Min: 58.85 / Avg: 221.64 / Max: 332.07 Min: 32.91 / Avg: 200.48 / Max: 302.35 Min: 53.17 / Avg: 198.24 / Max: 276.92 Min: 33.53 / Avg: 197.79 / Max: 292.33 Min: 27.88 / Avg: 173.22 / Max: 270.57 Min: 43.45 / Avg: 158.02 / Max: 214.1 Min: 21.07 / Avg: 148.26 / Max: 241.29 Min: 43.64 / Avg: 132.25 / Max: 173.77 Min: 17.62 / Avg: 103.47 / Max: 147.02 Min: 15.55 / Avg: 92.59 / Max: 128.11
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon 6766E 2P Xeon Max 9480 2P Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9754 EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 14 28 42 56 70 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.21, N = 3 SE +/- 0.07, N = 3 SE +/- 0.23, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 4 SE +/- 0.07, N = 4 SE +/- 0.01, N = 4 SE +/- 0.27, N = 4 SE +/- 0.52, N = 15 SE +/- 0.56, N = 5 SE +/- 0.40, N = 5 15.51 18.13 18.84 19.34 20.33 20.97 21.39 23.02 24.31 24.80 26.69 29.15 29.62 31.70 32.04 39.08 39.58 40.50 41.58 54.57 61.11 63.48 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon 6780E 2P EPYC 9684X 2P Xeon 6766E 2P EPYC 9684X EPYC 9654 2P EPYC 9754 2P Xeon 6780E EPYC 9654 Xeon 6766E EPYC 8534P EPYC 9754 EPYC 8534PN 0.0522 0.1044 0.1566 0.2088 0.261 0.050 0.053 0.054 0.065 0.065 0.066 0.066 0.080 0.082 0.090 0.130 0.135 0.135 0.148 0.151 0.169 0.172 0.181 0.185 0.200 0.207 0.232
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8380 EPYC 9654 Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 120 240 360 480 600 Min: 189.77 / Avg: 550.48 / Max: 652.57 Min: 209.31 / Avg: 533.47 / Max: 617.43 Min: 75.75 / Avg: 509.74 / Max: 682.24 Min: 168.08 / Avg: 490.42 / Max: 593.69 Min: 66.41 / Avg: 469.54 / Max: 685.47 Min: 56.07 / Avg: 404.28 / Max: 599.6 Min: 103.66 / Avg: 385.29 / Max: 444.98 Min: 38.26 / Avg: 323.31 / Max: 486.48 Min: 69.51 / Avg: 286.2 / Max: 325.03 Min: 77.93 / Avg: 280.57 / Max: 315.37 Min: 33.8 / Avg: 276.47 / Max: 362.01 Min: 34.18 / Avg: 273.99 / Max: 354.7 Min: 61.73 / Avg: 263.01 / Max: 306.52 Min: 106.92 / Avg: 243.13 / Max: 293.72 Min: 53 / Avg: 234.37 / Max: 263.04 Min: 26.12 / Avg: 219.12 / Max: 294.65 Min: 104.63 / Avg: 216.52 / Max: 253.59 Min: 20.71 / Avg: 188.76 / Max: 248.4 Min: 43.55 / Avg: 124.03 / Max: 147.77 Min: 17.56 / Avg: 121.69 / Max: 146.12 Min: 43.62 / Avg: 104.69 / Max: 123.24 Min: 15.7 / Avg: 99.33 / Max: 124.48
Pennant Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Max 9468 2P EPYC 8534PN Xeon Max 9480 2P EPYC 8534P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 6 12 18 24 30 SE +/- 0.034794, N = 3 SE +/- 0.001847, N = 3 SE +/- 0.013353, N = 3 SE +/- 0.002400, N = 3 SE +/- 0.002987, N = 3 SE +/- 0.052953, N = 3 SE +/- 0.003237, N = 4 SE +/- 0.029749, N = 4 SE +/- 0.003253, N = 4 SE +/- 0.024479, N = 4 SE +/- 0.016400, N = 4 SE +/- 0.018471, N = 4 SE +/- 0.052975, N = 7 SE +/- 0.080453, N = 15 SE +/- 0.074320, N = 15 SE +/- 0.040626, N = 15 SE +/- 0.041359, N = 15 SE +/- 0.037087, N = 15 25.789450 21.021120 19.882460 16.969100 16.030800 15.247190 13.211250 12.151320 12.106900 11.369640 11.284380 9.964526 5.916458 5.460660 5.147658 3.408337 3.081108 2.940456 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Pennant 1.0.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 189.6 / Avg: 573.95 / Max: 754.13 Min: 206.49 / Avg: 569.16 / Max: 751.77 Min: 148.41 / Avg: 535.71 / Max: 753.56 Min: 69.95 / Avg: 489.66 / Max: 753.78 Min: 101.05 / Avg: 438.87 / Max: 580.29 Min: 64.82 / Avg: 404.01 / Max: 819.66 Min: 55.22 / Avg: 351.84 / Max: 674.58 Min: 41.72 / Avg: 310.27 / Max: 663.85 Min: 72.63 / Avg: 303.18 / Max: 377.15 Min: 78.91 / Avg: 298.37 / Max: 377.04 Min: 57.56 / Avg: 287.94 / Max: 376.04 Min: 26.41 / Avg: 279.92 / Max: 376.36 Min: 30.95 / Avg: 242.71 / Max: 409.53 Min: 51.49 / Avg: 239.83 / Max: 289.95 Min: 26.98 / Avg: 200.64 / Max: 329.21 Min: 20.25 / Avg: 182.99 / Max: 330.83 Min: 19.05 / Avg: 123.57 / Max: 166.99 Min: 16.13 / Avg: 110.49 / Max: 145.79
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6766E 2P Xeon Platinum 8490H 2P Xeon 6780E 2P EPYC 9754 EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 14 28 42 56 70 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 3 SE +/- 0.05, N = 4 SE +/- 0.01, N = 4 SE +/- 0.07, N = 4 SE +/- 0.04, N = 4 SE +/- 0.47, N = 8 SE +/- 0.50, N = 5 SE +/- 0.26, N = 5 15.09 17.52 18.24 18.86 19.71 20.23 20.87 22.46 23.71 24.23 26.00 28.96 29.15 31.24 31.85 38.47 38.90 40.00 40.92 54.88 61.07 62.82 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X 2P EPYC 9684X EPYC 9654 2P Xeon 6780E EPYC 9654 EPYC 9754 2P Xeon 6766E EPYC 8534P EPYC 9754 EPYC 8534PN 0.0513 0.1026 0.1539 0.2052 0.2565 0.048 0.051 0.052 0.063 0.063 0.064 0.064 0.077 0.080 0.087 0.128 0.132 0.135 0.146 0.149 0.166 0.169 0.169 0.177 0.199 0.202 0.228
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8380 EPYC 9654 Xeon 6766E 2P EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 120 240 360 480 600 Min: 195.26 / Avg: 552.42 / Max: 652.44 Min: 210.38 / Avg: 537.83 / Max: 613.5 Min: 71.05 / Avg: 508.41 / Max: 687.83 Min: 168.67 / Avg: 496.87 / Max: 590.71 Min: 59.79 / Avg: 464.35 / Max: 680.95 Min: 58.04 / Avg: 409.96 / Max: 602.7 Min: 96.13 / Avg: 384.99 / Max: 445.25 Min: 38.94 / Avg: 325.22 / Max: 485.91 Min: 67.53 / Avg: 286.96 / Max: 322.9 Min: 80.03 / Avg: 279.05 / Max: 314.96 Min: 28.15 / Avg: 278.75 / Max: 351.38 Min: 30.18 / Avg: 273.17 / Max: 355.5 Min: 58.28 / Avg: 262.77 / Max: 303.74 Min: 105.65 / Avg: 248.74 / Max: 300.85 Min: 52.23 / Avg: 234.47 / Max: 262.38 Min: 28.16 / Avg: 229.8 / Max: 294.04 Min: 104.31 / Avg: 220.37 / Max: 264.43 Min: 21.44 / Avg: 190.72 / Max: 249.47 Min: 43.47 / Avg: 125.76 / Max: 153.18 Min: 17.7 / Avg: 119.03 / Max: 142.44 Min: 43.61 / Avg: 106.79 / Max: 125.47 Min: 15.1 / Avg: 98.52 / Max: 118.03
srsRAN Project srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Thread Xeon 6766E 2P Xeon 6766E Xeon 6780E Xeon 6780E 2P EPYC 9754 EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9684X 2P EPYC 9684X EPYC 9654 EPYC 9654 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 49.8 49.8 52.5 52.6 112.1 112.1 112.1 112.1 112.2 112.2 112.2 112.2 112.3 112.3 129.5 129.5 129.7 129.7 129.7 129.7 129.7 129.7 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
Mbps Per Watt
OpenBenchmarking.org Mbps Per Watt, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Thread Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon 6766E 2P EPYC 9684X 2P Xeon 6780E 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon 6766E Xeon 6780E Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.511 1.022 1.533 2.044 2.555 0.345 0.347 0.426 0.467 0.476 0.487 0.524 0.564 0.603 0.637 0.736 0.750 0.965 1.095 1.139 1.193 1.196 1.201 1.257 1.551 2.234 2.271
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN Project 23.10.1-20240325 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9754 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 70 140 210 280 350 Min: 207.62 / Avg: 375.78 / Max: 415.17 Min: 206.09 / Avg: 373.48 / Max: 412.46 Min: 160.99 / Avg: 304.32 / Max: 339.38 Min: 61.91 / Avg: 235.89 / Max: 267.82 Min: 80.8 / Avg: 229.54 / Max: 284.84 Min: 58.78 / Avg: 213.93 / Max: 242.48 Min: 97.13 / Avg: 186.14 / Max: 224.52 Min: 77.25 / Avg: 176.34 / Max: 199.62 Min: 40.92 / Avg: 175.84 / Max: 200.95 Min: 72.46 / Avg: 172.93 / Max: 196.41 Min: 59.93 / Avg: 134.44 / Max: 153.53 Min: 34.52 / Avg: 108.29 / Max: 130.82 Min: 104.39 / Avg: 107.97 / Max: 110.48 Min: 103.85 / Avg: 106.63 / Max: 109.21 Min: 34.3 / Avg: 102.46 / Max: 115.98 Min: 52.1 / Avg: 93.49 / Max: 102.87 Min: 27.03 / Avg: 89.27 / Max: 101.62 Min: 21.9 / Avg: 72.27 / Max: 82.25 Min: 16.97 / Avg: 50.19 / Max: 57.02 Min: 16.95 / Avg: 49.36 / Max: 56.04 Min: 21.98 / Avg: 44.02 / Max: 45.61 Min: 43.55 / Avg: 43.73 / Max: 45.56
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon Platinum 8380 Xeon 6766E 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon Max 9468 Xeon Max 9480 Xeon 6766E Xeon Platinum 8380 2P Xeon 6780E Xeon Platinum 8490H EPYC 8534PN Xeon Max 9468 2P Xeon Max 9480 2P EPYC 8534P EPYC 9754 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9654 EPYC 9684X 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.36, N = 15 SE +/- 0.04, N = 4 SE +/- 0.50, N = 15 SE +/- 0.06, N = 4 SE +/- 0.08, N = 4 SE +/- 0.04, N = 4 SE +/- 0.18, N = 4 SE +/- 0.00, N = 4 SE +/- 0.08, N = 4 SE +/- 0.07, N = 4 SE +/- 0.33, N = 4 SE +/- 0.29, N = 4 SE +/- 0.07, N = 5 SE +/- 0.63, N = 15 SE +/- 0.36, N = 5 SE +/- 0.45, N = 5 SE +/- 0.21, N = 5 SE +/- 0.71, N = 6 SE +/- 0.28, N = 6 SE +/- 0.62, N = 6 SE +/- 0.32, N = 6 31.25 36.40 38.02 38.92 40.23 41.34 41.86 44.11 46.18 50.03 51.51 51.91 52.23 54.60 59.01 65.38 67.64 68.56 72.68 74.03 76.83 78.15 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon Platinum 8490H Xeon 6766E 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X EPYC 9654 Xeon 6780E Xeon 6766E EPYC 9754 EPYC 8534P EPYC 8534PN 0.1332 0.2664 0.3996 0.5328 0.666 0.109 0.109 0.129 0.152 0.156 0.162 0.163 0.175 0.183 0.210 0.212 0.213 0.219 0.241 0.249 0.359 0.406 0.429 0.449 0.470 0.507 0.592
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 Xeon 6780E 2P Xeon 6766E 2P EPYC 9754 EPYC 8534P Xeon 6780E Xeon 6766E EPYC 8534PN 110 220 330 440 550 Min: 187.97 / Avg: 480.56 / Max: 609.82 Min: 190.55 / Avg: 476.69 / Max: 591.36 Min: 162.16 / Avg: 433.41 / Max: 581.27 Min: 73.01 / Avg: 374.34 / Max: 560.15 Min: 100.56 / Avg: 342.63 / Max: 431.07 Min: 66.01 / Avg: 338.64 / Max: 489.89 Min: 58.8 / Avg: 302.06 / Max: 438.45 Min: 71.86 / Avg: 253.88 / Max: 311.53 Min: 74.97 / Avg: 248.42 / Max: 303.88 Min: 39.35 / Avg: 237.06 / Max: 332.11 Min: 60.42 / Avg: 235.64 / Max: 301.41 Min: 32 / Avg: 217.45 / Max: 322.84 Min: 28.31 / Avg: 207.87 / Max: 283.73 Min: 53.82 / Avg: 205.21 / Max: 244.22 Min: 28.16 / Avg: 189.32 / Max: 280.14 Min: 106.42 / Avg: 185.19 / Max: 224.67 Min: 104.11 / Avg: 170.72 / Max: 196.41 Min: 21.76 / Avg: 145.81 / Max: 208.59 Min: 17.32 / Avg: 107.72 / Max: 144.07 Min: 43.47 / Avg: 107.62 / Max: 131.78 Min: 43.56 / Avg: 93.24 / Max: 111.07 Min: 15.21 / Avg: 87.02 / Max: 118.81
OpenFOAM OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN Xeon Platinum 8490H 2P EPYC 8534P Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ Xeon Platinum 8490H EPYC 9754 EPYC 9754 2P Xeon Platinum 8592+ 2P Xeon Max 9480 2P EPYC 9654 EPYC 9654 2P EPYC 9684X 2P EPYC 9684X 9 18 27 36 45 39.12 36.86 36.82 35.60 33.67 32.48 32.00 31.78 31.70 31.38 30.38 29.47 29.33 28.84 28.03 27.74 26.82 25.93 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Max 9468 EPYC 8534PN Xeon Platinum 8490H 2P Xeon Max 9480 EPYC 8534P Xeon Platinum 8592+ 2P Xeon Platinum 8490H EPYC 9754 2P EPYC 9754 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 2P EPYC 9684X 2P EPYC 9654 20 40 60 80 100 SE +/- 0.35, N = 15 SE +/- 0.03, N = 4 SE +/- 0.34, N = 3 SE +/- 0.02, N = 4 SE +/- 0.58, N = 5 SE +/- 0.09, N = 4 SE +/- 0.44, N = 15 SE +/- 0.52, N = 7 SE +/- 0.26, N = 4 SE +/- 0.67, N = 4 SE +/- 0.46, N = 4 SE +/- 0.29, N = 4 SE +/- 0.11, N = 4 SE +/- 0.79, N = 5 SE +/- 0.20, N = 5 SE +/- 0.31, N = 4 SE +/- 0.38, N = 5 SE +/- 0.22, N = 5 SE +/- 0.42, N = 5 SE +/- 0.40, N = 5 SE +/- 0.63, N = 5 SE +/- 0.56, N = 5 42.86 46.48 47.25 50.82 54.82 55.24 55.98 59.10 62.75 64.79 65.22 65.36 68.19 70.43 70.91 77.60 78.74 79.44 86.30 86.34 87.82 87.99 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon 6780E 2P EPYC 9684X 2P Xeon Platinum 8380 EPYC 9654 2P Xeon Platinum 8490H EPYC 9754 2P Xeon Platinum 8592+ EPYC 9684X Xeon 6780E Xeon 6766E EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.2147 0.4294 0.6441 0.8588 1.0735 0.124 0.126 0.179 0.224 0.227 0.278 0.286 0.299 0.306 0.321 0.336 0.349 0.362 0.388 0.439 0.570 0.587 0.595 0.653 0.737 0.879 0.954
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 2.0 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 196.2 / Avg: 442.62 / Max: 580.63 Min: 193.1 / Avg: 442.35 / Max: 576.63 Min: 171.54 / Avg: 364.29 / Max: 488.45 Min: 70.26 / Avg: 309.78 / Max: 476.6 Min: 62.22 / Avg: 273.59 / Max: 425.17 Min: 98.92 / Avg: 263.75 / Max: 406.42 Min: 56.85 / Avg: 247.1 / Max: 379.6 Min: 73.57 / Avg: 228.42 / Max: 325.25 Min: 76.76 / Avg: 226.08 / Max: 319.38 Min: 39.92 / Avg: 200.17 / Max: 302.35 Min: 59.76 / Avg: 195.92 / Max: 293.59 Min: 27.5 / Avg: 181.13 / Max: 316.97 Min: 51.15 / Avg: 164.49 / Max: 247.62 Min: 105.44 / Avg: 154.41 / Max: 213.01 Min: 31.53 / Avg: 151.3 / Max: 266.73 Min: 55.92 / Avg: 143.16 / Max: 199.83 Min: 28.36 / Avg: 134.72 / Max: 238.02 Min: 21.17 / Avg: 106.8 / Max: 187.26 Min: 43.44 / Avg: 86.61 / Max: 139.64 Min: 43.66 / Avg: 78.14 / Max: 117.48 Min: 16.05 / Avg: 77.57 / Max: 129.87 Min: 14.98 / Avg: 67.93 / Max: 107.89
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only EPYC 8534PN Xeon Platinum 8380 EPYC 8534P Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8490H EPYC 9654 Xeon Platinum 8380 2P EPYC 9754 Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 0.54 1.08 1.62 2.16 2.7 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 4 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 4 SE +/- 0.01, N = 4 0.80 0.86 0.86 0.98 1.07 1.08 1.14 1.28 1.29 1.31 1.48 1.50 1.51 1.58 1.64 1.67 1.68 1.71 1.72 1.74 2.18 2.40
Images / Sec Per Watt
OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 2.2 Run: RTLightmap.hdr.4096x4096 - Device: CPU-Only Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9480 EPYC 9684X EPYC 9754 2P Xeon 6766E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 0.0016 0.0032 0.0048 0.0064 0.008 0.003 0.003 0.003 0.003 0.003 0.003 0.003 0.003 0.004 0.004 0.004 0.004 0.004 0.004 0.004 0.004 0.004 0.005 0.005 0.006 0.006 0.007
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 2.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6766E 2P EPYC 9684X Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 198.59 / Avg: 608.01 / Max: 748.72 Min: 206.4 / Avg: 605.57 / Max: 749.65 Min: 66.51 / Avg: 585.9 / Max: 726.86 Min: 169.3 / Avg: 573.61 / Max: 745.77 Min: 79.35 / Avg: 534.18 / Max: 740.08 Min: 60.67 / Avg: 504.98 / Max: 617.56 Min: 108.06 / Avg: 500.21 / Max: 643.27 Min: 104.72 / Avg: 461.16 / Max: 559.61 Min: 40.88 / Avg: 433.56 / Max: 546.1 Min: 105.15 / Avg: 418.44 / Max: 529.24 Min: 35.65 / Avg: 329.68 / Max: 387.49 Min: 75.68 / Avg: 314.57 / Max: 370.97 Min: 78.93 / Avg: 313 / Max: 373.31 Min: 59.44 / Avg: 304.48 / Max: 364.78 Min: 35.29 / Avg: 290 / Max: 378.6 Min: 43.6 / Avg: 279.34 / Max: 327.38 Min: 26.15 / Avg: 266.61 / Max: 316.67 Min: 53.73 / Avg: 245.89 / Max: 283.33 Min: 22.02 / Avg: 239.18 / Max: 293.59 Min: 43.68 / Avg: 220.35 / Max: 250.91 Min: 17.84 / Avg: 136.47 / Max: 153.36 Min: 17.12 / Avg: 118.45 / Max: 132.79
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: BMW27 - Compute: CPU-Only Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon Max 9480 EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon 6766E Xeon 6780E Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P EPYC 9754 Xeon Platinum 8592+ 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 11 22 33 44 55 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.24, N = 3 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.17, N = 8 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 4 SE +/- 0.08, N = 4 SE +/- 0.04, N = 4 SE +/- 0.08, N = 4 SE +/- 0.01, N = 4 SE +/- 0.03, N = 4 SE +/- 0.06, N = 5 SE +/- 0.09, N = 5 SE +/- 0.02, N = 5 SE +/- 0.03, N = 6 SE +/- 0.02, N = 6 46.32 31.66 30.07 28.49 27.12 25.89 23.72 23.67 19.85 17.61 16.55 15.96 15.29 14.29 13.74 12.86 12.76 10.56 9.71 8.61 7.75 7.17
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 204.3 / Avg: 589.35 / Max: 754.59 Min: 211.29 / Avg: 584.52 / Max: 755.18 Min: 171.9 / Avg: 556.95 / Max: 754.1 Min: 73.16 / Avg: 522.14 / Max: 732.74 Min: 66.83 / Avg: 521.92 / Max: 820.17 Min: 103.59 / Avg: 467.53 / Max: 580.29 Min: 56.75 / Avg: 465.75 / Max: 695.98 Min: 41.39 / Avg: 414.63 / Max: 680.91 Min: 106.78 / Avg: 401.76 / Max: 612.07 Min: 104.11 / Avg: 337.47 / Max: 486.69 Min: 72.63 / Avg: 316.78 / Max: 376.8 Min: 35.39 / Avg: 314.77 / Max: 411.05 Min: 80.66 / Avg: 311.66 / Max: 376.47 Min: 57.12 / Avg: 303.66 / Max: 376.88 Min: 33.51 / Avg: 297.61 / Max: 376.94 Min: 27.61 / Avg: 264.26 / Max: 339.47 Min: 52.7 / Avg: 250.52 / Max: 290.53 Min: 21.13 / Avg: 247.78 / Max: 338.02 Min: 43.52 / Avg: 237.13 / Max: 302.65 Min: 43.62 / Avg: 189.01 / Max: 235.56 Min: 17.13 / Avg: 146.16 / Max: 171.02 Min: 18.72 / Avg: 121.31 / Max: 138.75
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 8534PN Xeon Platinum 8592+ EPYC 8534P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9754 EPYC 9684X 2P 50 100 150 200 250 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.38, N = 9 SE +/- 0.12, N = 4 SE +/- 0.84, N = 15 SE +/- 0.05, N = 5 SE +/- 0.61, N = 5 SE +/- 0.46, N = 15 SE +/- 1.19, N = 15 SE +/- 0.03, N = 6 SE +/- 0.20, N = 6 SE +/- 0.04, N = 6 SE +/- 1.28, N = 12 SE +/- 1.85, N = 12 SE +/- 0.81, N = 7 SE +/- 1.18, N = 7 SE +/- 3.27, N = 13 SE +/- 1.02, N = 8 SE +/- 3.98, N = 15 SE +/- 2.97, N = 13 SE +/- 0.70, N = 9 SE +/- 6.15, N = 12 39.17 43.55 47.26 63.62 70.84 76.60 82.85 84.35 85.29 98.21 106.40 107.35 108.40 114.90 133.63 136.95 151.95 199.73 214.62 217.85 229.91 236.61 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Billion Interactions/s Per Watt
OpenBenchmarking.org Billion Interactions/s Per Watt, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6780E 2P Xeon 6766E Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9684X EPYC 9654 2P EPYC 9654 EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9754 0.3179 0.6358 0.9537 1.2716 1.5895 0.204 0.206 0.222 0.228 0.231 0.236 0.249 0.255 0.262 0.280 0.291 0.324 0.445 0.503 0.611 0.640 0.655 0.706 0.732 1.008 1.043 1.413
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better miniBUDE 20210901 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon 6780E 2P EPYC 9654 2P Xeon 6766E 2P EPYC 9754 2P Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 Xeon 6780E EPYC 9654 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 188.58 / Avg: 496.58 / Max: 737.62 Min: 179.1 / Avg: 476.05 / Max: 713.49 Min: 149.89 / Avg: 459.2 / Max: 669.79 Min: 100.78 / Avg: 417.23 / Max: 578.66 Min: 63.44 / Avg: 396.77 / Max: 754.62 Min: 64.39 / Avg: 387.38 / Max: 798.84 Min: 107.92 / Avg: 357 / Max: 473.69 Min: 53.82 / Avg: 332.37 / Max: 634.66 Min: 105.45 / Avg: 300.28 / Max: 380.11 Min: 39.64 / Avg: 293.27 / Max: 587.35 Min: 60.74 / Avg: 255.91 / Max: 343.2 Min: 72.35 / Avg: 253.17 / Max: 324.27 Min: 71.42 / Avg: 242.48 / Max: 294.63 Min: 21.92 / Avg: 239.11 / Max: 377.96 Min: 29.7 / Avg: 237.41 / Max: 409.16 Min: 52.99 / Avg: 229.13 / Max: 286.06 Min: 43.42 / Avg: 196.03 / Max: 231.39 Min: 26.83 / Avg: 194.1 / Max: 318.58 Min: 19.01 / Avg: 162.7 / Max: 323.16 Min: 43.57 / Avg: 157.01 / Max: 182.38 Min: 18.42 / Avg: 106.48 / Max: 155.79 Min: 17.11 / Avg: 94.19 / Max: 135.5
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM1 Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 8534PN Xeon Platinum 8592+ EPYC 8534P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9754 EPYC 9684X 2P 1300 2600 3900 5200 6500 SE +/- 0.46, N = 3 SE +/- 0.29, N = 3 SE +/- 9.38, N = 9 SE +/- 2.91, N = 4 SE +/- 21.10, N = 15 SE +/- 1.36, N = 5 SE +/- 15.23, N = 5 SE +/- 11.58, N = 15 SE +/- 29.84, N = 15 SE +/- 0.82, N = 6 SE +/- 5.07, N = 6 SE +/- 0.97, N = 6 SE +/- 32.01, N = 12 SE +/- 46.19, N = 12 SE +/- 20.15, N = 7 SE +/- 29.52, N = 7 SE +/- 81.83, N = 13 SE +/- 25.44, N = 8 SE +/- 99.42, N = 15 SE +/- 74.36, N = 13 SE +/- 17.54, N = 9 SE +/- 153.85, N = 12 979.28 1088.83 1181.49 1590.50 1771.07 1915.04 2071.19 2108.68 2132.24 2455.16 2659.88 2683.83 2709.93 2872.56 3340.69 3423.63 3798.70 4993.34 5365.42 5446.16 5747.82 5915.25 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.6 Video Input: Bosphorus 4K Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon 6766E 2P Xeon Max 9468 2P EPYC 8534PN Xeon Max 9480 2P EPYC 9754 2P EPYC 8534P EPYC 9754 EPYC 9654 2P Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9480 EPYC 9654 EPYC 9684X 2P EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 9 18 27 36 45 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.22, N = 6 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.39, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.20, N = 4 SE +/- 0.11, N = 4 SE +/- 0.06, N = 4 SE +/- 0.09, N = 4 19.55 20.22 21.30 22.07 27.26 27.74 27.90 28.11 28.13 28.16 28.81 29.05 29.76 30.80 31.40 31.72 31.95 32.12 37.04 37.86 38.93 39.31 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better x265 3.6 Video Input: Bosphorus 4K Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 EPYC 9754 2P Xeon 6766E 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 0.0765 0.153 0.2295 0.306 0.3825 0.059 0.059 0.090 0.103 0.108 0.108 0.109 0.113 0.115 0.120 0.130 0.138 0.146 0.161 0.178 0.195 0.218 0.242 0.250 0.251 0.318 0.340
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better x265 3.6 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9754 2P Xeon Platinum 8380 Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 EPYC 9754 EPYC 8534P Xeon 6780E EPYC 8534PN Xeon 6766E 90 180 270 360 450 Min: 200.11 / Avg: 471.43 / Max: 532.57 Min: 195.59 / Avg: 458.96 / Max: 515.27 Min: 164.29 / Avg: 409.49 / Max: 491.55 Min: 76.83 / Avg: 359.11 / Max: 458.52 Min: 99.99 / Avg: 298.87 / Max: 362.74 Min: 64.95 / Avg: 296.42 / Max: 367.45 Min: 58.57 / Avg: 267.17 / Max: 327.8 Min: 72.13 / Avg: 261.62 / Max: 312.67 Min: 75.63 / Avg: 256.33 / Max: 294.6 Min: 59.53 / Avg: 234.38 / Max: 293.23 Min: 34.21 / Avg: 219.3 / Max: 292.58 Min: 40.31 / Avg: 216.07 / Max: 262.6 Min: 52.94 / Avg: 203.52 / Max: 247.27 Min: 105.18 / Avg: 169.56 / Max: 195.88 Min: 32.43 / Avg: 164.71 / Max: 212.57 Min: 104.34 / Avg: 160.26 / Max: 184.55 Min: 28.94 / Avg: 145.28 / Max: 189.25 Min: 20.91 / Avg: 112.7 / Max: 141.97 Min: 17.3 / Avg: 88.38 / Max: 113.06 Min: 43.45 / Avg: 88.07 / Max: 115.63 Min: 15.46 / Avg: 81.58 / Max: 101.27 Min: 43.65 / Avg: 80.41 / Max: 103.35
Timed FFmpeg Compilation This test times how long it takes to build the FFmpeg multimedia library. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 7.0 Time To Compile Xeon Platinum 8380 EPYC 8534PN Xeon 6766E EPYC 8534P Xeon Max 9468 Xeon Platinum 8380 2P Xeon 6766E 2P Xeon 6780E Xeon Max 9480 Xeon Platinum 8490H Xeon 6780E 2P EPYC 9754 Xeon Platinum 8592+ EPYC 9754 2P Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P EPYC 9684X Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.30, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 34.29 28.42 27.85 27.54 26.46 25.94 25.71 25.24 24.84 24.06 23.32 23.22 21.36 21.22 20.79 20.49 20.01 19.99 19.51 18.09 17.84 17.39
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed FFmpeg Compilation 7.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P Xeon 6766E EPYC 8534PN 140 280 420 560 700 Min: 208.48 / Avg: 470.97 / Max: 753.46 Min: 198.1 / Avg: 467.2 / Max: 752.99 Min: 157.82 / Avg: 400.67 / Max: 753.15 Min: 85.35 / Avg: 348.01 / Max: 755.27 Min: 65.37 / Avg: 314.5 / Max: 819.41 Min: 98.24 / Avg: 301.65 / Max: 581.66 Min: 55.22 / Avg: 281.94 / Max: 701.16 Min: 81.57 / Avg: 251.37 / Max: 376.37 Min: 74.35 / Avg: 250.86 / Max: 374.99 Min: 39.64 / Avg: 238.4 / Max: 679.1 Min: 57.21 / Avg: 220.08 / Max: 376.48 Min: 34.1 / Avg: 198.27 / Max: 377.58 Min: 52.91 / Avg: 184.1 / Max: 291.84 Min: 55.1 / Avg: 172.28 / Max: 647.64 Min: 32.76 / Avg: 171.98 / Max: 410.22 Min: 103.98 / Avg: 158.14 / Max: 527.88 Min: 28.44 / Avg: 151.49 / Max: 345.46 Min: 21.46 / Avg: 124.42 / Max: 336.98 Min: 43.39 / Avg: 101.96 / Max: 321.98 Min: 17.56 / Avg: 90.17 / Max: 171.06 Min: 43.59 / Avg: 88.1 / Max: 260.1 Min: 17.2 / Avg: 81.55 / Max: 145.14
Pennant Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 9684X Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9684X 2P 3 6 9 12 15 SE +/- 0.010812, N = 4 SE +/- 0.045713, N = 13 SE +/- 0.057580, N = 6 SE +/- 0.025580, N = 6 SE +/- 0.023904, N = 7 SE +/- 0.022393, N = 7 SE +/- 0.037316, N = 9 SE +/- 0.022698, N = 7 SE +/- 0.115723, N = 15 SE +/- 0.115702, N = 15 SE +/- 0.115724, N = 15 SE +/- 0.010204, N = 7 SE +/- 0.019069, N = 15 SE +/- 0.008354, N = 7 SE +/- 0.063684, N = 15 SE +/- 0.013568, N = 6 SE +/- 0.022246, N = 15 SE +/- 0.055800, N = 15 11.852130 6.852712 6.541768 5.930957 5.114161 4.955865 4.702557 4.182707 3.754835 3.654303 3.360453 2.881099 2.529807 2.527363 2.312977 2.159459 2.084384 2.076835 1. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Pennant 1.0.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9684X Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 191.18 / Avg: 450.17 / Max: 753.29 Min: 187.85 / Avg: 448.22 / Max: 752.01 Min: 144.69 / Avg: 414.55 / Max: 753.5 Min: 63.33 / Avg: 370.49 / Max: 818.97 Min: 100.92 / Avg: 344.84 / Max: 581.63 Min: 64.47 / Avg: 342.65 / Max: 753.04 Min: 54.46 / Avg: 322.18 / Max: 670.5 Min: 41.42 / Avg: 291.74 / Max: 665.7 Min: 71.8 / Avg: 241.62 / Max: 375.61 Min: 74.45 / Avg: 234.93 / Max: 375.6 Min: 57.31 / Avg: 222.1 / Max: 377.34 Min: 52.7 / Avg: 215.77 / Max: 289.7 Min: 33.15 / Avg: 196.35 / Max: 409.53 Min: 25.17 / Avg: 191.11 / Max: 377.76 Min: 27.07 / Avg: 170.76 / Max: 330.73 Min: 20.01 / Avg: 156.67 / Max: 328.66 Min: 18.14 / Avg: 107.18 / Max: 164.25 Min: 16.11 / Avg: 95.67 / Max: 145.23
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: AlexNet Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9684X Xeon 6766E Xeon Platinum 8592+ 2P Xeon 6780E EPYC 9654 Xeon Max 9480 2P EPYC 8534PN EPYC 8534P EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H 13 26 39 52 65 SE +/- 0.12, N = 15 SE +/- 0.19, N = 5 SE +/- 0.15, N = 9 SE +/- 0.17, N = 15 SE +/- 0.10, N = 6 SE +/- 0.07, N = 7 SE +/- 0.07, N = 6 SE +/- 0.45, N = 15 SE +/- 0.08, N = 7 SE +/- 0.18, N = 7 SE +/- 0.52, N = 15 SE +/- 0.04, N = 7 SE +/- 0.05, N = 7 SE +/- 0.48, N = 15 SE +/- 0.66, N = 15 SE +/- 0.33, N = 15 SE +/- 0.44, N = 15 SE +/- 0.57, N = 15 SE +/- 0.05, N = 7 SE +/- 1.22, N = 15 SE +/- 0.76, N = 15 SE +/- 0.08, N = 8 16.24 18.34 18.59 19.88 19.92 26.23 29.56 30.76 31.99 32.56 33.21 34.35 34.51 35.08 35.50 37.26 37.57 37.76 42.05 43.67 48.28 56.53
images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 1 - Model: AlexNet EPYC 9684X 2P EPYC 9654 2P Xeon Max 9480 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X Xeon Max 9480 Xeon Max 9468 EPYC 9654 Xeon Platinum 8592+ Xeon Platinum 8380 Xeon Platinum 8490H EPYC 9754 Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 0.1287 0.2574 0.3861 0.5148 0.6435 0.065 0.071 0.080 0.083 0.087 0.094 0.094 0.106 0.111 0.154 0.181 0.234 0.274 0.275 0.286 0.340 0.374 0.375 0.404 0.407 0.538 0.572
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 187.03 / Avg: 414.71 / Max: 652.72 Min: 190.72 / Avg: 403 / Max: 643.72 Min: 146.77 / Avg: 355.03 / Max: 612.45 Min: 62.19 / Avg: 307.72 / Max: 505.41 Min: 56.56 / Avg: 280.47 / Max: 458.42 Min: 77.54 / Avg: 276.92 / Max: 490.49 Min: 97.99 / Avg: 242.28 / Max: 449.95 Min: 38.63 / Avg: 224.78 / Max: 359.48 Min: 105.47 / Avg: 195.16 / Max: 299.02 Min: 104 / Avg: 187.73 / Max: 277.66 Min: 73.08 / Avg: 186.7 / Max: 334.25 Min: 75.83 / Avg: 176.45 / Max: 326.47 Min: 59.91 / Avg: 151.32 / Max: 308.57 Min: 32.86 / Avg: 144.8 / Max: 258 Min: 26.69 / Avg: 124.1 / Max: 239.48 Min: 49.46 / Avg: 123.85 / Max: 241.53 Min: 26.55 / Avg: 118.55 / Max: 230.07 Min: 19.64 / Avg: 93.48 / Max: 194.83 Min: 43.45 / Avg: 78.62 / Max: 138.98 Min: 43.59 / Avg: 73.23 / Max: 123.49 Min: 16.75 / Avg: 64.2 / Max: 124.93 Min: 15.49 / Avg: 60.05 / Max: 115.86
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9754 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9754 2P EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P 80K 160K 240K 320K 400K SE +/- 11.99, N = 3 SE +/- 14.31, N = 3 SE +/- 23.20, N = 3 SE +/- 67.02, N = 3 SE +/- 9.58, N = 3 SE +/- 150.79, N = 3 SE +/- 33.85, N = 3 SE +/- 31.76, N = 4 SE +/- 72.03, N = 4 SE +/- 126.50, N = 4 SE +/- 679.14, N = 4 SE +/- 420.81, N = 4 SE +/- 560.20, N = 4 SE +/- 2064.71, N = 6 SE +/- 1178.78, N = 6 SE +/- 1528.09, N = 5 SE +/- 1929.89, N = 5 SE +/- 1666.53, N = 6 37567.61 52684.93 52745.64 58815.36 69776.41 71245.26 90420.25 109416.42 125191.11 127519.37 135939.25 141954.15 147311.14 214017.18 225311.82 228184.68 256584.67 390520.93 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C Xeon Platinum 8380 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 8534P Xeon Platinum 8592+ EPYC 8534PN Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9754 2P EPYC 9754 EPYC 9654 2P EPYC 9684X EPYC 9684X 2P 200 400 600 800 1000 151.21 189.97 203.59 229.75 240.55 243.32 251.86 275.88 393.05 411.62 441.50 515.52 547.32 567.85 590.51 649.64 882.53 916.62
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 183.64 / Avg: 563.63 / Max: 754.82 Min: 187.62 / Avg: 558.68 / Max: 751.91 Min: 158.17 / Avg: 533.96 / Max: 753.09 Min: 101.91 / Avg: 444.12 / Max: 565.31 Min: 68.95 / Avg: 442.63 / Max: 754.48 Min: 63.25 / Avg: 426.04 / Max: 818.12 Min: 56.6 / Avg: 394.96 / Max: 670.11 Min: 41.44 / Avg: 376.89 / Max: 668.41 Min: 73.26 / Avg: 309.61 / Max: 365.04 Min: 74.98 / Avg: 303.7 / Max: 376.9 Min: 60.29 / Avg: 296.18 / Max: 370.22 Min: 26.78 / Avg: 265.82 / Max: 376.59 Min: 32.04 / Avg: 255.3 / Max: 409.27 Min: 52.53 / Avg: 248.45 / Max: 283.18 Min: 26 / Avg: 228.74 / Max: 319.02 Min: 22.12 / Avg: 215.95 / Max: 323.68 Min: 18.23 / Avg: 134.2 / Max: 159.66 Min: 17.36 / Avg: 119.33 / Max: 138.69
PyBench This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Xeon 6766E 2P Xeon 6766E Xeon 6780E Xeon 6780E 2P EPYC 8534P EPYC 8534PN EPYC 9754 Xeon Platinum 8380 EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9654 EPYC 9684X EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Max 9480 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 200 400 600 800 1000 SE +/- 0.33, N = 3 SE +/- 1.15, N = 3 SE +/- 0.88, N = 3 SE +/- 0.58, N = 3 SE +/- 1.45, N = 3 SE +/- 2.40, N = 3 SE +/- 0.58, N = 3 SE +/- 2.85, N = 3 SE +/- 1.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.86, N = 3 SE +/- 2.19, N = 3 SE +/- 2.08, N = 3 SE +/- 1.20, N = 3 SE +/- 1.15, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.48, N = 4 SE +/- 0.41, N = 4 1119 1117 1007 1005 976 974 974 973 972 971 822 818 818 818 767 765 763 763 763 762 692 691
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyBench 2018-02-16 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X Xeon Platinum 8380 Xeon Platinum 8490H EPYC 9654 Xeon Platinum 8592+ EPYC 9754 EPYC 8534P EPYC 8534PN Xeon 6780E Xeon 6766E 60 120 180 240 300 Min: 205.54 / Avg: 276.95 / Max: 327.1 Min: 206.86 / Avg: 276.72 / Max: 343.62 Min: 65.07 / Avg: 232.2 / Max: 264.86 Min: 163.51 / Avg: 228.16 / Max: 305.07 Min: 57.47 / Avg: 207.73 / Max: 239.74 Min: 79.78 / Avg: 194.14 / Max: 289.01 Min: 98.37 / Avg: 177.98 / Max: 196.22 Min: 38.38 / Avg: 175.13 / Max: 196.99 Min: 83.03 / Avg: 121.48 / Max: 133.99 Min: 74.61 / Avg: 114.52 / Max: 125.95 Min: 106.05 / Avg: 107.95 / Max: 109.82 Min: 103.97 / Avg: 107.3 / Max: 109.09 Min: 33.11 / Avg: 99.97 / Max: 113.9 Min: 49.36 / Avg: 92.52 / Max: 101.33 Min: 58.93 / Avg: 88.45 / Max: 123.25 Min: 28.15 / Avg: 88.41 / Max: 100.93 Min: 33.53 / Avg: 85.96 / Max: 134.17 Min: 19.44 / Avg: 72.53 / Max: 81.29 Min: 15.93 / Avg: 48.41 / Max: 54.07 Min: 14.86 / Avg: 47.57 / Max: 53.35 Min: 43.46 / Avg: 45.25 / Max: 46 Min: 43.58 / Avg: 43.95 / Max: 46.08
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Xeon Platinum 8380 Xeon Max 9468 EPYC 8534PN Xeon Max 9480 EPYC 8534P Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 EPYC 9754 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 130K 260K 390K 520K 650K SE +/- 123.65, N = 3 SE +/- 71.37, N = 3 SE +/- 274.93, N = 3 SE +/- 37.04, N = 4 SE +/- 314.42, N = 4 SE +/- 130.20, N = 4 SE +/- 155.95, N = 4 SE +/- 213.44, N = 5 SE +/- 441.66, N = 5 SE +/- 411.20, N = 5 SE +/- 398.40, N = 5 SE +/- 789.76, N = 5 SE +/- 2566.89, N = 15 SE +/- 1849.65, N = 6 SE +/- 726.00, N = 5 SE +/- 4162.49, N = 6 SE +/- 1879.23, N = 6 SE +/- 5800.63, N = 15 98557.16 126171.52 130839.12 131606.86 133284.46 135125.15 185954.54 232012.77 246822.52 257384.55 261127.09 269047.28 279397.45 362511.43 455312.09 472931.04 551955.55 588329.32 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ EPYC 8534P Xeon Platinum 8592+ 2P EPYC 8534PN EPYC 9654 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 EPYC 9684X EPYC 9754 2P 400 800 1200 1600 2000 422.75 445.10 449.20 449.46 459.15 478.19 503.44 522.54 960.89 1120.43 1127.30 1212.35 1333.71 1335.18 1398.79 1409.22 1613.95 1808.53
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 196.19 / Avg: 538.25 / Max: 736.91 Min: 194.99 / Avg: 537.56 / Max: 710.4 Min: 157.28 / Avg: 499.73 / Max: 701.36 Min: 99.57 / Avg: 417.78 / Max: 563.12 Min: 67.67 / Avg: 403.9 / Max: 715.05 Min: 65.04 / Avg: 394.59 / Max: 765.59 Min: 56.83 / Avg: 354.21 / Max: 638.12 Min: 40.45 / Avg: 325.31 / Max: 668.91 Min: 76.87 / Avg: 292.98 / Max: 353.23 Min: 74.49 / Avg: 280.72 / Max: 336.16 Min: 59.44 / Avg: 268.4 / Max: 328.81 Min: 26.25 / Avg: 241.46 / Max: 364.07 Min: 51.86 / Avg: 233.13 / Max: 282.84 Min: 32.65 / Avg: 224.61 / Max: 370.12 Min: 26.14 / Avg: 201.73 / Max: 306.76 Min: 21.38 / Avg: 198.26 / Max: 322.68 Min: 17.95 / Avg: 118.96 / Max: 149.72 Min: 17.84 / Avg: 107.92 / Max: 134.69
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Thorough Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 EPYC 8534PN Xeon 6766E EPYC 8534P Xeon Max 9480 Xeon 6780E Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon 6766E 2P Xeon Max 9468 2P EPYC 9684X Xeon 6780E 2P Xeon Max 9480 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 30 60 90 120 150 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 4 SE +/- 0.03, N = 4 SE +/- 0.01, N = 3 SE +/- 0.01, N = 4 SE +/- 0.05, N = 4 SE +/- 0.01, N = 4 SE +/- 0.42, N = 4 SE +/- 0.05, N = 4 SE +/- 0.06, N = 5 SE +/- 0.85, N = 4 SE +/- 0.03, N = 5 SE +/- 0.01, N = 5 SE +/- 0.19, N = 5 SE +/- 0.55, N = 5 SE +/- 0.73, N = 15 SE +/- 1.46, N = 12 SE +/- 1.20, N = 5 15.50 30.03 37.01 37.96 40.69 41.02 42.98 45.21 51.30 54.45 65.30 71.02 72.33 73.38 79.29 83.34 86.01 86.98 97.94 105.41 116.12 121.30 1. (CXX) g++ options: -O3 -flto -pthread
MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.7 Preset: Thorough Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E Xeon Platinum 8592+ 2P Xeon 6766E Xeon 6780E 2P Xeon 6766E 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 9654 EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 0.1136 0.2272 0.3408 0.4544 0.568 0.068 0.074 0.139 0.153 0.164 0.179 0.203 0.214 0.244 0.259 0.262 0.290 0.299 0.310 0.316 0.319 0.330 0.338 0.359 0.384 0.456 0.505
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.7 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon 6780E 2P Xeon Max 9480 Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 204.94 / Avg: 472.75 / Max: 744.21 Min: 195.71 / Avg: 466.49 / Max: 741.06 Min: 147.85 / Avg: 428.35 / Max: 731.41 Min: 99.18 / Avg: 403.9 / Max: 572.69 Min: 76.68 / Avg: 373.98 / Max: 732.13 Min: 63.05 / Avg: 367.67 / Max: 734.43 Min: 55.87 / Avg: 330.17 / Max: 623.66 Min: 38.72 / Avg: 265.99 / Max: 577.68 Min: 72.98 / Avg: 265.38 / Max: 375.06 Min: 106.82 / Avg: 264.73 / Max: 530.48 Min: 78.02 / Avg: 261.71 / Max: 374.53 Min: 60.85 / Avg: 239.45 / Max: 374.18 Min: 103.99 / Avg: 228.94 / Max: 433.24 Min: 49.99 / Avg: 228.75 / Max: 289.57 Min: 34.05 / Avg: 223.18 / Max: 369.47 Min: 33.53 / Avg: 222.24 / Max: 407.18 Min: 28.71 / Avg: 193.35 / Max: 335.29 Min: 43.44 / Avg: 174.24 / Max: 297.52 Min: 20.4 / Avg: 170.2 / Max: 353.81 Min: 43.64 / Avg: 140.53 / Max: 230.96 Min: 15.96 / Avg: 114.12 / Max: 173.87 Min: 15.09 / Avg: 98.95 / Max: 145.65
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 9684X Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 3K 6K 9K 12K 15K SE +/- 11.05, N = 3 SE +/- 14.39, N = 4 SE +/- 9.85, N = 4 SE +/- 6.56, N = 3 SE +/- 15.55, N = 4 SE +/- 18.08, N = 4 SE +/- 8.35, N = 4 SE +/- 12.99, N = 4 SE +/- 4.96, N = 4 SE +/- 23.92, N = 4 SE +/- 8.92, N = 4 SE +/- 17.53, N = 5 SE +/- 35.67, N = 5 SE +/- 29.95, N = 5 SE +/- 155.00, N = 15 SE +/- 85.04, N = 8 SE +/- 76.70, N = 10 SE +/- 119.22, N = 6 2266.32 2718.94 2746.20 2865.72 3050.16 3076.66 3345.45 3816.70 3819.83 3960.28 4059.70 5229.41 5702.13 6346.15 7437.81 9771.41 10139.69 12296.27 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 8534P EPYC 8534PN EPYC 9654 EPYC 9754 2P EPYC 9684X EPYC 9654 2P EPYC 9684X 2P EPYC 9754 8 16 24 32 40 7.258 7.333 8.360 8.646 10.738 11.707 11.814 11.909 18.030 18.332 25.260 27.818 29.667 31.780 32.045 32.063 35.302 36.454
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 196.74 / Avg: 526.3 / Max: 723.61 Min: 196.72 / Avg: 520.51 / Max: 703.63 Min: 145.91 / Avg: 473.71 / Max: 694.3 Min: 67.06 / Avg: 405.72 / Max: 726.27 Min: 103.51 / Avg: 386.95 / Max: 547.42 Min: 66.48 / Avg: 348.31 / Max: 715.01 Min: 54.94 / Avg: 316.24 / Max: 616.93 Min: 41.36 / Avg: 307.47 / Max: 647.96 Min: 75.39 / Avg: 262.81 / Max: 362.43 Min: 75.18 / Avg: 256.12 / Max: 347.73 Min: 60.58 / Avg: 242.56 / Max: 344.06 Min: 25.68 / Avg: 225.16 / Max: 371.3 Min: 54.69 / Avg: 211.05 / Max: 280.75 Min: 32.82 / Avg: 198.04 / Max: 362.78 Min: 25.79 / Avg: 176.27 / Max: 304.26 Min: 20.68 / Avg: 156.42 / Max: 284.24 Min: 19.1 / Avg: 108.72 / Max: 150.47 Min: 9.26 / Avg: 97.74 / Max: 132.42
Timed Mesa Compilation This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 24.0 Time To Compile Xeon 6766E Xeon 6766E 2P Xeon Platinum 8380 Xeon 6780E 2P Xeon 6780E EPYC 8534PN Xeon Platinum 8380 2P EPYC 8534P Xeon Max 9468 EPYC 9754 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9684X EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.17, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 4 SE +/- 0.08, N = 4 SE +/- 0.05, N = 4 25.89 25.88 23.66 23.46 23.41 21.53 21.44 21.04 20.18 19.91 19.65 19.56 19.23 18.47 18.29 18.14 17.26 16.96 16.67 16.41 16.40 16.18
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Mesa Compilation 24.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9684X Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E EPYC 8534P EPYC 8534PN Xeon 6766E 140 280 420 560 700 Min: 199.11 / Avg: 446.38 / Max: 751.99 Min: 195.35 / Avg: 442.47 / Max: 753.73 Min: 171.78 / Avg: 374.89 / Max: 753.6 Min: 82.26 / Avg: 324.23 / Max: 753.39 Min: 65.81 / Avg: 287.81 / Max: 802.37 Min: 99.18 / Avg: 266.43 / Max: 584.3 Min: 53.33 / Avg: 251.26 / Max: 671.83 Min: 74.89 / Avg: 232.74 / Max: 375.37 Min: 73.22 / Avg: 228.31 / Max: 375.9 Min: 41.25 / Avg: 215.57 / Max: 638.97 Min: 32.86 / Avg: 176.64 / Max: 377.39 Min: 57 / Avg: 172.35 / Max: 378.42 Min: 52.69 / Avg: 166.64 / Max: 291.22 Min: 33.71 / Avg: 153.28 / Max: 411.05 Min: 106.87 / Avg: 146.41 / Max: 572.5 Min: 104.21 / Avg: 137.28 / Max: 498.1 Min: 27.72 / Avg: 132.61 / Max: 328.77 Min: 20.4 / Avg: 109.13 / Max: 324.24 Min: 43.31 / Avg: 79.63 / Max: 313.34 Min: 18.48 / Avg: 79 / Max: 166.34 Min: 16.52 / Avg: 73.01 / Max: 143.27 Min: 43.62 / Avg: 71.87 / Max: 255.49
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9754 EPYC 9654 Xeon Max 9468 2P EPYC 9684X Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 6 12 18 24 30 SE +/- 0.01216869, N = 3 SE +/- 0.10237421, N = 3 SE +/- 0.01040414, N = 3 SE +/- 0.04445674, N = 4 SE +/- 0.01004100, N = 4 SE +/- 0.01708632, N = 4 SE +/- 0.02691998, N = 4 SE +/- 0.02923582, N = 4 SE +/- 0.03951909, N = 5 SE +/- 0.06577912, N = 5 SE +/- 0.01741826, N = 5 SE +/- 0.05847189, N = 6 SE +/- 0.05695382, N = 15 SE +/- 0.04312801, N = 5 SE +/- 0.03329814, N = 5 SE +/- 0.01633300, N = 4 SE +/- 0.04312156, N = 5 SE +/- 0.00891960, N = 5 23.97082840 21.17803070 20.93791390 13.96923760 12.92934130 12.79975820 11.24980160 10.19670660 8.87225914 8.25383511 7.29349117 6.88121279 6.66387510 6.39169817 5.39125967 4.51061893 4.26078596 3.75319901 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 196.28 / Avg: 524.59 / Max: 749.74 Min: 187.55 / Avg: 524.04 / Max: 746.57 Min: 151.7 / Avg: 495.02 / Max: 746.22 Min: 64.22 / Avg: 431.35 / Max: 814.6 Min: 78.61 / Avg: 426.75 / Max: 741.39 Min: 100.46 / Avg: 415.93 / Max: 564.56 Min: 57.92 / Avg: 371 / Max: 659.72 Min: 40.05 / Avg: 313.08 / Max: 632.39 Min: 75.94 / Avg: 288.56 / Max: 366.2 Min: 77.21 / Avg: 283.32 / Max: 372.73 Min: 58.88 / Avg: 278.29 / Max: 373.12 Min: 34.54 / Avg: 254.46 / Max: 403.7 Min: 24.14 / Avg: 251.56 / Max: 369.25 Min: 53.04 / Avg: 237.24 / Max: 284.02 Min: 30.56 / Avg: 216.15 / Max: 325.7 Min: 22.21 / Avg: 200.17 / Max: 312.99 Min: 19.02 / Avg: 124.9 / Max: 149.76 Min: 17.28 / Avg: 114.52 / Max: 138.44
Y-Cruncher Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 1B Xeon 6766E Xeon Platinum 8380 EPYC 8534PN Xeon 6780E EPYC 8534P EPYC 9684X 2P Xeon Max 9468 EPYC 9654 2P Xeon 6766E 2P Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9684X Xeon 6780E 2P Xeon Platinum 8490H EPYC 9754 EPYC 9654 Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 3 6 9 12 15 SE +/- 0.018, N = 4 SE +/- 0.011, N = 4 SE +/- 0.001, N = 4 SE +/- 0.020, N = 4 SE +/- 0.005, N = 4 SE +/- 0.012, N = 4 SE +/- 0.045, N = 5 SE +/- 0.012, N = 4 SE +/- 0.007, N = 4 SE +/- 0.026, N = 5 SE +/- 0.049, N = 4 SE +/- 0.010, N = 5 SE +/- 0.008, N = 4 SE +/- 0.002, N = 4 SE +/- 0.005, N = 5 SE +/- 0.007, N = 4 SE +/- 0.008, N = 5 SE +/- 0.030, N = 5 SE +/- 0.122, N = 15 SE +/- 0.142, N = 12 SE +/- 0.010, N = 6 SE +/- 0.007, N = 6 11.198 10.712 10.427 10.386 10.205 8.992 8.300 8.196 7.967 7.959 7.915 7.744 7.471 7.468 7.047 6.928 6.743 6.701 6.334 6.266 5.110 5.008
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Y-Cruncher 0.8.3 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 191.23 / Avg: 496.54 / Max: 748.22 Min: 193.6 / Avg: 493.66 / Max: 748.88 Min: 166.8 / Avg: 424.33 / Max: 738.75 Min: 66.34 / Avg: 404.17 / Max: 643.66 Min: 76.49 / Avg: 362.82 / Max: 745.4 Min: 98.98 / Avg: 352.71 / Max: 555.83 Min: 58.9 / Avg: 351.79 / Max: 591.63 Min: 105.25 / Avg: 293.09 / Max: 598.55 Min: 40.66 / Avg: 284.7 / Max: 529.69 Min: 104.12 / Avg: 272.77 / Max: 508.32 Min: 76.02 / Avg: 255.33 / Max: 373.96 Min: 73.1 / Avg: 254.54 / Max: 371.3 Min: 30.38 / Avg: 222.94 / Max: 366.15 Min: 32.32 / Avg: 212.59 / Max: 399.38 Min: 32.02 / Avg: 198.74 / Max: 364.57 Min: 53.53 / Avg: 195.15 / Max: 284.61 Min: 28.49 / Avg: 178.56 / Max: 342.72 Min: 43.37 / Avg: 168.68 / Max: 308.71 Min: 21.57 / Avg: 148.59 / Max: 323.95 Min: 43.6 / Avg: 141.11 / Max: 252.27 Min: 16.07 / Avg: 105.12 / Max: 171.94 Min: 16.4 / Avg: 94.34 / Max: 147.45
Timed ImageMagick Compilation This test times how long it takes to build ImageMagick. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile Xeon 6766E Xeon 6766E 2P Xeon 6780E Xeon 6780E 2P Xeon Platinum 8380 EPYC 8534PN EPYC 8534P EPYC 9754 Xeon Platinum 8380 2P Xeon Max 9468 EPYC 9754 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ EPYC 9684X EPYC 9684X 2P Xeon Platinum 8592+ 2P 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 4 SE +/- 0.13, N = 4 SE +/- 0.15, N = 4 SE +/- 0.02, N = 4 SE +/- 0.06, N = 4 SE +/- 0.10, N = 4 SE +/- 0.11, N = 4 SE +/- 0.07, N = 4 SE +/- 0.09, N = 4 SE +/- 0.13, N = 4 SE +/- 0.04, N = 4 SE +/- 0.10, N = 4 SE +/- 0.06, N = 4 SE +/- 0.04, N = 4 SE +/- 0.03, N = 4 20.91 20.59 19.20 18.85 18.84 18.18 17.92 16.39 16.33 16.08 15.81 15.38 14.72 14.40 14.09 13.47 13.26 12.75 12.60 12.20 11.72 11.49
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed ImageMagick Compilation 6.9.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 Xeon 6780E 2P EPYC 9684X Xeon 6766E 2P EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 203.42 / Avg: 435.59 / Max: 750.99 Min: 198.51 / Avg: 429.23 / Max: 750.07 Min: 164.76 / Avg: 362.03 / Max: 752.14 Min: 81.81 / Avg: 295.33 / Max: 748.04 Min: 62.42 / Avg: 273.56 / Max: 669.18 Min: 97.82 / Avg: 252.21 / Max: 581.41 Min: 57.57 / Avg: 245.77 / Max: 578.82 Min: 73.52 / Avg: 220.79 / Max: 376.49 Min: 75.62 / Avg: 220.24 / Max: 379.25 Min: 40.62 / Avg: 204.88 / Max: 561.52 Min: 60.5 / Avg: 186.22 / Max: 378.44 Min: 26.01 / Avg: 162.46 / Max: 377 Min: 51.29 / Avg: 152.46 / Max: 291.86 Min: 107.23 / Avg: 143.22 / Max: 459.28 Min: 32.48 / Avg: 139.23 / Max: 409.7 Min: 103.94 / Avg: 137.3 / Max: 386.07 Min: 28.39 / Avg: 120.39 / Max: 332.54 Min: 21.44 / Avg: 97.43 / Max: 329.22 Min: 43.41 / Avg: 74.98 / Max: 300.96 Min: 43.53 / Avg: 69.56 / Max: 253.22 Min: 17.83 / Avg: 69.48 / Max: 164.08 Min: 16.43 / Avg: 65.12 / Max: 142.84
m-queens A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 8534PN Xeon Platinum 8592+ EPYC 8534P Xeon Platinum 8380 2P Xeon 6766E Xeon Max 9468 2P Xeon 6780E Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9754 Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 6 12 18 24 30 SE +/- 0.023, N = 3 SE +/- 0.031, N = 3 SE +/- 0.035, N = 3 SE +/- 0.025, N = 4 SE +/- 0.029, N = 4 SE +/- 0.030, N = 4 SE +/- 0.019, N = 4 SE +/- 0.066, N = 4 SE +/- 0.039, N = 5 SE +/- 0.021, N = 5 SE +/- 0.032, N = 5 SE +/- 0.028, N = 5 SE +/- 0.021, N = 6 SE +/- 0.019, N = 6 SE +/- 0.028, N = 6 SE +/- 0.025, N = 6 SE +/- 0.021, N = 6 SE +/- 0.035, N = 7 SE +/- 0.034, N = 7 SE +/- 0.093, N = 15 SE +/- 0.064, N = 15 SE +/- 0.031, N = 8 24.175 21.030 18.102 15.211 14.493 14.257 13.250 12.390 11.479 10.840 10.301 9.285 7.881 7.738 7.402 6.950 6.350 6.045 5.512 4.609 4.133 3.981 1. (CXX) g++ options: -fopenmp -O2 -march=native
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better m-queens 1.2 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Max 9468 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon 6780E 2P EPYC 9654 2P Xeon 6766E 2P EPYC 9754 2P Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8490H Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon 6780E EPYC 9654 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 180.86 / Avg: 502.47 / Max: 745.73 Min: 165.88 / Avg: 497.84 / Max: 742.37 Min: 77.88 / Avg: 481.61 / Max: 753.74 Min: 201.32 / Avg: 465.55 / Max: 574.13 Min: 99.79 / Avg: 431.33 / Max: 582.73 Min: 63.38 / Avg: 412.8 / Max: 820.43 Min: 108.43 / Avg: 381.31 / Max: 634.03 Min: 52.18 / Avg: 366.51 / Max: 668.54 Min: 105.96 / Avg: 317.88 / Max: 500.32 Min: 41.4 / Avg: 316.2 / Max: 657.62 Min: 32.66 / Avg: 278.57 / Max: 374.34 Min: 31.01 / Avg: 267.9 / Max: 411.07 Min: 62.12 / Avg: 266.4 / Max: 324.62 Min: 77.06 / Avg: 260.39 / Max: 302.34 Min: 75.51 / Avg: 241.11 / Max: 276.68 Min: 54.03 / Avg: 238.8 / Max: 290.84 Min: 43.54 / Avg: 226.9 / Max: 315.05 Min: 28.35 / Avg: 221.83 / Max: 330.6 Min: 20.79 / Avg: 202.95 / Max: 326.11 Min: 43.69 / Avg: 180.19 / Max: 242.1 Min: 19.39 / Avg: 122.5 / Max: 158.25 Min: 15.51 / Avg: 106.99 / Max: 136.77
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8490H EPYC 9654 Xeon 6766E 2P Xeon Platinum 8380 2P EPYC 9754 Xeon 6780E 2P Xeon Platinum 8592+ EPYC 9684X 2P Xeon Max 9468 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 1.1453 2.2906 3.4359 4.5812 5.7265 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.02, N = 4 SE +/- 0.00, N = 4 SE +/- 0.01, N = 4 SE +/- 0.01, N = 4 SE +/- 0.00, N = 5 SE +/- 0.03, N = 6 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.02, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 SE +/- 0.01, N = 6 SE +/- 0.03, N = 6 1.69 1.80 1.81 1.93 2.11 2.27 2.39 2.66 2.71 2.73 2.97 3.10 3.16 3.31 3.32 3.47 3.49 3.49 3.57 3.66 4.48 5.09
Images / Sec Per Watt
OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 2.2 Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-Only Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9654 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9684X Xeon 6780E Xeon Platinum 8490H EPYC 9754 2P Xeon 6766E Xeon Platinum 8592+ 2P EPYC 9654 Xeon Platinum 8592+ EPYC 9754 EPYC 8534P EPYC 8534PN 0.0036 0.0072 0.0108 0.0144 0.018 0.006 0.007 0.007 0.008 0.008 0.008 0.008 0.008 0.008 0.008 0.009 0.009 0.009 0.010 0.010 0.010 0.012 0.012 0.013 0.015 0.015 0.016
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 2.2 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon 6780E 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 208.03 / Avg: 550.26 / Max: 748.26 Min: 193.7 / Avg: 538.98 / Max: 749.89 Min: 63.03 / Avg: 499.92 / Max: 728.7 Min: 165.7 / Avg: 496.66 / Max: 745.69 Min: 80.74 / Avg: 440.63 / Max: 738.2 Min: 108.16 / Avg: 427.37 / Max: 638.82 Min: 57.66 / Avg: 424.59 / Max: 613.78 Min: 100.45 / Avg: 406.6 / Max: 560.45 Min: 40.05 / Avg: 372.52 / Max: 545.78 Min: 105.15 / Avg: 359.38 / Max: 527.77 Min: 73.66 / Avg: 286.68 / Max: 372.63 Min: 76.35 / Avg: 284.74 / Max: 374.26 Min: 32.55 / Avg: 282.53 / Max: 386.33 Min: 59.91 / Avg: 268.44 / Max: 367.04 Min: 26.77 / Avg: 249.97 / Max: 378.66 Min: 43.54 / Avg: 247.22 / Max: 322.66 Min: 27.41 / Avg: 233.36 / Max: 317.91 Min: 52.95 / Avg: 224.45 / Max: 283.1 Min: 21.62 / Avg: 205.54 / Max: 298.26 Min: 43.72 / Avg: 199.4 / Max: 250.2 Min: 18.74 / Avg: 123.7 / Max: 154.19 Min: 17.42 / Avg: 107.91 / Max: 132.12
Result
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 2.2 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8490H EPYC 9654 Xeon 6766E 2P Xeon Platinum 8380 2P EPYC 9754 Xeon Platinum 8592+ Xeon 6780E 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9468 2P EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 1.1318 2.2636 3.3954 4.5272 5.659 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.01, N = 4 SE +/- 0.00, N = 4 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 SE +/- 0.00, N = 5 SE +/- 0.03, N = 5 SE +/- 0.00, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.04, N = 5 SE +/- 0.03, N = 6 SE +/- 0.03, N = 6 1.69 1.79 1.81 1.93 2.11 2.26 2.38 2.64 2.71 2.73 2.98 3.08 3.12 3.31 3.31 3.45 3.48 3.51 3.59 3.65 4.41 5.03
Images / Sec Per Watt
OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 2.2 Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-Only Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9654 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9684X Xeon 6780E Xeon Platinum 8490H EPYC 9754 2P Xeon 6766E Xeon Platinum 8592+ 2P EPYC 9654 Xeon Platinum 8592+ EPYC 8534P EPYC 9754 EPYC 8534PN 0.0036 0.0072 0.0108 0.0144 0.018 0.006 0.007 0.007 0.008 0.008 0.008 0.008 0.008 0.008 0.008 0.009 0.009 0.009 0.010 0.010 0.010 0.011 0.012 0.013 0.014 0.015 0.016
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 2.2 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 EPYC 9684X Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6780E EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 203.58 / Avg: 542.52 / Max: 747.25 Min: 193.14 / Avg: 539.15 / Max: 749.93 Min: 66.11 / Avg: 502.25 / Max: 723.91 Min: 177.66 / Avg: 501.77 / Max: 743.78 Min: 72.33 / Avg: 443.88 / Max: 736.09 Min: 56.38 / Avg: 425.53 / Max: 615.08 Min: 107.69 / Avg: 422.71 / Max: 638.83 Min: 100.7 / Avg: 406.71 / Max: 559.15 Min: 40.47 / Avg: 369.54 / Max: 546.36 Min: 104.93 / Avg: 363.85 / Max: 529.39 Min: 73.14 / Avg: 287.37 / Max: 372.13 Min: 32.59 / Avg: 284.36 / Max: 386.47 Min: 76.26 / Avg: 283.96 / Max: 374.08 Min: 60.35 / Avg: 271.32 / Max: 366.61 Min: 26.29 / Avg: 249.88 / Max: 378.95 Min: 43.49 / Avg: 246.81 / Max: 322.99 Min: 25.93 / Avg: 230.11 / Max: 317.81 Min: 53.39 / Avg: 224.83 / Max: 282.65 Min: 21.86 / Avg: 203.92 / Max: 294.28 Min: 43.68 / Avg: 198.71 / Max: 249.99 Min: 19.01 / Avg: 124.67 / Max: 154.19 Min: 17.3 / Avg: 107.16 / Max: 132.19
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8380 2P EPYC 9754 EPYC 9654 Xeon Platinum 8490H 2P EPYC 9684X EPYC 9754 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 20K 40K 60K 80K 100K SE +/- 207.19, N = 6 SE +/- 126.79, N = 6 SE +/- 34.34, N = 6 SE +/- 243.41, N = 12 SE +/- 313.88, N = 7 SE +/- 260.16, N = 15 SE +/- 28.62, N = 7 SE +/- 480.71, N = 15 SE +/- 393.67, N = 15 SE +/- 178.23, N = 8 SE +/- 386.70, N = 9 SE +/- 545.82, N = 5 SE +/- 328.18, N = 8 SE +/- 545.92, N = 15 SE +/- 560.41, N = 15 SE +/- 779.47, N = 7 SE +/- 661.05, N = 7 SE +/- 271.54, N = 6 21684.80 22229.94 22655.32 33811.63 35116.55 35234.06 38906.13 43799.78 53182.77 58128.24 62071.10 63265.01 63760.45 65396.22 66492.44 84477.72 88487.91 98764.93 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Xeon Platinum 8380 2P Xeon Platinum 8380 Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H Xeon Max 9468 EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 90 180 270 360 450 119.68 119.97 145.15 153.93 154.97 155.78 156.61 157.12 226.89 244.61 254.62 283.84 295.11 302.72 305.56 356.27 384.09 401.38
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9684X Xeon Platinum 8592+ EPYC 9754 EPYC 9654 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 189.85 / Avg: 429.08 / Max: 754.24 Min: 187.39 / Avg: 424.86 / Max: 754.4 Min: 146.08 / Avg: 400.48 / Max: 754.34 Min: 100.01 / Avg: 325.09 / Max: 579.93 Min: 54.43 / Avg: 323.22 / Max: 766.2 Min: 58.39 / Avg: 299.85 / Max: 772.2 Min: 55.55 / Avg: 279.06 / Max: 655.46 Min: 38.61 / Avg: 248.47 / Max: 653.54 Min: 71.23 / Avg: 226.18 / Max: 377.45 Min: 74.58 / Avg: 223.5 / Max: 376.44 Min: 57.02 / Avg: 215.9 / Max: 374.98 Min: 52.98 / Avg: 188.84 / Max: 288.7 Min: 17.06 / Avg: 161.61 / Max: 378.41 Min: 25.74 / Avg: 158.85 / Max: 377.04 Min: 19.49 / Avg: 154.31 / Max: 321.83 Min: 26.59 / Avg: 149.28 / Max: 317.86 Min: 17.31 / Avg: 97.98 / Max: 151 Min: 16.9 / Avg: 88.65 / Max: 135.53
GNU Octave Benchmark This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 8.4.0 Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 8534PN EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon Platinum 8490H 2P Xeon Max 9480 EPYC 9654 2P Xeon Max 9468 Xeon Platinum 8490H EPYC 9654 EPYC 9684X 2P EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 3 6 9 12 15 SE +/- 0.096, N = 5 SE +/- 0.082, N = 5 SE +/- 0.023, N = 5 SE +/- 0.108, N = 7 SE +/- 0.035, N = 5 SE +/- 0.051, N = 5 SE +/- 0.052, N = 5 SE +/- 0.017, N = 5 SE +/- 0.007, N = 5 SE +/- 0.011, N = 5 SE +/- 0.025, N = 5 SE +/- 0.014, N = 5 SE +/- 0.019, N = 6 SE +/- 0.024, N = 6 SE +/- 0.004, N = 6 SE +/- 0.015, N = 6 SE +/- 0.015, N = 6 SE +/- 0.009, N = 6 SE +/- 0.007, N = 6 SE +/- 0.018, N = 6 SE +/- 0.019, N = 6 SE +/- 0.020, N = 6 12.617 12.578 12.245 11.619 10.996 10.243 9.694 9.104 8.948 8.929 8.848 8.801 8.036 7.748 7.645 7.622 7.532 7.528 6.955 6.857 6.856 6.458
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GNU Octave Benchmark 8.4.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8380 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 80 160 240 320 400 Min: 202.03 / Avg: 373.8 / Max: 446.62 Min: 197.53 / Avg: 371.49 / Max: 456.41 Min: 167.67 / Avg: 296.93 / Max: 375.38 Min: 61.74 / Avg: 205.11 / Max: 301.54 Min: 56.62 / Avg: 189.57 / Max: 270.57 Min: 99.24 / Avg: 180.92 / Max: 246.72 Min: 79.51 / Avg: 166.55 / Max: 232.48 Min: 74.85 / Avg: 164.13 / Max: 237.93 Min: 40.57 / Avg: 161.36 / Max: 222.38 Min: 56.04 / Avg: 133.36 / Max: 217.89 Min: 104.36 / Avg: 116.68 / Max: 139.31 Min: 103.69 / Avg: 114.72 / Max: 127.74 Min: 32.85 / Avg: 108.34 / Max: 202.86 Min: 53.19 / Avg: 97.85 / Max: 151.32 Min: 34.49 / Avg: 95.8 / Max: 154.31 Min: 27.81 / Avg: 84.26 / Max: 135.67 Min: 20.26 / Avg: 67.77 / Max: 105.08 Min: 43.45 / Avg: 55 / Max: 74.81 Min: 43.6 / Avg: 52.88 / Max: 68.56 Min: 17.25 / Avg: 49.95 / Max: 77.01 Min: 15.49 / Avg: 47.63 / Max: 72.89
Y-Cruncher Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Y-Cruncher 0.8.3 Pi Digits To Calculate: 500M Xeon 6766E EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon 6780E EPYC 9684X 2P EPYC 9654 2P EPYC 9684X EPYC 9754 2P EPYC 9754 EPYC 9654 Xeon Max 9468 Xeon Platinum 8380 2P Xeon Max 9480 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8592+ Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8592+ 2P Xeon Platinum 8490H 2P 1.1648 2.3296 3.4944 4.6592 5.824 SE +/- 0.005, N = 6 SE +/- 0.008, N = 6 SE +/- 0.006, N = 6 SE +/- 0.003, N = 6 SE +/- 0.007, N = 6 SE +/- 0.007, N = 5 SE +/- 0.003, N = 5 SE +/- 0.003, N = 6 SE +/- 0.015, N = 5 SE +/- 0.005, N = 6 SE +/- 0.003, N = 6 SE +/- 0.010, N = 7 SE +/- 0.006, N = 7 SE +/- 0.023, N = 15 SE +/- 0.004, N = 6 SE +/- 0.004, N = 6 SE +/- 0.008, N = 7 SE +/- 0.003, N = 7 SE +/- 0.064, N = 15 SE +/- 0.074, N = 15 SE +/- 0.004, N = 7 SE +/- 0.002, N = 8 5.177 5.165 5.077 4.874 4.770 4.510 4.329 4.312 4.100 3.968 3.850 3.781 3.724 3.704 3.629 3.411 3.391 3.267 3.110 2.961 2.659 2.364
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Y-Cruncher 0.8.3 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H EPYC 9684X Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 197.01 / Avg: 434.63 / Max: 747.05 Min: 189.46 / Avg: 425.51 / Max: 749.34 Min: 164.95 / Avg: 367.73 / Max: 733.59 Min: 66.18 / Avg: 327.67 / Max: 622.14 Min: 97.45 / Avg: 293.71 / Max: 562.12 Min: 53.19 / Avg: 293.51 / Max: 558.3 Min: 81.75 / Avg: 285.35 / Max: 686.94 Min: 37.77 / Avg: 238.41 / Max: 478.35 Min: 106.12 / Avg: 236.59 / Max: 561.92 Min: 104.3 / Avg: 221.86 / Max: 497.5 Min: 74.95 / Avg: 212.09 / Max: 370.6 Min: 70.98 / Avg: 211.16 / Max: 373.06 Min: 57.55 / Avg: 181.21 / Max: 363.23 Min: 32.78 / Avg: 173.58 / Max: 352.72 Min: 52.29 / Avg: 167.23 / Max: 285.41 Min: 31.93 / Avg: 151.06 / Max: 346.25 Min: 27.89 / Avg: 146.25 / Max: 317.02 Min: 43.46 / Avg: 134.29 / Max: 274.09 Min: 20.76 / Avg: 118.84 / Max: 272.84 Min: 43.7 / Avg: 116.04 / Max: 224.06 Min: 16.15 / Avg: 86.13 / Max: 163.32 Min: 16.77 / Avg: 78.49 / Max: 143.84
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Max 9480 Xeon 6766E Xeon Platinum 8490H Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9654 Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H 2P EPYC 9684X EPYC 9754 EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P EPYC 9684X 2P 50 100 150 200 250 SE +/- 0.04, N = 4 SE +/- 0.05, N = 5 SE +/- 0.03, N = 5 SE +/- 0.04, N = 5 SE +/- 0.11, N = 5 SE +/- 0.04, N = 5 SE +/- 0.05, N = 5 SE +/- 0.05, N = 5 SE +/- 0.29, N = 6 SE +/- 0.13, N = 6 SE +/- 0.63, N = 6 SE +/- 1.20, N = 15 SE +/- 0.03, N = 6 SE +/- 0.10, N = 6 SE +/- 0.16, N = 7 SE +/- 0.13, N = 7 SE +/- 0.07, N = 7 SE +/- 0.12, N = 7 SE +/- 1.54, N = 8 SE +/- 0.26, N = 8 SE +/- 1.88, N = 7 SE +/- 2.04, N = 8 55.42 73.91 75.21 75.47 83.49 84.71 91.99 92.88 99.24 112.66 125.75 129.75 132.49 138.85 151.25 152.75 155.12 156.39 185.71 199.61 208.31 231.43
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon 6780E Xeon 6766E EPYC 9684X 2P EPYC 8534P EPYC 9754 2P EPYC 9684X EPYC 8534PN EPYC 9654 EPYC 9754 0.194 0.388 0.582 0.776 0.97 0.246 0.253 0.253 0.258 0.276 0.312 0.323 0.428 0.453 0.457 0.494 0.508 0.518 0.520 0.550 0.564 0.613 0.620 0.662 0.706 0.735 0.862
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 4.3 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X Xeon Platinum 8592+ Xeon Platinum 8380 Xeon Platinum 8490H EPYC 9754 EPYC 9654 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 185.96 / Avg: 511.91 / Max: 753.56 Min: 200.84 / Avg: 511.17 / Max: 752.67 Min: 166.53 / Avg: 472.72 / Max: 754.96 Min: 59.43 / Avg: 410.15 / Max: 817.39 Min: 66.59 / Avg: 393.21 / Max: 754.66 Min: 102.21 / Avg: 383.99 / Max: 581.28 Min: 55.21 / Avg: 358.56 / Max: 646.17 Min: 42.62 / Avg: 335.83 / Max: 642.99 Min: 108.43 / Avg: 333.95 / Max: 567.53 Min: 105.4 / Avg: 303.74 / Max: 488.69 Min: 66.39 / Avg: 273.07 / Max: 377.18 Min: 74.25 / Avg: 267.87 / Max: 377.44 Min: 31.26 / Avg: 234.18 / Max: 410.22 Min: 24.21 / Avg: 228.28 / Max: 376.12 Min: 54.93 / Avg: 219.18 / Max: 290.54 Min: 60.02 / Avg: 215.03 / Max: 377.71 Min: 20.65 / Avg: 181.41 / Max: 329.67 Min: 28.26 / Avg: 180.38 / Max: 335.4 Min: 43.49 / Avg: 178.58 / Max: 261.5 Min: 43.66 / Avg: 153.94 / Max: 217.83 Min: 18.74 / Avg: 122.78 / Max: 171.96 Min: 16.8 / Avg: 104.66 / Max: 145.45
WebP Image Encode This is a test of Google's libwebp with the cwebp image encode utility and using a sample 6000x4000 pixel JPEG image as the input. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9754 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ 2P Xeon Platinum 8592+ EPYC 9684X EPYC 9684X 2P EPYC 9654 EPYC 9654 2P 0.8145 1.629 2.4435 3.258 4.0725 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 SE +/- 0.00, N = 6 2.23 2.23 2.47 2.49 2.81 2.82 3.03 3.03 3.03 3.04 3.07 3.08 3.09 3.09 3.10 3.10 3.46 3.47 3.61 3.62 3.62 3.62 1. (CC) gcc options: -fvisibility=hidden -O2 -lm
MP/s Per Watt
OpenBenchmarking.org MP/s Per Watt, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P EPYC 9654 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H EPYC 9684X EPYC 9654 EPYC 9754 Xeon Platinum 8592+ Xeon 6766E Xeon 6780E EPYC 8534P EPYC 8534PN 0.0162 0.0324 0.0486 0.0648 0.081 0.011 0.011 0.014 0.017 0.019 0.019 0.020 0.021 0.021 0.023 0.026 0.028 0.033 0.035 0.044 0.048 0.049 0.051 0.051 0.056 0.069 0.072
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better WebP Image Encode 1.2.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9684X EPYC 9654 Xeon Platinum 8592+ EPYC 9754 EPYC 8534P Xeon 6780E Xeon 6766E EPYC 8534PN 70 140 210 280 350 Min: 205.94 / Avg: 277 / Max: 371.07 Min: 200.76 / Avg: 274.15 / Max: 348.74 Min: 148.59 / Avg: 222.03 / Max: 316.69 Min: 63.07 / Avg: 192.89 / Max: 262.1 Min: 74.68 / Avg: 186.13 / Max: 288.17 Min: 56.66 / Avg: 176 / Max: 238.56 Min: 100.4 / Avg: 169.36 / Max: 210.51 Min: 39.42 / Avg: 149.38 / Max: 197.42 Min: 81.36 / Avg: 119.53 / Max: 163.62 Min: 70.24 / Avg: 111.05 / Max: 144.04 Min: 105.24 / Avg: 107.9 / Max: 111.31 Min: 103.85 / Avg: 107.03 / Max: 109.06 Min: 59.48 / Avg: 88.57 / Max: 151.52 Min: 50.09 / Avg: 86.28 / Max: 102.41 Min: 32.65 / Avg: 82.63 / Max: 115.67 Min: 28.98 / Avg: 75.95 / Max: 101.21 Min: 34.25 / Avg: 68.3 / Max: 101.37 Min: 20.53 / Avg: 61.84 / Max: 81.06 Min: 16.45 / Avg: 44.16 / Max: 57.18 Min: 43.35 / Avg: 44.16 / Max: 45.33 Min: 43.59 / Avg: 43.93 / Max: 46.02 Min: 16.53 / Avg: 42.26 / Max: 55.05
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown Xeon Platinum 8380 EPYC 8534PN Xeon Max 9468 EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon Max 9468 2P EPYC 9654 Xeon Max 9480 2P Xeon 6766E 2P Xeon Platinum 8490H 2P EPYC 9754 EPYC 9684X Xeon 6780E 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P EPYC 9684X 2P 50 100 150 200 250 SE +/- 0.07, N = 3 SE +/- 0.07, N = 4 SE +/- 0.05, N = 4 SE +/- 0.04, N = 4 SE +/- 0.02, N = 4 SE +/- 0.07, N = 5 SE +/- 0.05, N = 5 SE +/- 0.02, N = 5 SE +/- 0.08, N = 5 SE +/- 0.05, N = 5 SE +/- 0.14, N = 6 SE +/- 0.08, N = 6 SE +/- 0.48, N = 6 SE +/- 0.11, N = 6 SE +/- 0.12, N = 6 SE +/- 0.64, N = 6 SE +/- 0.20, N = 7 SE +/- 0.14, N = 6 SE +/- 0.07, N = 7 SE +/- 0.43, N = 7 SE +/- 1.04, N = 7 SE +/- 1.23, N = 8 43.67 58.28 58.42 62.19 65.33 70.05 73.96 81.83 82.92 82.97 107.63 110.53 116.61 121.43 124.71 126.15 130.79 133.42 153.16 176.21 190.08 214.02
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown Xeon Platinum 8380 Xeon Max 9468 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8592+ 2P Xeon 6780E 2P Xeon 6766E 2P Xeon 6780E Xeon 6766E EPYC 9654 2P EPYC 8534P EPYC 9684X 2P EPYC 9654 EPYC 8534PN EPYC 9684X EPYC 9754 2P EPYC 9754 0.1415 0.283 0.4245 0.566 0.7075 0.192 0.205 0.205 0.206 0.226 0.232 0.252 0.258 0.331 0.363 0.373 0.377 0.381 0.422 0.468 0.482 0.499 0.499 0.517 0.522 0.532 0.629
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 4.3 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon 6780E 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 Xeon 6780E EPYC 9754 Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 192.27 / Avg: 525.15 / Max: 751.36 Min: 178.12 / Avg: 516.97 / Max: 755.2 Min: 171.82 / Avg: 493.94 / Max: 734.13 Min: 60.99 / Avg: 428.94 / Max: 819.87 Min: 65.93 / Avg: 422.5 / Max: 748.67 Min: 102.04 / Avg: 404.97 / Max: 574.07 Min: 58.37 / Avg: 376.52 / Max: 669.54 Min: 105.86 / Avg: 357.3 / Max: 564.3 Min: 39.31 / Avg: 357.16 / Max: 678.39 Min: 104.47 / Avg: 322.07 / Max: 484.23 Min: 71.98 / Avg: 284.3 / Max: 376.72 Min: 75.4 / Avg: 281.67 / Max: 377.64 Min: 60.79 / Avg: 271.03 / Max: 377.88 Min: 26.17 / Avg: 250.53 / Max: 384.62 Min: 32.54 / Avg: 250.47 / Max: 410.99 Min: 53.87 / Avg: 227.2 / Max: 288.12 Min: 27.85 / Avg: 221.71 / Max: 341.98 Min: 43.42 / Avg: 214.8 / Max: 302.74 Min: 20.38 / Avg: 200.39 / Max: 335.38 Min: 43.6 / Avg: 175.27 / Max: 236.71 Min: 17.65 / Avg: 128.92 / Max: 171.09 Min: 16.58 / Avg: 112.82 / Max: 146.36
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Medium Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 EPYC 8534PN Xeon Max 9480 Xeon 6766E EPYC 8534P Xeon 6780E Xeon Platinum 8592+ Xeon Platinum 8490H Xeon 6766E 2P Xeon 6780E 2P Xeon Max 9468 2P EPYC 9654 EPYC 9754 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9654 2P EPYC 9684X EPYC 9684X 2P EPYC 9754 Xeon Platinum 8592+ 2P 120 240 360 480 600 SE +/- 0.32, N = 4 SE +/- 2.26, N = 5 SE +/- 0.03, N = 6 SE +/- 0.07, N = 6 SE +/- 0.08, N = 6 SE +/- 0.18, N = 5 SE +/- 0.07, N = 6 SE +/- 0.13, N = 6 SE +/- 1.17, N = 6 SE +/- 0.16, N = 6 SE +/- 1.77, N = 5 SE +/- 2.01, N = 5 SE +/- 0.52, N = 6 SE +/- 0.20, N = 7 SE +/- 0.52, N = 6 SE +/- 0.77, N = 6 SE +/- 2.79, N = 6 SE +/- 3.54, N = 6 SE +/- 0.63, N = 7 SE +/- 3.11, N = 7 SE +/- 0.39, N = 7 SE +/- 1.56, N = 7 126.44 216.97 247.30 273.67 284.33 284.46 294.62 314.62 327.78 333.99 338.15 363.38 441.65 449.11 462.24 483.10 484.55 491.53 500.77 508.09 527.80 550.02 1. (CXX) g++ options: -O3 -flto -pthread
MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.7 Preset: Medium Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9468 Xeon Max 9480 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Platinum 8490H EPYC 9684X 2P Xeon Platinum 8592+ 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon 6766E 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E Xeon 6766E EPYC 9684X EPYC 9654 EPYC 8534P EPYC 8534PN EPYC 9754 1.1363 2.2726 3.4089 4.5452 5.6815 0.720 0.741 1.094 1.167 1.215 1.373 1.414 1.923 1.966 1.983 2.012 2.048 2.084 2.099 2.377 3.076 3.191 3.488 3.553 3.926 3.989 5.050
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.7 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 202.14 / Avg: 403.63 / Max: 727.09 Min: 188.21 / Avg: 397.48 / Max: 724.85 Min: 149.65 / Avg: 342.67 / Max: 671.28 Min: 94.9 / Avg: 291.19 / Max: 532.11 Min: 75.77 / Avg: 277.37 / Max: 691.02 Min: 60.92 / Avg: 258.49 / Max: 596.25 Min: 57.21 / Avg: 234.22 / Max: 515.92 Min: 73.51 / Avg: 211.87 / Max: 372.54 Min: 46.45 / Avg: 207.12 / Max: 368.04 Min: 38.51 / Avg: 194.48 / Max: 419.92 Min: 105.97 / Avg: 177.44 / Max: 411 Min: 49.69 / Avg: 175.72 / Max: 288.95 Min: 60.47 / Avg: 173.64 / Max: 368.66 Min: 26.56 / Avg: 162.88 / Max: 364.95 Min: 103.94 / Avg: 162.27 / Max: 347.6 Min: 32.4 / Avg: 143.57 / Max: 393.87 Min: 27.98 / Avg: 126.4 / Max: 324.02 Min: 20.85 / Avg: 104.51 / Max: 314.72 Min: 43.4 / Avg: 102.28 / Max: 269.1 Min: 43.61 / Avg: 89.14 / Max: 212.79 Min: 16.05 / Avg: 75.04 / Max: 166.06 Min: 15.15 / Avg: 68.61 / Max: 143.04
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon Max 9468 2P Xeon 6780E Xeon Max 9480 2P Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H 2P EPYC 8534PN EPYC 9684X 2P Xeon Platinum 8490H EPYC 8534P Xeon Platinum 8592+ 2P EPYC 9684X EPYC 9754 2P EPYC 9754 EPYC 9654 2P Xeon Platinum 8592+ EPYC 9654 40 80 120 160 200 SE +/- 0.88, N = 5 SE +/- 0.08, N = 6 SE +/- 1.07, N = 6 SE +/- 0.83, N = 5 SE +/- 0.15, N = 6 SE +/- 0.97, N = 6 SE +/- 0.48, N = 6 SE +/- 1.28, N = 6 SE +/- 0.61, N = 7 SE +/- 0.40, N = 7 SE +/- 0.25, N = 7 SE +/- 0.78, N = 6 SE +/- 0.88, N = 6 SE +/- 0.41, N = 7 SE +/- 0.71, N = 6 SE +/- 0.42, N = 7 SE +/- 0.43, N = 7 SE +/- 1.41, N = 6 SE +/- 1.32, N = 6 SE +/- 1.88, N = 15 SE +/- 0.20, N = 7 SE +/- 0.80, N = 7 108.50 115.35 117.68 122.09 126.59 127.55 134.07 140.76 146.10 151.72 156.52 157.36 163.80 164.25 165.09 165.50 165.75 168.78 169.23 171.22 177.86 178.52 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Max 9468 Xeon Max 9480 EPYC 9654 2P Xeon 6766E 2P Xeon 6780E 2P EPYC 9754 2P Xeon Platinum 8380 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon 6766E EPYC 9654 Xeon 6780E EPYC 9754 EPYC 8534P EPYC 8534PN 0.6399 1.2798 1.9197 2.5596 3.1995 0.306 0.318 0.500 0.638 0.675 0.709 0.784 0.812 0.829 0.833 0.843 1.001 1.054 1.097 1.363 1.399 1.703 1.714 1.741 2.019 2.784 2.844
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 2.0 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon Platinum 8592+ Xeon 6766E 2P Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 192.02 / Avg: 400.5 / Max: 567.38 Min: 206.55 / Avg: 399.09 / Max: 553.52 Min: 162.99 / Avg: 313.03 / Max: 463.03 Min: 72.44 / Avg: 245.05 / Max: 463.8 Min: 64.22 / Avg: 231.05 / Max: 380.24 Min: 98.84 / Avg: 220.59 / Max: 378.11 Min: 57.32 / Avg: 206.47 / Max: 350.04 Min: 70.86 / Avg: 186.8 / Max: 304.11 Min: 78.53 / Avg: 186.44 / Max: 299.02 Min: 39.75 / Avg: 168.64 / Max: 285.91 Min: 58.81 / Avg: 149.76 / Max: 276.69 Min: 105.73 / Avg: 139.65 / Max: 205.54 Min: 27.81 / Avg: 130.54 / Max: 271.31 Min: 104.27 / Avg: 130.28 / Max: 174.4 Min: 49.17 / Avg: 127.22 / Max: 220.81 Min: 28.14 / Avg: 118.49 / Max: 228.43 Min: 25.96 / Avg: 104.16 / Max: 214.25 Min: 21.46 / Avg: 83.8 / Max: 173.31 Min: 43.49 / Avg: 72.69 / Max: 125.26 Min: 43.6 / Avg: 67.73 / Max: 107.71 Min: 16.3 / Avg: 59.31 / Max: 124.91 Min: 14.97 / Avg: 55.32 / Max: 108.24
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534PN EPYC 8534P Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9754 2P EPYC 9754 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8490H 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9654 Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8592+ 2P 3 6 9 12 15 SE +/- 0.054, N = 5 SE +/- 0.038, N = 5 SE +/- 0.012, N = 5 SE +/- 0.010, N = 6 SE +/- 0.016, N = 6 SE +/- 0.027, N = 6 SE +/- 0.011, N = 6 SE +/- 0.009, N = 6 SE +/- 0.027, N = 6 SE +/- 0.035, N = 6 SE +/- 0.025, N = 6 SE +/- 0.007, N = 6 SE +/- 0.045, N = 6 SE +/- 0.033, N = 6 SE +/- 0.013, N = 7 SE +/- 0.022, N = 7 SE +/- 0.015, N = 7 SE +/- 0.020, N = 7 SE +/- 0.010, N = 7 SE +/- 0.025, N = 7 SE +/- 0.014, N = 7 SE +/- 0.031, N = 7 9.960 9.351 9.188 8.359 8.201 7.388 7.301 7.182 7.121 7.038 6.986 6.853 6.836 6.605 6.278 6.172 5.950 5.846 5.799 5.784 5.757 5.613 1. (CXX) g++ options: -O3 -fPIC -lm
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 1.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon Platinum 8380 Xeon 6780E 2P Xeon Platinum 8592+ Xeon 6766E 2P EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 197.54 / Avg: 390.59 / Max: 684.36 Min: 196.47 / Avg: 378.09 / Max: 677.18 Min: 143.68 / Avg: 313.6 / Max: 692.26 Min: 74.34 / Avg: 248.3 / Max: 649.52 Min: 61.29 / Avg: 220.4 / Max: 507.64 Min: 95.62 / Avg: 213.07 / Max: 530.05 Min: 51.5 / Avg: 198.44 / Max: 459.76 Min: 74.59 / Avg: 193.8 / Max: 362.37 Min: 69.76 / Avg: 191.83 / Max: 376.91 Min: 39.73 / Avg: 165.83 / Max: 352.71 Min: 61.6 / Avg: 158.79 / Max: 375.47 Min: 48.9 / Avg: 132.08 / Max: 290.31 Min: 106.3 / Avg: 128.53 / Max: 249.32 Min: 26.64 / Avg: 128.43 / Max: 374.81 Min: 53.34 / Avg: 123.17 / Max: 220.64 Min: 29.45 / Avg: 115.08 / Max: 342.75 Min: 27.48 / Avg: 100.34 / Max: 306.84 Min: 20.4 / Avg: 80.51 / Max: 234.12 Min: 43.39 / Avg: 64.09 / Max: 183.29 Min: 43.56 / Avg: 59.76 / Max: 149.48 Min: 15.99 / Avg: 55.18 / Max: 149.59 Min: 15.05 / Avg: 53.07 / Max: 124.5
ACES DGEMM This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate Xeon Platinum 8380 Xeon 6766E Xeon 6780E Xeon Max 9468 EPYC 8534PN EPYC 8534P Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 2P Xeon Platinum 8592+ Xeon 6766E 2P Xeon 6780E 2P EPYC 9654 Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9754 EPYC 9684X Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.01, N = 4 SE +/- 0.01, N = 4 SE +/- 0.04, N = 4 SE +/- 0.10, N = 5 SE +/- 0.16, N = 5 SE +/- 0.09, N = 5 SE +/- 0.09, N = 5 SE +/- 0.09, N = 5 SE +/- 0.08, N = 6 SE +/- 0.03, N = 6 SE +/- 0.04, N = 6 SE +/- 0.22, N = 7 SE +/- 0.06, N = 7 SE +/- 0.04, N = 7 SE +/- 0.17, N = 7 SE +/- 0.40, N = 7 SE +/- 0.28, N = 7 SE +/- 0.11, N = 8 SE +/- 0.10, N = 9 SE +/- 0.39, N = 9 SE +/- 0.19, N = 10 13.49 15.94 17.85 19.77 21.00 21.82 22.54 23.54 24.97 29.14 31.48 35.20 39.09 39.35 44.67 44.97 45.25 45.97 58.25 68.87 78.50 84.69 1. (CC) gcc options: -O3 -march=native -fopenmp
GFLOP/s Per Watt
OpenBenchmarking.org GFLOP/s Per Watt, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9468 2P Xeon Max 9480 Xeon Max 9480 2P Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon 6780E Xeon 6766E Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8592+ 2P EPYC 9684X EPYC 8534P EPYC 9654 EPYC 9684X 2P EPYC 8534PN EPYC 9654 2P EPYC 9754 EPYC 9754 2P 0.0657 0.1314 0.1971 0.2628 0.3285 0.059 0.063 0.071 0.078 0.081 0.090 0.093 0.101 0.105 0.107 0.112 0.114 0.121 0.149 0.196 0.198 0.214 0.215 0.220 0.228 0.252 0.292
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ACES DGEMM 1.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon 6780E 2P EPYC 9654 2P EPYC 9754 2P Xeon 6766E 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 193.63 / Avg: 507 / Max: 747.89 Min: 194.98 / Avg: 496.59 / Max: 754.16 Min: 164.24 / Avg: 453.94 / Max: 741.45 Min: 99.45 / Avg: 398.61 / Max: 554.79 Min: 68.08 / Avg: 390.95 / Max: 737.84 Min: 63.45 / Avg: 364.55 / Max: 774.44 Min: 106.31 / Avg: 312.9 / Max: 465.14 Min: 56.61 / Avg: 302.67 / Max: 601.18 Min: 40.76 / Avg: 290.43 / Max: 650.39 Min: 104.19 / Avg: 277.33 / Max: 390.75 Min: 73.75 / Avg: 277.15 / Max: 377.23 Min: 75.8 / Avg: 276.9 / Max: 361.7 Min: 53.98 / Avg: 252.19 / Max: 377.52 Min: 23.09 / Avg: 239.87 / Max: 363.28 Min: 31.49 / Avg: 230.52 / Max: 409.55 Min: 52.19 / Avg: 226.98 / Max: 281.28 Min: 28.2 / Avg: 182.5 / Max: 306.04 Min: 22.22 / Avg: 178.2 / Max: 342.37 Min: 43.36 / Avg: 170.6 / Max: 222.09 Min: 43.57 / Avg: 148.35 / Max: 183.52 Min: 17.88 / Avg: 109.94 / Max: 158.28 Min: 16.53 / Avg: 95.47 / Max: 135.35
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 10, Lossless Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon 6780E Xeon Platinum 8380 2P Xeon Platinum 8380 EPYC 9754 2P EPYC 8534P EPYC 8534PN EPYC 9754 Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 EPYC 9654 2P EPYC 9654 EPYC 9684X Xeon Platinum 8592+ 2P Xeon Platinum 8592+ 2 4 6 8 10 SE +/- 0.021, N = 6 SE +/- 0.016, N = 6 SE +/- 0.009, N = 6 SE +/- 0.003, N = 6 SE +/- 0.011, N = 7 SE +/- 0.008, N = 7 SE +/- 0.006, N = 7 SE +/- 0.006, N = 7 SE +/- 0.010, N = 7 SE +/- 0.004, N = 7 SE +/- 0.019, N = 7 SE +/- 0.028, N = 7 SE +/- 0.014, N = 7 SE +/- 0.003, N = 7 SE +/- 0.006, N = 7 SE +/- 0.005, N = 7 SE +/- 0.015, N = 7 SE +/- 0.006, N = 8 SE +/- 0.006, N = 8 SE +/- 0.002, N = 8 SE +/- 0.015, N = 8 SE +/- 0.008, N = 8 8.094 7.603 7.507 6.849 5.919 5.906 5.740 5.735 5.734 5.662 5.317 5.311 5.074 4.943 4.923 4.916 4.867 4.829 4.792 4.770 4.579 4.456 1. (CXX) g++ options: -O3 -fPIC -lm
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 1.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9468 Xeon Max 9480 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 100 200 300 400 500 Min: 198.99 / Avg: 348.01 / Max: 540.22 Min: 197.84 / Avg: 346.41 / Max: 545.23 Min: 134.59 / Avg: 276.23 / Max: 451.3 Min: 76.28 / Avg: 204.47 / Max: 438.17 Min: 59.66 / Avg: 192.17 / Max: 352.61 Min: 97.81 / Avg: 180.38 / Max: 349.14 Min: 54.59 / Avg: 171.46 / Max: 320.72 Min: 73.28 / Avg: 159.39 / Max: 303.29 Min: 72.94 / Avg: 159.29 / Max: 307.76 Min: 39.49 / Avg: 147.26 / Max: 254.64 Min: 58.72 / Avg: 130.94 / Max: 271.24 Min: 106.05 / Avg: 116.77 / Max: 170.77 Min: 103.88 / Avg: 113.94 / Max: 151.55 Min: 49.47 / Avg: 100.66 / Max: 234.57 Min: 26.86 / Avg: 95.6 / Max: 261.18 Min: 31.1 / Avg: 89.96 / Max: 203.77 Min: 27.35 / Avg: 79.69 / Max: 177.97 Min: 20.59 / Avg: 64.93 / Max: 140.09 Min: 43.45 / Avg: 52.35 / Max: 100.96 Min: 43.59 / Avg: 50.67 / Max: 89.41 Min: 15.89 / Avg: 45.79 / Max: 103.55 Min: 15.19 / Avg: 43.89 / Max: 93.61
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Platinum 8490H Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8380 2P EPYC 9654 EPYC 9754 EPYC 9684X Xeon Platinum 8490H 2P Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P 50K 100K 150K 200K 250K SE +/- 53.56, N = 9 SE +/- 301.54, N = 8 SE +/- 167.65, N = 8 SE +/- 152.92, N = 9 SE +/- 436.97, N = 10 SE +/- 382.59, N = 10 SE +/- 406.29, N = 9 SE +/- 233.83, N = 9 SE +/- 1153.71, N = 15 SE +/- 884.47, N = 9 SE +/- 1372.89, N = 15 SE +/- 1262.04, N = 9 SE +/- 1298.67, N = 9 SE +/- 1415.96, N = 9 SE +/- 2707.72, N = 14 SE +/- 1422.07, N = 7 SE +/- 7207.31, N = 15 SE +/- 1776.37, N = 11 57317.66 62449.55 63930.64 83448.70 85910.95 86407.46 107321.89 110742.15 116725.04 125567.07 134994.14 163333.21 171436.47 172614.10 194942.32 220893.78 244738.81 245447.72 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Xeon Platinum 8380 Xeon Platinum 8380 2P Xeon Max 9480 2P Xeon Max 9468 2P Xeon Max 9480 Xeon Platinum 8490H 2P Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8592+ 2P EPYC 9654 2P Xeon Platinum 8592+ EPYC 8534P EPYC 9684X 2P EPYC 8534PN EPYC 9754 2P EPYC 9654 EPYC 9684X EPYC 9754 300 600 900 1200 1500 378.76 446.48 454.47 476.05 480.22 496.64 499.08 517.49 757.48 823.46 858.24 906.46 928.22 953.72 988.65 1070.68 1119.20 1265.55
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P EPYC 9754 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8490H Xeon Platinum 8380 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 193.92 / Avg: 377.22 / Max: 729.73 Min: 183.3 / Avg: 362.6 / Max: 714.29 Min: 142.29 / Avg: 328.87 / Max: 698.64 Min: 70.18 / Avg: 291.62 / Max: 590.65 Min: 62.46 / Avg: 263.66 / Max: 710.66 Min: 40.32 / Avg: 248.27 / Max: 531.63 Min: 99.93 / Avg: 248.03 / Max: 546.61 Min: 55.9 / Avg: 236.74 / Max: 614.68 Min: 73.21 / Avg: 179.93 / Max: 359.94 Min: 72.77 / Avg: 172.14 / Max: 347.7 Min: 59.14 / Avg: 161.26 / Max: 333.63 Min: 52.21 / Avg: 151.33 / Max: 280.05 Min: 25.53 / Avg: 125.05 / Max: 346.36 Min: 29.67 / Avg: 120.62 / Max: 340.18 Min: 27.57 / Avg: 109.02 / Max: 286.49 Min: 21.58 / Avg: 99.22 / Max: 284.09 Min: 17.11 / Avg: 70.53 / Max: 141.22 Min: 16.49 / Avg: 65.48 / Max: 127.89
srsRAN Project srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Thread Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E Xeon Platinum 8380 Xeon Platinum 8380 2P EPYC 8534P EPYC 8534PN EPYC 9754 2P EPYC 9754 Xeon Max 9468 2P Xeon Max 9480 2P EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8490H 2P Xeon Platinum 8490H EPYC 9684X EPYC 9654 Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8592+ Xeon Platinum 8592+ 2P 160 320 480 640 800 SE +/- 0.32, N = 5 SE +/- 0.32, N = 5 SE +/- 0.66, N = 5 SE +/- 0.24, N = 5 SE +/- 3.57, N = 7 SE +/- 2.08, N = 7 SE +/- 3.14, N = 7 SE +/- 1.24, N = 7 SE +/- 4.48, N = 7 SE +/- 0.80, N = 7 SE +/- 3.86, N = 8 SE +/- 5.02, N = 8 SE +/- 5.52, N = 8 SE +/- 3.72, N = 8 SE +/- 2.57, N = 8 SE +/- 1.17, N = 8 SE +/- 3.13, N = 8 SE +/- 1.71, N = 8 SE +/- 1.64, N = 8 SE +/- 1.27, N = 8 SE +/- 1.34, N = 8 SE +/- 1.89, N = 8 293.1 299.4 323.7 333.2 484.8 490.3 557.9 563.6 576.8 596.2 651.9 663.8 664.7 673.4 675.5 680.2 680.7 684.7 702.6 705.5 742.9 755.5 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -fno-trapping-math -fno-math-errno -ldl
Mbps Per Watt
OpenBenchmarking.org Mbps Per Watt, More Is Better srsRAN Project 23.10.1-20240325 Test: PDSCH Processor Benchmark, Throughput Thread Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 Xeon Max 9468 Xeon Platinum 8380 Xeon Platinum 8490H Xeon 6766E Xeon 6780E EPYC 9684X Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 4 8 12 16 20 2.035 2.065 2.598 2.726 2.979 2.998 3.639 4.074 4.162 4.200 4.788 5.085 5.866 6.116 6.807 7.249 8.628 8.929 9.795 10.675 13.548 14.524
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN Project 23.10.1-20240325 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9684X 2P Xeon Platinum 8380 2P EPYC 9654 2P Xeon Max 9480 Xeon Max 9468 EPYC 9754 2P Xeon Platinum 8490H Xeon 6780E 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 70 140 210 280 350 Min: 199.86 / Avg: 321.38 / Max: 411.1 Min: 204.49 / Avg: 320.28 / Max: 415.75 Min: 161.37 / Avg: 259.97 / Max: 337.8 Min: 80.15 / Avg: 185.44 / Max: 287.05 Min: 63.99 / Avg: 182.65 / Max: 268.9 Min: 98.94 / Avg: 163.54 / Max: 216.84 Min: 56.59 / Avg: 161.78 / Max: 243.41 Min: 85.93 / Avg: 147.34 / Max: 200.38 Min: 73.91 / Avg: 138.16 / Max: 195.36 Min: 38.06 / Avg: 137.34 / Max: 200.95 Min: 62.63 / Avg: 111.22 / Max: 152.68 Min: 104.77 / Avg: 108.64 / Max: 112.06 Min: 103.98 / Avg: 107.54 / Max: 109.81 Min: 24.93 / Avg: 83.2 / Max: 132.66 Min: 51.21 / Avg: 82.65 / Max: 104.34 Min: 30.33 / Avg: 78.89 / Max: 117.61 Min: 28.33 / Avg: 69.9 / Max: 103.51 Min: 20.14 / Avg: 55.85 / Max: 81.57 Min: 43.52 / Avg: 45.97 / Max: 48.12 Min: 43.56 / Avg: 43.98 / Max: 45.49 Min: 18.39 / Avg: 41.18 / Max: 58.06 Min: 13.69 / Avg: 38.81 / Max: 55.52
LAMMPS Molecular Dynamics Simulator LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein Xeon Platinum 8380 EPYC 8534PN EPYC 8534P Xeon Max 9468 Xeon Platinum 8490H Xeon Max 9480 Xeon Platinum 8380 2P Xeon Platinum 8592+ EPYC 9654 EPYC 9684X EPYC 9754 Xeon Platinum 8490H 2P Xeon Max 9468 2P EPYC 9654 2P EPYC 9754 2P Xeon Max 9480 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P 12 24 36 48 60 SE +/- 0.28, N = 15 SE +/- 0.30, N = 15 SE +/- 0.29, N = 15 SE +/- 0.05, N = 11 SE +/- 0.36, N = 15 SE +/- 0.04, N = 11 SE +/- 0.53, N = 15 SE +/- 0.29, N = 15 SE +/- 0.14, N = 11 SE +/- 0.35, N = 15 SE +/- 0.29, N = 10 SE +/- 0.33, N = 8 SE +/- 0.11, N = 9 SE +/- 0.39, N = 7 SE +/- 0.24, N = 5 SE +/- 0.09, N = 8 SE +/- 0.43, N = 7 SE +/- 0.97, N = 15 21.16 21.94 24.25 27.63 28.72 30.84 33.54 34.30 36.15 40.00 40.39 42.28 47.51 50.12 51.63 52.24 53.77 55.50 1. (CXX) g++ options: -O3 -lm -ldl
ns/day Per Watt
OpenBenchmarking.org ns/day Per Watt, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein Xeon Platinum 8490H 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon Max 9468 Xeon Platinum 8380 EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9754 2P Xeon Platinum 8490H Xeon Max 9480 Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 EPYC 8534PN EPYC 8534P 0.104 0.208 0.312 0.416 0.52 0.119 0.129 0.136 0.148 0.179 0.184 0.186 0.189 0.196 0.204 0.209 0.209 0.341 0.358 0.372 0.451 0.451 0.462
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P EPYC 9684X 2P Xeon Platinum 8592+ 2P EPYC 9654 2P EPYC 9754 2P Xeon Platinum 8380 2P Xeon Max 9468 Xeon Max 9480 Xeon Platinum 8490H Xeon Platinum 8380 EPYC 9684X Xeon Platinum 8592+ EPYC 9654 EPYC 9754 EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 185.06 / Avg: 384.54 / Max: 575.71 Min: 188.46 / Avg: 368.48 / Max: 640.19 Min: 158.94 / Avg: 354.59 / Max: 652.14 Min: 60.69 / Avg: 300.13 / Max: 690.91 Min: 63.52 / Avg: 283.35 / Max: 590.85 Min: 56.67 / Avg: 265.38 / Max: 605.84 Min: 41.5 / Avg: 252.99 / Max: 566.7 Min: 99.81 / Avg: 226.26 / Max: 547.72 Min: 74.62 / Avg: 150.09 / Max: 352.27 Min: 73.75 / Avg: 147.45 / Max: 350.72 Min: 59.51 / Avg: 137.71 / Max: 356.46 Min: 51.92 / Avg: 113.55 / Max: 290.07 Min: 27.48 / Avg: 111.71 / Max: 349.02 Min: 22.32 / Avg: 100.63 / Max: 327.13 Min: 26.87 / Avg: 97.2 / Max: 234.7 Min: 20.56 / Avg: 89.57 / Max: 288.34 Min: 16.36 / Avg: 52.44 / Max: 142.05 Min: 15.52 / Avg: 48.67 / Max: 132.86
libavif avifenc This is a test of the AOMedia libavif library testing the encoding of a JPEG image to AV1 Image Format (AVIF). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 Xeon 6766E 2P Xeon 6780E 2P Xeon 6766E Xeon Platinum 8380 Xeon 6780E Xeon Max 9468 2P Xeon Max 9480 2P Xeon Max 9468 EPYC 8534PN Xeon Max 9480 Xeon Platinum 8380 2P EPYC 8534P EPYC 9754 2P EPYC 9754 Xeon Platinum 8490H Xeon Platinum 8490H 2P Xeon Platinum 8592+ EPYC 9684X 2P EPYC 9654 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X 1.0865 2.173 3.2595 4.346 5.4325 SE +/- 0.023, N = 8 SE +/- 0.034, N = 8 SE +/- 0.003, N = 8 SE +/- 0.010, N = 8 SE +/- 0.004, N = 8 SE +/- 0.029, N = 8 SE +/- 0.022, N = 9 SE +/- 0.017, N = 9 SE +/- 0.011, N = 9 SE +/- 0.011, N = 9 SE +/- 0.023, N = 15 SE +/- 0.016, N = 9 SE +/- 0.026, N = 9 SE +/- 0.002, N = 9 SE +/- 0.022, N = 9 SE +/- 0.008, N = 9 SE +/- 0.016, N = 9 SE +/- 0.005, N = 9 SE +/- 0.008, N = 10 SE +/- 0.009, N = 10 SE +/- 0.011, N = 10 SE +/- 0.005, N = 10 4.829 4.486 4.243 4.093 3.872 3.776 3.738 3.730 3.623 3.550 3.528 3.484 3.341 3.251 3.169 3.044 2.971 2.890 2.810 2.805 2.756 2.723 1. (CXX) g++ options: -O3 -fPIC -lm
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better libavif avifenc 1.0 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P Xeon Max 9480 Xeon Max 9468 EPYC 9654 2P Xeon Platinum 8490H EPYC 9754 2P Xeon 6780E 2P Xeon Platinum 8380 Xeon 6766E 2P Xeon Platinum 8592+ EPYC 9684X EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 194.63 / Avg: 375.42 / Max: 682.97 Min: 196.21 / Avg: 370.24 / Max: 687.54 Min: 141.74 / Avg: 294.92 / Max: 681.8 Min: 66.73 / Avg: 224.06 / Max: 669.89 Min: 96.12 / Avg: 215.89 / Max: 534.91 Min: 59.74 / Avg: 193.24 / Max: 500.52 Min: 71.59 / Avg: 183.17 / Max: 376.96 Min: 73.48 / Avg: 180.42 / Max: 357.76 Min: 54.93 / Avg: 178.85 / Max: 447.63 Min: 59.37 / Avg: 149.47 / Max: 376.13 Min: 35.83 / Avg: 144.55 / Max: 349.42 Min: 106.17 / Avg: 135.03 / Max: 247.79 Min: 49.52 / Avg: 131.52 / Max: 290.38 Min: 103.77 / Avg: 129.25 / Max: 219.98 Min: 27.77 / Avg: 125.51 / Max: 374.47 Min: 29.87 / Avg: 106.31 / Max: 349.7 Min: 26.55 / Avg: 92.59 / Max: 299.06 Min: 18.49 / Avg: 76.34 / Max: 238.8 Min: 43.39 / Avg: 69.56 / Max: 179.96 Min: 43.55 / Avg: 64.88 / Max: 147.13 Min: 15.86 / Avg: 54.43 / Max: 150.92 Min: 15.57 / Avg: 49.3 / Max: 126.89
Primesieve Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e12 Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 Xeon 6766E Xeon Platinum 8490H EPYC 8534PN Xeon 6780E Xeon Platinum 8592+ EPYC 8534P Xeon Platinum 8380 2P Xeon Max 9468 2P Xeon Max 9480 2P Xeon 6766E 2P Xeon 6780E 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X EPYC 9754 EPYC 9754 2P EPYC 9654 2P EPYC 9684X 2P 2 4 6 8 10 SE +/- 0.006, N = 6 SE +/- 0.006, N = 7 SE +/- 0.010, N = 7 SE +/- 0.003, N = 8 SE +/- 0.019, N = 8 SE +/- 0.003, N = 8 SE +/- 0.003, N = 8 SE +/- 0.007, N = 8 SE +/- 0.006, N = 8 SE +/- 0.003, N = 9 SE +/- 0.004, N = 9 SE +/- 0.005, N = 10 SE +/- 0.012, N = 10 SE +/- 0.008, N = 10 SE +/- 0.006, N = 10 SE +/- 0.008, N = 11 SE +/- 0.003, N = 11 SE +/- 0.004, N = 11 SE +/- 0.002, N = 11 SE +/- 0.010, N = 15 SE +/- 0.005, N = 12 SE +/- 0.003, N = 12 6.673 6.160 5.332 4.806 4.576 4.545 4.324 4.250 3.801 3.366 3.121 2.691 2.605 2.337 2.325 2.187 2.058 1.984 1.921 1.359 1.242 1.199 1. (CXX) g++ options: -O3
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Primesieve 12.1 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon 6780E 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X 2P Xeon 6766E 2P EPYC 9654 2P Xeon Platinum 8490H Xeon Platinum 8592+ Xeon Platinum 8380 EPYC 9754 2P Xeon 6780E EPYC 9684X EPYC 9654 Xeon 6766E EPYC 9754 EPYC 8534P EPYC 8534PN 140 280 420 560 700 Min: 185.19 / Avg: 432.51 / Max: 754.28 Min: 188 / Avg: 419.03 / Max: 755.09 Min: 167.18 / Avg: 384.89 / Max: 756.1 Min: 99.97 / Avg: 315.19 / Max: 581.5 Min: 70.6 / Avg: 304.92 / Max: 755.57 Min: 105.81 / Avg: 260.26 / Max: 569.59 Min: 41.72 / Avg: 247.24 / Max: 378.01 Min: 75.05 / Avg: 240.32 / Max: 376.42 Min: 65.08 / Avg: 239.55 / Max: 813.29 Min: 104.53 / Avg: 228.57 / Max: 454.64 Min: 58.4 / Avg: 217.76 / Max: 736.92 Min: 53.72 / Avg: 216.08 / Max: 377.44 Min: 20.57 / Avg: 195.27 / Max: 377.63 Min: 52.68 / Avg: 193.17 / Max: 291 Min: 39.28 / Avg: 188.39 / Max: 630.34 Min: 43.47 / Avg: 160.81 / Max: 278.45 Min: 33.95 / Avg: 157.31 / Max: 410.23 Min: 26.05 / Avg: 142.51 / Max: 369.88 Min: 43.73 / Avg: 134.25 / Max: 215.68 Min: 21.44 / Avg: 116.27 / Max: 317.57 Min: 16.53 / Avg: 87.74 / Max: 161.22 Min: 16.77 / Avg: 72.3 / Max: 123.74
Parallel BZIP2 Compression This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression Xeon Platinum 8380 Xeon Max 9468 Xeon 6766E EPYC 8534PN Xeon Max 9480 Xeon 6780E EPYC 8534P Xeon Platinum 8380 2P Xeon Platinum 8490H Xeon Max 9468 2P Xeon 6766E 2P Xeon Platinum 8592+ Xeon 6780E 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P EPYC 9654 EPYC 9684X EPYC 9754 EPYC 9654 2P EPYC 9684X 2P EPYC 9754 2P 0.7635 1.527 2.2905 3.054 3.8175 SE +/- 0.048155, N = 15 SE +/- 0.023295, N = 15 SE +/- 0.012826, N = 10 SE +/- 0.016947, N = 15 SE +/- 0.020941, N = 15 SE +/- 0.014326, N = 10 SE +/- 0.023387, N = 15 SE +/- 0.026496, N = 15 SE +/- 0.007749, N = 10 SE +/- 0.030907, N = 15 SE +/- 0.015355, N = 15 SE +/- 0.023842, N = 15 SE +/- 0.015943, N = 15 SE +/- 0.028863, N = 15 SE +/- 0.017240, N = 15 SE +/- 0.024402, N = 15 SE +/- 0.014512, N = 15 SE +/- 0.015384, N = 15 SE +/- 0.010826, N = 15 SE +/- 0.019468, N = 15 SE +/- 0.015217, N = 15 SE +/- 0.012053, N = 15 3.393189 2.632077 2.504621 2.321195 2.287766 2.279971 2.200497 2.181455 2.144857 1.982932 1.857642 1.847537 1.718022 1.711296 1.469210 1.432362 1.422954 1.369063 1.355737 1.126329 1.109446 1.068398 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Parallel BZIP2 Compression 1.1.13 CPU Power Consumption Monitor Xeon Max 9468 2P Xeon Max 9480 2P Xeon Platinum 8490H 2P Xeon Platinum 8380 2P Xeon Platinum 8592+ 2P Xeon Max 9468 Xeon Max 9480 EPYC 9684X 2P EPYC 9654 2P Xeon 6780E 2P Xeon Platinum 8490H Xeon 6766E 2P Xeon Platinum 8380 EPYC 9754 2P Xeon Platinum 8592+ EPYC 9684X EPYC 9654 Xeon 6780E Xeon 6766E EPYC 9754 EPYC 8534P EPYC 8534PN 120 240 360 480 600 Min: 199.37 / Avg: 345.8 / Max: 682.95 Min: 193.42 / Avg: 340.67 / Max: 703.88 Min: 162.27 / Avg: 288.67 / Max: 640.02 Min: 95.47 / Avg: 220.44 / Max: 552.38 Min: 71.11 / Avg: 201.02 / Max: 594.06 Min: 72.25 / Avg: 174.54 / Max: 371.49 Min: 73.85 / Avg: 174.26 / Max: 374.82 Min: 58 / Avg: 170.11 / Max: 493.47 Min: 52.77 / Avg: 151.26 / Max: 452.63 Min: 104.74 / Avg: 150.21 / Max: 342.71 Min: 59.1 / Avg: 149.7 / Max: 374.85 Min: 103.93 / Avg: 141.47 / Max: 301.99 Min: 50.9 / Avg: 141.25 / Max: 290.87 Min: 39.33 / Avg: 126.08 / Max: 368.96 Min: 33.01 / Avg: 124.42 / Max: 372.52 Min: 32.91 / Avg: 100.67 / Max: 337.76 Min: 26.03 / Avg: 87.61 / Max: 297.16 Min: 43.43 / Avg: 79.98 / Max: 238.53 Min: 43.62 / Avg: 72.77 / Max: 199.71 Min: 21.06 / Avg: 71.78 / Max: 246.91 Min: 15.97 / Avg: 55.16 / Max: 153.03 Min: 16.36 / Avg: 50.15 / Max: 132.7
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.4 Harness: Deconvolution Batch shapes_3d - Engine: CPU Xeon 6766E 2P Xeon 6766E Xeon 6780E 2P Xeon 6780E EPYC 8534PN EPYC 8534P Xeon Platinum 8380 Xeon Max 9468 Xeon Max 9480 EPYC 9654 EPYC 9684X Xeon Platinum 8490H EPYC 9654 2P EPYC 9684X 2P Xeon Max 9468 2P EPYC 9754 Xeon Platinum 8592+ Xeon Platinum 8380 2P Xeon Max 9480 2P EPYC 9754 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P 0.5619 1.1238 1.6857 2.2476 2.8095 SE +/- 0.001467, N = 9 SE +/- 0.001097, N = 9 SE +/- 0.001365, N = 9 SE +/- 0.002181, N = 9 SE +/- 0.001685, N = 9 SE +/- 0.000791, N = 9 SE +/- 0.006599, N = 9 SE +/- 0.000508, N = 9 SE +/- 0.000927, N = 9 SE +/- 0.001484, N = 9 SE +/- 0.001272, N = 9 SE +/- 0.000805, N = 9 SE +/- 0.001921, N = 9 SE +/- 0.002070, N = 9 SE +/- 0.000806, N = 9 SE +/- 0.001089, N = 9 SE +/- 0.000392, N = 9 SE +/- 0.001091, N = 9 SE +/- 0.001240, N = 9 SE +/- 0.003127, N = 9 SE +/- 0.001274, N = 9 SE +/- 0.000902, N = 9 2.497340 2.297120 2.245260 2.049100 1.797490 1.498350 1.422130 1.264070 1.196430 1.154870 1.119230 1.077430 1.009473 1.001914 0.945075 0.943621 0.907161 0.867065 0.864358 0.829653 0.736170 0.624250 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better oneDNN 3.4 CPU Power Consumption Monitor Xeon Max 9480 2P Xeon Max 9468 2P Xeon Platinum 8490H 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9684X 2P EPYC 9654 2P EPYC 9754 2P Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon 6766E 2P Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9684X Xeon Platinum 8380 EPYC 9654 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 130 260 390 520 650 Min: 187.54 / Avg: 431.59 / Max: 733.22 Min: 194.92 / Avg: 425.54 / Max: 706.02 Min: 169.45 / Avg: 409.27 / Max: 716.88 Min: 70.82 / Avg: 355.72 / Max: 740.88 Min: 98.61 / Avg: 304.22 / Max: 566.32 Min: 62.97 / Avg: 300.29 / Max: 621 Min: 53.59 / Avg: 275.56 / Max: 567.73 Min: 40.43 / Avg: 245.22 / Max: 491.94 Min: 105.63 / Avg: 213.96 / Max: 368.1 Min: 69.85 / Avg: 202.05 / Max: 376 Min: 73.57 / Avg: 201.22 / Max: 367.75 Min: 103.52 / Avg: 196.1 / Max: 321.17 Min: 51.81 / Avg: 187.58 / Max: 359.76 Min: 23.58 / Avg: 173.49 / Max: 373.63 Min: 32.75 / Avg: 155.62 / Max: 314.15 Min: 48.87 / Avg: 151.05 / Max: 290.31 Min: 26.3 / Avg: 135.34 / Max: 274.99 Min: 20.19 / Avg: 122.35 / Max: 259.22 Min: 43.45 / Avg: 112.89 / Max: 208.27 Min: 43.57 / Avg: 98.35 / Max: 172.87 Min: 16.93 / Avg: 70.08 / Max: 140.81 Min: 15.81 / Avg: 62.56 / Max: 121.69
CPU Power Consumption Monitor OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring Xeon Max 9480 2P Xeon Max 9468 2P EPYC 9684X 2P Xeon Platinum 8490H 2P EPYC 9654 2P Xeon Platinum 8592+ 2P Xeon Platinum 8380 2P EPYC 9754 2P Xeon 6780E 2P Xeon Max 9480 Xeon Max 9468 Xeon 6766E 2P EPYC 9684X Xeon Platinum 8490H Xeon Platinum 8592+ EPYC 9654 Xeon Platinum 8380 EPYC 9754 Xeon 6780E Xeon 6766E EPYC 8534P EPYC 8534PN 170 340 510 680 850 Min: 95.52 / Avg: 569.8 / Max: 760.61 Min: 102.49 / Avg: 566.6 / Max: 756.48 Min: 33.66 / Avg: 525.49 / Max: 837.69 Min: 87.48 / Avg: 517.33 / Max: 758.17 Min: 35.7 / Avg: 464.49 / Max: 751.79 Min: 39.72 / Avg: 455.07 / Max: 946.96 Min: 51.38 / Avg: 437.37 / Max: 583.47 Min: 20.22 / Avg: 375.51 / Max: 735.74 Min: 53.44 / Avg: 321.01 / Max: 713.33 Min: 38.16 / Avg: 295.53 / Max: 384.53 Min: 38.11 / Avg: 291.53 / Max: 379.76 Min: 52.85 / Avg: 291.05 / Max: 542.48 Min: 17.06 / Avg: 290.08 / Max: 413.51 Min: 30.38 / Avg: 278.1 / Max: 383.24 Min: 17.77 / Avg: 260.08 / Max: 405.42 Min: 14.69 / Avg: 244.69 / Max: 373.1 Min: 26.31 / Avg: 237.91 / Max: 292.14 Min: 10.09 / Avg: 225.05 / Max: 397.44 Min: 21.7 / Avg: 169.1 / Max: 357.69 Min: 21.86 / Avg: 142.1 / Max: 271.22 Min: 8.43 / Avg: 128.7 / Max: 184.62 Min: 9.26 / Avg: 114.13 / Max: 155.71
Xeon Platinum 8490H Processor: Intel Xeon Platinum 8490H @ 3.50GHz (60 Cores / 120 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000590Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 16 April 2024 00:42 by user phoronix.
Xeon Platinum 8490H 2P Processor: 2 x Intel Xeon Platinum 8490H @ 3.50GHz (120 Cores / 240 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2b000590Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 17 April 2024 09:38 by user phoronix.
Xeon Platinum 8592+ Processor: INTEL XEON PLATINUM 8592+ @ 3.90GHz (64 Cores / 128 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 512GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000200Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 April 2024 18:15 by user phoronix.
Xeon Platinum 8592+ 2P Processor: 2 x INTEL XEON PLATINUM 8592+ @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1008GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x21000200Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 8 April 2024 10:49 by user phoronix.
Xeon Max 9468 Processor: Intel Xeon Max 9468 @ 3.50GHz (48 Cores / 96 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 576GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 21 April 2024 09:58 by user phoronix.
Xeon Max 9468 2P Processor: 2 x Intel Xeon Max 9468 @ 3.50GHz (96 Cores / 192 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1136GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 22 April 2024 15:30 by user phoronix.
Xeon Max 9480 Processor: Intel Xeon Max 9480 @ 3.50GHz (56 Cores / 112 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 576GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 26 April 2024 09:38 by user phoronix.
Xeon Max 9480 2P Processor: 2 x Intel Xeon Max 9480 @ 3.50GHz (112 Cores / 224 Threads), Motherboard: Quanta Cloud QuantaGrid D54Q-2U S6Q-MB-MPS (3B05.TEL4P1 BIOS), Chipset: Intel Device 1bce, Memory: 1136GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Intel X710 for 10GBASE-T
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x2c000290Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 27 April 2024 16:18 by user phoronix.
Xeon Platinum 8380 2P Processor: 2 x Intel Xeon Platinum 8380 @ 3.40GHz (80 Cores / 160 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Ice Lake IEH, Memory: 512GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd0003d1Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 7 May 2024 16:33 by user phoronix.
Xeon Platinum 8380 Processor: Intel Xeon Platinum 8380 @ 3.40GHz (40 Cores / 80 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Ice Lake IEH, Memory: 256GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0xd0003d1Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Mitigation of Microcode + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 9 May 2024 13:53 by user phoronix.
EPYC 9684X 2P Processor: 2 x AMD EPYC 9684X 96-Core @ 2.55GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 11 May 2024 02:04 by user phoronix.
EPYC 9684X Processor: AMD EPYC 9684X 96-Core @ 2.55GHz (96 Cores / 192 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 12 May 2024 12:29 by user phoronix.
EPYC 9654 Processor: AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 13 May 2024 14:14 by user phoronix.
EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 14 May 2024 15:08 by user phoronix.
EPYC 9754 Processor: AMD EPYC 9754 128-Core @ 2.25GHz (128 Cores / 256 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 15 May 2024 21:09 by user phoronix.
EPYC 9754 2P Processor: 2 x AMD EPYC 9754 128-Core @ 2.25GHz (256 Cores / 512 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00116Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 17 May 2024 00:34 by user phoronix.
EPYC 8534P Processor: AMD EPYC 8534P 64-Core @ 2.30GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DDR5-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92 + 2000GB Corsair MP700 PRO, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00213Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 18 May 2024 13:07 by user phoronix.
EPYC 8534PN Processor: AMD EPYC 8534PN 64-Core @ 2.00GHz (64 Cores / 128 Threads), Motherboard: AMD Cinnabar (RCB1009C BIOS), Chipset: AMD Device 14a4, Memory: 6 x 32GB DDR5-4800MT/s Samsung M321R4GA0BB0-CQKMG, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xaa00213Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 May 2024 17:06 by user phoronix.
Xeon 6766E 2P Processor: 2 x Intel Xeon 6766E @ 2.70GHz (288 Cores), Motherboard: Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS), Chipset: Intel Ice Lake IEH, Memory: 512GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS + 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 24 May 2024 12:45 by user phoronix.
Xeon 6766E Processor: Intel Xeon 6766E @ 2.70GHz (144 Cores), Motherboard: Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS), Chipset: Intel Ice Lake IEH, Memory: 256GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92 + 3201GB Micron_7450_MTFDKCB3T2TFS, Graphics: ASPEED, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 25 May 2024 14:43 by user phoronix.
Xeon 6780E Processor: Intel Xeon 6780E @ 3.00GHz (144 Cores), Motherboard: Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS), Chipset: Intel Ice Lake IEH, Memory: 256GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS + 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 26 May 2024 18:38 by user phoronix.
Xeon 6780E 2P Processor: 2 x Intel Xeon 6780E @ 3.00GHz (288 Cores), Motherboard: Quanta Cloud QuantaGrid D55Q-2U S7Q-MB-MPS-MDP (2A05.QCT001 BIOS), Chipset: Intel Ice Lake IEH, Memory: 512GB, Disk: 3201GB Micron_7450_MTFDKCB3T2TFS + 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x13000131Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 27 May 2024 18:06 by user phoronix.