Tests for a future article on Phoronix.
EPYC 7713 2P Processor: 2 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 7713 Changed Processor to AMD EPYC 7713 64-Core @ 2.00GHz (64 Cores / 128 Threads) .
Changed Memory to 256GB .
EPYC 7763 Changed Processor to AMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads) .
EPYC 7763 2P Changed Processor to 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads) .
Changed Memory to 512GB .
EPYC 7773X Changed Processor to AMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads) .
Changed Memory to 256GB .
Processor Change: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa001229
EPYC 7773X 2P Changed Processor to 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads) .
Changed Memory to 512GB .
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 IEHMemory: 256GBDisk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xd000375Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Xeon Platinum 8362 Changed Processor to Intel Xeon Platinum 8362 @ 3.60GHz (32 Cores / 64 Threads) .
Xeon Platinum 8362 2P Changed Processor to 2 x Intel Xeon Platinum 8362 @ 3.60GHz (64 Cores / 128 Threads) .
Changed Memory to 512GB .
EPYC 9654 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9654 - Power Processor: AMD EPYC 9654 96-Core @ 3.71GHz (96 Cores / 192 Threads)Motherboard: AMD Titanite_4G (RTI1002E BIOS)Chipset: AMD Device 14a4Memory: 768GBDisk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMINetwork: Broadcom NetXtreme BCM5720 PCIe
EPYC 9654 2P EPYC 9654 2P - Power Changed Processor to 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads) .
Changed Memory to 1520GB .
EPYC 75F3 2P Processor: 2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads)Motherboard: AMD DAYTONA_X (RYM1009B BIOS)Chipset: AMD Starship/MatisseMemory: 512GBDisk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228Network: 2 x Mellanox MT27710
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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 75F3 Changed Processor to AMD EPYC 75F3 32-Core @ 2.95GHz (32 Cores / 64 Threads) .
Changed Memory to 256GB .
EPYC 9554 2P 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9554 2P - Power Processor: 2 x AMD EPYC 9554 64-Core @ 3.76GHz (128 Cores / 256 Threads)Motherboard: AMD Titanite_4G (RTI1002E BIOS)Chipset: AMD Device 14a4Memory: 1520GBDisk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMINetwork: Broadcom NetXtreme BCM5720 PCIe
EPYC 9554 - Power EPYC 9554 Changed Processor to AMD EPYC 9554 64-Core @ 3.76GHz (64 Cores / 128 Threads) .
Changed Memory to 768GB .
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 IEHMemory: 512GBDisk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xd000375Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 3K 6K 9K 12K 15K SE +/- 14.36, N = 3 SE +/- 9.84, N = 3 SE +/- 16.12, N = 3 SE +/- 11.42, N = 3 SE +/- 3.55, N = 3 SE +/- 0.72, N = 3 SE +/- 0.65, N = 3 SE +/- 3.81, N = 3 SE +/- 5.13, N = 3 SE +/- 7.76, N = 3 SE +/- 5.49, N = 3 SE +/- 3.31, N = 3 SE +/- 3.26, N = 3 SE +/- 1.28, N = 3 SE +/- 1.40, N = 3 SE +/- 2.25, N = 3 SE +/- 0.83, N = 3 SE +/- 2.45, N = 3 SE +/- 1.18, N = 3 SE +/- 4.40, N = 3 4360.68 4978.42 5429.94 9215.52 9148.55 1257.26 2400.26 12490.17 11178.65 6582.28 6003.73 3873.02 1976.25 2255.59 3659.99 1864.66 3748.34 1901.21 1694.53 3317.72 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2K 4K 6K 8K 10K SE +/- 8.28, N = 3 SE +/- 2.56, N = 3 SE +/- 12.97, N = 3 SE +/- 5.54, N = 3 SE +/- 6.11, N = 3 SE +/- 0.72, N = 3 SE +/- 0.14, N = 3 SE +/- 0.76, N = 3 SE +/- 3.74, N = 3 SE +/- 8.43, N = 3 SE +/- 5.10, N = 3 SE +/- 5.47, N = 3 SE +/- 2.38, N = 3 SE +/- 1.06, N = 3 SE +/- 1.92, N = 3 SE +/- 0.30, N = 3 SE +/- 0.68, N = 3 SE +/- 0.54, N = 3 SE +/- 0.76, N = 3 SE +/- 5.98, N = 3 2007.14 4762.61 4936.15 7429.47 7395.02 1128.76 2023.85 9661.33 9010.78 6138.92 5763.31 1727.84 984.42 1127.83 3202.24 1876.12 2914.32 1637.96 1520.03 2682.29 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 800 1600 2400 3200 4000 SE +/- 5.16, N = 3 SE +/- 0.18, N = 3 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 SE +/- 0.37, N = 3 SE +/- 4.30, N = 3 SE +/- 1.37, N = 3 SE +/- 1.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.45, N = 3 SE +/- 0.29, N = 3 SE +/- 0.65, N = 3 SE +/- 2.14, N = 3 SE +/- 4.78, N = 3 SE +/- 5.57, N = 3 SE +/- 1.12, N = 3 SE +/- 2.80, N = 3 SE +/- 3.86, N = 3 SE +/- 5.55, N = 3 SE +/- 9.94, N = 3 831.48 766.80 744.44 383.87 389.27 2386.41 1432.86 435.80 468.17 890.80 955.51 730.17 1466.52 1645.06 1821.21 3059.08 1982.52 3238.66 3554.86 2018.73 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 129.52 / Avg: 501.81 / Max: 578 Min: 21.63 / Avg: 320.86 / Max: 354.8 Min: 19.13 / Avg: 352.43 / Max: 391.7 Min: 43.77 / Avg: 663.63 / Max: 739.28 Min: 42.37 / Avg: 622.51 / Max: 694.58 Min: 42.13 / Avg: 230.46 / Max: 274.71 Min: 88.88 / Avg: 420.96 / Max: 501.02 Min: 55.25 / Avg: 729.04 / Max: 819.1 Min: 46.88 / Avg: 629.14 / Max: 707.31 Min: 26.55 / Avg: 368.56 / Max: 409.49 Min: 25.28 / Avg: 325.94 / Max: 359.96 Min: 109.7 / Avg: 492.64 / Max: 566.4 Min: 58.35 / Avg: 247.17 / Max: 283.31 Min: 60.77 / Avg: 251.92 / Max: 290.86 Min: 74.42 / Avg: 404.4 / Max: 487.19 Min: 33.88 / Avg: 220.05 / Max: 263.39 Min: 77.84 / Avg: 381.29 / Max: 466.33 Min: 35.68 / Avg: 218.18 / Max: 263.67 Min: 37.75 / Avg: 202.6 / Max: 230.61 Min: 80.94 / Avg: 382.72 / Max: 448.61
Sysbench This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200K 400K 600K 800K 1000K SE +/- 2.38, N = 3 SE +/- 24.46, N = 3 SE +/- 51.83, N = 3 SE +/- 425.17, N = 3 SE +/- 284.53, N = 3 SE +/- 5.76, N = 3 SE +/- 153.88, N = 3 SE +/- 1525.81, N = 3 SE +/- 1204.93, N = 3 SE +/- 28.32, N = 3 SE +/- 1162.56, N = 3 SE +/- 19.61, N = 3 SE +/- 28.31, N = 3 SE +/- 3.27, N = 3 SE +/- 738.28, N = 3 SE +/- 64.96, N = 3 SE +/- 171.45, N = 3 SE +/- 16.30, N = 3 SE +/- 35.68, N = 3 SE +/- 661.98, N = 3 214410.59 309133.88 309102.11 615220.30 615405.64 154204.56 307896.27 910333.64 896449.81 457526.55 446395.22 200101.40 99997.31 107244.82 528491.57 265046.14 503926.60 252773.24 252327.02 500770.94 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm Events Per Second Per Watt
OpenBenchmarking.org Events Per Second Per Watt, More Is Better Sysbench 1.0.20 Test: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300 600 900 1200 1500 418.68 1468.84 1475.90 1361.03 1376.52 760.39 758.58 1467.99 1592.51 1559.96 1599.81 393.03 390.69 419.36 1130.40 1187.26 1256.25 1281.01 1187.22 1154.84 Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Sysbench 1.0.20 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 133.37 / Avg: 512.11 / Max: 536.26 Min: 21.98 / Avg: 210.46 / Max: 219.68 Min: 19.52 / Avg: 209.43 / Max: 219.45 Min: 43.53 / Avg: 452.02 / Max: 474.52 Min: 43.15 / Avg: 447.07 / Max: 474.53 Min: 43.78 / Avg: 202.8 / Max: 211.21 Min: 88.49 / Avg: 405.89 / Max: 426.02 Min: 53.84 / Avg: 620.12 / Max: 648.97 Min: 52.11 / Avg: 562.92 / Max: 590.67 Min: 27.37 / Avg: 293.29 / Max: 307.2 Min: 26.6 / Avg: 279.03 / Max: 292.72 Min: 112.98 / Avg: 509.12 / Max: 538.71 Min: 58.17 / Avg: 255.95 / Max: 279.42 Min: 59.73 / Avg: 255.74 / Max: 269.41 Min: 73.89 / Avg: 467.53 / Max: 491.8 Min: 34.66 / Avg: 223.24 / Max: 232.82 Min: 76.92 / Avg: 401.14 / Max: 423.62 Min: 36.21 / Avg: 197.32 / Max: 205.71 Min: 37.95 / Avg: 212.54 / Max: 221.84 Min: 82.44 / Avg: 433.63 / Max: 453.81
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 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 12 24 36 48 60 SE +/- 0.04916, N = 3 SE +/- 0.05480, N = 3 SE +/- 0.00729, N = 3 SE +/- 0.04942, N = 3 SE +/- 0.02772, N = 3 SE +/- 0.01042, N = 3 SE +/- 0.01491, N = 3 SE +/- 0.07975, N = 3 SE +/- 0.03899, N = 3 SE +/- 0.18329, N = 3 SE +/- 0.01091, N = 3 SE +/- 0.13341, N = 3 SE +/- 0.00577, N = 3 SE +/- 0.05149, N = 3 SE +/- 0.00542, N = 3 SE +/- 0.00528, N = 3 SE +/- 0.01650, N = 3 SE +/- 0.01245, N = 3 SE +/- 0.00239, N = 3 SE +/- 0.00705, N = 3 20.86190 21.52230 22.02300 37.95240 37.04640 5.74578 10.41370 51.70710 43.96430 30.55600 26.53200 18.78300 9.55766 10.84000 16.39690 9.14710 16.40950 9.05040 7.85484 13.41800 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/ao/real_time Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0209 0.0418 0.0627 0.0836 0.1045 0.041 0.078 0.076 0.067 0.068 0.022 0.020 0.071 0.077 0.081 0.093 0.037 0.038 0.043 0.031 0.035 0.032 0.035 0.037 0.032 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 127.43 / Avg: 513.17 / Max: 572.31 Min: 21.74 / Avg: 275.05 / Max: 292.85 Min: 19.92 / Avg: 289.8 / Max: 309.28 Min: 43.36 / Avg: 568.56 / Max: 614.04 Min: 41.82 / Avg: 545.74 / Max: 585.64 Min: 42.69 / Avg: 262.52 / Max: 283.6 Min: 88.55 / Avg: 514.75 / Max: 560.47 Min: 52.35 / Avg: 729.01 / Max: 793.2 Min: 48.96 / Avg: 568.99 / Max: 610.31 Min: 26.97 / Avg: 377.47 / Max: 404.56 Min: 26.96 / Avg: 285.52 / Max: 304.14 Min: 113.04 / Avg: 505.67 / Max: 564 Min: 60.72 / Avg: 249.73 / Max: 284.5 Min: 60.99 / Avg: 253.97 / Max: 289.38 Min: 74.4 / Avg: 525.27 / Max: 573.49 Min: 34.24 / Avg: 260.9 / Max: 286.01 Min: 77.91 / Avg: 520.5 / Max: 571.78 Min: 35.68 / Avg: 260.57 / Max: 285.01 Min: 37.7 / Avg: 214.08 / Max: 230.02 Min: 80.62 / Avg: 425.96 / Max: 459.85
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 6 12 18 24 30 SE +/- 0.032603, N = 4 SE +/- 0.064993, N = 6 SE +/- 0.036194, N = 6 SE +/- 0.057833, N = 15 SE +/- 0.066125, N = 12 SE +/- 0.030708, N = 4 SE +/- 0.030410, N = 6 SE +/- 0.035923, N = 15 SE +/- 0.044883, N = 15 SE +/- 0.084204, N = 15 SE +/- 0.049036, N = 15 SE +/- 0.010884, N = 3 SE +/- 0.069582, N = 3 SE +/- 0.051396, N = 3 SE +/- 0.041035, N = 7 SE +/- 0.073072, N = 10 SE +/- 0.063855, N = 15 SE +/- 0.071304, N = 5 SE +/- 0.062388, N = 4 SE +/- 0.049975, N = 15 15.720770 7.065542 6.936430 3.816929 3.832093 14.199920 7.652095 3.053326 3.512603 5.211232 5.846230 16.740790 27.341180 26.161180 5.124529 9.518781 5.500317 10.160930 11.318450 5.691778 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 138.88 / Avg: 459.33 / Max: 580.58 Min: 21.71 / Avg: 196.03 / Max: 311.73 Min: 20.47 / Avg: 203.22 / Max: 321.5 Min: 42.55 / Avg: 331.09 / Max: 669.31 Min: 42.73 / Avg: 309.24 / Max: 626.41 Min: 42.75 / Avg: 218.89 / Max: 280.44 Min: 88.61 / Avg: 367.96 / Max: 557.1 Min: 52.51 / Avg: 366.42 / Max: 820.19 Min: 49.54 / Avg: 317.46 / Max: 648.56 Min: 27.15 / Avg: 233.06 / Max: 409.48 Min: 23.61 / Avg: 190.32 / Max: 318.29 Min: 112.92 / Avg: 451.46 / Max: 568.74 Min: 57.58 / Avg: 238.3 / Max: 285.3 Min: 60.36 / Avg: 240.55 / Max: 289.96 Min: 74.82 / Avg: 326.7 / Max: 569.99 Min: 34.37 / Avg: 196.34 / Max: 278.95 Min: 77.38 / Avg: 305.1 / Max: 503.65 Min: 35.82 / Avg: 192.68 / Max: 271.42 Min: 37.57 / Avg: 174.18 / Max: 230.02 Min: 81.62 / Avg: 298.2 / Max: 460.73
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: Eigen Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2K 4K 6K 8K 10K SE +/- 31.21, N = 3 SE +/- 105.96, N = 3 SE +/- 109.97, N = 3 SE +/- 83.80, N = 3 SE +/- 22.88, N = 3 SE +/- 9.29, N = 3 SE +/- 81.86, N = 9 SE +/- 125.50, N = 4 SE +/- 125.11, N = 3 SE +/- 7.94, N = 3 SE +/- 107.55, N = 4 SE +/- 88.45, N = 3 SE +/- 15.30, N = 3 SE +/- 37.69, N = 3 SE +/- 62.77, N = 3 SE +/- 13.96, N = 3 SE +/- 32.87, N = 3 SE +/- 27.81, N = 3 SE +/- 40.72, N = 3 SE +/- 39.68, N = 3 5899 8996 9607 10188 9699 1165 7022 10387 9009 10155 9258 6643 1682 4458 5808 5286 4598 3898 3596 4184 1. (CXX) g++ options: -flto -pthread Nodes Per Second Per Watt
OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better LeelaChessZero 0.28 Backend: Eigen Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 9 18 27 36 45 14.422 38.612 38.560 28.079 28.044 4.330 14.376 26.073 24.870 37.268 38.966 14.745 6.518 17.276 17.202 22.815 13.348 17.366 17.303 12.451 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LeelaChessZero 0.28 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 129.92 / Avg: 409.04 / Max: 574.47 Min: 21.98 / Avg: 232.99 / Max: 280.55 Min: 19.32 / Avg: 249.14 / Max: 321 Min: 40.65 / Avg: 362.83 / Max: 456.39 Min: 38.93 / Avg: 345.85 / Max: 457.56 Min: 42.91 / Avg: 269.07 / Max: 284.94 Min: 88.92 / Avg: 488.45 / Max: 564.37 Min: 54.05 / Avg: 398.38 / Max: 493.26 Min: 52.53 / Avg: 362.24 / Max: 491.7 Min: 27.02 / Avg: 272.49 / Max: 343.72 Min: 26.67 / Avg: 237.59 / Max: 276.76 Min: 113.94 / Avg: 450.52 / Max: 566.04 Min: 58.7 / Avg: 258.07 / Max: 286.34 Min: 60.23 / Avg: 258.05 / Max: 290.93 Min: 75.25 / Avg: 337.64 / Max: 556.57 Min: 34.57 / Avg: 231.69 / Max: 286.96 Min: 77.47 / Avg: 344.48 / Max: 526.64 Min: 35.86 / Avg: 224.46 / Max: 272.15 Min: 37.95 / Avg: 207.82 / Max: 230.35 Min: 81.41 / Avg: 336.04 / Max: 460.71
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 2021.01.31 Threads: 256 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 3000M 6000M 9000M 12000M 15000M SE +/- 968389.27, N = 3 SE +/- 8467191.58, N = 3 SE +/- 3002406.44, N = 3 SE +/- 3352776.63, N = 3 SE +/- 2940710.42, N = 3 SE +/- 2331189.49, N = 3 SE +/- 1593040.42, N = 3 SE +/- 11259563.84, N = 3 SE +/- 4841946.35, N = 3 SE +/- 9056182.66, N = 3 SE +/- 6811836.10, N = 3 SE +/- 12187197.29, N = 3 SE +/- 4336793.49, N = 3 SE +/- 9781672.20, N = 3 SE +/- 3023794.53, N = 3 SE +/- 1549551.91, N = 3 SE +/- 1437976.97, N = 3 SE +/- 1083717.88, N = 3 SE +/- 4246174.75, N = 3 SE +/- 1471205.10, N = 3 2970366667 4512600000 4948166667 9696366667 8713666667 2165866667 4101633333 12204333333 10334333333 6140266667 5193466667 2722233333 1405466667 1561866667 5852900000 3040433333 6047133333 3093166667 2781400000 5383866667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 256 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4M 8M 12M 16M 20M 6232902.36 16727149.57 15186590.26 14774448.75 16357169.01 9018545.80 8668105.08 17848245.05 19291460.05 17902710.48 19130113.02 5871083.39 6015221.53 6588124.73 13456898.87 14094001.65 13862058.97 14192271.39 14037706.65 13659807.24 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 141.09 / Avg: 476.56 / Max: 581.22 Min: 22 / Avg: 269.78 / Max: 325.99 Min: 20.51 / Avg: 325.82 / Max: 396.66 Min: 43.55 / Avg: 656.29 / Max: 791.43 Min: 43.01 / Avg: 532.71 / Max: 652.53 Min: 43.12 / Avg: 240.16 / Max: 280.79 Min: 88.03 / Avg: 473.51 / Max: 558.64 Min: 54.28 / Avg: 683.78 / Max: 820.45 Min: 52.32 / Avg: 535.69 / Max: 637.06 Min: 27.42 / Avg: 342.98 / Max: 407.81 Min: 25.36 / Avg: 271.48 / Max: 329.23 Min: 111.28 / Avg: 463.67 / Max: 569.41 Min: 60.26 / Avg: 233.65 / Max: 284.33 Min: 59.44 / Avg: 237.07 / Max: 290.72 Min: 74.27 / Avg: 434.94 / Max: 514.5 Min: 34.76 / Avg: 215.73 / Max: 253.58 Min: 76.59 / Avg: 436.24 / Max: 515.01 Min: 36.1 / Avg: 217.95 / Max: 256.61 Min: 37.97 / Avg: 198.14 / Max: 230.29 Min: 81.13 / Avg: 394.14 / Max: 460.57
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 Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20K 40K 60K 80K 100K SE +/- 63.40, N = 3 SE +/- 130.07, N = 3 SE +/- 136.28, N = 3 SE +/- 97.02, N = 4 SE +/- 112.63, N = 4 SE +/- 68.14, N = 3 SE +/- 37.10, N = 3 SE +/- 454.82, N = 5 SE +/- 111.70, N = 5 SE +/- 124.44, N = 4 SE +/- 55.16, N = 3 SE +/- 4.72, N = 3 SE +/- 13.24, N = 3 SE +/- 15.93, N = 3 SE +/- 155.40, N = 3 SE +/- 55.66, N = 3 SE +/- 33.60, N = 3 SE +/- 83.10, N = 3 SE +/- 91.06, N = 3 SE +/- 32.01, N = 3 26408.3 48513.8 48786.0 82034.8 81468.5 24666.2 37718.9 111088.8 103903.1 63045.5 58736.1 23539.9 12857.1 14460.6 43442.8 36431.4 57031.0 31459.2 28571.8 51273.3 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 6.12.1 Variant: Monero - Hash Count: 1M Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 53.69 169.64 167.37 166.04 165.78 95.55 78.85 201.87 216.49 194.36 209.00 48.29 50.72 56.07 91.52 145.42 126.34 126.23 140.12 135.54 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xmrig 6.12.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 132.78 / Avg: 491.87 / Max: 582.24 Min: 22.21 / Avg: 285.98 / Max: 345.86 Min: 20.9 / Avg: 291.49 / Max: 349.98 Min: 43.74 / Avg: 494.08 / Max: 682.71 Min: 43.83 / Avg: 491.43 / Max: 677.19 Min: 44.19 / Avg: 258.14 / Max: 283.62 Min: 88.16 / Avg: 478.35 / Max: 559.52 Min: 51.91 / Avg: 550.3 / Max: 819.66 Min: 50.75 / Avg: 479.95 / Max: 694.59 Min: 27.67 / Avg: 324.37 / Max: 409.46 Min: 26.21 / Avg: 281.03 / Max: 351.04 Min: 114.69 / Avg: 487.48 / Max: 570.26 Min: 54.26 / Avg: 253.49 / Max: 285.15 Min: 60.51 / Avg: 257.92 / Max: 290.71 Min: 73.39 / Avg: 474.7 / Max: 573.8 Min: 34.87 / Avg: 250.52 / Max: 286.59 Min: 77.22 / Avg: 451.42 / Max: 572.12 Min: 36.21 / Avg: 249.23 / Max: 283.56 Min: 38.64 / Avg: 203.92 / Max: 227.36 Min: 80.65 / Avg: 378.29 / Max: 459.74
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 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 8 16 24 32 40 SE +/- 0.04, 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 +/- 0.04, 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 = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 32.97 7.67 7.47 3.89 3.94 20.75 10.73 4.41 4.79 9.00 9.58 29.08 28.57 32.35 13.27 26.75 14.88 28.38 31.07 16.66 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 127.08 / Avg: 511.78 / Max: 574.1 Min: 22.1 / Avg: 325.33 / Max: 349.43 Min: 16.88 / Avg: 358.27 / Max: 386.48 Min: 43.32 / Avg: 680.1 / Max: 731.29 Min: 44.23 / Avg: 632.86 / Max: 682.67 Min: 43.89 / Avg: 251.88 / Max: 278.03 Min: 88.4 / Avg: 516.39 / Max: 556.19 Min: 53.28 / Avg: 755.72 / Max: 818.65 Min: 52.98 / Avg: 646.33 / Max: 695.49 Min: 27.49 / Avg: 371.62 / Max: 399.48 Min: 27.35 / Avg: 331.57 / Max: 355.09 Min: 124.71 / Avg: 502.67 / Max: 557.19 Min: 57.3 / Avg: 251.82 / Max: 283.44 Min: 57.34 / Avg: 256.67 / Max: 290.07 Min: 73.9 / Avg: 485.83 / Max: 527.34 Min: 34.91 / Avg: 229.56 / Max: 245.74 Min: 76.07 / Avg: 484.48 / Max: 531.86 Min: 36.26 / Avg: 240.25 / Max: 261.15 Min: 38.33 / Avg: 217.16 / Max: 230.32 Min: 80.84 / Avg: 433.13 / Max: 460.49
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300K 600K 900K 1200K 1500K SE +/- 809.22, N = 3 SE +/- 388.18, N = 3 SE +/- 950.26, N = 3 SE +/- 14137.94, N = 3 SE +/- 2445.95, N = 3 SE +/- 523.94, N = 3 SE +/- 1532.17, N = 3 SE +/- 6319.46, N = 3 SE +/- 14710.35, N = 3 SE +/- 2286.04, N = 3 SE +/- 105.81, N = 3 SE +/- 947.19, N = 3 SE +/- 458.21, N = 3 SE +/- 310.55, N = 3 SE +/- 3553.28, N = 3 SE +/- 1089.17, N = 3 SE +/- 6731.38, N = 4 SE +/- 1349.13, N = 3 SE +/- 450.42, N = 3 SE +/- 4163.69, N = 3 362466 523531 524476 947566 943273 247250 471378 1332056 1166359 741536 652970 331746 166227 187642 748109 412150 719323 385205 351178 633847 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 500 1000 1500 2000 2500 748.83 2116.21 2101.80 1947.26 1982.19 1102.05 1058.13 2260.07 2279.19 2342.27 2438.80 707.75 692.96 764.02 1676.79 1748.22 1641.75 1723.26 1795.18 1639.46 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better 7-Zip Compression 22.01 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 132.02 / Avg: 484.04 / Max: 580.93 Min: 21.88 / Avg: 247.39 / Max: 325.57 Min: 19.38 / Avg: 249.54 / Max: 324.53 Min: 43.48 / Avg: 486.62 / Max: 682.22 Min: 43.34 / Avg: 475.88 / Max: 663.17 Min: 42.12 / Avg: 224.35 / Max: 279.98 Min: 88.21 / Avg: 445.48 / Max: 559.88 Min: 53.76 / Avg: 589.39 / Max: 820.59 Min: 51.77 / Avg: 511.74 / Max: 676.06 Min: 26.81 / Avg: 316.59 / Max: 409.42 Min: 27 / Avg: 267.74 / Max: 342.23 Min: 113.76 / Avg: 468.74 / Max: 571.36 Min: 60.38 / Avg: 239.88 / Max: 284.68 Min: 59 / Avg: 245.6 / Max: 290.47 Min: 73.96 / Avg: 446.16 / Max: 575.33 Min: 34.01 / Avg: 235.75 / Max: 286.58 Min: 77.06 / Avg: 438.14 / Max: 572.08 Min: 35.74 / Avg: 223.53 / Max: 282.25 Min: 37.37 / Avg: 195.62 / Max: 228.43 Min: 82.19 / Avg: 386.62 / Max: 460.57
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2M 4M 6M 8M 10M SE +/- 4774.22, N = 3 SE +/- 16091.05, N = 3 SE +/- 13633.41, N = 3 SE +/- 9387.28, N = 3 SE +/- 6330.65, N = 3 SE +/- 1838.99, N = 3 SE +/- 341.38, N = 3 SE +/- 58302.36, N = 3 SE +/- 75759.77, N = 3 SE +/- 17803.94, N = 3 SE +/- 4348.78, N = 3 SE +/- 8718.18, N = 3 SE +/- 640.30, N = 3 SE +/- 10749.57, N = 3 SE +/- 1391.68, N = 3 SE +/- 8411.66, N = 3 SE +/- 1745.40, N = 3 SE +/- 8067.73, N = 3 SE +/- 4825.91, N = 3 SE +/- 1100.55, N = 3 2375492.46 2950220.28 2930510.79 6023637.43 6009403.02 1218318.31 2438301.75 8413564.08 7536121.01 4111551.58 3753920.39 2006324.38 1055949.56 1177693.06 3867411.27 1987443.33 3706923.16 1876249.14 1824524.48 3659583.24 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 EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 3K 6K 9K 12K 15K 5213.68 10290.14 10263.85 10960.81 11096.41 5332.27 5734.17 12752.39 13185.91 11463.14 12028.36 4541.14 4345.28 4826.62 8823.29 8292.50 9770.07 9060.92 8860.52 9452.24 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Coremark 1.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 135.53 / Avg: 455.63 / Max: 581.62 Min: 21.8 / Avg: 286.7 / Max: 330.39 Min: 18.96 / Avg: 285.52 / Max: 330.11 Min: 41.92 / Avg: 549.62 / Max: 689.76 Min: 43.39 / Avg: 541.56 / Max: 678.9 Min: 42.82 / Avg: 228.48 / Max: 255.09 Min: 87.58 / Avg: 425.22 / Max: 501.61 Min: 54.9 / Avg: 659.76 / Max: 819.63 Min: 49.56 / Avg: 571.53 / Max: 694.44 Min: 27.17 / Avg: 358.68 / Max: 409.43 Min: 25.85 / Avg: 312.09 / Max: 350.86 Min: 115.56 / Avg: 441.81 / Max: 570.14 Min: 57.93 / Avg: 243.01 / Max: 285.04 Min: 59.83 / Avg: 244 / Max: 290.9 Min: 73.84 / Avg: 438.32 / Max: 552.26 Min: 34.59 / Avg: 239.67 / Max: 273.41 Min: 77.24 / Avg: 379.42 / Max: 466.36 Min: 35.78 / Avg: 206.43 / Max: 232.22 Min: 37.96 / Avg: 205.92 / Max: 230.4 Min: 81.6 / Avg: 387.17 / Max: 460.57
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 10 20 30 40 50 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.19, N = 3 SE +/- 0.43, N = 4 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 13.18 23.07 23.90 37.16 36.22 5.29 9.82 41.74 38.04 29.74 27.74 11.88 6.18 6.89 15.26 7.97 14.39 7.59 6.79 13.01 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.36, N = 3 SE +/- 0.16, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.22, N = 3 SE +/- 0.20, N = 3 SE +/- 0.11, N = 3 SE +/- 0.17, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 12.97 23.12 23.84 37.60 35.97 5.28 9.81 41.21 37.95 29.68 27.55 11.67 6.08 6.74 15.12 8.02 14.38 7.58 6.78 12.84 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
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.
Blender Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Classroom - Compute: CPU-Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30 60 90 120 150 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.21, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.26, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.36, N = 3 61.32 46.00 43.27 22.30 24.43 106.72 55.60 17.66 20.12 33.39 38.72 67.57 136.41 120.92 36.39 70.57 35.06 68.17 77.11 41.29 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 3.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 132.59 / Avg: 509.72 / Max: 580.3 Min: 21.5 / Avg: 291.14 / Max: 320.36 Min: 21.77 / Avg: 336.97 / Max: 375.67 Min: 44.25 / Avg: 642.52 / Max: 783.84 Min: 42.2 / Avg: 542.58 / Max: 649.46 Min: 43.51 / Avg: 264.43 / Max: 285.07 Min: 87.7 / Avg: 514.05 / Max: 559.85 Min: 54.84 / Avg: 647.13 / Max: 822.09 Min: 52.51 / Avg: 545.23 / Max: 665.45 Min: 25.2 / Avg: 359.1 / Max: 409.47 Min: 24.98 / Avg: 294.94 / Max: 330.97 Min: 106.71 / Avg: 501.83 / Max: 568.1 Min: 59.32 / Avg: 257.67 / Max: 283.56 Min: 56.01 / Avg: 261.76 / Max: 290.12 Min: 74.02 / Avg: 505.3 / Max: 573.26 Min: 34.44 / Avg: 248.86 / Max: 265.31 Min: 77.09 / Avg: 498.75 / Max: 572.45 Min: 36.13 / Avg: 251.56 / Max: 270.91 Min: 37.95 / Avg: 219.17 / Max: 230.29 Min: 81.42 / Avg: 420.72 / Max: 462.13
oneDNN Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 0.4513 0.9026 1.3539 1.8052 2.2565 SE +/- 0.002890, N = 7 SE +/- 0.000785, N = 7 SE +/- 0.000585, N = 7 SE +/- 0.002431, N = 15 SE +/- 0.001079, N = 7 SE +/- 0.003190, N = 7 SE +/- 0.057585, N = 15 SE +/- 0.003853, N = 15 SE +/- 0.002791, N = 7 SE +/- 0.001337, N = 7 SE +/- 0.001445, N = 7 SE +/- 0.002951, N = 7 SE +/- 0.001673, N = 7 SE +/- 0.000570, N = 7 1.162240 0.281845 0.260069 0.284125 0.294229 1.603390 0.967021 0.351182 0.382159 0.275194 0.290728 2.005820 1.518720 1.404650 MIN: 1 MIN: 1.54 MIN: 0.48 MIN: 0.28 MIN: 1.91 MIN: 1.37 MIN: 1.3 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 100 200 300 400 500 Min: 140.15 / Avg: 372.78 / Max: 544.3 Min: 21.84 / Avg: 159.9 / Max: 289.41 Min: 19.48 / Avg: 176.32 / Max: 334.1 Min: 42.96 / Avg: 278.57 / Max: 533.26 Min: 42.96 / Avg: 272.84 / Max: 499.84 Min: 42.49 / Avg: 179.78 / Max: 275.94 Min: 88.95 / Avg: 322.27 / Max: 563.96 Min: 51.09 / Avg: 302.77 / Max: 504.58 Min: 52.41 / Avg: 285.05 / Max: 457.29 Min: 24.97 / Avg: 169.11 / Max: 304.83 Min: 24.59 / Avg: 157.28 / Max: 278.01 Min: 111.42 / Avg: 339.64 / Max: 541.17 Min: 59.77 / Avg: 186.16 / Max: 285.37 Min: 62.27 / Avg: 192.86 / Max: 290.91
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 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 13K 26K 39K 52K 65K SE +/- 129.10, N = 3 SE +/- 7.54, N = 3 SE +/- 7.06, N = 3 SE +/- 8.50, N = 3 SE +/- 13.62, N = 3 SE +/- 11.61, N = 3 SE +/- 51.24, N = 3 SE +/- 13.35, N = 3 SE +/- 6.17, N = 3 SE +/- 20.21, N = 3 SE +/- 11.92, N = 3 SE +/- 41.65, N = 3 SE +/- 51.07, N = 3 SE +/- 20.67, N = 3 SE +/- 24.26, N = 3 SE +/- 77.82, N = 3 SE +/- 67.34, N = 3 SE +/- 43.02, N = 3 SE +/- 6.36, N = 3 SE +/- 21.40, N = 3 21309 20623 19898 10640 11454 61287 29634 8043 9256 14722 16971 23834 48204 41655 17605 34169 18319 35029 39631 22287 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 128.6 / Avg: 471.86 / Max: 581.11 Min: 22.2 / Avg: 271.56 / Max: 315.3 Min: 19.16 / Avg: 322.92 / Max: 353.67 Min: 43.88 / Avg: 655.95 / Max: 724.52 Min: 43.72 / Avg: 581.28 / Max: 636.26 Min: 43.82 / Avg: 232.41 / Max: 282.26 Min: 87.78 / Avg: 516.82 / Max: 562.96 Min: 54.65 / Avg: 741.05 / Max: 819.64 Min: 53.17 / Avg: 603.65 / Max: 661.43 Min: 27.26 / Avg: 377.13 / Max: 409.81 Min: 27.24 / Avg: 283.11 / Max: 325.84 Min: 121.56 / Avg: 470.26 / Max: 570.64 Min: 60.09 / Avg: 244.51 / Max: 285.41 Min: 58.31 / Avg: 245.16 / Max: 290.86 Min: 74.73 / Avg: 516.72 / Max: 573.18 Min: 34.98 / Avg: 236.08 / Max: 269.11 Min: 77.38 / Avg: 522.21 / Max: 572.83 Min: 36.38 / Avg: 239.96 / Max: 273.64 Min: 38.19 / Avg: 209.32 / Max: 230.29 Min: 81.04 / Avg: 404.33 / Max: 460.76
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 13K 26K 39K 52K 65K SE +/- 99.88, N = 3 SE +/- 16.33, N = 3 SE +/- 14.57, N = 3 SE +/- 12.91, N = 3 SE +/- 5.69, N = 3 SE +/- 82.30, N = 3 SE +/- 26.54, N = 3 SE +/- 11.98, N = 3 SE +/- 14.38, N = 3 SE +/- 40.04, N = 3 SE +/- 9.61, N = 3 SE +/- 13.45, N = 3 SE +/- 54.60, N = 3 SE +/- 44.86, N = 3 SE +/- 49.96, N = 3 SE +/- 81.80, N = 3 SE +/- 35.24, N = 3 SE +/- 38.76, N = 3 SE +/- 34.59, N = 3 SE +/- 21.23, N = 3 21525 20946 20230 10889 11646 62092 30313 8172 9375 14926 17162 24058 48613 41940 18019 34424 18614 35372 40095 22769 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 137.83 / Avg: 471.33 / Max: 580.77 Min: 20.92 / Avg: 271.79 / Max: 314.2 Min: 20.21 / Avg: 297.74 / Max: 349.18 Min: 44.16 / Avg: 650.5 / Max: 715.4 Min: 42.47 / Avg: 580.52 / Max: 633.47 Min: 44.04 / Avg: 233.73 / Max: 281.06 Min: 88.3 / Avg: 486.93 / Max: 558.33 Min: 54.05 / Avg: 742.12 / Max: 820.47 Min: 48.15 / Avg: 603.05 / Max: 660.76 Min: 27.15 / Avg: 370.8 / Max: 409.46 Min: 25.71 / Avg: 283.43 / Max: 325.14 Min: 114.82 / Avg: 471.05 / Max: 570.25 Min: 59.35 / Avg: 244.46 / Max: 285.43 Min: 57.77 / Avg: 245.62 / Max: 291.14 Min: 73.71 / Avg: 523.4 / Max: 574.59 Min: 34.65 / Avg: 237.06 / Max: 269.55 Min: 77.27 / Avg: 521.61 / Max: 572.05 Min: 36.47 / Avg: 240.84 / Max: 274.95 Min: 38.31 / Avg: 209.64 / Max: 230.29 Min: 81.8 / Avg: 405.29 / Max: 460.3
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 15K 30K 45K 60K 75K SE +/- 140.36, N = 3 SE +/- 19.97, N = 3 SE +/- 8.19, N = 3 SE +/- 3.06, N = 3 SE +/- 14.85, N = 3 SE +/- 111.69, N = 3 SE +/- 41.34, N = 3 SE +/- 10.97, N = 3 SE +/- 16.26, N = 3 SE +/- 30.02, N = 3 SE +/- 5.61, N = 3 SE +/- 41.79, N = 3 SE +/- 112.43, N = 3 SE +/- 123.33, N = 3 SE +/- 17.36, N = 3 SE +/- 121.66, N = 3 SE +/- 27.62, N = 3 SE +/- 26.14, N = 3 SE +/- 66.46, N = 3 SE +/- 132.07, N = 3 25437 24607 23782 12789 13690 72153 35221 9597 11055 17569 20228 28432 62896 49610 20876 40556 21718 41538 47147 26852 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 150 300 450 600 750 Min: 127.34 / Avg: 480.17 / Max: 581.09 Min: 22.08 / Avg: 277.5 / Max: 315.91 Min: 18.99 / Avg: 305.36 / Max: 351.77 Min: 25.19 / Avg: 608.28 / Max: 722.11 Min: 42.6 / Avg: 581.4 / Max: 636.49 Min: 43.66 / Avg: 238.54 / Max: 280.94 Min: 88.1 / Avg: 496.61 / Max: 563.03 Min: 53.67 / Avg: 747.78 / Max: 829.46 Min: 52.62 / Avg: 605.85 / Max: 658.79 Min: 25.4 / Avg: 355.59 / Max: 409.43 Min: 26.99 / Avg: 281.81 / Max: 326.48 Min: 121.61 / Avg: 493.09 / Max: 570.32 Min: 60.08 / Avg: 222.55 / Max: 285.42 Min: 58.68 / Avg: 248.85 / Max: 290.97 Min: 74.44 / Avg: 486.72 / Max: 573.73 Min: 34.87 / Avg: 240.56 / Max: 269.15 Min: 77.87 / Avg: 487.23 / Max: 572.76 Min: 36.3 / Avg: 243.56 / Max: 273.59 Min: 38.47 / Avg: 212.43 / Max: 230.29 Min: 80.91 / Avg: 411.29 / Max: 460.57
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 6 12 18 24 30 SE +/- 0.058, N = 4 SE +/- 0.016, N = 5 SE +/- 0.021, N = 5 SE +/- 0.054, N = 15 SE +/- 0.057, N = 15 SE +/- 0.037, N = 3 SE +/- 0.012, N = 5 SE +/- 0.084, N = 15 SE +/- 0.063, N = 15 SE +/- 0.022, N = 7 SE +/- 0.012, N = 6 SE +/- 0.034, N = 4 SE +/- 0.079, N = 3 SE +/- 0.065, N = 3 SE +/- 0.044, N = 7 SE +/- 0.010, N = 5 SE +/- 0.023, N = 7 SE +/- 0.017, N = 5 SE +/- 0.014, N = 4 SE +/- 0.033, N = 6 11.264 8.541 8.572 4.491 4.723 17.154 8.808 3.361 3.780 5.804 6.662 12.554 25.077 22.186 5.782 11.010 5.576 10.953 12.350 6.357 1. (CC) gcc options: -lm -lpthread -O3 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better C-Ray 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 127 / Avg: 435 / Max: 581.42 Min: 21.43 / Avg: 198.78 / Max: 293.1 Min: 21.67 / Avg: 199.42 / Max: 294.26 Min: 41.89 / Avg: 331.12 / Max: 620.01 Min: 42.98 / Avg: 318.97 / Max: 602.19 Min: 43.94 / Avg: 228.5 / Max: 283.05 Min: 88.29 / Avg: 395.01 / Max: 552.06 Min: 48.79 / Avg: 355.72 / Max: 817.84 Min: 50.47 / Avg: 308.29 / Max: 616.72 Min: 27.3 / Avg: 244.38 / Max: 407.82 Min: 25.48 / Avg: 197.51 / Max: 307.86 Min: 115.35 / Avg: 426.65 / Max: 570.32 Min: 58.4 / Avg: 236.25 / Max: 284.8 Min: 57.94 / Avg: 236.91 / Max: 293.02 Min: 74.47 / Avg: 342.11 / Max: 565.28 Min: 34.67 / Avg: 202.53 / Max: 271.17 Min: 77.28 / Avg: 337.09 / Max: 551.66 Min: 36.06 / Avg: 201.94 / Max: 275.62 Min: 37.95 / Avg: 178.97 / Max: 230.28 Min: 81.45 / Avg: 306.54 / Max: 460.64
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 60K 120K 180K 240K 300K SE +/- 121.52, N = 3 SE +/- 341.83, N = 4 SE +/- 114.35, N = 4 SE +/- 1312.27, N = 6 SE +/- 525.61, N = 6 SE +/- 51.11, N = 3 SE +/- 202.53, N = 4 SE +/- 1129.41, N = 6 SE +/- 951.51, N = 6 SE +/- 276.27, N = 4 SE +/- 300.99, N = 4 SE +/- 117.02, N = 3 SE +/- 22.24, N = 3 SE +/- 4.44, N = 3 SE +/- 1083.89, N = 6 SE +/- 208.16, N = 3 SE +/- 290.00, N = 4 SE +/- 21.43, N = 3 SE +/- 29.35, N = 3 SE +/- 369.61, N = 4 90535.96 119972.76 120312.32 239623.83 241831.07 50624.72 113978.98 263182.48 257843.16 126790.36 125438.45 89186.77 35288.04 37710.58 230050.33 89188.95 114669.27 51889.31 51976.91 113107.52 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 4.1.4 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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 150 300 450 600 750 196.49 591.48 599.20 674.17 688.94 229.59 268.85 621.31 681.62 532.11 553.57 199.33 144.02 151.15 635.03 401.85 285.67 258.55 273.22 318.27 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 132.66 / Avg: 460.76 / Max: 574.25 Min: 21.85 / Avg: 202.84 / Max: 309.57 Min: 19.22 / Avg: 200.79 / Max: 299.54 Min: 40.01 / Avg: 355.43 / Max: 628.54 Min: 42.44 / Avg: 351.02 / Max: 619.6 Min: 42.79 / Avg: 220.5 / Max: 250.31 Min: 89 / Avg: 423.95 / Max: 563.14 Min: 51.89 / Avg: 423.59 / Max: 788.43 Min: 50.84 / Avg: 378.28 / Max: 653.05 Min: 25.33 / Avg: 238.28 / Max: 360.21 Min: 24.73 / Avg: 226.6 / Max: 317.79 Min: 102.78 / Avg: 447.43 / Max: 563.81 Min: 60.05 / Avg: 245.02 / Max: 280.56 Min: 63.77 / Avg: 249.49 / Max: 281.76 Min: 75.07 / Avg: 362.27 / Max: 573.72 Min: 34.17 / Avg: 221.95 / Max: 286.4 Min: 77.66 / Avg: 401.4 / Max: 554.66 Min: 35.98 / Avg: 200.69 / Max: 258.06 Min: 37.52 / Avg: 190.24 / Max: 226.33 Min: 82.68 / Avg: 355.38 / Max: 459.47
Blender Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Barbershop - Compute: CPU-Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120 240 360 480 600 SE +/- 0.23, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.20, N = 3 SE +/- 0.05, N = 3 SE +/- 0.19, N = 3 SE +/- 0.72, N = 3 SE +/- 0.37, N = 3 SE +/- 0.38, N = 3 SE +/- 0.09, N = 3 SE +/- 0.15, N = 3 SE +/- 0.29, N = 3 SE +/- 0.14, N = 3 SE +/- 0.14, N = 3 SE +/- 0.21, N = 3 SE +/- 0.36, N = 3 SE +/- 0.21, N = 3 SE +/- 0.70, N = 3 SE +/- 0.45, N = 3 243.75 172.18 164.66 89.46 97.97 417.99 222.68 73.39 81.56 127.11 143.31 274.88 538.81 471.45 140.20 266.64 142.26 264.87 300.10 171.98 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 3.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 136.98 / Avg: 523.77 / Max: 581.11 Min: 22.17 / Avg: 311.56 / Max: 327.13 Min: 20.7 / Avg: 353.63 / Max: 377.1 Min: 42.67 / Avg: 690.2 / Max: 773.11 Min: 44.36 / Avg: 597.83 / Max: 655.52 Min: 44.36 / Avg: 279.97 / Max: 286.58 Min: 87.6 / Avg: 533.36 / Max: 557.47 Min: 53.12 / Avg: 719.83 / Max: 819.66 Min: 54.7 / Avg: 610.24 / Max: 681.39 Min: 27.24 / Avg: 383.77 / Max: 409.88 Min: 26.02 / Avg: 317.46 / Max: 336.08 Min: 112.44 / Avg: 516.5 / Max: 569 Min: 58.36 / Avg: 261.48 / Max: 283.8 Min: 58.51 / Avg: 265.76 / Max: 290.33 Min: 73.89 / Avg: 535.52 / Max: 574.08 Min: 34.9 / Avg: 257.53 / Max: 269.51 Min: 76.96 / Avg: 529.68 / Max: 573.16 Min: 36.31 / Avg: 264.77 / Max: 277.04 Min: 38.1 / Avg: 224.82 / Max: 230.29 Min: 81.22 / Avg: 437.68 / Max: 466.06
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 6 12 18 24 30 SE +/- 0.126, N = 4 SE +/- 0.036, N = 5 SE +/- 0.024, N = 5 SE +/- 0.026, N = 7 SE +/- 0.028, N = 7 SE +/- 0.005, N = 3 SE +/- 0.026, N = 5 SE +/- 0.014, N = 9 SE +/- 0.023, N = 8 SE +/- 0.014, N = 6 SE +/- 0.033, N = 6 SE +/- 0.025, N = 4 SE +/- 0.031, N = 3 SE +/- 0.050, N = 3 SE +/- 0.008, N = 7 SE +/- 0.017, N = 5 SE +/- 0.016, N = 6 SE +/- 0.041, N = 4 SE +/- 0.024, N = 4 SE +/- 0.017, N = 6 12.571 9.619 9.566 5.029 5.016 19.182 9.793 3.738 4.217 6.953 7.988 13.522 27.391 24.578 5.915 11.281 6.443 12.304 12.794 6.659 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 136.79 / Avg: 449.65 / Max: 581.57 Min: 21.71 / Avg: 223.44 / Max: 315.83 Min: 18.99 / Avg: 232.52 / Max: 330.95 Min: 43.43 / Avg: 389.44 / Max: 696.88 Min: 41.25 / Avg: 364.51 / Max: 645.15 Min: 42.07 / Avg: 226.06 / Max: 273.38 Min: 88.48 / Avg: 403.96 / Max: 561.16 Min: 52.35 / Avg: 400.23 / Max: 818.85 Min: 49.76 / Avg: 345.25 / Max: 654.52 Min: 26.55 / Avg: 258.32 / Max: 409.42 Min: 25.13 / Avg: 221.41 / Max: 326.56 Min: 112.98 / Avg: 441.21 / Max: 569.98 Min: 57.66 / Avg: 238.42 / Max: 284.94 Min: 58.99 / Avg: 240.92 / Max: 290.9 Min: 74.08 / Avg: 351.89 / Max: 558.03 Min: 33.63 / Avg: 208.69 / Max: 277.71 Min: 77.26 / Avg: 335.57 / Max: 514.44 Min: 35.58 / Avg: 198.17 / Max: 257.22 Min: 37.59 / Avg: 180.07 / Max: 230.27 Min: 81.84 / Avg: 310.69 / Max: 460.57
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 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30K 60K 90K 120K 150K SE +/- 93.72, N = 3 SE +/- 34.87, N = 3 SE +/- 60.79, N = 3 SE +/- 12.86, N = 3 SE +/- 24.88, N = 3 SE +/- 189.04, N = 3 SE +/- 134.17, N = 3 SE +/- 9.49, N = 3 SE +/- 47.26, N = 3 SE +/- 52.88, N = 3 SE +/- 75.68, N = 3 SE +/- 73.98, N = 3 SE +/- 503.46, N = 3 SE +/- 425.81, N = 3 SE +/- 73.14, N = 3 SE +/- 88.52, N = 3 SE +/- 85.62, N = 3 SE +/- 72.64, N = 3 SE +/- 107.07, N = 3 SE +/- 132.40, N = 3 43126 41738 40406 21776 23309 119256 66469 16356 18823 29715 34323 48349 102068 89385 36025 74833 37232 77108 85606 45701 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 133.55 / Avg: 491.25 / Max: 581.62 Min: 20.54 / Avg: 283.56 / Max: 314.9 Min: 19.46 / Avg: 311.82 / Max: 349.66 Min: 44.58 / Avg: 614.55 / Max: 714.62 Min: 43.47 / Avg: 554.04 / Max: 633.13 Min: 43.63 / Avg: 254.02 / Max: 281.95 Min: 88.2 / Avg: 464.69 / Max: 559 Min: 54.4 / Avg: 705.52 / Max: 819.63 Min: 53.03 / Avg: 602.58 / Max: 659.44 Min: 27.46 / Avg: 379.13 / Max: 409.44 Min: 24.3 / Avg: 289.45 / Max: 325.83 Min: 111.07 / Avg: 487.63 / Max: 570.63 Min: 58.92 / Avg: 236.52 / Max: 285.46 Min: 59.31 / Avg: 235.92 / Max: 290.71 Min: 73.59 / Avg: 505.26 / Max: 573.44 Min: 34.93 / Avg: 224.4 / Max: 269.29 Min: 77.59 / Avg: 503.5 / Max: 572.84 Min: 36.28 / Avg: 228.99 / Max: 275.37 Min: 38.5 / Avg: 201.57 / Max: 230.51 Min: 81.09 / Avg: 419.78 / Max: 460.55
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30K 60K 90K 120K 150K SE +/- 30.38, N = 3 SE +/- 31.01, N = 3 SE +/- 55.41, N = 3 SE +/- 33.62, N = 3 SE +/- 43.24, N = 3 SE +/- 246.64, N = 3 SE +/- 326.00, N = 3 SE +/- 32.54, N = 3 SE +/- 50.75, N = 3 SE +/- 57.52, N = 3 SE +/- 53.67, N = 3 SE +/- 41.00, N = 3 SE +/- 529.70, N = 3 SE +/- 220.19, N = 3 SE +/- 69.38, N = 3 SE +/- 173.71, N = 3 SE +/- 102.80, N = 3 SE +/- 88.75, N = 3 SE +/- 307.61, N = 3 SE +/- 112.83, N = 3 42753 41316 39777 21323 22971 117436 65291 16134 18567 29445 33978 47738 101492 89020 35270 74550 36625 76200 85202 44894 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 134.45 / Avg: 490.63 / Max: 581.36 Min: 22.31 / Avg: 284.49 / Max: 315.65 Min: 20.59 / Avg: 316.04 / Max: 355.87 Min: 44.07 / Avg: 621.39 / Max: 725.27 Min: 44.03 / Avg: 554.35 / Max: 636.3 Min: 43.46 / Avg: 253.29 / Max: 283.1 Min: 87.93 / Avg: 463.17 / Max: 557.69 Min: 53.79 / Avg: 701.35 / Max: 820.47 Min: 53.4 / Avg: 592.83 / Max: 660.88 Min: 26.93 / Avg: 379.3 / Max: 409.44 Min: 27.36 / Avg: 289.19 / Max: 326.08 Min: 121.54 / Avg: 487.1 / Max: 570.57 Min: 59.99 / Avg: 236.65 / Max: 285.39 Min: 60.59 / Avg: 235.73 / Max: 290.97 Min: 74.52 / Avg: 501.81 / Max: 576.02 Min: 34.68 / Avg: 224.35 / Max: 269.84 Min: 76.89 / Avg: 501.94 / Max: 572.75 Min: 36.32 / Avg: 227.45 / Max: 273.38 Min: 37.94 / Avg: 200.86 / Max: 230.29 Min: 81.04 / Avg: 419.77 / Max: 460.55
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40K 80K 120K 160K 200K SE +/- 187.68, N = 3 SE +/- 69.14, N = 3 SE +/- 52.00, N = 3 SE +/- 1059.23, N = 3 SE +/- 1226.28, N = 3 SE +/- 13.32, N = 3 SE +/- 34.76, N = 3 SE +/- 462.02, N = 3 SE +/- 625.00, N = 3 SE +/- 7.87, N = 3 SE +/- 105.34, N = 3 SE +/- 14.05, N = 3 SE +/- 19.72, N = 3 SE +/- 13.80, N = 3 SE +/- 23.57, N = 3 SE +/- 39.91, N = 3 SE +/- 25.85, N = 3 SE +/- 6.50, N = 3 SE +/- 26.93, N = 3 SE +/- 135.49, N = 3 59056.82 97379.56 99729.06 161750.11 161378.10 22886.83 43222.99 166260.62 144811.67 118385.58 112325.82 51258.54 24550.40 28673.99 68270.41 35966.80 64899.71 33814.38 32070.12 59879.34 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
Blender Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Pabellon Barcelona - Compute: CPU-Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 SE +/- 0.25, N = 3 SE +/- 0.08, N = 3 SE +/- 0.28, N = 3 SE +/- 0.33, N = 3 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 SE +/- 0.36, N = 3 SE +/- 0.20, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.19, N = 3 76.24 58.18 54.76 28.57 31.11 130.99 69.48 23.48 25.71 43.03 48.89 84.55 170.47 150.59 45.22 87.40 44.08 85.51 96.20 53.99 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 3.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 134.11 / Avg: 512.93 / Max: 580.72 Min: 21.87 / Avg: 301.95 / Max: 332.61 Min: 18.33 / Avg: 350.8 / Max: 391.49 Min: 44.03 / Avg: 668.43 / Max: 811.15 Min: 42.93 / Avg: 570.69 / Max: 670.38 Min: 43.92 / Avg: 273.26 / Max: 285.4 Min: 88.42 / Avg: 519.83 / Max: 562.66 Min: 55.45 / Avg: 660.59 / Max: 818.87 Min: 49.34 / Avg: 570.67 / Max: 687.28 Min: 27.17 / Avg: 364.55 / Max: 409.44 Min: 25.66 / Avg: 306.41 / Max: 341.6 Min: 114.03 / Avg: 506.36 / Max: 568.52 Min: 58.24 / Avg: 258.51 / Max: 284.11 Min: 59.92 / Avg: 262.59 / Max: 291.47 Min: 74.25 / Avg: 512.13 / Max: 571.66 Min: 35.09 / Avg: 247.25 / Max: 261.74 Min: 77.03 / Avg: 508.98 / Max: 572.82 Min: 36.28 / Avg: 249.71 / Max: 265.73 Min: 38.35 / Avg: 220.22 / Max: 230.29 Min: 81.4 / Avg: 423.53 / Max: 460.7
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 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 14 28 42 56 70 SE +/- 0.04257, N = 3 SE +/- 0.01023, N = 3 SE +/- 0.01551, N = 3 SE +/- 0.02681, N = 3 SE +/- 0.01513, N = 3 SE +/- 0.00228, N = 3 SE +/- 0.00771, N = 3 SE +/- 0.10304, N = 3 SE +/- 0.09801, N = 3 SE +/- 0.03060, N = 3 SE +/- 0.02040, N = 3 SE +/- 0.06779, N = 3 SE +/- 0.02192, N = 3 SE +/- 0.02171, N = 3 SE +/- 0.01802, N = 3 SE +/- 0.00386, N = 3 SE +/- 0.01341, N = 3 SE +/- 0.00699, N = 3 SE +/- 0.00883, N = 3 SE +/- 0.00831, N = 3 25.33280 25.69800 26.44810 48.05910 46.03120 8.84111 16.47180 64.14410 54.20930 36.32030 31.16640 23.19100 11.99210 13.37990 25.68200 13.81140 25.94820 13.86820 12.24060 21.38870 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 2.10 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0241 0.0482 0.0723 0.0964 0.1205 0.050 0.092 0.088 0.080 0.082 0.034 0.032 0.086 0.093 0.096 0.107 0.046 0.048 0.053 0.048 0.055 0.049 0.055 0.057 0.049 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 2.10 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 126.69 / Avg: 511.75 / Max: 569.24 Min: 22.04 / Avg: 279.75 / Max: 298.79 Min: 20.32 / Avg: 300.6 / Max: 322.07 Min: 44.86 / Avg: 602.57 / Max: 652.98 Min: 38.38 / Avg: 561.84 / Max: 607.06 Min: 44.03 / Avg: 262.56 / Max: 283.7 Min: 87.97 / Avg: 511.65 / Max: 558.13 Min: 53.66 / Avg: 743.7 / Max: 809.64 Min: 51.21 / Avg: 581.85 / Max: 629.35 Min: 26.48 / Avg: 376.75 / Max: 405.08 Min: 26.73 / Avg: 290.73 / Max: 310.58 Min: 110.52 / Avg: 503.78 / Max: 563.23 Min: 57.93 / Avg: 249.62 / Max: 284.72 Min: 59.84 / Avg: 253.53 / Max: 289.3 Min: 73.63 / Avg: 534.28 / Max: 573.98 Min: 35.02 / Avg: 250.8 / Max: 273.87 Min: 77.15 / Avg: 528.35 / Max: 570.48 Min: 36.43 / Avg: 249.93 / Max: 274.6 Min: 38.62 / Avg: 214.08 / Max: 229.88 Min: 81.02 / Avg: 433.67 / Max: 460.16
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 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30K 60K 90K 120K 150K SE +/- 44.01, N = 3 SE +/- 30.66, N = 3 SE +/- 21.43, N = 3 SE +/- 30.95, N = 3 SE +/- 32.90, N = 3 SE +/- 218.50, N = 3 SE +/- 70.43, N = 3 SE +/- 26.91, N = 3 SE +/- 20.98, N = 3 SE +/- 70.57, N = 3 SE +/- 80.97, N = 3 SE +/- 63.56, N = 3 SE +/- 279.04, N = 3 SE +/- 406.86, N = 3 SE +/- 141.78, N = 3 SE +/- 132.68, N = 3 SE +/- 75.07, N = 3 SE +/- 64.26, N = 3 SE +/- 132.46, N = 3 SE +/- 168.11, N = 3 50891 49152 47638 25561 27438 138034 75886 19215 22083 35059 40492 62545 119989 105213 41907 86930 43415 89230 99775 53386 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 150 300 450 600 750 Min: 128.71 / Avg: 497.61 / Max: 580.71 Min: 22.17 / Avg: 289.31 / Max: 316.17 Min: 19.18 / Avg: 319.57 / Max: 353.2 Min: 44.9 / Avg: 632.49 / Max: 724.3 Min: 45.4 / Avg: 565.57 / Max: 636.02 Min: 43.67 / Avg: 257.61 / Max: 282.2 Min: 88.07 / Avg: 472.78 / Max: 559.24 Min: 54.73 / Avg: 749.96 / Max: 833.55 Min: 52.98 / Avg: 576.98 / Max: 664.2 Min: 27.39 / Avg: 362.89 / Max: 409.43 Min: 26.9 / Avg: 294.52 / Max: 326.8 Min: 120.32 / Avg: 441.23 / Max: 570.58 Min: 60.61 / Avg: 240.69 / Max: 285.43 Min: 57.41 / Avg: 240.02 / Max: 290.7 Min: 74.19 / Avg: 512.55 / Max: 574.01 Min: 35.18 / Avg: 229.78 / Max: 269.09 Min: 76.94 / Avg: 512.14 / Max: 573.72 Min: 36.36 / Avg: 233.12 / Max: 273.78 Min: 38.14 / Avg: 205.16 / Max: 230.29 Min: 81.78 / Avg: 424.6 / Max: 460.55
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 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 17.94 11.23 11.10 5.06 5.27 20.58 10.67 5.93 6.44 14.04 13.99 15.55 30.56 36.22 13.68 26.55 14.70 30.14 33.82 16.78 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 128.01 / Avg: 513.68 / Max: 580.79 Min: 21.9 / Avg: 310.73 / Max: 334.31 Min: 20.88 / Avg: 347.4 / Max: 391.65 Min: 44.47 / Avg: 673.34 / Max: 726.22 Min: 40.05 / Avg: 614.61 / Max: 661.01 Min: 43.88 / Avg: 264.24 / Max: 284.01 Min: 87.58 / Avg: 525.47 / Max: 565.52 Min: 53.36 / Avg: 737.22 / Max: 805.07 Min: 53.73 / Avg: 622.84 / Max: 671.18 Min: 27.23 / Avg: 352.69 / Max: 385 Min: 25.9 / Avg: 321.35 / Max: 346.63 Min: 116.95 / Avg: 501.26 / Max: 566.41 Min: 59.62 / Avg: 251.58 / Max: 284.64 Min: 57.18 / Avg: 255.83 / Max: 288.97 Min: 74.32 / Avg: 512.92 / Max: 556.01 Min: 34.8 / Avg: 230.18 / Max: 246.28 Min: 76.38 / Avg: 513.68 / Max: 555.61 Min: 36.54 / Avg: 255.05 / Max: 274.02 Min: 38.09 / Avg: 216.73 / Max: 230.45 Min: 81.08 / Avg: 434.26 / Max: 460.68
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 150 300 450 600 750 SE +/- 1.45, N = 3 SE +/- 0.26, N = 3 SE +/- 0.30, N = 3 SE +/- 0.55, N = 3 SE +/- 0.32, N = 3 SE +/- 0.23, N = 3 SE +/- 0.41, N = 3 SE +/- 0.50, N = 3 SE +/- 0.33, N = 3 217.41 329.12 358.43 694.62 629.11 98.94 185.56 428.44 401.20
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 0.11 Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 800 1600 2400 3200 4000 SE +/- 4.10, N = 3 SE +/- 1.86, N = 3 SE +/- 1.53, N = 3 SE +/- 1.15, N = 3 SE +/- 0.67, N = 3 SE +/- 2.65, N = 3 SE +/- 1.73, N = 3 SE +/- 1.53, N = 3 SE +/- 1.53, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 1.00, N = 3 SE +/- 6.64, N = 3 SE +/- 4.16, N = 3 SE +/- 0.33, N = 3 SE +/- 1.20, N = 3 SE +/- 2.19, N = 3 SE +/- 1.33, N = 3 SE +/- 3.28, N = 3 SE +/- 2.40, N = 3 1350 1310 1262 683 731 3558 1901 510 600 926 1071 1509 3036 2622 1134 2140 1158 2195 2494 1422 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 133.78 / Avg: 480.48 / Max: 580.3 Min: 22.07 / Avg: 277.15 / Max: 313.22 Min: 20.86 / Avg: 305.54 / Max: 347.67 Min: 44.49 / Avg: 616.22 / Max: 710.03 Min: 44.12 / Avg: 551.99 / Max: 629.69 Min: 43.78 / Avg: 255.99 / Max: 282.47 Min: 86.92 / Avg: 496.06 / Max: 560.34 Min: 51.39 / Avg: 735.93 / Max: 819.25 Min: 45.96 / Avg: 565.25 / Max: 653.18 Min: 27.73 / Avg: 358.5 / Max: 409.27 Min: 27.24 / Avg: 288.42 / Max: 324.83 Min: 114.02 / Avg: 474.01 / Max: 570.24 Min: 60.05 / Avg: 241.52 / Max: 285.5 Min: 55.84 / Avg: 243.44 / Max: 290.91 Min: 73.58 / Avg: 499.23 / Max: 573.99 Min: 34.99 / Avg: 238.65 / Max: 270.52 Min: 78.08 / Avg: 495.23 / Max: 572.83 Min: 36.27 / Avg: 242.36 / Max: 276.85 Min: 38.01 / Avg: 208.64 / Max: 230.3 Min: 82.85 / Avg: 407.83 / Max: 460.37
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 Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30K 60K 90K 120K 150K SE +/- 99.58, N = 3 SE +/- 86.61, N = 3 SE +/- 46.14, N = 3 SE +/- 164.95, N = 4 SE +/- 83.46, N = 4 SE +/- 128.10, N = 3 SE +/- 35.95, N = 3 SE +/- 156.60, N = 5 SE +/- 196.84, N = 5 SE +/- 49.38, N = 4 SE +/- 23.53, N = 4 SE +/- 76.17, N = 3 SE +/- 76.21, N = 3 SE +/- 91.33, N = 3 SE +/- 236.60, N = 3 SE +/- 22.36, N = 3 SE +/- 212.72, N = 3 SE +/- 59.15, N = 3 SE +/- 206.18, N = 3 SE +/- 49.46, N = 3 41319.4 60490.2 61774.2 98131.4 97269.4 26562.4 41290.0 137480.4 126187.4 82117.1 75830.9 35545.4 19709.1 22902.9 49905.7 40297.2 49895.4 42583.6 37205.6 41903.7 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 6.12.1 Variant: Wownero - Hash Count: 1M Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 60 120 180 240 300 87.66 215.17 211.81 205.71 206.12 103.82 87.57 268.95 277.74 265.50 275.14 75.82 78.83 91.04 108.69 163.34 114.59 174.08 185.78 108.48 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xmrig 6.12.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 128.24 / Avg: 471.37 / Max: 582.05 Min: 22.18 / Avg: 281.13 / Max: 350.22 Min: 19.05 / Avg: 291.65 / Max: 372.12 Min: 43.6 / Avg: 477.04 / Max: 697.13 Min: 43.64 / Avg: 471.91 / Max: 679.44 Min: 44.08 / Avg: 255.85 / Max: 284.07 Min: 88.08 / Avg: 471.52 / Max: 562.95 Min: 51.62 / Avg: 512.22 / Max: 819.63 Min: 52.22 / Avg: 454.34 / Max: 698.13 Min: 27.52 / Avg: 309.29 / Max: 409.43 Min: 25.11 / Avg: 275.61 / Max: 360.1 Min: 112.93 / Avg: 468.8 / Max: 570.59 Min: 59.75 / Avg: 250.01 / Max: 285.21 Min: 60.58 / Avg: 251.56 / Max: 290.86 Min: 74.23 / Avg: 459.17 / Max: 573.45 Min: 34.77 / Avg: 246.71 / Max: 286.59 Min: 76.91 / Avg: 435.41 / Max: 531 Min: 36.06 / Avg: 244.62 / Max: 286.2 Min: 38.49 / Avg: 200.26 / Max: 228.96 Min: 81.97 / Avg: 386.29 / Max: 458.4
Tachyon This is a test of the threaded Tachyon, a parallel ray-tracing system, measuring the time to ray-trace a sample scene. The sample scene used is the Teapot scene ray-traced to 8K x 8K with 32 samples. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99.2 Total Time Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 12 24 36 48 60 SE +/- 0.1125, N = 3 SE +/- 0.0168, N = 3 SE +/- 0.0045, N = 3 SE +/- 0.0480, N = 5 SE +/- 0.0786, N = 5 SE +/- 0.0355, N = 3 SE +/- 0.0327, N = 3 SE +/- 0.0339, N = 6 SE +/- 0.0823, N = 7 SE +/- 0.0145, N = 4 SE +/- 0.0101, N = 3 SE +/- 0.0251, N = 3 SE +/- 0.0267, N = 3 SE +/- 0.0916, N = 3 SE +/- 0.0692, N = 4 SE +/- 0.0033, N = 3 SE +/- 0.0272, N = 4 SE +/- 0.0274, N = 3 SE +/- 0.0206, N = 3 SE +/- 0.1158, N = 3 24.8988 19.9688 18.8063 9.8306 10.4833 42.4559 21.4287 7.9829 8.8633 14.6145 16.7586 27.4718 55.5577 49.3315 14.6966 28.5036 14.1652 27.7869 31.1600 16.3356 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Tachyon 0.99.2 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 125.62 / Avg: 481.76 / Max: 580.41 Min: 22.12 / Avg: 273.45 / Max: 329.78 Min: 18.88 / Avg: 311.31 / Max: 388.8 Min: 44.22 / Avg: 526.42 / Max: 775.03 Min: 43.1 / Avg: 468.26 / Max: 658.51 Min: 42.9 / Avg: 210.51 / Max: 283.69 Min: 88.11 / Avg: 470.84 / Max: 555.03 Min: 50.3 / Avg: 532.09 / Max: 819.67 Min: 49.47 / Avg: 462.62 / Max: 672.63 Min: 26.61 / Avg: 318.22 / Max: 409.6 Min: 24.12 / Avg: 268.95 / Max: 336.68 Min: 117.51 / Avg: 477.63 / Max: 567.93 Min: 55.24 / Avg: 251.02 / Max: 283.81 Min: 58.76 / Avg: 253.47 / Max: 290.49 Min: 73.46 / Avg: 412.43 / Max: 542.18 Min: 34.82 / Avg: 227.03 / Max: 267.82 Min: 76.4 / Avg: 412.54 / Max: 539.13 Min: 35.61 / Avg: 229.98 / Max: 270.54 Min: 37.31 / Avg: 207.18 / Max: 230.31 Min: 81.4 / Avg: 378.13 / Max: 460.55
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 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2000M 4000M 6000M 8000M 10000M SE +/- 16840460.54, N = 3 SE +/- 1467802.59, N = 3 SE +/- 2027587.51, N = 3 SE +/- 11228881.41, N = 3 SE +/- 7408178.66, N = 3 SE +/- 2772083.05, N = 3 SE +/- 2061013.77, N = 3 SE +/- 9653036.37, N = 3 SE +/- 3501904.24, N = 3 SE +/- 2200000.00, N = 3 SE +/- 1556705.92, N = 3 SE +/- 3240541.79, N = 3 SE +/- 6982199.59, N = 3 SE +/- 1596175.99, N = 3 SE +/- 7366666.67, N = 3 SE +/- 3002406.44, N = 3 SE +/- 1058825.34, N = 3 SE +/- 2645751.31, N = 3 SE +/- 264575.13, N = 3 SE +/- 11583657.07, N = 3 3079533333 4435766667 4854166667 9226733333 8545966667 2045966667 4030766667 9107033333 8048400000 6182900000 5174800000 2636866667 1331866667 1491366667 5597333333 2963733333 5593866667 3033300000 2720500000 5105933333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 128 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4M 8M 12M 16M 20M 6433426.01 16694782.71 14883619.33 15360984.59 16549656.26 8616980.02 8487800.09 14100272.89 15847755.77 18092615.32 19341095.51 5676506.71 5734280.06 6285536.67 12211064.82 13840999.16 12221345.92 13977299.84 13812517.41 12946685.49 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 134.94 / Avg: 478.68 / Max: 581.44 Min: 21.88 / Avg: 265.7 / Max: 323.97 Min: 20.2 / Avg: 326.14 / Max: 389.24 Min: 43.35 / Avg: 600.66 / Max: 725.07 Min: 43.61 / Avg: 516.38 / Max: 616.22 Min: 43.09 / Avg: 237.43 / Max: 284 Min: 87.77 / Avg: 474.89 / Max: 557.48 Min: 52.21 / Avg: 645.88 / Max: 770.26 Min: 50.03 / Avg: 507.86 / Max: 608.37 Min: 27.28 / Avg: 342.12 / Max: 409.41 Min: 24.79 / Avg: 267.55 / Max: 318.54 Min: 113.06 / Avg: 464.52 / Max: 568.93 Min: 57.21 / Avg: 232.26 / Max: 284.17 Min: 60.6 / Avg: 237.27 / Max: 290.47 Min: 73.29 / Avg: 458.38 / Max: 538.88 Min: 34.27 / Avg: 214.13 / Max: 253.59 Min: 76.25 / Avg: 457.71 / Max: 539.38 Min: 36 / Avg: 217.02 / Max: 257.48 Min: 37.83 / Avg: 196.96 / Max: 230.28 Min: 80.64 / Avg: 394.38 / Max: 461.26
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 0.11 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 700 1400 2100 2800 3500 SE +/- 2.85, N = 3 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 3.51, N = 3 SE +/- 1.45, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 SE +/- 6.94, N = 3 SE +/- 2.33, N = 3 SE +/- 1.86, N = 3 SE +/- 0.33, N = 3 SE +/- 2.52, N = 3 SE +/- 1.76, N = 3 SE +/- 5.24, N = 3 SE +/- 4.26, N = 3 1333 1289 1240 667 717 3478 1853 503 579 916 1060 1492 3003 2603 1101 2125 1137 2171 2464 1397 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 127.89 / Avg: 480.62 / Max: 581.05 Min: 22.27 / Avg: 276.61 / Max: 313.92 Min: 21.34 / Avg: 308.56 / Max: 351.88 Min: 44.54 / Avg: 621.34 / Max: 719.23 Min: 43.45 / Avg: 555.02 / Max: 633.36 Min: 43.79 / Avg: 254.57 / Max: 282.75 Min: 88.05 / Avg: 496.4 / Max: 563.09 Min: 54.3 / Avg: 723.85 / Max: 819.12 Min: 52.72 / Avg: 595.42 / Max: 656.14 Min: 25.82 / Avg: 359.82 / Max: 409.29 Min: 26.01 / Avg: 287.74 / Max: 325.01 Min: 120.66 / Avg: 473.89 / Max: 569.7 Min: 60.78 / Avg: 240.81 / Max: 285.44 Min: 56.79 / Avg: 243.49 / Max: 290.76 Min: 74.4 / Avg: 498.45 / Max: 573.74 Min: 35.05 / Avg: 237.51 / Max: 268.97 Min: 76.67 / Avg: 497.05 / Max: 571.49 Min: 36.3 / Avg: 240.48 / Max: 274.42 Min: 38.04 / Avg: 208.26 / Max: 230.89 Min: 81.33 / Avg: 408.84 / Max: 460.14
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 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 60 120 180 240 300 SE +/- 0.47, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.40, N = 3 SE +/- 0.21, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.38, N = 3 SE +/- 0.25, N = 3 SE +/- 0.13, N = 3 SE +/- 0.28, N = 3 SE +/- 0.07, N = 3 SE +/- 0.53, N = 3 SE +/- 0.48, N = 3 SE +/- 0.44, N = 3 SE +/- 0.77, N = 3 86.60 71.08 67.89 39.56 40.34 177.91 91.84 46.23 49.26 81.27 87.52 77.55 129.37 142.37 116.19 227.77 125.80 243.26 273.28 143.18 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 130.44 / Avg: 508.13 / Max: 565.96 Min: 21.97 / Avg: 313.83 / Max: 343.53 Min: 20.79 / Avg: 341.76 / Max: 384.28 Min: 43.58 / Avg: 632.25 / Max: 689.05 Min: 42.22 / Avg: 606.15 / Max: 663.43 Min: 43.08 / Avg: 255.49 / Max: 280.39 Min: 88.4 / Avg: 491.23 / Max: 554.28 Min: 54.57 / Avg: 734.94 / Max: 810.12 Min: 48.57 / Avg: 626.83 / Max: 682.29 Min: 27.24 / Avg: 360.71 / Max: 402.68 Min: 23.72 / Avg: 321.25 / Max: 352.53 Min: 118.42 / Avg: 497.59 / Max: 553.2 Min: 56.73 / Avg: 249.64 / Max: 280.2 Min: 60.07 / Avg: 253.39 / Max: 284.83 Min: 74.75 / Avg: 487.24 / Max: 549 Min: 34.7 / Avg: 245.99 / Max: 275.5 Min: 77.5 / Avg: 451.89 / Max: 502.79 Min: 36.3 / Avg: 241.31 / Max: 265.26 Min: 38.39 / Avg: 212.8 / Max: 230.3 Min: 81.73 / Avg: 422.64 / Max: 460.3
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 0.11 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 900 1800 2700 3600 4500 SE +/- 5.90, N = 3 SE +/- 1.15, N = 3 SE +/- 1.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 7.37, N = 3 SE +/- 2.33, N = 3 SE +/- 1.76, N = 3 SE +/- 1.45, N = 3 SE +/- 1.20, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 7.94, N = 3 SE +/- 4.67, N = 3 SE +/- 1.20, N = 3 SE +/- 1.00, N = 3 SE +/- 2.33, N = 3 SE +/- 4.33, N = 3 SE +/- 2.03, N = 3 SE +/- 1.53, N = 3 1594 1537 1483 799 859 4140 2205 603 693 1095 1263 1781 3595 3105 1303 2517 1350 2582 2934 1649 1. (CXX) g++ options: -O3 -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 0.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 134.53 / Avg: 481.49 / Max: 581.55 Min: 21.99 / Avg: 279.43 / Max: 314.94 Min: 21.06 / Avg: 308.78 / Max: 350.12 Min: 44.44 / Avg: 624.08 / Max: 716.51 Min: 43.9 / Avg: 556.37 / Max: 632.79 Min: 43.93 / Avg: 256.21 / Max: 282.2 Min: 88.33 / Avg: 497.23 / Max: 557.49 Min: 54.6 / Avg: 711.27 / Max: 818.85 Min: 53.68 / Avg: 576.92 / Max: 656.86 Min: 27.51 / Avg: 361.36 / Max: 409.45 Min: 26.65 / Avg: 288.47 / Max: 325.67 Min: 122.79 / Avg: 474.85 / Max: 570.45 Min: 57.6 / Avg: 241.44 / Max: 285.51 Min: 56.89 / Avg: 243.66 / Max: 290.96 Min: 73.75 / Avg: 500.2 / Max: 574.07 Min: 34.89 / Avg: 238.2 / Max: 269.11 Min: 77.25 / Avg: 497.92 / Max: 572.72 Min: 36.3 / Avg: 241.92 / Max: 274.98 Min: 38.13 / Avg: 209.29 / Max: 230.29 Min: 81.55 / Avg: 410.79 / Max: 460.78
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 4.0 Preset: Exhaustive Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4 8 12 16 20 SE +/- 0.0066, N = 4 SE +/- 0.0005, N = 4 SE +/- 0.0021, N = 4 SE +/- 0.0010, N = 6 SE +/- 0.0052, N = 5 SE +/- 0.0005, N = 3 SE +/- 0.0024, N = 4 SE +/- 0.0373, N = 6 SE +/- 0.0146, N = 6 SE +/- 0.0031, N = 5 SE +/- 0.0016, N = 4 SE +/- 0.0047, N = 4 SE +/- 0.0023, N = 3 SE +/- 0.0026, N = 3 SE +/- 0.0027, N = 5 SE +/- 0.0013, N = 3 SE +/- 0.0017, N = 5 SE +/- 0.0004, N = 3 SE +/- 0.0012, N = 3 SE +/- 0.0540, N = 15 4.5138 5.0295 5.3824 10.7069 9.6418 2.3227 4.6306 13.6998 11.7394 7.0368 5.9568 4.0998 1.9978 2.2629 7.1407 3.6271 7.2392 3.6189 3.2068 6.0529 1. (CXX) g++ options: -O3 -flto -pthread MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0088 0.0176 0.0264 0.0352 0.044 0.012 0.026 0.025 0.030 0.030 0.011 0.012 0.039 0.038 0.032 0.031 0.011 0.009 0.010 0.023 0.020 0.024 0.019 0.019 0.021 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 133.27 / Avg: 383.87 / Max: 581.9 Min: 21.81 / Avg: 196.41 / Max: 316.35 Min: 18.75 / Avg: 216.91 / Max: 372.59 Min: 43.99 / Avg: 356.2 / Max: 780.95 Min: 41.73 / Avg: 316.36 / Max: 640.6 Min: 42.98 / Avg: 218.37 / Max: 279.19 Min: 88.31 / Avg: 372.16 / Max: 560.73 Min: 52.12 / Avg: 348.31 / Max: 819.6 Min: 51.43 / Avg: 310.36 / Max: 660.18 Min: 24.19 / Avg: 219.83 / Max: 409.42 Min: 27.19 / Avg: 190.99 / Max: 326.44 Min: 110.7 / Avg: 378.14 / Max: 569.98 Min: 60.84 / Avg: 217.97 / Max: 284.13 Min: 62.42 / Avg: 217.22 / Max: 290.81 Min: 74.74 / Avg: 304.69 / Max: 572.87 Min: 34.22 / Avg: 182.57 / Max: 266.54 Min: 77.27 / Avg: 300.98 / Max: 561.82 Min: 35.81 / Avg: 185.86 / Max: 268.16 Min: 37.71 / Avg: 170.09 / Max: 230.29 Min: 81.62 / Avg: 290.5 / Max: 461.32
Blender Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: BMW27 - Compute: CPU-Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 12 24 36 48 60 SE +/- 0.22, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 6 SE +/- 0.03, N = 5 SE +/- 0.04, N = 4 SE +/- 0.15, N = 4 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 4 SE +/- 0.03, N = 3 SE +/- 0.04, N = 4 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.17, N = 3 23.71 18.39 17.45 9.26 10.01 41.50 22.13 7.50 8.43 13.59 15.63 25.80 51.42 45.60 14.61 27.53 14.27 26.96 30.41 17.00 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 3.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 138.27 / Avg: 471.12 / Max: 581.86 Min: 21.91 / Avg: 260.34 / Max: 327.42 Min: 20.69 / Avg: 292.6 / Max: 376.85 Min: 43.42 / Avg: 495.05 / Max: 783.7 Min: 36.24 / Avg: 450.32 / Max: 661.36 Min: 42.19 / Avg: 249.84 / Max: 279.48 Min: 88.59 / Avg: 467.04 / Max: 558.68 Min: 52.81 / Avg: 507.84 / Max: 821.24 Min: 48.57 / Avg: 434.72 / Max: 679.42 Min: 26.02 / Avg: 303.99 / Max: 409.81 Min: 25.84 / Avg: 257.58 / Max: 334.97 Min: 103.19 / Avg: 465.9 / Max: 568.37 Min: 59.08 / Avg: 247.52 / Max: 284.03 Min: 60.71 / Avg: 249.58 / Max: 290.33 Min: 74.18 / Avg: 438.62 / Max: 572.33 Min: 33.92 / Avg: 227.63 / Max: 264.34 Min: 76.98 / Avg: 428.23 / Max: 573.36 Min: 35.66 / Avg: 228.22 / Max: 270.31 Min: 37.66 / Avg: 202.18 / Max: 230.29 Min: 78.61 / Avg: 366.6 / Max: 466.57
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.16, N = 5 SE +/- 0.26, N = 6 SE +/- 0.25, N = 6 SE +/- 0.06, N = 8 SE +/- 0.04, N = 8 SE +/- 0.12, N = 6 SE +/- 0.11, N = 5 SE +/- 0.08, N = 9 SE +/- 0.07, N = 9 SE +/- 0.17, N = 7 SE +/- 0.28, N = 7 SE +/- 0.04, N = 5 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.35, N = 8 SE +/- 0.20, N = 15 SE +/- 0.34, N = 8 SE +/- 0.20, N = 5 SE +/- 0.14, N = 5 SE +/- 0.22, N = 6 24.64 30.03 30.13 54.57 54.67 11.79 21.43 80.40 70.48 43.95 39.15 23.03 12.13 13.50 51.05 29.46 38.91 23.48 20.73 32.63 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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0563 0.1126 0.1689 0.2252 0.2815 0.058 0.176 0.177 0.187 0.188 0.060 0.054 0.250 0.249 0.212 0.227 0.055 0.053 0.058 0.166 0.162 0.115 0.118 0.120 0.107 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ACES DGEMM 1.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 134.02 / Avg: 424.38 / Max: 579.58 Min: 20.11 / Avg: 170.25 / Max: 273.42 Min: 18.66 / Avg: 169.96 / Max: 273.35 Min: 40.75 / Avg: 291.69 / Max: 543.96 Min: 42.14 / Avg: 290.27 / Max: 542.34 Min: 42.79 / Avg: 195.92 / Max: 279.94 Min: 89.51 / Avg: 400.3 / Max: 567.84 Min: 52.97 / Avg: 321.33 / Max: 728.61 Min: 47.54 / Avg: 282.78 / Max: 575.81 Min: 26.44 / Avg: 207.46 / Max: 382.17 Min: 25.18 / Avg: 172.25 / Max: 294.67 Min: 113.19 / Avg: 417.81 / Max: 562.48 Min: 63.11 / Avg: 230.44 / Max: 285.2 Min: 62.27 / Avg: 231.15 / Max: 290.96 Min: 75.05 / Avg: 306.94 / Max: 557.08 Min: 34.25 / Avg: 182.12 / Max: 283.48 Min: 78.33 / Avg: 338.07 / Max: 573.32 Min: 35.98 / Avg: 198.96 / Max: 286.6 Min: 37.54 / Avg: 172.94 / Max: 230.4 Min: 81.51 / Avg: 304.01 / Max: 460.41
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.
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 11K 22K 33K 44K 55K SE +/- 173.15, N = 3 SE +/- 21.02, N = 3 SE +/- 10.36, N = 3 SE +/- 12.09, N = 3 SE +/- 19.62, N = 3 SE +/- 7.57, N = 3 SE +/- 0.22, N = 3 SE +/- 95.15, N = 3 SE +/- 25.12, N = 3 SE +/- 27.29, N = 3 SE +/- 0.35, N = 3 SE +/- 89.52, N = 3 SE +/- 94.29, N = 3 SE +/- 8.67, N = 3 SE +/- 13.15, N = 3 SE +/- 25.24, N = 3 SE +/- 22.46, N = 3 SE +/- 3.42, N = 3 SE +/- 1.23, N = 3 SE +/- 9.34, N = 3 17391.5 17536.0 17546.1 35088.9 34900.0 8401.6 16807.9 51406.6 44516.7 25901.8 22205.3 16041.5 7690.3 8462.5 27127.8 13762.3 26521.8 13287.5 12612.1 24998.0 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13 Binary: Pathtracer - Model: Crown Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 SE +/- 0.09, N = 5 SE +/- 0.09, N = 6 SE +/- 0.09, N = 6 SE +/- 0.31, N = 7 SE +/- 0.36, N = 7 SE +/- 0.09, N = 4 SE +/- 0.11, N = 5 SE +/- 0.43, N = 8 SE +/- 0.38, N = 8 SE +/- 0.08, N = 7 SE +/- 0.14, N = 6 SE +/- 0.14, N = 5 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.14, N = 7 SE +/- 0.12, N = 5 SE +/- 0.24, N = 7 SE +/- 0.10, N = 5 SE +/- 0.06, N = 4 SE +/- 0.10, N = 6 61.90 85.56 89.31 147.85 141.64 40.91 73.11 202.58 175.90 115.54 102.97 57.65 30.94 35.09 127.85 68.86 111.94 63.19 51.89 89.47 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1161 0.2322 0.3483 0.4644 0.5805 0.143 0.402 0.393 0.407 0.409 0.180 0.183 0.516 0.511 0.478 0.490 0.137 0.134 0.152 0.368 0.333 0.310 0.301 0.294 0.282 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 138.31 / Avg: 431.58 / Max: 553.94 Min: 21.76 / Avg: 212.93 / Max: 326.79 Min: 18.61 / Avg: 227.05 / Max: 354.33 Min: 43.4 / Avg: 363.07 / Max: 666.17 Min: 42.99 / Avg: 346.42 / Max: 628.48 Min: 43.2 / Avg: 226.79 / Max: 281.33 Min: 89.27 / Avg: 400.3 / Max: 564.9 Min: 51.96 / Avg: 392.47 / Max: 793.58 Min: 51.86 / Avg: 344.3 / Max: 647.11 Min: 27.14 / Avg: 241.52 / Max: 409.75 Min: 25.04 / Avg: 211.53 / Max: 336.95 Min: 109.32 / Avg: 420.27 / Max: 545.8 Min: 57.8 / Avg: 230.93 / Max: 281.7 Min: 60.62 / Avg: 231.51 / Max: 284.99 Min: 75.28 / Avg: 347.73 / Max: 573.73 Min: 34.39 / Avg: 206.49 / Max: 286.83 Min: 77.73 / Avg: 360.72 / Max: 570 Min: 35.98 / Avg: 209.64 / Max: 286.12 Min: 37.81 / Avg: 176.67 / Max: 229.66 Min: 81.51 / Avg: 316.85 / Max: 458.86
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 3.0 Algorithm: RSA4096 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 700K 1400K 2100K 2800K 3500K SE +/- 5774.79, N = 3 SE +/- 79.86, N = 3 SE +/- 60.43, N = 3 SE +/- 169.85, N = 3 SE +/- 160.33, N = 3 SE +/- 27.52, N = 3 SE +/- 130.95, N = 3 SE +/- 708.03, N = 3 SE +/- 457.50, N = 3 SE +/- 137.73, N = 3 SE +/- 93.24, N = 3 SE +/- 1640.19, N = 3 SE +/- 438.19, N = 3 SE +/- 1367.77, N = 3 SE +/- 180.37, N = 3 SE +/- 1242.31, N = 3 SE +/- 3081.20, N = 3 SE +/- 79.21, N = 3 SE +/- 70.93, N = 3 SE +/- 296.25, N = 3 1180376.6 1141402.4 1141575.6 2282801.7 2282702.1 546929.9 1093482.1 3369633.3 2936111.9 1689673.1 1463630.7 1068009.0 519444.7 588480.5 1780874.6 902005.3 1728763.7 867678.4 823890.5 1633628.1 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl verify/s Per Watt
OpenBenchmarking.org verify/s Per Watt, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1100 2200 3300 4400 5500 2287.36 4166.23 4192.40 3945.99 4008.64 2200.08 2209.70 4393.56 5076.30 4436.14 5041.50 2120.85 2057.08 2294.96 3406.12 3480.19 3684.04 3732.85 3818.51 3743.44 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 134.67 / Avg: 516.04 / Max: 577.89 Min: 21.91 / Avg: 273.97 / Max: 293.4 Min: 20.79 / Avg: 272.3 / Max: 293.21 Min: 43.5 / Avg: 578.51 / Max: 623.99 Min: 44.94 / Avg: 569.45 / Max: 611.93 Min: 41.86 / Avg: 248.6 / Max: 269 Min: 87.1 / Avg: 494.75 / Max: 538.6 Min: 52.92 / Avg: 766.95 / Max: 819.56 Min: 52.18 / Avg: 578.4 / Max: 618.02 Min: 26.79 / Avg: 380.89 / Max: 409.2 Min: 26.55 / Avg: 290.32 / Max: 309.1 Min: 120.46 / Avg: 503.58 / Max: 563.4 Min: 58.58 / Avg: 252.52 / Max: 283.31 Min: 57.59 / Avg: 256.42 / Max: 285.94 Min: 73.81 / Avg: 522.85 / Max: 558.9 Min: 33.67 / Avg: 259.18 / Max: 275.99 Min: 75.87 / Avg: 469.26 / Max: 502.71 Min: 35.37 / Avg: 232.44 / Max: 250.32 Min: 37.6 / Avg: 215.76 / Max: 230.29 Min: 80.4 / Avg: 436.4 / Max: 460.57
Blender Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 3.3 Blend File: Fishy Cat - Compute: CPU-Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 15 30 45 60 75 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 4 SE +/- 0.06, N = 4 SE +/- 0.03, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 5 SE +/- 0.05, N = 4 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 SE +/- 0.28, N = 3 SE +/- 0.36, N = 3 SE +/- 0.10, N = 3 SE +/- 0.15, N = 3 SE +/- 0.18, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 31.34 24.00 22.59 12.32 13.49 52.40 28.14 10.54 11.50 18.05 20.47 34.34 68.08 60.84 18.70 34.97 18.49 34.51 39.04 22.03 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 3.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 131.06 / Avg: 477.43 / Max: 581.35 Min: 21.92 / Avg: 270.57 / Max: 334.84 Min: 19.61 / Avg: 312.96 / Max: 390.87 Min: 44.14 / Avg: 550.33 / Max: 816.8 Min: 39.01 / Avg: 475.03 / Max: 673.61 Min: 43.43 / Avg: 256.79 / Max: 281.84 Min: 88.72 / Avg: 469.83 / Max: 561.75 Min: 53.7 / Avg: 518.36 / Max: 818.89 Min: 52.38 / Avg: 472.49 / Max: 697.48 Min: 26.42 / Avg: 314.29 / Max: 409.54 Min: 26.5 / Avg: 271.1 / Max: 343.62 Min: 111.8 / Avg: 474.06 / Max: 569.73 Min: 56.93 / Avg: 248.86 / Max: 285.13 Min: 60.15 / Avg: 253.04 / Max: 290.82 Min: 73.68 / Avg: 438.18 / Max: 570.62 Min: 34.77 / Avg: 227.62 / Max: 261.3 Min: 77.03 / Avg: 441.66 / Max: 572.82 Min: 36.34 / Avg: 230.4 / Max: 265.86 Min: 38.12 / Avg: 204.63 / Max: 230.29 Min: 82.09 / Avg: 378.81 / Max: 460.57
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 400 800 1200 1600 2000 SE +/- 0.94, N = 3 SE +/- 0.93, N = 3 SE +/- 0.74, N = 3 SE +/- 1.89, N = 3 SE +/- 0.15, N = 3 SE +/- 0.32, N = 3 SE +/- 0.95, N = 3 SE +/- 0.46, N = 3 SE +/- 0.42, N = 3 824.35 843.37 879.22 1739.26 1615.51 269.46 534.96 1133.41 1014.62
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 6 12 18 24 30 SE +/- 0.01369263, N = 4 SE +/- 0.04408610, N = 5 SE +/- 0.02649159, N = 5 SE +/- 0.02752118, N = 7 SE +/- 0.03372817, N = 7 SE +/- 0.03504156, N = 3 SE +/- 0.03398896, N = 4 SE +/- 0.01984368, N = 7 SE +/- 0.01966452, N = 7 SE +/- 0.02766243, N = 5 SE +/- 0.05206844, N = 5 SE +/- 0.02271047, N = 4 SE +/- 0.09921822, N = 3 SE +/- 0.00677335, N = 3 SE +/- 0.09231981, N = 15 SE +/- 0.05294615, N = 3 SE +/- 0.03743001, N = 4 SE +/- 0.17583211, N = 3 SE +/- 0.14874204, N = 3 SE +/- 0.03902515, N = 4 11.14601710 9.56905289 9.59882088 4.95660475 4.96696207 23.30647790 11.31388070 4.29938201 4.36289297 8.07779980 8.22620277 12.24763610 26.45376970 23.96615350 9.50778993 16.87535610 11.00870180 21.80955890 21.84940530 11.01479630 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 133.65 / Avg: 433.59 / Max: 573.18 Min: 21.8 / Avg: 176.93 / Max: 268.24 Min: 20.77 / Avg: 177.37 / Max: 272.91 Min: 43.27 / Avg: 311.22 / Max: 568.25 Min: 41.67 / Avg: 308.38 / Max: 565.43 Min: 43.02 / Avg: 209.88 / Max: 248.43 Min: 88.96 / Avg: 391.04 / Max: 524.43 Min: 52.18 / Avg: 372.18 / Max: 736.95 Min: 47.6 / Avg: 337.9 / Max: 635.69 Min: 26.9 / Avg: 219.7 / Max: 356.39 Min: 26.49 / Avg: 205.6 / Max: 312.92 Min: 112.05 / Avg: 426.75 / Max: 552.75 Min: 61.56 / Avg: 238.04 / Max: 281.81 Min: 61.08 / Avg: 238.73 / Max: 286 Min: 75.26 / Avg: 380.71 / Max: 554.29 Min: 34.27 / Avg: 204.74 / Max: 265.73 Min: 77.17 / Avg: 363 / Max: 507.42 Min: 35.99 / Avg: 193.89 / Max: 243.81 Min: 37.59 / Avg: 185.98 / Max: 224.07 Min: 81.62 / Avg: 343.27 / Max: 459.46
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 4.0 Preset: Thorough Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30 60 90 120 150 SE +/- 0.05, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.02, N = 7 SE +/- 0.01, N = 6 SE +/- 0.03, N = 4 SE +/- 0.07, N = 5 SE +/- 0.08, N = 7 SE +/- 0.05, N = 7 SE +/- 0.04, N = 6 SE +/- 0.01, N = 6 SE +/- 0.02, N = 5 SE +/- 0.03, N = 3 SE +/- 0.06, N = 4 SE +/- 0.02, N = 6 SE +/- 0.01, N = 5 SE +/- 0.02, N = 6 SE +/- 0.04, N = 5 SE +/- 0.01, N = 4 SE +/- 0.04, N = 5 44.69 47.54 50.94 98.40 90.55 22.20 43.46 122.12 106.62 65.40 56.20 40.31 19.94 22.48 65.61 34.11 66.28 33.89 30.13 57.79 1. (CXX) g++ options: -O3 -flto -pthread MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Thorough Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1022 0.2044 0.3066 0.4088 0.511 0.138 0.307 0.296 0.374 0.370 0.119 0.142 0.454 0.447 0.384 0.365 0.126 0.104 0.119 0.267 0.226 0.276 0.222 0.211 0.246 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 131.43 / Avg: 324.78 / Max: 578.88 Min: 21.29 / Avg: 154.83 / Max: 319.96 Min: 17.5 / Avg: 172.37 / Max: 375.08 Min: 41.59 / Avg: 263.41 / Max: 746.56 Min: 36.21 / Avg: 244.65 / Max: 634.14 Min: 42.46 / Avg: 187.24 / Max: 279.23 Min: 88.27 / Avg: 305.68 / Max: 560.1 Min: 50.83 / Avg: 269.14 / Max: 789.43 Min: 48.74 / Avg: 238.35 / Max: 648.9 Min: 26.13 / Avg: 170.39 / Max: 406.52 Min: 25.18 / Avg: 154.01 / Max: 327.7 Min: 115.74 / Avg: 320.48 / Max: 567.62 Min: 57.02 / Avg: 191.95 / Max: 283.95 Min: 62.68 / Avg: 188.93 / Max: 290.14 Min: 53.91 / Avg: 245.35 / Max: 557.89 Min: 34.1 / Avg: 151.17 / Max: 266.02 Min: 77.06 / Avg: 240.15 / Max: 544.48 Min: 35.65 / Avg: 152.63 / Max: 268.09 Min: 37.38 / Avg: 142.84 / Max: 229.92 Min: 81.4 / Avg: 234.73 / Max: 457.03
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 3.1.1 Test: Basic - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 160 320 480 640 800 SE +/- 3.95, N = 3 SE +/- 2.72, N = 5 SE +/- 2.75, N = 5 SE +/- 1.24, N = 12 SE +/- 0.15, N = 3 SE +/- 3.73, N = 3 SE +/- 0.08, N = 3 SE +/- 1.23, N = 12 SE +/- 0.19, N = 3 SE +/- 2.38, N = 6 SE +/- 2.71, N = 5 SE +/- 3.97, N = 3 SE +/- 2.68, N = 3 SE +/- 2.68, N = 3 SE +/- 1.24, N = 12 SE +/- 3.13, N = 4 SE +/- 3.63, N = 4 SE +/- 4.68, N = 3 SE +/- 4.48, N = 3 SE +/- 3.65, N = 4 367.12 256.41 250.95 130.65 131.60 456.68 228.07 127.04 127.52 245.03 247.09 383.39 763.20 716.75 147.36 276.59 293.34 566.38 572.31 296.13 1. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -lmpi_cxx -lmpi CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RELION 3.1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 127.53 / Avg: 530.35 / Max: 581.46 Min: 21.92 / Avg: 317.75 / Max: 329.29 Min: 20.04 / Avg: 350.24 / Max: 378.72 Min: 44.26 / Avg: 701.18 / Max: 749.35 Min: 45.13 / Avg: 626.7 / Max: 678.86 Min: 44.02 / Avg: 280.84 / Max: 286.74 Min: 87.71 / Avg: 545 / Max: 564.54 Min: 50.2 / Avg: 768.67 / Max: 821.55 Min: 54.3 / Avg: 631.92 / Max: 691.01 Min: 27.29 / Avg: 395.54 / Max: 410.63 Min: 25.55 / Avg: 318.87 / Max: 343.27 Min: 119.22 / Avg: 520.9 / Max: 568.83 Min: 57.1 / Avg: 262.72 / Max: 284.94 Min: 59.38 / Avg: 267.45 / Max: 290.73 Min: 73.82 / Avg: 546.92 / Max: 575.58 Min: 34.87 / Avg: 278.21 / Max: 286.87 Min: 76.42 / Avg: 519.5 / Max: 540.12 Min: 36.37 / Avg: 263.51 / Max: 280.53 Min: 38.42 / Avg: 219.85 / Max: 230.07 Min: 80.52 / Avg: 443.28 / Max: 460.81
Rodinia Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 3.1 Test: OpenMP LavaMD Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 4 SE +/- 0.04, N = 4 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 SE +/- 0.28, N = 3 SE +/- 0.30, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 44.82 32.55 29.78 17.09 18.72 60.45 33.00 14.68 16.63 24.49 28.61 48.11 86.92 78.72 25.19 43.78 23.95 42.24 46.16 26.92 1. (CXX) g++ options: -O2 -lOpenCL CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Rodinia 3.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 130.05 / Avg: 440.43 / Max: 580.4 Min: 21.27 / Avg: 254.39 / Max: 316.05 Min: 19.7 / Avg: 304.64 / Max: 393.06 Min: 42.57 / Avg: 524.99 / Max: 796.61 Min: 43.72 / Avg: 442.63 / Max: 635.66 Min: 42.48 / Avg: 250.41 / Max: 282.02 Min: 88.22 / Avg: 454.63 / Max: 561.08 Min: 53.98 / Avg: 510.06 / Max: 818.39 Min: 50.79 / Avg: 442.59 / Max: 653.45 Min: 26.92 / Avg: 306.15 / Max: 409.43 Min: 25.75 / Avg: 251.91 / Max: 319.37 Min: 114.83 / Avg: 438.41 / Max: 568.34 Min: 60.99 / Avg: 239.81 / Max: 283.33 Min: 61.2 / Avg: 240.53 / Max: 290.23 Min: 75.31 / Avg: 382.95 / Max: 522.19 Min: 34.12 / Avg: 213.78 / Max: 256.75 Min: 77.33 / Avg: 387.34 / Max: 541.97 Min: 35.9 / Avg: 217.47 / Max: 260.35 Min: 37.58 / Avg: 200.34 / Max: 230.29 Min: 81.32 / Avg: 359.71 / Max: 460.69
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13 Binary: Pathtracer - Model: Asian Dragon Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 SE +/- 0.27, N = 5 SE +/- 0.36, N = 6 SE +/- 0.12, N = 6 SE +/- 0.18, N = 8 SE +/- 0.23, N = 8 SE +/- 0.16, N = 4 SE +/- 0.13, N = 5 SE +/- 0.29, N = 9 SE +/- 0.20, N = 8 SE +/- 0.14, N = 7 SE +/- 0.26, N = 7 SE +/- 0.36, N = 5 SE +/- 0.09, N = 3 SE +/- 0.20, N = 4 SE +/- 1.00, N = 6 SE +/- 0.18, N = 6 SE +/- 0.51, N = 5 SE +/- 0.10, N = 5 SE +/- 0.27, N = 5 SE +/- 0.64, N = 5 79.57 98.44 100.16 163.83 160.24 45.93 68.04 210.04 193.25 137.93 120.76 69.99 35.80 41.97 100.04 80.65 73.61 71.15 63.11 68.66 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1458 0.2916 0.4374 0.5832 0.729 0.191 0.505 0.501 0.521 0.511 0.209 0.169 0.593 0.648 0.623 0.629 0.172 0.161 0.185 0.270 0.408 0.212 0.352 0.373 0.206 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 134.06 / Avg: 415.83 / Max: 567.98 Min: 21.71 / Avg: 195.07 / Max: 317.74 Min: 20.26 / Avg: 199.95 / Max: 325.78 Min: 42.3 / Avg: 314.17 / Max: 619.28 Min: 41.25 / Avg: 313.58 / Max: 605.6 Min: 42.89 / Avg: 219.37 / Max: 278.11 Min: 88.63 / Avg: 402.18 / Max: 552.56 Min: 50.69 / Avg: 353.92 / Max: 774.1 Min: 50.08 / Avg: 298.24 / Max: 627.42 Min: 27.03 / Avg: 221.37 / Max: 408.7 Min: 25.23 / Avg: 191.99 / Max: 327.43 Min: 110.47 / Avg: 407.12 / Max: 558.97 Min: 60.17 / Avg: 223.03 / Max: 282.48 Min: 63.01 / Avg: 227.12 / Max: 287.74 Min: 75.11 / Avg: 370.31 / Max: 572.65 Min: 34.2 / Avg: 197.6 / Max: 286.69 Min: 76.66 / Avg: 347.1 / Max: 489.15 Min: 35.92 / Avg: 201.91 / Max: 285.06 Min: 37.73 / Avg: 169.36 / Max: 229.44 Min: 81.08 / Avg: 332.65 / Max: 456.24
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.C Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4K 8K 12K 16K 20K SE +/- 86.42, N = 15 SE +/- 131.05, N = 15 SE +/- 140.16, N = 15 SE +/- 23.76, N = 12 SE +/- 108.53, N = 15 SE +/- 11.53, N = 9 SE +/- 46.76, N = 15 SE +/- 97.05, N = 15 SE +/- 112.63, N = 12 SE +/- 39.65, N = 15 SE +/- 86.35, N = 15 SE +/- 67.04, N = 15 SE +/- 28.44, N = 15 SE +/- 32.11, N = 11 SE +/- 128.91, N = 15 SE +/- 92.00, N = 15 SE +/- 26.79, N = 11 SE +/- 49.37, N = 15 SE +/- 31.46, N = 15 SE +/- 117.79, N = 15 7976.70 7198.90 6940.40 12962.47 12851.16 3230.69 6159.65 18773.11 16424.61 9551.94 8633.62 7622.71 3979.08 4390.98 9285.18 4968.98 9241.56 4982.82 4531.17 8241.13 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 4.1.4 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30 60 90 120 150 31.58 83.95 82.78 97.41 94.98 25.98 30.61 122.21 109.79 96.43 99.20 32.47 27.99 31.30 52.90 45.51 55.33 49.42 45.19 48.19 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 132.91 / Avg: 252.58 / Max: 580.21 Min: 19.86 / Avg: 85.75 / Max: 293.08 Min: 19.78 / Avg: 83.84 / Max: 295.32 Min: 43.03 / Avg: 133.07 / Max: 483.5 Min: 42.21 / Avg: 135.3 / Max: 499.15 Min: 42.94 / Avg: 124.37 / Max: 252.85 Min: 88.35 / Avg: 201.23 / Max: 512.61 Min: 52.63 / Avg: 153.62 / Max: 524.45 Min: 49.16 / Avg: 149.6 / Max: 483.71 Min: 26.35 / Avg: 99.05 / Max: 374.16 Min: 24.64 / Avg: 87.03 / Max: 315.37 Min: 110.33 / Avg: 234.74 / Max: 569.46 Min: 59.95 / Avg: 142.18 / Max: 285.34 Min: 59.73 / Avg: 140.28 / Max: 290.91 Min: 74.72 / Avg: 175.53 / Max: 570.42 Min: 34.49 / Avg: 109.2 / Max: 286.78 Min: 77.07 / Avg: 167.02 / Max: 487.64 Min: 36.03 / Avg: 100.83 / Max: 251.97 Min: 37.68 / Avg: 100.27 / Max: 230.29 Min: 81.39 / Avg: 171.01 / Max: 460.76
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120K 240K 360K 480K 600K SE +/- 520.33, N = 4 SE +/- 455.33, N = 4 SE +/- 649.68, N = 4 SE +/- 4145.25, N = 6 SE +/- 3154.34, N = 6 SE +/- 44.90, N = 3 SE +/- 179.20, N = 4 SE +/- 3150.15, N = 6 SE +/- 2523.78, N = 6 SE +/- 1011.25, N = 5 SE +/- 1212.90, N = 4 SE +/- 706.35, N = 4 SE +/- 152.73, N = 3 SE +/- 356.18, N = 3 SE +/- 1679.40, N = 5 SE +/- 269.58, N = 3 SE +/- 401.49, N = 4 SE +/- 218.03, N = 3 SE +/- 363.87, N = 3 SE +/- 1004.45, N = 4 193069.48 235197.75 237735.42 462177.87 463499.49 98277.99 199380.33 543554.45 500990.52 274024.34 267319.17 194987.49 95180.72 115359.20 369239.47 166563.21 252416.39 133198.16 127746.66 232312.47 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 4.1.4 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300 600 900 1200 1500 424.33 1089.24 1103.70 1230.87 1245.30 420.73 455.64 1233.95 1317.21 1078.97 1199.97 441.20 395.01 481.28 949.97 720.51 610.29 598.05 667.70 656.43 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 135.14 / Avg: 455 / Max: 570.08 Min: 22.28 / Avg: 215.93 / Max: 300.37 Min: 20.74 / Avg: 215.4 / Max: 304.25 Min: 44.08 / Avg: 375.49 / Max: 640.03 Min: 35.98 / Avg: 372.2 / Max: 632.39 Min: 44.1 / Avg: 233.59 / Max: 264.12 Min: 88.11 / Avg: 437.59 / Max: 547.17 Min: 52.11 / Avg: 440.5 / Max: 799.04 Min: 49.37 / Avg: 380.34 / Max: 651.21 Min: 26.45 / Avg: 253.97 / Max: 373.87 Min: 25.66 / Avg: 222.77 / Max: 316.46 Min: 113.59 / Avg: 441.95 / Max: 566.18 Min: 58.62 / Avg: 240.96 / Max: 281.37 Min: 57.63 / Avg: 239.69 / Max: 285.89 Min: 73.46 / Avg: 388.68 / Max: 574.14 Min: 34.93 / Avg: 231.17 / Max: 286.53 Min: 78.26 / Avg: 413.6 / Max: 561.99 Min: 36.32 / Avg: 222.72 / Max: 279.78 Min: 38.16 / Avg: 191.33 / Max: 228.07 Min: 80.42 / Avg: 353.9 / Max: 461.11
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13 Binary: Pathtracer ISPC - Model: Crown Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 SE +/- 0.15, N = 5 SE +/- 0.09, N = 6 SE +/- 0.23, N = 6 SE +/- 0.24, N = 8 SE +/- 0.35, N = 8 SE +/- 0.03, N = 3 SE +/- 0.01, N = 5 SE +/- 0.25, N = 8 SE +/- 0.38, N = 8 SE +/- 0.12, N = 7 SE +/- 0.16, N = 7 SE +/- 0.10, N = 5 SE +/- 0.06, N = 4 SE +/- 0.04, N = 4 SE +/- 0.26, N = 7 SE +/- 0.08, N = 5 SE +/- 0.13, N = 6 SE +/- 0.08, N = 5 SE +/- 0.20, N = 4 SE +/- 0.09, N = 6 73.78 91.72 96.79 157.17 149.02 37.32 67.21 212.17 182.48 123.62 109.92 68.36 38.76 43.06 116.08 63.47 101.57 58.17 47.92 82.57 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1256 0.2512 0.3768 0.5024 0.628 0.177 0.438 0.433 0.453 0.443 0.183 0.164 0.558 0.541 0.518 0.538 0.168 0.172 0.190 0.325 0.304 0.273 0.272 0.266 0.254 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 144.57 / Avg: 417.79 / Max: 550.19 Min: 21.77 / Avg: 209.43 / Max: 325.08 Min: 19.51 / Avg: 223.64 / Max: 358.7 Min: 43.54 / Avg: 346.69 / Max: 671.94 Min: 43.58 / Avg: 336.54 / Max: 623.72 Min: 43.3 / Avg: 204 / Max: 278.98 Min: 88.97 / Avg: 410.23 / Max: 562.89 Min: 52.81 / Avg: 380.46 / Max: 786.19 Min: 52.49 / Avg: 337.04 / Max: 641.13 Min: 26.88 / Avg: 238.47 / Max: 409.7 Min: 24.69 / Avg: 204.49 / Max: 335.69 Min: 109.22 / Avg: 407.21 / Max: 538.58 Min: 61.27 / Avg: 225.19 / Max: 282.19 Min: 59.17 / Avg: 226.55 / Max: 286.08 Min: 75.76 / Avg: 357.51 / Max: 574.22 Min: 34.55 / Avg: 208.51 / Max: 286.78 Min: 77 / Avg: 371.81 / Max: 570.4 Min: 35.93 / Avg: 214.22 / Max: 286.3 Min: 37.8 / Avg: 180.27 / Max: 230.16 Min: 81.81 / Avg: 325.57 / Max: 458.59
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 200 400 600 800 1000 SE +/- 0.70, N = 3 SE +/- 0.64, N = 3 SE +/- 0.23, N = 3 SE +/- 2.55, N = 3 SE +/- 1.74, N = 3 SE +/- 0.11, N = 3 SE +/- 0.52, N = 3 SE +/- 0.57, N = 3 SE +/- 0.82, N = 3 333.61 364.70 388.32 776.30 710.90 136.87 268.01 499.75 447.55
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 SE +/- 0.32, N = 6 SE +/- 0.15, N = 7 SE +/- 0.21, N = 7 SE +/- 0.35, N = 8 SE +/- 0.39, N = 8 SE +/- 0.17, N = 4 SE +/- 0.10, N = 5 SE +/- 0.42, N = 9 SE +/- 0.22, N = 9 SE +/- 0.21, N = 8 SE +/- 0.07, N = 7 SE +/- 0.50, N = 6 SE +/- 0.16, N = 4 SE +/- 0.59, N = 5 SE +/- 0.75, N = 15 SE +/- 0.24, N = 5 SE +/- 0.55, N = 15 SE +/- 0.04, N = 5 SE +/- 0.10, N = 5 SE +/- 0.61, N = 15 105.21 111.70 116.10 178.97 176.35 41.49 64.56 232.40 213.25 154.64 136.11 89.10 49.57 55.87 94.10 72.23 68.26 66.09 56.87 67.30 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1679 0.3358 0.5037 0.6716 0.8395 0.269 0.589 0.583 0.573 0.575 0.185 0.158 0.706 0.719 0.718 0.746 0.228 0.229 0.257 0.248 0.359 0.187 0.321 0.329 0.199 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 3.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 127.89 / Avg: 390.5 / Max: 568.04 Min: 21.84 / Avg: 189.68 / Max: 317.79 Min: 19.02 / Avg: 199.15 / Max: 342.05 Min: 42.48 / Avg: 312.24 / Max: 624.66 Min: 23.44 / Avg: 306.63 / Max: 605.53 Min: 43.06 / Avg: 223.76 / Max: 280.65 Min: 88.71 / Avg: 408.11 / Max: 565.18 Min: 53.01 / Avg: 329.31 / Max: 780.45 Min: 50.4 / Avg: 296.8 / Max: 627.13 Min: 27.3 / Avg: 215.36 / Max: 409.29 Min: 25.63 / Avg: 182.41 / Max: 327.04 Min: 113.65 / Avg: 391.24 / Max: 556.48 Min: 57.31 / Avg: 216.6 / Max: 284.33 Min: 60.24 / Avg: 217.28 / Max: 289.41 Min: 74.79 / Avg: 379.44 / Max: 573.7 Min: 34.44 / Avg: 201.37 / Max: 286.62 Min: 76.52 / Avg: 365.03 / Max: 506.28 Min: 35.95 / Avg: 205.84 / Max: 285.83 Min: 37.87 / Avg: 173.03 / Max: 229.33 Min: 81.28 / Avg: 338.6 / Max: 459.35
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 2022.2.dev Model: Person Detection FP32 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1000 2000 3000 4000 5000 SE +/- 2.36, N = 3 SE +/- 5.54, N = 3 SE +/- 2.35, N = 3 SE +/- 8.23, N = 3 SE +/- 4.19, N = 3 SE +/- 6.44, N = 3 SE +/- 1.82, N = 3 SE +/- 6.16, N = 3 SE +/- 7.07, N = 3 SE +/- 6.56, N = 3 SE +/- 9.11, N = 3 SE +/- 1.83, N = 3 SE +/- 4.22, N = 3 SE +/- 3.45, N = 3 SE +/- 12.20, N = 3 SE +/- 7.16, N = 3 SE +/- 7.70, N = 3 SE +/- 10.19, N = 3 SE +/- 5.69, N = 3 SE +/- 3.97, N = 3 1527.18 1372.74 1330.39 846.31 884.80 3000.17 1616.40 1157.04 1256.41 1598.26 1722.48 1359.69 2594.30 2916.12 2084.77 3931.31 2191.71 4147.58 4633.47 2453.37 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 129.02 / Avg: 502.34 / Max: 565.55 Min: 22.35 / Avg: 317.06 / Max: 355.01 Min: 17.72 / Avg: 350.77 / Max: 398.33 Min: 27.06 / Avg: 585.13 / Max: 676.02 Min: 43.77 / Avg: 561.37 / Max: 647.04 Min: 43.56 / Avg: 255.79 / Max: 283.25 Min: 87.57 / Avg: 498.18 / Max: 557.81 Min: 54.94 / Avg: 640.22 / Max: 761.83 Min: 50.37 / Avg: 567.32 / Max: 663.98 Min: 26.81 / Avg: 366.11 / Max: 409.38 Min: 27.02 / Avg: 325.1 / Max: 363.54 Min: 116.34 / Avg: 491.73 / Max: 562.09 Min: 61.01 / Avg: 247.42 / Max: 283.69 Min: 60.15 / Avg: 251.98 / Max: 290.9 Min: 73.77 / Avg: 491.56 / Max: 568.56 Min: 34.78 / Avg: 241.45 / Max: 283.98 Min: 76.6 / Avg: 467.08 / Max: 547.05 Min: 36.03 / Avg: 239.68 / Max: 271.85 Min: 38.03 / Avg: 211.61 / Max: 230.33 Min: 80.54 / Avg: 417.09 / Max: 460.49
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 120 240 360 480 600 SE +/- 0.10, N = 3 SE +/- 0.57, N = 3 SE +/- 0.48, N = 3 SE +/- 2.06, N = 3 SE +/- 0.61, N = 3 SE +/- 0.06, N = 3 SE +/- 0.29, N = 3 SE +/- 1.13, N = 3 SE +/- 1.28, N = 3 219.68 262.96 281.83 557.55 509.13 102.66 200.01 336.60 316.56
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 2022.2.dev Model: Person Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1000 2000 3000 4000 5000 SE +/- 4.07, N = 3 SE +/- 2.15, N = 3 SE +/- 3.90, N = 3 SE +/- 1.97, N = 3 SE +/- 3.73, N = 3 SE +/- 7.45, N = 3 SE +/- 10.93, N = 3 SE +/- 5.11, N = 3 SE +/- 13.83, N = 4 SE +/- 4.15, N = 3 SE +/- 2.17, N = 3 SE +/- 0.67, N = 3 SE +/- 4.45, N = 3 SE +/- 3.72, N = 3 SE +/- 6.50, N = 3 SE +/- 4.41, N = 3 SE +/- 5.23, N = 3 SE +/- 4.63, N = 3 SE +/- 1.50, N = 3 SE +/- 4.14, N = 3 1502.67 1373.83 1326.74 855.64 878.55 2995.55 1613.85 1142.24 1253.98 1597.31 1714.98 1336.05 2557.14 2868.21 2067.02 3956.74 2191.23 4151.95 4623.96 2425.01 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 127.59 / Avg: 502.07 / Max: 564.76 Min: 21.77 / Avg: 317.08 / Max: 353.34 Min: 19.26 / Avg: 349.46 / Max: 395.98 Min: 43.21 / Avg: 578.98 / Max: 669.77 Min: 44.33 / Avg: 562.48 / Max: 654.04 Min: 43.84 / Avg: 253.32 / Max: 281.68 Min: 88.7 / Avg: 495.12 / Max: 557.36 Min: 53.83 / Avg: 641.01 / Max: 764.62 Min: 52.02 / Avg: 567.58 / Max: 667.35 Min: 27.28 / Avg: 365.31 / Max: 409.3 Min: 27.1 / Avg: 323.97 / Max: 362.52 Min: 112.16 / Avg: 493.49 / Max: 564.7 Min: 57.83 / Avg: 247.26 / Max: 284.17 Min: 57.72 / Avg: 252.44 / Max: 290.56 Min: 73.79 / Avg: 488.35 / Max: 567.03 Min: 34.97 / Avg: 239.69 / Max: 279.27 Min: 76.68 / Avg: 460.77 / Max: 546.28 Min: 36.17 / Avg: 237.59 / Max: 272.11 Min: 19.72 / Avg: 210.29 / Max: 230.42 Min: 80.9 / Avg: 413.56 / Max: 460.64
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 200 400 600 800 1000 SE +/- 0.95, N = 3 SE +/- 0.71, N = 3 SE +/- 1.32, N = 3 SE +/- 3.40, N = 3 SE +/- 0.91, N = 3 SE +/- 0.39, N = 3 SE +/- 0.23, N = 3 SE +/- 1.04, N = 3 SE +/- 2.07, N = 3 450.62 520.75 557.26 1090.99 996.36 202.66 394.16 666.25 626.04
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 days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1358 0.2716 0.4074 0.5432 0.679 SE +/- 0.00024, N = 3 SE +/- 0.00012, N = 4 SE +/- 0.00035, N = 4 SE +/- 0.00089, N = 5 SE +/- 0.00088, N = 3 SE +/- 0.00096, N = 3 SE +/- 0.00184, N = 3 SE +/- 0.00027, N = 3 SE +/- 0.00008, N = 3 SE +/- 0.00029, N = 4 SE +/- 0.00061, N = 3 SE +/- 0.00027, N = 3 SE +/- 0.00127, N = 3 SE +/- 0.00094, N = 3 SE +/- 0.00076, N = 4 SE +/- 0.00050, N = 3 SE +/- 0.00135, N = 4 SE +/- 0.00059, N = 3 SE +/- 0.00055, N = 3 SE +/- 0.00094, N = 3 0.28669 0.28101 0.26207 0.15564 0.17214 0.58459 0.30850 0.11211 0.12797 0.22157 0.24798 0.30429 0.60335 0.54442 0.22366 0.37636 0.22418 0.38226 0.45521 0.26727 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAMD 2.14 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 129.75 / Avg: 495.47 / Max: 581.83 Min: 22.65 / Avg: 259.28 / Max: 327.68 Min: 20.63 / Avg: 287.68 / Max: 382.82 Min: 44.69 / Avg: 501.53 / Max: 743.54 Min: 44.9 / Avg: 553.79 / Max: 677.35 Min: 43.61 / Avg: 252.35 / Max: 281.75 Min: 87.84 / Avg: 489.57 / Max: 556.05 Min: 55.92 / Avg: 348.32 / Max: 818.81 Min: 51.73 / Avg: 388.35 / Max: 686.86 Min: 27.92 / Avg: 307.64 / Max: 409.42 Min: 26.15 / Avg: 294.87 / Max: 343.34 Min: 113.85 / Avg: 457.36 / Max: 570.55 Min: 58.06 / Avg: 243.95 / Max: 285.11 Min: 58.04 / Avg: 244.69 / Max: 290.83 Min: 73.65 / Avg: 439.59 / Max: 565.59 Min: 34.83 / Avg: 232.88 / Max: 279.66 Min: 76.87 / Avg: 432.25 / Max: 560.68 Min: 36.11 / Avg: 237.08 / Max: 282.83 Min: 37.94 / Avg: 200.14 / Max: 230.29 Min: 81.71 / Avg: 379.24 / Max: 460.57
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110K 220K 330K 440K 550K SE +/- 263.39, N = 4 SE +/- 702.52, N = 5 SE +/- 1412.50, N = 5 SE +/- 3515.49, N = 7 SE +/- 3622.62, N = 7 SE +/- 666.33, N = 3 SE +/- 895.16, N = 6 SE +/- 4645.52, N = 7 SE +/- 3747.09, N = 7 SE +/- 741.37, N = 6 SE +/- 1225.90, N = 6 SE +/- 188.68, N = 5 SE +/- 206.77, N = 3 SE +/- 277.89, N = 3 SE +/- 2945.88, N = 10 SE +/- 1813.78, N = 5 SE +/- 886.34, N = 6 SE +/- 382.95, N = 4 SE +/- 304.31, N = 4 SE +/- 2085.69, N = 5 185454.54 254430.04 253395.11 473377.17 471697.13 121293.26 267834.17 507823.13 490393.91 272077.94 274263.37 188856.06 97670.64 97758.15 392397.67 255823.48 287345.28 144112.86 135885.31 258224.35 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 4.1.4 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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300 600 900 1200 1500 427.06 1388.21 1407.22 1465.93 1458.84 571.83 700.68 1465.65 1498.73 1354.53 1408.79 448.44 420.16 412.79 1147.28 1308.26 804.16 740.63 761.13 812.80 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120 240 360 480 600 Min: 132.16 / Avg: 434.26 / Max: 576.61 Min: 21.91 / Avg: 183.28 / Max: 279.37 Min: 19.33 / Avg: 180.07 / Max: 281.7 Min: 21.9 / Avg: 322.92 / Max: 619.45 Min: 41.91 / Avg: 323.34 / Max: 616.97 Min: 42.85 / Avg: 212.12 / Max: 264.24 Min: 88.57 / Avg: 382.25 / Max: 558.12 Min: 53.91 / Avg: 346.48 / Max: 669.89 Min: 46.3 / Avg: 327.21 / Max: 619.61 Min: 26.43 / Avg: 200.87 / Max: 312.27 Min: 25.13 / Avg: 194.68 / Max: 300.95 Min: 110.65 / Avg: 421.14 / Max: 564.66 Min: 64.46 / Avg: 232.46 / Max: 283.08 Min: 61.43 / Avg: 236.82 / Max: 286.05 Min: 74.39 / Avg: 342.03 / Max: 572.62 Min: 34.37 / Avg: 195.55 / Max: 286.78 Min: 77.45 / Avg: 357.32 / Max: 552.51 Min: 35.89 / Avg: 194.58 / Max: 246.86 Min: 37.62 / Avg: 178.53 / Max: 227.64 Min: 81.57 / Avg: 317.7 / Max: 460.01
oneDNN Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 0.5093 1.0186 1.5279 2.0372 2.5465 SE +/- 0.004482, N = 7 SE +/- 0.001014, N = 7 SE +/- 0.000630, N = 7 SE +/- 0.003117, N = 7 SE +/- 0.002491, N = 7 SE +/- 0.000614, N = 7 SE +/- 0.002087, N = 7 SE +/- 0.003698, N = 15 SE +/- 0.003944, N = 15 SE +/- 0.001009, N = 7 SE +/- 0.000897, N = 7 SE +/- 0.001727, N = 7 SE +/- 0.002168, N = 7 SE +/- 0.000937, N = 7 1.420480 0.597698 0.585913 0.438693 0.439404 1.174550 0.687495 0.488721 0.529838 0.610119 0.669803 2.263500 1.611930 1.474330 MIN: 1.26 MIN: 0.56 MIN: 0.57 MIN: 0.36 MIN: 0.37 MIN: 1.13 MIN: 0.62 MIN: 0.41 MIN: 0.44 MIN: 0.58 MIN: 0.6 MIN: 2.13 MIN: 1.56 MIN: 1.43 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 100 200 300 400 500 Min: 130.27 / Avg: 365.16 / Max: 520.56 Min: 21.59 / Avg: 167.74 / Max: 289.3 Min: 19.68 / Avg: 177.37 / Max: 308.01 Min: 39.74 / Avg: 302.72 / Max: 562.15 Min: 43.44 / Avg: 304.87 / Max: 560.32 Min: 42.73 / Avg: 172.62 / Max: 268.79 Min: 88.4 / Avg: 319.32 / Max: 533.72 Min: 51.71 / Avg: 341.54 / Max: 576.51 Min: 50.16 / Avg: 315.25 / Max: 534.19 Min: 26.61 / Avg: 195.66 / Max: 341.85 Min: 24.68 / Avg: 167.15 / Max: 271.25 Min: 110.59 / Avg: 335.3 / Max: 502.95 Min: 58.48 / Avg: 189.87 / Max: 285.45 Min: 58.56 / Avg: 193.19 / Max: 291.03
asmFish This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 90M 180M 270M 360M 450M SE +/- 692156.92, N = 3 SE +/- 1373257.95, N = 3 SE +/- 835429.68, N = 3 SE +/- 3711493.29, N = 5 SE +/- 1040134.87, N = 3 SE +/- 868554.02, N = 3 SE +/- 1101907.90, N = 3 SE +/- 1520548.58, N = 3 SE +/- 2695071.60, N = 3 SE +/- 1169064.32, N = 3 SE +/- 2828612.84, N = 3 SE +/- 1526020.25, N = 3 SE +/- 654954.01, N = 3 SE +/- 478355.71, N = 3 SE +/- 2388608.17, N = 9 SE +/- 348426.38, N = 3 SE +/- 451407.56, N = 3 SE +/- 1045666.18, N = 3 SE +/- 809742.81, N = 3 SE +/- 611665.63, N = 3 163269037 209533141 212598823 373466857 368462801 94858095 182958960 397046539 368919863 280313823 249175879 144818313 76999877 87974578 291760604 156507344 291595066 159120297 138377960 246888854 Nodes/second Per Watt
OpenBenchmarking.org Nodes/second Per Watt, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200K 400K 600K 800K 1000K 310526.93 683901.12 686285.33 613695.97 610955.11 347225.25 345458.36 551147.09 609038.86 735469.95 780512.54 280949.53 297149.59 333734.85 531830.79 574873.97 542075.99 590632.17 622742.08 556845.74 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better asmFish 2018-07-23 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 130.45 / Avg: 525.78 / Max: 579.65 Min: 21.71 / Avg: 306.38 / Max: 333.46 Min: 20.95 / Avg: 309.78 / Max: 346.59 Min: 43.97 / Avg: 608.55 / Max: 680.5 Min: 43.03 / Avg: 603.09 / Max: 664.84 Min: 42.23 / Avg: 273.19 / Max: 286.72 Min: 88.43 / Avg: 529.61 / Max: 558.49 Min: 52.16 / Avg: 720.4 / Max: 806.03 Min: 52.21 / Avg: 605.74 / Max: 651.37 Min: 26.77 / Avg: 381.14 / Max: 409.6 Min: 24.59 / Avg: 319.25 / Max: 343.12 Min: 109.78 / Avg: 515.46 / Max: 568.73 Min: 58.56 / Avg: 259.08 / Max: 284.77 Min: 59.2 / Avg: 263.61 / Max: 290.8 Min: 73.64 / Avg: 548.6 / Max: 573.18 Min: 33.71 / Avg: 272.25 / Max: 286.6 Min: 76.49 / Avg: 537.92 / Max: 569.61 Min: 35.54 / Avg: 269.41 / Max: 286.78 Min: 37.18 / Avg: 222.21 / Max: 230.33 Min: 80.29 / Avg: 443.37 / Max: 460.8
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 Intel oneAPI. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.8623 1.7246 2.5869 3.4492 4.3115 SE +/- 0.001547, N = 9 SE +/- 0.000646, N = 9 SE +/- 0.000782, N = 9 SE +/- 0.001619, N = 9 SE +/- 0.001947, N = 9 SE +/- 0.012562, N = 9 SE +/- 0.018693, N = 15 SE +/- 0.002404, N = 9 SE +/- 0.001925, N = 9 SE +/- 0.000988, N = 9 SE +/- 0.000926, N = 9 SE +/- 0.001612, N = 9 SE +/- 0.002798, N = 9 SE +/- 0.003420, N = 9 SE +/- 0.017848, N = 9 SE +/- 0.017156, N = 9 SE +/- 0.026880, N = 9 SE +/- 0.004502, N = 9 SE +/- 0.019741, N = 9 SE +/- 0.036406, N = 15 0.928917 1.120080 1.115740 0.745265 0.759754 2.949200 2.089180 0.938707 0.984734 1.089590 1.143180 1.005595 1.639830 1.561990 3.759780 3.217710 3.832660 3.178910 3.202410 3.742470 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 138.82 / Avg: 333.5 / Max: 572.77 Min: 21.46 / Avg: 123.7 / Max: 262.83 Min: 21.1 / Avg: 122.7 / Max: 263.45 Min: 42.96 / Avg: 235.88 / Max: 502.65 Min: 38.27 / Avg: 234.21 / Max: 512.37 Min: 42.46 / Avg: 118.44 / Max: 221.57 Min: 88.44 / Avg: 245.77 / Max: 477.18 Min: 51.4 / Avg: 256.62 / Max: 539.02 Min: 47.05 / Avg: 243.6 / Max: 500.56 Min: 26.87 / Avg: 131.24 / Max: 275.56 Min: 21.96 / Avg: 122.88 / Max: 254.08 Min: 116.28 / Avg: 305.53 / Max: 546.92 Min: 60.21 / Avg: 157.83 / Max: 285.66 Min: 57.54 / Avg: 159.03 / Max: 287.88 Min: 74.39 / Avg: 190.36 / Max: 351.09 Min: 34.16 / Avg: 103.4 / Max: 208.72 Min: 77.51 / Avg: 181.29 / Max: 320.13 Min: 35.79 / Avg: 103.03 / Max: 199.73 Min: 37.6 / Avg: 106.12 / Max: 216.52 Min: 80.57 / Avg: 195.97 / Max: 348.21
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.5078 1.0156 1.5234 2.0312 2.539 SE +/- 0.009335, N = 15 SE +/- 0.000621, N = 7 SE +/- 0.001196, N = 7 SE +/- 0.002336, N = 7 SE +/- 0.001952, N = 7 SE +/- 0.001361, N = 7 SE +/- 0.004918, N = 12 SE +/- 0.004281, N = 7 SE +/- 0.004050, N = 7 SE +/- 0.001657, N = 7 SE +/- 0.002654, N = 7 SE +/- 0.002078, N = 7 SE +/- 0.001429, N = 7 SE +/- 0.000989, N = 7 SE +/- 0.003100, N = 7 SE +/- 0.001090, N = 7 SE +/- 0.003588, N = 7 SE +/- 0.000743, N = 7 SE +/- 0.000772, N = 7 SE +/- 0.002779, N = 7 1.526420 0.595116 0.586275 0.442635 0.439175 1.175260 0.698392 0.476241 0.525458 0.611600 0.670970 2.256860 1.596850 1.479470 0.593235 0.836359 0.627969 0.863593 0.936288 0.632210 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 127.88 / Avg: 368.95 / Max: 528 Min: 21.06 / Avg: 168.1 / Max: 287.88 Min: 19.85 / Avg: 177.43 / Max: 308.8 Min: 43.04 / Avg: 304.28 / Max: 558.85 Min: 43.35 / Avg: 304.73 / Max: 558.21 Min: 43.07 / Avg: 173.16 / Max: 269.36 Min: 88.48 / Avg: 328.29 / Max: 556.37 Min: 53.75 / Avg: 339.2 / Max: 581.24 Min: 51.16 / Avg: 313.54 / Max: 547.68 Min: 27.19 / Avg: 195.31 / Max: 340.16 Min: 26.37 / Avg: 165.59 / Max: 271.25 Min: 117.39 / Avg: 336.97 / Max: 503.01 Min: 56.14 / Avg: 187.7 / Max: 285.59 Min: 58.53 / Avg: 193.26 / Max: 290.84 Min: 74.01 / Avg: 283.64 / Max: 465.81 Min: 34.64 / Avg: 157.62 / Max: 252.91 Min: 77.15 / Avg: 262.05 / Max: 417.56 Min: 35.99 / Avg: 151.13 / Max: 248.03 Min: 37.94 / Avg: 149.21 / Max: 230.51 Min: 81.05 / Avg: 277.17 / Max: 438.3
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.
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 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 SE +/- 0.51, N = 3 SE +/- 0.14, N = 3 SE +/- 0.71, N = 3 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 SE +/- 2.85, N = 3 SE +/- 0.87, N = 3 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 SE +/- 0.89, N = 3 SE +/- 0.87, N = 3 SE +/- 4.12, N = 3 SE +/- 0.82, N = 3 SE +/- 2.89, N = 3 SE +/- 0.17, N = 3 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 SE +/- 0.30, N = 3 SE +/- 0.28, N = 3 SE +/- 0.26, N = 3 296.32 268.58 268.65 133.96 134.33 624.50 383.39 124.23 125.39 253.41 254.85 312.03 588.06 556.33 265.94 573.31 297.43 603.54 602.44 298.32 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120 240 360 480 600 Min: 132.7 / Avg: 533.04 / Max: 564.45 Min: 22.17 / Avg: 226.11 / Max: 244.66 Min: 16.53 / Avg: 226.41 / Max: 253 Min: 44.01 / Avg: 489.37 / Max: 526.86 Min: 43.75 / Avg: 491.61 / Max: 527.91 Min: 43.04 / Avg: 236.43 / Max: 262.83 Min: 89.36 / Avg: 478.35 / Max: 511.54 Min: 49.9 / Avg: 622.11 / Max: 667.92 Min: 52.93 / Avg: 578.5 / Max: 613.82 Min: 26.7 / Avg: 290.91 / Max: 319.71 Min: 25.71 / Avg: 275.68 / Max: 309.16 Min: 119.89 / Avg: 523.06 / Max: 553.06 Min: 61.76 / Avg: 262.86 / Max: 282.79 Min: 60.22 / Avg: 267.71 / Max: 283.36 Min: 74.4 / Avg: 498.45 / Max: 544.95 Min: 34.48 / Avg: 224.91 / Max: 274.82 Min: 77.69 / Avg: 462.38 / Max: 512.37 Min: 35.9 / Avg: 214.87 / Max: 250.35 Min: 37.79 / Avg: 210.47 / Max: 222.24 Min: 81.65 / Avg: 435.66 / Max: 455.43
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.B Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50K 100K 150K 200K 250K SE +/- 114.69, N = 9 SE +/- 1837.39, N = 15 SE +/- 2022.23, N = 15 SE +/- 3716.81, N = 15 SE +/- 3991.38, N = 15 SE +/- 208.44, N = 8 SE +/- 1204.13, N = 15 SE +/- 2791.46, N = 15 SE +/- 1703.57, N = 15 SE +/- 2245.97, N = 15 SE +/- 1433.38, N = 15 SE +/- 509.59, N = 8 SE +/- 46.80, N = 6 SE +/- 36.55, N = 6 SE +/- 1611.06, N = 15 SE +/- 2164.09, N = 15 SE +/- 1060.57, N = 9 SE +/- 677.41, N = 10 SE +/- 564.25, N = 8 SE +/- 1364.07, N = 15 119784.28 164817.94 167629.48 214561.41 222846.94 83421.88 159375.74 238644.03 219454.01 168014.13 162758.97 111259.33 48063.40 49434.69 163786.88 135254.12 136460.44 88708.75 90065.57 134888.06 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 4.1.4 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300 600 900 1200 1500 365.19 1381.04 1426.95 1038.51 1122.20 523.97 621.03 990.95 967.78 1169.95 1282.71 351.30 244.59 248.79 667.00 1044.53 530.78 604.33 700.99 576.84 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 126.76 / Avg: 328 / Max: 580.38 Min: 21.51 / Avg: 119.34 / Max: 317.38 Min: 18.96 / Avg: 117.47 / Max: 317.19 Min: 42.16 / Avg: 206.61 / Max: 615.41 Min: 38.58 / Avg: 198.58 / Max: 615.69 Min: 42.92 / Avg: 159.21 / Max: 277.96 Min: 88.35 / Avg: 256.63 / Max: 565.04 Min: 52.38 / Avg: 240.82 / Max: 753.71 Min: 51.71 / Avg: 226.76 / Max: 639.17 Min: 13.57 / Avg: 143.61 / Max: 383.44 Min: 25.5 / Avg: 126.89 / Max: 320.64 Min: 102.59 / Avg: 316.71 / Max: 570.01 Min: 60.32 / Avg: 196.5 / Max: 284.33 Min: 59.99 / Avg: 198.7 / Max: 290.26 Min: 74.87 / Avg: 245.56 / Max: 573.17 Min: 34.4 / Avg: 129.49 / Max: 286.69 Min: 77.47 / Avg: 257.09 / Max: 555.9 Min: 35.94 / Avg: 146.79 / Max: 269.17 Min: 37.77 / Avg: 128.48 / Max: 229.58 Min: 82.29 / Avg: 233.84 / Max: 459.91
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 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, 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 +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 9.94 6.71 6.48 4.30 4.32 14.16 7.89 4.96 5.32 7.81 8.32 9.22 16.22 17.70 9.98 17.04 10.96 19.51 21.03 11.91 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 130.38 / Avg: 507.15 / Max: 556.7 Min: 22.01 / Avg: 309.27 / Max: 335.72 Min: 22.18 / Avg: 344 / Max: 375.25 Min: 43.63 / Avg: 569.74 / Max: 619.83 Min: 42.97 / Avg: 567.3 / Max: 619.05 Min: 43.49 / Avg: 233.47 / Max: 256.76 Min: 88.89 / Avg: 478.64 / Max: 531.41 Min: 52.91 / Avg: 655.36 / Max: 727.05 Min: 53.49 / Avg: 580.05 / Max: 643.41 Min: 27.21 / Avg: 355.76 / Max: 394.97 Min: 24.96 / Avg: 315.93 / Max: 344.11 Min: 116.73 / Avg: 494.37 / Max: 532.54 Min: 62.03 / Avg: 250.43 / Max: 284.65 Min: 58 / Avg: 255.41 / Max: 290.14 Min: 73.89 / Avg: 467.19 / Max: 522.52 Min: 34.79 / Avg: 230.36 / Max: 249.22 Min: 76.67 / Avg: 448.21 / Max: 493.47 Min: 36.31 / Avg: 235.52 / Max: 255.01 Min: 37.99 / Avg: 214.5 / Max: 230.34 Min: 81.56 / Avg: 423.4 / Max: 460.14
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 5.18 Build: allmodconfig Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 SE +/- 0.43, N = 3 SE +/- 0.52, N = 3 SE +/- 0.42, N = 3 SE +/- 0.39, N = 3 SE +/- 0.36, N = 3 SE +/- 0.39, N = 3 SE +/- 0.60, N = 3 SE +/- 0.08, N = 3 SE +/- 0.47, N = 3 SE +/- 0.49, N = 3 SE +/- 0.43, N = 3 SE +/- 0.29, N = 3 SE +/- 0.63, N = 3 SE +/- 0.49, N = 3 SE +/- 0.69, N = 3 SE +/- 0.45, N = 3 SE +/- 0.39, N = 3 SE +/- 0.62, N = 3 SE +/- 0.64, N = 3 SE +/- 0.51, N = 3 229.49 185.81 179.86 109.24 113.17 390.39 219.46 98.28 107.14 158.32 173.11 250.89 461.54 409.15 155.91 263.29 160.02 267.50 312.94 184.69 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Linux Kernel Compilation 5.18 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 135.62 / Avg: 478.32 / Max: 581.34 Min: 21.85 / Avg: 269.08 / Max: 326.03 Min: 17.37 / Avg: 288.6 / Max: 358.69 Min: 43.83 / Avg: 523 / Max: 743.97 Min: 43.05 / Avg: 486.87 / Max: 660.18 Min: 43.14 / Avg: 263.68 / Max: 286.44 Min: 88.43 / Avg: 478.57 / Max: 560.92 Min: 52.26 / Avg: 562.19 / Max: 820.32 Min: 53.43 / Avg: 490.83 / Max: 680.64 Min: 27.18 / Avg: 322.29 / Max: 409.65 Min: 26.6 / Avg: 272.16 / Max: 338.41 Min: 118.16 / Avg: 475.75 / Max: 570.15 Min: 63.22 / Avg: 251.63 / Max: 284.54 Min: 56.65 / Avg: 253.46 / Max: 290.53 Min: 73.95 / Avg: 442.94 / Max: 574.3 Min: 34.69 / Avg: 250.12 / Max: 286.86 Min: 78.97 / Avg: 441.25 / Max: 573.43 Min: 36.42 / Avg: 247.41 / Max: 286.21 Min: 37.72 / Avg: 205.71 / Max: 229.95 Min: 80.97 / Avg: 381.5 / Max: 460.33
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: DLSC - Acceleration: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 6 12 18 24 30 SE +/- 0.07, N = 10 SE +/- 0.05, N = 3 SE +/- 0.11, N = 10 SE +/- 0.15, N = 3 SE +/- 0.47, N = 15 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 1.00, N = 15 SE +/- 0.07, N = 3 SE +/- 0.21, N = 15 SE +/- 0.02, N = 3 SE +/- 0.09, N = 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 15 8.80 12.86 13.60 21.53 17.68 6.15 9.74 23.01 17.66 17.07 14.31 7.98 4.92 5.63 13.72 9.45 13.76 9.47 8.33 12.74 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.011 0.022 0.033 0.044 0.055 0.017 0.045 0.043 0.037 0.034 0.023 0.019 0.035 0.032 0.045 0.049 0.016 0.020 0.022 0.026 0.037 0.028 0.037 0.039 0.030 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.6 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 132.77 / Avg: 513.72 / Max: 577.53 Min: 21.92 / Avg: 285.22 / Max: 309.98 Min: 19.5 / Avg: 315.2 / Max: 359.1 Min: 45.58 / Avg: 584.91 / Max: 687.18 Min: 42.09 / Avg: 520.01 / Max: 622.3 Min: 43.77 / Avg: 262.95 / Max: 283.94 Min: 88.6 / Avg: 506.73 / Max: 553.51 Min: 50.6 / Avg: 666.94 / Max: 816.47 Min: 47.67 / Avg: 543.9 / Max: 632.56 Min: 26.22 / Avg: 376.47 / Max: 415.76 Min: 26.95 / Avg: 290.15 / Max: 318.94 Min: 107.47 / Avg: 503.53 / Max: 569.03 Min: 57.63 / Avg: 250.95 / Max: 282.97 Min: 57.52 / Avg: 256.07 / Max: 288.3 Min: 74.82 / Avg: 528.3 / Max: 578.83 Min: 34.9 / Avg: 253.55 / Max: 276.7 Min: 76.48 / Avg: 492.47 / Max: 570.87 Min: 36.09 / Avg: 255.67 / Max: 275.44 Min: 38.36 / Avg: 214.84 / Max: 230.14 Min: 81.81 / Avg: 429.93 / Max: 463.56
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 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 1.63, N = 12 SE +/- 0.03, N = 3 SE +/- 0.37, N = 3 SE +/- 2.93, N = 10 SE +/- 0.01, N = 3 SE +/- 0.17, N = 3 SE +/- 0.13, N = 3 SE +/- 0.49, N = 3 SE +/- 0.45, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 SE +/- 0.00, N = 3 SE +/- 0.08, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 40.77 42.81 45.30 58.17 83.61 19.62 37.86 87.16 86.02 44.48 45.22 39.96 20.18 20.67 38.24 19.71 37.32 19.12 19.13 37.25 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 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.045 0.09 0.135 0.18 0.225 0.077 0.190 0.200 0.109 0.164 0.090 0.084 0.137 0.145 0.154 0.164 0.077 0.078 0.078 0.084 0.093 0.090 0.098 0.093 0.087 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better High Performance Conjugate Gradient 3.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 128.39 / Avg: 529.35 / Max: 559.35 Min: 21.29 / Avg: 225.92 / Max: 273.11 Min: 21.42 / Avg: 227.04 / Max: 250.54 Min: 44.22 / Avg: 532.48 / Max: 600.46 Min: 37.09 / Avg: 508.31 / Max: 638.18 Min: 43.84 / Avg: 218.95 / Max: 250.34 Min: 88.42 / Avg: 449.19 / Max: 503.01 Min: 57.01 / Avg: 635.85 / Max: 740.37 Min: 50.95 / Avg: 593.6 / Max: 664.08 Min: 28.92 / Avg: 288.25 / Max: 334.64 Min: 25.92 / Avg: 275.49 / Max: 322.43 Min: 111.71 / Avg: 517.64 / Max: 548.7 Min: 60.9 / Avg: 258.73 / Max: 280.41 Min: 58.87 / Avg: 264.38 / Max: 279.83 Min: 73.98 / Avg: 457.8 / Max: 557.32 Min: 34.75 / Avg: 212.26 / Max: 269.67 Min: 76.49 / Avg: 415.42 / Max: 503.21 Min: 36.22 / Avg: 195.94 / Max: 245.53 Min: 38.32 / Avg: 205.39 / Max: 221.61 Min: 80.88 / Avg: 430.12 / Max: 451.32
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 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 5 10 15 20 25 SE +/- 0.090, N = 5 SE +/- 0.011, N = 3 SE +/- 0.020, N = 3 SE +/- 0.022, N = 3 SE +/- 0.058, N = 3 SE +/- 0.010, N = 3 SE +/- 0.026, N = 3 SE +/- 1.013, N = 12 SE +/- 0.011, N = 3 SE +/- 0.010, N = 3 SE +/- 0.012, N = 3 SE +/- 0.003, N = 3 SE +/- 0.010, N = 3 SE +/- 0.024, N = 3 SE +/- 0.020, N = 3 SE +/- 0.021, N = 3 SE +/- 0.109, N = 3 SE +/- 0.014, N = 3 SE +/- 0.017, N = 3 SE +/- 0.025, N = 3 9.021 9.641 10.345 18.382 17.104 4.358 7.601 19.834 18.686 12.956 11.147 8.656 4.388 4.980 11.216 7.165 10.072 5.772 5.164 8.318 1. (CXX) g++ options: -O3 Ns Per Day Per Watt
OpenBenchmarking.org Ns Per Day Per Watt, More Is Better GROMACS 2022.1 Implementation: MPI CPU - Input: water_GMX50_bare Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0095 0.019 0.0285 0.038 0.0475 0.019 0.038 0.037 0.035 0.035 0.017 0.016 0.031 0.035 0.040 0.042 0.018 0.018 0.020 0.023 0.029 0.022 0.024 0.025 0.021 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GROMACS 2022.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 128.82 / Avg: 485.17 / Max: 581.79 Min: 22.34 / Avg: 254.44 / Max: 329.22 Min: 19.76 / Avg: 278.99 / Max: 355.02 Min: 44.7 / Avg: 523.22 / Max: 726.49 Min: 41.63 / Avg: 482.66 / Max: 674.91 Min: 43.57 / Avg: 255.66 / Max: 281.15 Min: 88.42 / Avg: 479.96 / Max: 554.17 Min: 53.77 / Avg: 631.57 / Max: 819.82 Min: 54.73 / Avg: 529.27 / Max: 691.14 Min: 29.11 / Avg: 321.58 / Max: 409.45 Min: 28.15 / Avg: 266.89 / Max: 344.42 Min: 111.8 / Avg: 475.18 / Max: 569.68 Min: 58.76 / Avg: 247.8 / Max: 284.53 Min: 58.09 / Avg: 250.48 / Max: 290.58 Min: 75.9 / Avg: 480.16 / Max: 572.88 Min: 34.72 / Avg: 248.64 / Max: 286.57 Min: 76.57 / Avg: 458.81 / Max: 563.75 Min: 36.17 / Avg: 240.03 / Max: 275.37 Min: 38.34 / Avg: 206.57 / Max: 230.27 Min: 80.95 / Avg: 400.98 / Max: 460.81
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300 600 900 1200 1500 SE +/- 1.73, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.67, N = 3 SE +/- 3.18, N = 3 SE +/- 0.00, N = 3 SE +/- 2.52, N = 3 SE +/- 2.91, N = 3 SE +/- 3.46, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 2.03, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 1.86, N = 3 SE +/- 2.08, N = 3 628 697 704 1114 1102 387 643 1393 1183 999 843 579 317 348 875 595 858 582 511 760 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.7274 1.4548 2.1822 2.9096 3.637 1.220 2.787 2.781 2.351 2.420 1.503 1.347 2.353 2.513 2.884 3.233 1.153 1.260 1.357 1.930 2.364 1.924 2.352 2.457 1.912 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.38 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 132.42 / Avg: 514.56 / Max: 551.37 Min: 21.94 / Avg: 250.12 / Max: 267.34 Min: 20.77 / Avg: 253.15 / Max: 270.87 Min: 43.69 / Avg: 473.83 / Max: 511.53 Min: 41.25 / Avg: 455.45 / Max: 494.13 Min: 43.46 / Avg: 257.5 / Max: 275.68 Min: 88.01 / Avg: 477.28 / Max: 513.71 Min: 53.41 / Avg: 591.95 / Max: 642.81 Min: 51.6 / Avg: 470.71 / Max: 507.71 Min: 26.2 / Avg: 346.36 / Max: 370.94 Min: 27.04 / Avg: 260.73 / Max: 278.32 Min: 113.83 / Avg: 502.31 / Max: 538.94 Min: 56.27 / Avg: 251.61 / Max: 280.65 Min: 60.49 / Avg: 256.53 / Max: 286.81 Min: 74.52 / Avg: 453.39 / Max: 488.38 Min: 34.65 / Avg: 251.71 / Max: 271.79 Min: 77.37 / Avg: 446.06 / Max: 481.79 Min: 35.6 / Avg: 247.46 / Max: 270.5 Min: 37.41 / Avg: 207.95 / Max: 222.57 Min: 81.94 / Avg: 397.55 / Max: 427.13
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 EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 900M 1800M 2700M 3600M 4500M SE +/- 5959719.32, N = 3 SE +/- 2222006.08, N = 3 SE +/- 3446302.00, N = 3 SE +/- 14635410.92, N = 3 SE +/- 13428026.69, N = 3 SE +/- 910976.46, N = 3 SE +/- 3326024.77, N = 3 SE +/- 9793366.81, N = 3 SE +/- 3661935.20, N = 3 SE +/- 3283111.96, N = 3 SE +/- 1264541.59, N = 3 SE +/- 2102078.13, N = 3 SE +/- 754992.35, N = 3 SE +/- 806586.84, N = 3 SE +/- 3210600.38, N = 3 SE +/- 423657.23, N = 3 SE +/- 1653035.32, N = 3 SE +/- 808623.73, N = 3 SE +/- 417323.62, N = 3 SE +/- 563451.27, N = 3 2065741000 2353380000 2355505667 4279539333 4258717333 1023022333 1925362667 4414763333 4358309667 2341996333 2333430333 2067115333 1067806333 1081131000 1998897333 1057050667 1929891667 1014445000 1014254000 1917570000 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 EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 3M 6M 9M 12M 15M 4363115.44 12305245.00 12349121.68 9672874.20 9699094.78 5269915.43 4824699.91 7960362.35 8697792.65 9428761.65 9892055.31 4581780.36 4742505.93 4624732.42 4557540.60 5260039.45 4886141.12 5507035.54 5357001.29 4825129.72 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Algebraic Multi-Grid Benchmark 1.2 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120 240 360 480 600 Min: 131.43 / Avg: 473.46 / Max: 567.84 Min: 22.07 / Avg: 191.25 / Max: 270.54 Min: 19.25 / Avg: 190.74 / Max: 269.47 Min: 43.87 / Avg: 442.43 / Max: 592.15 Min: 41.53 / Avg: 439.08 / Max: 586.28 Min: 44.4 / Avg: 194.13 / Max: 256.47 Min: 87.75 / Avg: 399.06 / Max: 510.44 Min: 51.78 / Avg: 554.59 / Max: 707.69 Min: 50.49 / Avg: 501.08 / Max: 634.57 Min: 25.66 / Avg: 248.39 / Max: 337.41 Min: 25.27 / Avg: 235.89 / Max: 298.91 Min: 117.36 / Avg: 451.16 / Max: 548.45 Min: 59.87 / Avg: 225.16 / Max: 280.47 Min: 57.3 / Avg: 233.77 / Max: 283.86 Min: 73.2 / Avg: 438.59 / Max: 546 Min: 35.14 / Avg: 200.96 / Max: 257.66 Min: 76.85 / Avg: 394.97 / Max: 502.93 Min: 36.32 / Avg: 184.21 / Max: 249.64 Min: 37.97 / Avg: 189.33 / Max: 216.77 Min: 81.35 / Avg: 397.41 / Max: 450.5
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40K 80K 120K 160K 200K SE +/- 1442.94, N = 3 SE +/- 119.74, N = 3 SE +/- 114.30, N = 3 SE +/- 1524.49, N = 7 SE +/- 2309.74, N = 3 SE +/- 105.89, N = 3 SE +/- 64.38, N = 3 SE +/- 731.54, N = 3 SE +/- 734.15, N = 3 SE +/- 151.20, N = 3 SE +/- 169.28, N = 3 SE +/- 2609.49, N = 12 SE +/- 527.93, N = 15 SE +/- 972.77, N = 15 SE +/- 1215.82, N = 3 SE +/- 101.99, N = 3 SE +/- 544.04, N = 3 SE +/- 47.17, N = 3 SE +/- 50.17, N = 3 SE +/- 1255.87, N = 3 118721.53 132051.79 133585.43 171196.42 175383.10 41209.65 79094.25 173823.44 166269.03 159812.84 149560.47 108301.83 48059.01 56565.01 108150.75 57873.68 106094.98 55150.32 51141.57 101816.87 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50K 100K 150K 200K 250K SE +/- 171.50, N = 11 SE +/- 1359.91, N = 15 SE +/- 1333.51, N = 15 SE +/- 1222.97, N = 12 SE +/- 990.19, N = 12 SE +/- 304.81, N = 9 SE +/- 427.89, N = 10 SE +/- 2783.28, N = 15 SE +/- 1834.92, N = 15 SE +/- 1317.18, N = 15 SE +/- 764.03, N = 15 SE +/- 470.20, N = 11 SE +/- 255.08, N = 9 SE +/- 45.67, N = 9 SE +/- 980.49, N = 15 SE +/- 157.87, N = 9 SE +/- 444.87, N = 10 SE +/- 238.68, N = 9 SE +/- 233.80, N = 9 SE +/- 430.76, N = 10 118435.74 125660.14 128432.87 232995.13 233220.37 56330.80 102839.19 202432.69 197332.18 121727.31 120349.96 116706.64 55604.70 57809.35 123247.08 60128.52 98920.03 57200.16 57128.29 100065.12 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 4.1.4 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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 400 800 1200 1600 2000 440.34 1536.06 1606.34 1703.05 1739.36 460.38 485.78 1207.82 1176.43 1267.70 1234.72 473.94 348.56 362.92 621.83 536.49 499.84 514.65 499.96 507.57 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 127.48 / Avg: 268.97 / Max: 565.85 Min: 10.82 / Avg: 81.81 / Max: 252.77 Min: 18.62 / Avg: 79.95 / Max: 250.72 Min: 42.68 / Avg: 136.81 / Max: 473.85 Min: 39.57 / Avg: 134.08 / Max: 479.57 Min: 42.61 / Avg: 122.36 / Max: 240.28 Min: 88.4 / Avg: 211.7 / Max: 497.35 Min: 51.88 / Avg: 167.6 / Max: 586 Min: 50.61 / Avg: 167.74 / Max: 577.22 Min: 25.12 / Avg: 96.02 / Max: 282.14 Min: 21.91 / Avg: 97.47 / Max: 279.97 Min: 114.37 / Avg: 246.25 / Max: 558.09 Min: 60.82 / Avg: 159.53 / Max: 283.99 Min: 60.64 / Avg: 159.29 / Max: 286.36 Min: 74.32 / Avg: 198.2 / Max: 543.59 Min: 34.31 / Avg: 112.08 / Max: 231.47 Min: 77.36 / Avg: 197.9 / Max: 469.52 Min: 35.82 / Avg: 111.14 / Max: 218.53 Min: 37.73 / Avg: 114.27 / Max: 220.72 Min: 81.49 / Avg: 197.14 / Max: 456.08
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 129 Cells Per Direction Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1.3481 2.6962 4.0443 5.3924 6.7405 SE +/- 0.01225371, N = 9 SE +/- 0.01662956, N = 9 SE +/- 0.01464622, N = 9 SE +/- 0.01173139, N = 15 SE +/- 0.01020043, N = 10 SE +/- 0.02359108, N = 7 SE +/- 0.02063230, N = 8 SE +/- 0.01039810, N = 15 SE +/- 0.01070461, N = 10 SE +/- 0.01859828, N = 9 SE +/- 0.02850743, N = 15 SE +/- 0.02095749, N = 9 SE +/- 0.03922970, N = 6 SE +/- 0.02863178, N = 7 SE +/- 0.03428839, N = 15 SE +/- 0.02518485, N = 7 SE +/- 0.04202120, N = 12 SE +/- 0.03796824, N = 15 SE +/- 0.02956314, N = 7 SE +/- 0.02528928, N = 9 2.61658181 2.54647279 2.48146391 1.51555521 1.49829830 5.63562012 3.28871903 1.44810847 1.48172070 2.24137110 2.28903530 2.90179335 5.99175715 5.33026232 2.24685712 4.38225862 3.13147511 5.17996677 5.03929220 3.08943621 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 131.71 / Avg: 317.09 / Max: 578.06 Min: 21.93 / Avg: 114.23 / Max: 275.44 Min: 19.84 / Avg: 112.17 / Max: 274.87 Min: 42.69 / Avg: 183.88 / Max: 555.15 Min: 39.17 / Avg: 185.69 / Max: 550.21 Min: 43.41 / Avg: 162.25 / Max: 260.62 Min: 88.82 / Avg: 272.57 / Max: 518.4 Min: 49.26 / Avg: 241.51 / Max: 739.87 Min: 45.64 / Avg: 219.35 / Max: 637.93 Min: 25.8 / Avg: 137.57 / Max: 365.51 Min: 25.02 / Avg: 128.83 / Max: 314.74 Min: 111.59 / Avg: 306.54 / Max: 562.31 Min: 62.76 / Avg: 188.63 / Max: 284.26 Min: 61.87 / Avg: 184.8 / Max: 288.9 Min: 73.77 / Avg: 247.14 / Max: 568.91 Min: 20.53 / Avg: 145.83 / Max: 267.78 Min: 77.33 / Avg: 251.33 / Max: 508.06 Min: 36.07 / Avg: 145.66 / Max: 250.26 Min: 37.86 / Avg: 139.4 / Max: 228.43 Min: 81.25 / Avg: 242.68 / Max: 456.81
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 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.4748 0.9496 1.4244 1.8992 2.374 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 +/- 0.01, N = 3 1.33 0.52 0.51 0.51 0.51 1.39 1.47 0.52 0.54 0.62 0.65 1.23 1.29 1.37 1.85 1.77 1.95 1.88 1.98 2.11 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120 240 360 480 600 Min: 126.63 / Avg: 512.38 / Max: 581.22 Min: 21.92 / Avg: 317.35 / Max: 342.55 Min: 20.96 / Avg: 329.32 / Max: 357.39 Min: 43.92 / Avg: 557.67 / Max: 620.79 Min: 43.74 / Avg: 555.91 / Max: 619.67 Min: 43.73 / Avg: 237.71 / Max: 264.74 Min: 88.04 / Avg: 500.39 / Max: 543.79 Min: 54.93 / Avg: 627.85 / Max: 695.26 Min: 53.06 / Avg: 552.4 / Max: 602.19 Min: 27.07 / Avg: 354.09 / Max: 386.31 Min: 21.91 / Avg: 319.86 / Max: 349.34 Min: 114.98 / Avg: 503.57 / Max: 570.82 Min: 58.93 / Avg: 251.51 / Max: 285.09 Min: 58.43 / Avg: 255.86 / Max: 290.66 Min: 75.5 / Avg: 486.15 / Max: 530.93 Min: 34.81 / Avg: 232.11 / Max: 251.88 Min: 76.76 / Avg: 465.21 / Max: 497.38 Min: 36.16 / Avg: 219.83 / Max: 238.66 Min: 37.99 / Avg: 217.05 / Max: 230.29 Min: 81.39 / Avg: 433.08 / Max: 460.67
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: FT.C Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50K 100K 150K 200K 250K SE +/- 103.75, N = 7 SE +/- 704.40, N = 8 SE +/- 565.95, N = 8 SE +/- 1649.35, N = 12 SE +/- 1508.85, N = 10 SE +/- 35.88, N = 6 SE +/- 557.99, N = 8 SE +/- 2780.73, N = 15 SE +/- 1534.56, N = 9 SE +/- 986.09, N = 10 SE +/- 377.17, N = 8 SE +/- 602.31, N = 7 SE +/- 80.21, N = 6 SE +/- 76.54, N = 6 SE +/- 898.92, N = 15 SE +/- 81.03, N = 6 SE +/- 811.29, N = 8 SE +/- 449.74, N = 6 SE +/- 171.64, N = 6 SE +/- 472.14, N = 8 99537.68 124561.13 127498.51 234367.13 234088.25 61146.13 105557.99 222687.11 215057.58 125326.19 121799.77 97993.30 56879.46 56704.82 127733.49 64733.33 118231.73 60945.14 61089.33 116524.99 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 4.1.4 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200 400 600 800 1000 285.63 917.39 929.03 1081.65 1147.41 349.58 350.11 904.19 917.93 801.69 829.26 288.34 288.99 285.47 458.52 399.84 427.78 377.63 412.88 454.09 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120 240 360 480 600 Min: 131.36 / Avg: 348.48 / Max: 550.87 Min: 20.65 / Avg: 135.78 / Max: 281.45 Min: 20 / Avg: 137.24 / Max: 300.22 Min: 43.47 / Avg: 216.68 / Max: 626.6 Min: 43.47 / Avg: 204.01 / Max: 604.26 Min: 43.31 / Avg: 174.91 / Max: 263.74 Min: 88.13 / Avg: 301.5 / Max: 544.53 Min: 50.25 / Avg: 246.28 / Max: 669 Min: 51.36 / Avg: 234.29 / Max: 614.75 Min: 26.72 / Avg: 156.33 / Max: 326.33 Min: 26.62 / Avg: 146.88 / Max: 294.99 Min: 114.19 / Avg: 339.85 / Max: 543.47 Min: 56.65 / Avg: 196.82 / Max: 280.17 Min: 59.07 / Avg: 198.64 / Max: 278.17 Min: 75.01 / Avg: 278.58 / Max: 547.25 Min: 34.71 / Avg: 161.9 / Max: 254.88 Min: 76.52 / Avg: 276.38 / Max: 526.47 Min: 36.03 / Avg: 161.39 / Max: 255.96 Min: 37.83 / Avg: 147.96 / Max: 222.19 Min: 81.74 / Avg: 256.61 / Max: 455.94
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 4.0 Preset: Medium Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 SE +/- 0.23, N = 7 SE +/- 0.06, N = 8 SE +/- 0.07, N = 8 SE +/- 0.91, N = 8 SE +/- 0.91, N = 8 SE +/- 0.06, N = 7 SE +/- 0.71, N = 8 SE +/- 1.79, N = 8 SE +/- 1.52, N = 8 SE +/- 0.34, N = 8 SE +/- 0.19, N = 8 SE +/- 0.42, N = 7 SE +/- 0.09, N = 6 SE +/- 0.19, N = 6 SE +/- 0.67, N = 7 SE +/- 0.09, N = 7 SE +/- 0.32, N = 7 SE +/- 0.15, N = 7 SE +/- 0.16, N = 7 SE +/- 1.54, N = 7 320.08 360.55 388.57 613.64 548.85 177.16 321.91 601.36 571.61 480.19 422.02 289.38 148.60 167.02 452.17 264.50 450.11 262.03 233.06 379.49 1. (CXX) g++ options: -O3 -flto -pthread MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.0 Preset: Medium Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1.0708 2.1416 3.2124 4.2832 5.354 1.322 3.988 4.116 3.712 3.415 1.418 1.561 3.158 3.136 4.759 4.437 1.227 1.037 1.191 2.689 2.777 2.640 2.685 2.426 2.189 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 127.43 / Avg: 242.03 / Max: 566.49 Min: 21.73 / Avg: 90.41 / Max: 312.5 Min: 18.33 / Avg: 94.41 / Max: 363.23 Min: 43.44 / Avg: 165.3 / Max: 478.82 Min: 40.86 / Avg: 160.72 / Max: 547.02 Min: 42.98 / Avg: 124.95 / Max: 280.86 Min: 87.94 / Avg: 206.19 / Max: 552.08 Min: 53.65 / Avg: 190.43 / Max: 636.18 Min: 50.83 / Avg: 182.25 / Max: 547.05 Min: 26.45 / Avg: 100.9 / Max: 389.29 Min: 26.4 / Avg: 95.12 / Max: 320.29 Min: 113.07 / Avg: 235.82 / Max: 557.82 Min: 57.49 / Avg: 143.36 / Max: 282.66 Min: 57.95 / Avg: 140.22 / Max: 288.42 Min: 73.95 / Avg: 168.14 / Max: 533.91 Min: 34.3 / Avg: 95.24 / Max: 267.43 Min: 76.21 / Avg: 170.48 / Max: 533.06 Min: 35.78 / Avg: 97.61 / Max: 269.68 Min: 37.57 / Avg: 96.06 / Max: 229.23 Min: 80.77 / Avg: 173.37 / Max: 451.13
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.
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200K 400K 600K 800K 1000K SE +/- 691.15, N = 3 SE +/- 3953.49, N = 3 SE +/- 544.47, N = 3 SE +/- 3650.73, N = 3 SE +/- 6929.10, N = 3 SE +/- 256.67, N = 3 SE +/- 2831.65, N = 3 SE +/- 6383.59, N = 3 SE +/- 1019.34, N = 3 SE +/- 903.59, N = 3 SE +/- 1109.48, N = 3 SE +/- 1105.00, N = 3 SE +/- 596.11, N = 3 SE +/- 281.22, N = 3 SE +/- 2720.84, N = 3 SE +/- 518.75, N = 3 SE +/- 6365.85, N = 4 SE +/- 367.42, N = 3 SE +/- 369.10, N = 3 SE +/- 1355.40, N = 3 397534 545728 551395 762777 752608 276829 416644 890889 871440 700085 658923 364730 216263 242466 547385 403718 582384 386411 358505 525654 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
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.
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 22.1 Input: Carbon Nanotube Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.27, N = 15 SE +/- 0.18, N = 3 SE +/- 0.26, N = 13 SE +/- 0.02, N = 3 SE +/- 0.21, N = 3 SE +/- 0.74, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.19, N = 3 SE +/- 0.35, N = 4 SE +/- 0.35, N = 3 SE +/- 0.38, N = 12 SE +/- 0.13, N = 3 SE +/- 0.70, N = 7 SE +/- 0.21, N = 3 SE +/- 0.54, N = 3 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 SE +/- 0.41, N = 3 SE +/- 0.23, N = 3 46.78 40.29 39.22 23.50 24.65 79.55 55.17 21.01 23.15 32.55 35.83 48.87 83.28 77.79 38.20 59.85 42.51 69.89 73.43 44.23 1. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GPAW 22.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 129.19 / Avg: 507.62 / Max: 580.17 Min: 21.18 / Avg: 282.73 / Max: 329.91 Min: 18.64 / Avg: 301.6 / Max: 369.7 Min: 42.07 / Avg: 569.12 / Max: 715.11 Min: 43.08 / Avg: 543.54 / Max: 666.05 Min: 43.43 / Avg: 244.69 / Max: 272.76 Min: 85.98 / Avg: 466.59 / Max: 553.15 Min: 52.05 / Avg: 660.57 / Max: 815.23 Min: 50.88 / Avg: 560.54 / Max: 686.46 Min: 26.7 / Avg: 355.17 / Max: 409.43 Min: 27.07 / Avg: 293.04 / Max: 344.46 Min: 106.7 / Avg: 498.27 / Max: 569.46 Min: 58.54 / Avg: 255.21 / Max: 283.22 Min: 55.09 / Avg: 259.4 / Max: 289.37 Min: 73.06 / Avg: 469.56 / Max: 569.83 Min: 33.71 / Avg: 242.73 / Max: 284.93 Min: 75.28 / Avg: 431.01 / Max: 540.73 Min: 35.86 / Avg: 220.9 / Max: 264.59 Min: 37.54 / Avg: 213.88 / Max: 229.99 Min: 78.37 / Avg: 419.83 / Max: 460.3
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 7 14 21 28 35 SE +/- 0.15, N = 5 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.57, N = 15 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.20, N = 3 SE +/- 0.19, N = 3 SE +/- 0.73, N = 15 SE +/- 0.02, N = 3 SE +/- 0.15, N = 15 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.28, N = 15 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 14.23 18.50 18.63 26.85 25.82 9.19 15.76 30.79 29.13 23.62 21.49 12.67 7.79 8.79 21.23 13.43 21.76 13.91 12.49 18.49 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0167 0.0334 0.0501 0.0668 0.0835 0.028 0.067 0.062 0.050 0.051 0.035 0.031 0.049 0.053 0.065 0.074 0.026 0.032 0.035 0.041 0.053 0.043 0.055 0.059 0.044 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.6 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 132.12 / Avg: 502.67 / Max: 581.3 Min: 22.01 / Avg: 274.77 / Max: 310.93 Min: 20.15 / Avg: 301 / Max: 352 Min: 43 / Avg: 537.42 / Max: 680.52 Min: 43.55 / Avg: 509.51 / Max: 622.64 Min: 43.77 / Avg: 259.79 / Max: 284.35 Min: 87.85 / Avg: 505.93 / Max: 558.01 Min: 54.27 / Avg: 630.75 / Max: 818.98 Min: 51.8 / Avg: 552.29 / Max: 644.32 Min: 25.97 / Avg: 363.95 / Max: 409.49 Min: 25.45 / Avg: 288.54 / Max: 323.49 Min: 114.23 / Avg: 492.58 / Max: 569.37 Min: 58.79 / Avg: 247.05 / Max: 284.34 Min: 58.17 / Avg: 251.21 / Max: 290.24 Min: 75.16 / Avg: 520.33 / Max: 574.4 Min: 34.75 / Avg: 251.95 / Max: 278.69 Min: 76.62 / Avg: 508.84 / Max: 573.51 Min: 36.25 / Avg: 253.87 / Max: 283.18 Min: 38.12 / Avg: 212.28 / Max: 230.28 Min: 81.68 / Avg: 418.63 / Max: 460.88
Timed LLVM Compilation This test times how long it takes to build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Ninja Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 60 120 180 240 300 SE +/- 0.57, N = 3 SE +/- 0.56, N = 3 SE +/- 0.53, N = 3 SE +/- 0.07, N = 3 SE +/- 0.21, N = 3 SE +/- 0.36, N = 3 SE +/- 0.26, N = 3 SE +/- 0.21, N = 3 SE +/- 0.18, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.33, N = 3 SE +/- 0.62, N = 3 SE +/- 1.02, N = 3 SE +/- 0.31, N = 3 SE +/- 0.70, N = 3 SE +/- 0.33, N = 3 SE +/- 0.71, N = 3 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 149.60 117.76 115.77 81.68 83.34 219.94 135.10 71.33 74.65 97.62 105.19 159.49 267.73 239.58 108.52 159.22 112.58 167.05 186.43 121.48 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed LLVM Compilation 13.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 138.89 / Avg: 420.82 / Max: 581.9 Min: 22.14 / Avg: 221.99 / Max: 321.94 Min: 20.49 / Avg: 230.51 / Max: 342.46 Min: 43.32 / Avg: 387.92 / Max: 719.13 Min: 42.98 / Avg: 369.11 / Max: 649.4 Min: 43.05 / Avg: 245.83 / Max: 285.6 Min: 88.54 / Avg: 417.17 / Max: 564.38 Min: 54.06 / Avg: 419.38 / Max: 820.96 Min: 52 / Avg: 380.13 / Max: 676.33 Min: 26.83 / Avg: 256.16 / Max: 409.54 Min: 25.81 / Avg: 220.93 / Max: 331.81 Min: 113.34 / Avg: 426.1 / Max: 570.51 Min: 58.05 / Avg: 241.17 / Max: 284.78 Min: 61.11 / Avg: 238.98 / Max: 290.9 Min: 73.6 / Avg: 350 / Max: 574.31 Min: 34.46 / Avg: 215.85 / Max: 286.7 Min: 78.22 / Avg: 352.57 / Max: 572.69 Min: 36.17 / Avg: 213.92 / Max: 286.31 Min: 38.39 / Avg: 185.95 / Max: 229.99 Min: 81.1 / Avg: 323.59 / Max: 460.46
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 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20K 40K 60K 80K 100K SE +/- 87.17, N = 8 SE +/- 289.00, N = 8 SE +/- 342.99, N = 8 SE +/- 735.83, N = 15 SE +/- 964.25, N = 15 SE +/- 184.99, N = 7 SE +/- 752.96, N = 15 SE +/- 875.77, N = 15 SE +/- 1179.69, N = 15 SE +/- 691.56, N = 15 SE +/- 546.79, N = 15 SE +/- 67.42, N = 8 SE +/- 27.03, N = 6 SE +/- 18.32, N = 6 SE +/- 413.94, N = 8 SE +/- 271.08, N = 8 SE +/- 404.03, N = 15 SE +/- 74.99, N = 6 SE +/- 131.39, N = 6 SE +/- 272.04, N = 8 39249.47 45631.34 46439.60 81468.95 82493.40 30040.20 42579.32 82256.89 79107.08 55458.39 54251.02 37782.16 22162.94 22812.43 51069.45 40140.36 46814.82 24379.67 23979.79 47508.34 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 4.1.4 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 EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 80 160 240 320 400 111.33 325.11 339.83 351.43 374.26 178.91 152.00 323.62 324.45 373.81 385.48 113.09 114.48 116.99 206.78 311.33 189.86 152.95 163.07 191.84 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 120 240 360 480 600 Min: 137.23 / Avg: 352.55 / Max: 581.48 Min: 22.11 / Avg: 140.35 / Max: 305.39 Min: 19.38 / Avg: 136.66 / Max: 301.81 Min: 40.56 / Avg: 231.82 / Max: 657.98 Min: 39.69 / Avg: 220.42 / Max: 650.35 Min: 42.61 / Avg: 167.91 / Max: 278.6 Min: 89.36 / Avg: 280.12 / Max: 519.92 Min: 50.85 / Avg: 254.18 / Max: 695.59 Min: 51.87 / Avg: 243.82 / Max: 639.01 Min: 26.93 / Avg: 148.36 / Max: 338.17 Min: 26.06 / Avg: 140.74 / Max: 309.33 Min: 114.27 / Avg: 334.09 / Max: 570.83 Min: 62.64 / Avg: 193.59 / Max: 285.44 Min: 57.44 / Avg: 195 / Max: 290.85 Min: 75.02 / Avg: 246.98 / Max: 526.93 Min: 34.04 / Avg: 128.93 / Max: 261.76 Min: 77.83 / Avg: 246.58 / Max: 496.35 Min: 35.76 / Avg: 159.4 / Max: 262.98 Min: 37.57 / Avg: 147.05 / Max: 229.52 Min: 82.17 / Avg: 247.64 / Max: 460.6
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 400 800 1200 1600 2000 SE +/- 4.91, N = 3 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 SE +/- 4.51, N = 3 SE +/- 1.45, N = 3 SE +/- 0.33, N = 3 SE +/- 11.66, N = 4 SE +/- 14.97, N = 3 SE +/- 8.96, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 1.45, N = 3 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 SE +/- 3.67, N = 3 SE +/- 0.88, N = 3 SE +/- 1.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 2.08, N = 3 1064 1216 1239 1737 1756 703 1093 2080 1923 1665 1429 998 560 617 1456 1039 1446 1036 934 1289 1. (CC) gcc options: -fopenmp -O2 -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1.2438 2.4876 3.7314 4.9752 6.219 2.069 4.956 4.877 3.946 4.044 2.811 2.369 3.878 4.113 4.991 5.528 1.993 2.213 2.406 3.297 4.274 3.321 4.322 4.496 3.276 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.38 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 131.93 / Avg: 514.14 / Max: 545.1 Min: 21.94 / Avg: 245.36 / Max: 265.19 Min: 18.81 / Avg: 254.05 / Max: 272.8 Min: 43.13 / Avg: 440.21 / Max: 474.83 Min: 42.43 / Avg: 434.23 / Max: 468.43 Min: 42.42 / Avg: 250.09 / Max: 270.02 Min: 87.79 / Avg: 461.38 / Max: 497.91 Min: 54.76 / Avg: 536.33 / Max: 584.95 Min: 53.13 / Avg: 467.57 / Max: 504.28 Min: 26.49 / Avg: 333.6 / Max: 360.91 Min: 25.15 / Avg: 258.49 / Max: 277.83 Min: 115.67 / Avg: 500.83 / Max: 531.91 Min: 55.41 / Avg: 253.01 / Max: 279.88 Min: 61.55 / Avg: 256.41 / Max: 285.69 Min: 73.75 / Avg: 441.57 / Max: 473.61 Min: 33.89 / Avg: 243.1 / Max: 260.41 Min: 76.42 / Avg: 435.35 / Max: 468.07 Min: 35.9 / Avg: 239.7 / Max: 261.26 Min: 38.3 / Avg: 207.73 / Max: 221.06 Min: 81.3 / Avg: 393.43 / Max: 419.97
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 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only - Average Latency Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 0.1089 0.2178 0.3267 0.4356 0.5445 SE +/- 0.003, N = 12 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 SE +/- 0.002, N = 4 SE +/- 0.001, N = 12 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.266 0.192 0.191 0.151 0.154 0.484 0.256 0.135 0.160 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 15 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 100 200 300 400 500 Min: 128.43 / Avg: 481.67 / Max: 581.46 Min: 21.66 / Avg: 263.52 / Max: 309.63 Min: 20.13 / Avg: 277.24 / Max: 321.83 Min: 42.22 / Avg: 453.52 / Max: 532.31 Min: 41.31 / Avg: 451.37 / Max: 537.14 Min: 43.21 / Avg: 246.17 / Max: 286.68 Min: 88.17 / Avg: 483.77 / Max: 557.65 Min: 26.75 / Avg: 354.29 / Max: 409.82 Min: 24.54 / Avg: 273.42 / Max: 316.58
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 500 - Mode: Read Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 800K 1600K 2400K 3200K 4000K SE +/- 21999.01, N = 12 SE +/- 21803.70, N = 3 SE +/- 9277.57, N = 3 SE +/- 35856.09, N = 4 SE +/- 28561.38, N = 12 SE +/- 1604.60, N = 3 SE +/- 8234.43, N = 3 SE +/- 7182.94, N = 3 SE +/- 5336.89, N = 3 1882111 2601026 2614770 3314790 3256442 1032195 1950276 3700395 3120414 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Result
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only - Average Latency Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 0.0533 0.1066 0.1599 0.2132 0.2665 SE +/- 0.003, N = 12 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 4 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.134 0.094 0.095 0.074 0.074 0.237 0.128 0.067 0.080 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 15 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 100 200 300 400 500 Min: 126.61 / Avg: 481.51 / Max: 581.41 Min: 21.49 / Avg: 262.96 / Max: 309.11 Min: 19.27 / Avg: 276.89 / Max: 320.98 Min: 43.15 / Avg: 460.13 / Max: 539.13 Min: 40.96 / Avg: 459.11 / Max: 534.06 Min: 43.59 / Avg: 246.41 / Max: 283.54 Min: 88.3 / Avg: 483.14 / Max: 557.01 Min: 25.51 / Avg: 353.91 / Max: 409.83 Min: 26.11 / Avg: 273.33 / Max: 316.12
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 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1000M 2000M 3000M 4000M 5000M SE +/- 3499682.53, N = 3 SE +/- 2017699.46, N = 3 SE +/- 7785956.02, N = 3 SE +/- 8029321.27, N = 3 SE +/- 8247895.35, N = 3 SE +/- 2066666.67, N = 3 SE +/- 2909180.87, N = 3 SE +/- 7438936.60, N = 3 SE +/- 1985782.80, N = 3 SE +/- 14090698.27, N = 3 SE +/- 3507610.77, N = 3 SE +/- 3329164.06, N = 3 SE +/- 2271563.34, N = 3 SE +/- 4740018.75, N = 3 SE +/- 2138535.32, N = 3 SE +/- 2403007.38, N = 3 SE +/- 4504442.25, N = 3 SE +/- 5026927.49, N = 3 SE +/- 5460565.70, N = 3 SE +/- 6615386.11, N = 3 2930033333 4349733333 4612933333 4625400000 4614166667 2024033333 3686200000 4551866667 4564800000 4547533333 4054500000 2986100000 1309500000 1611666667 3338000000 2844933333 3187000000 2810400000 2578033333 3184700000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 64 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4M 8M 12M 16M 20M 6169952.53 17015933.04 15567645.40 11382288.44 11424962.32 8504773.53 7876217.57 10452974.21 10395089.54 14370003.51 16032141.36 6405230.98 5624845.63 6840650.66 8500179.15 12678254.22 9308668.77 12341073.06 13030689.99 8566420.30 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 124.81 / Avg: 474.89 / Max: 581.24 Min: 21.94 / Avg: 255.63 / Max: 306.09 Min: 19.58 / Avg: 296.32 / Max: 357.09 Min: 43.47 / Avg: 406.37 / Max: 482.4 Min: 42.85 / Avg: 403.87 / Max: 482.6 Min: 42.92 / Avg: 237.99 / Max: 278.54 Min: 87.54 / Avg: 468.02 / Max: 563.25 Min: 53.87 / Avg: 435.46 / Max: 520.65 Min: 52.43 / Avg: 439.13 / Max: 520.9 Min: 25.44 / Avg: 316.46 / Max: 379.6 Min: 25.5 / Avg: 252.9 / Max: 301.99 Min: 112.97 / Avg: 466.2 / Max: 569.94 Min: 59.48 / Avg: 232.81 / Max: 283.79 Min: 59.92 / Avg: 235.6 / Max: 290.7 Min: 73.82 / Avg: 393.1 / Max: 466.4 Min: 34.14 / Avg: 224.39 / Max: 265.21 Min: 76.77 / Avg: 342.37 / Max: 401.64 Min: 36.02 / Avg: 227.73 / Max: 269.77 Min: 37.64 / Avg: 197.84 / Max: 230.29 Min: 80.83 / Avg: 371.77 / Max: 433.39
PostgreSQL This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 800K 1600K 2400K 3200K 4000K SE +/- 30910.94, N = 12 SE +/- 13108.55, N = 3 SE +/- 6219.97, N = 3 SE +/- 38847.19, N = 3 SE +/- 20578.11, N = 3 SE +/- 5827.48, N = 3 SE +/- 15905.36, N = 10 SE +/- 16283.20, N = 3 SE +/- 3064.84, N = 3 1993675 2717872 2722794 3464865 3439045 1086708 2011081 3818131 3236019 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Result
OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 500 - Mode: Read Only - Average Latency Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 0.1035 0.207 0.3105 0.414 0.5175 SE +/- 0.004, N = 12 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 10 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 0.252 0.184 0.183 0.144 0.145 0.460 0.249 0.131 0.154 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 15 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 100 200 300 400 500 Min: 125.54 / Avg: 498.37 / Max: 581.82 Min: 21.43 / Avg: 274.42 / Max: 307.49 Min: 19.76 / Avg: 290.04 / Max: 325.57 Min: 42.21 / Avg: 470.1 / Max: 529 Min: 42.91 / Avg: 465.53 / Max: 523.23 Min: 43.75 / Avg: 253.79 / Max: 282.57 Min: 44.29 / Avg: 500.27 / Max: 553.85 Min: 27.03 / Avg: 367.27 / Max: 409.83 Min: 24.89 / Avg: 282.81 / Max: 315.56
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 100 - Clients: 250 - Mode: Read Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 800K 1600K 2400K 3200K 4000K SE +/- 43235.34, N = 12 SE +/- 5489.82, N = 3 SE +/- 12477.20, N = 3 SE +/- 41178.99, N = 4 SE +/- 34621.78, N = 3 SE +/- 2659.26, N = 3 SE +/- 3592.47, N = 3 SE +/- 8254.16, N = 3 SE +/- 21432.95, N = 3 1871425 2648375 2640654 3411434 3360070 1057177 1956708 3701462 3135626 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
OpenBenchmarking.org TPS, More Is Better PostgreSQL 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 800K 1600K 2400K 3200K 4000K SE +/- 22335.44, N = 3 SE +/- 14108.92, N = 3 SE +/- 15618.98, N = 3 SE +/- 38023.52, N = 3 SE +/- 23179.98, N = 3 SE +/- 2870.95, N = 3 SE +/- 9474.73, N = 3 SE +/- 17338.24, N = 3 SE +/- 16481.46, N = 3 2075926 2760167 2754409 3460345 3444340 1106044 2056512 3872473 3286136 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.8798 1.7596 2.6394 3.5192 4.399 SE +/- 0.01, N = 5 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 2.89 2.67 2.73 3.91 3.84 1.12 1.88 3.70 3.57 3.33 3.04 2.71 1.59 1.74 1.94 1.65 2.56 1.65 1.41 2.25 Images / Sec Per Watt
OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.hdr_alb_nrm.3840x2160 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0043 0.0086 0.0129 0.0172 0.0215 0.009 0.017 0.017 0.015 0.015 0.006 0.006 0.012 0.013 0.018 0.019 0.009 0.009 0.010 0.007 0.010 0.009 0.010 0.010 0.008 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 131.81 / Avg: 332.8 / Max: 547.47 Min: 21.83 / Avg: 157.17 / Max: 307.71 Min: 18.79 / Avg: 161.98 / Max: 322.59 Min: 43.5 / Avg: 267.42 / Max: 580.63 Min: 42.82 / Avg: 262.61 / Max: 559.95 Min: 42.87 / Avg: 172.32 / Max: 275.62 Min: 88.58 / Avg: 319.19 / Max: 549.93 Min: 51.97 / Avg: 299.55 / Max: 617.7 Min: 51.19 / Avg: 284.94 / Max: 570.34 Min: 25.31 / Avg: 181.53 / Max: 376.37 Min: 24.9 / Avg: 156.91 / Max: 319.59 Min: 108.33 / Avg: 318.05 / Max: 530.98 Min: 57.5 / Avg: 176.66 / Max: 275.71 Min: 56.84 / Avg: 174.32 / Max: 281.35 Min: 74.88 / Avg: 288.05 / Max: 489.14 Min: 34.51 / Avg: 165.16 / Max: 275.31 Min: 77.56 / Avg: 282 / Max: 504.94 Min: 36.09 / Avg: 160.31 / Max: 266.9 Min: 37.76 / Avg: 142.83 / Max: 228.91 Min: 82.32 / Avg: 265.39 / Max: 455.12
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 15 Scaling Factor: 1 - Clients: 250 - Mode: Read Only - Average Latency Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 0.0509 0.1018 0.1527 0.2036 0.2545 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.120 0.091 0.091 0.072 0.073 0.226 0.122 0.065 0.076 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PostgreSQL 15 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 100 200 300 400 500 Min: 124.9 / Avg: 497.79 / Max: 581.6 Min: 13.31 / Avg: 273.86 / Max: 307.05 Min: 16.55 / Avg: 288.82 / Max: 324.23 Min: 42.99 / Avg: 465.31 / Max: 529.97 Min: 43.67 / Avg: 465.22 / Max: 523.01 Min: 43.68 / Avg: 254.49 / Max: 283.45 Min: 87.85 / Avg: 500.67 / Max: 553.81 Min: 25.21 / Avg: 367.46 / Max: 409.82 Min: 24.89 / Avg: 283.75 / Max: 316.05
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.8753 1.7506 2.6259 3.5012 4.3765 SE +/- 0.00, N = 5 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 2.89 2.67 2.73 3.89 3.82 1.12 1.89 3.69 3.57 3.33 3.05 2.72 1.60 1.74 1.96 1.66 2.57 1.65 1.41 2.27 Images / Sec Per Watt
OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RT.ldr_alb_nrm.3840x2160 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0043 0.0086 0.0129 0.0172 0.0215 0.009 0.017 0.017 0.015 0.015 0.006 0.006 0.012 0.013 0.018 0.019 0.009 0.009 0.010 0.007 0.010 0.009 0.010 0.010 0.009 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 134.8 / Avg: 339.23 / Max: 551.84 Min: 21.79 / Avg: 159.22 / Max: 308.03 Min: 17.8 / Avg: 161.87 / Max: 322.22 Min: 42.7 / Avg: 267.3 / Max: 577.91 Min: 43.57 / Avg: 259.59 / Max: 557.44 Min: 42.41 / Avg: 178.73 / Max: 276.3 Min: 88.73 / Avg: 322.02 / Max: 548.99 Min: 48.83 / Avg: 295.78 / Max: 618.27 Min: 50.5 / Avg: 283.08 / Max: 568.84 Min: 27.02 / Avg: 183.71 / Max: 374.52 Min: 25.5 / Avg: 158.18 / Max: 318.63 Min: 111.17 / Avg: 315.31 / Max: 531.55 Min: 58.23 / Avg: 177.12 / Max: 276.42 Min: 60.13 / Avg: 177.78 / Max: 283.24 Min: 74.51 / Avg: 285.01 / Max: 497.66 Min: 34.19 / Avg: 164.79 / Max: 275.13 Min: 77.71 / Avg: 285.57 / Max: 502.39 Min: 35.8 / Avg: 158.76 / Max: 267.81 Min: 37.65 / Avg: 143.77 / Max: 229.31 Min: 81.41 / Avg: 261.76 / Max: 457.39
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 95, Compression Effort 7 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1035 0.207 0.3105 0.414 0.5175 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 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 0.27 0.36 0.36 0.46 0.46 0.18 0.31 0.45 0.46 0.45 0.41 0.26 0.14 0.15 0.36 0.26 0.35 0.24 0.24 0.34 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl MP/s Per Watt
OpenBenchmarking.org MP/s Per Watt, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 95, Compression Effort 7 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0005 0.001 0.0015 0.002 0.0025 0.001 0.001 0.001 0.001 0.001 0.001 0.001 0.001 0.001 0.001 0.002 0.001 0.001 0.001 0.001 0.001 0.001 0.001 0.001 0.001 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better WebP2 Image Encode 20220823 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 128.48 / Avg: 466.73 / Max: 581.47 Min: 21.96 / Avg: 259.1 / Max: 328.49 Min: 19.8 / Avg: 273.76 / Max: 358.7 Min: 43.05 / Avg: 435.42 / Max: 572.53 Min: 43.38 / Avg: 433.86 / Max: 571.58 Min: 43.32 / Avg: 248.29 / Max: 286.58 Min: 87.47 / Avg: 457.06 / Max: 552.02 Min: 52.81 / Avg: 465.83 / Max: 609.26 Min: 50.14 / Avg: 464.4 / Max: 597.62 Min: 26.9 / Avg: 320.99 / Max: 409.44 Min: 26.58 / Avg: 272.99 / Max: 324.6 Min: 115.13 / Avg: 469.27 / Max: 569.8 Min: 59.14 / Avg: 248.53 / Max: 283.73 Min: 59.97 / Avg: 247.02 / Max: 290.11 Min: 73.8 / Avg: 418.65 / Max: 554.95 Min: 34.63 / Avg: 231.2 / Max: 286.58 Min: 75.63 / Avg: 359.07 / Max: 460.9 Min: 35.95 / Avg: 216.91 / Max: 262.24 Min: 38.14 / Avg: 204.74 / Max: 230.29 Min: 80.5 / Avg: 379.05 / Max: 460.63
Intel Open Image Denoise Open Image Denoise is a denoising library for ray-tracing and part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.414 0.828 1.242 1.656 2.07 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 +/- 0.01, 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 1.38 1.26 1.29 1.84 1.81 0.56 0.94 1.77 1.69 1.58 1.44 1.30 0.76 0.83 0.95 0.82 1.26 0.81 0.70 1.11 Images / Sec Per Watt
OpenBenchmarking.org Images / Sec Per Watt, More Is Better Intel Open Image Denoise 1.4.0 Run: RTLightmap.hdr.4096x4096 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0018 0.0036 0.0054 0.0072 0.009 0.004 0.007 0.007 0.006 0.006 0.003 0.003 0.005 0.005 0.008 0.008 0.004 0.004 0.004 0.003 0.005 0.004 0.005 0.005 0.004 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Intel Open Image Denoise 1.4.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 129.72 / Avg: 373 / Max: 546.19 Min: 19.89 / Avg: 181.61 / Max: 303.1 Min: 18.87 / Avg: 185.67 / Max: 317.74 Min: 39.75 / Avg: 309.56 / Max: 574.98 Min: 42.02 / Avg: 309.07 / Max: 554.58 Min: 42.43 / Avg: 186.74 / Max: 275.69 Min: 88.56 / Avg: 349.12 / Max: 548.99 Min: 52.23 / Avg: 346.81 / Max: 620.13 Min: 50.79 / Avg: 332.07 / Max: 568.97 Min: 26.82 / Avg: 209.76 / Max: 374.86 Min: 24.48 / Avg: 185.42 / Max: 315.03 Min: 109.43 / Avg: 355.13 / Max: 530.48 Min: 59.01 / Avg: 186.93 / Max: 275.84 Min: 58.82 / Avg: 189.95 / Max: 281.13 Min: 74.55 / Avg: 309.86 / Max: 493.81 Min: 17.66 / Avg: 176.2 / Max: 273.56 Min: 77.34 / Avg: 313.88 / Max: 503.4 Min: 35.88 / Avg: 171.24 / Max: 264.72 Min: 37.69 / Avg: 153.21 / Max: 229 Min: 82.21 / Avg: 294.59 / Max: 457.99
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 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 13K 26K 39K 52K 65K SE +/- 35.30, N = 4 SE +/- 124.44, N = 4 SE +/- 122.69, N = 4 SE +/- 99.91, N = 4 SE +/- 124.43, N = 4 SE +/- 71.44, N = 5 SE +/- 42.26, N = 4 SE +/- 227.17, N = 4 SE +/- 186.02, N = 4 SE +/- 141.39, N = 4 SE +/- 142.06, N = 4 SE +/- 51.78, N = 4 SE +/- 11.73, N = 5 SE +/- 20.86, N = 5 SE +/- 106.16, N = 3 SE +/- 83.18, N = 3 SE +/- 178.54, N = 3 SE +/- 36.15, N = 3 SE +/- 66.62, N = 3 SE +/- 136.51, N = 3 34993.47 30166.92 30428.09 60173.87 59398.79 19112.56 30531.61 59160.90 58017.07 30521.12 29508.59 35687.90 18713.27 18563.48 43886.00 22729.59 38255.51 19943.09 19643.92 37996.49 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 EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 81.31 192.43 192.86 173.27 172.72 113.82 83.58 154.08 156.70 174.47 173.54 85.00 91.16 90.32 115.32 125.28 105.34 113.89 115.41 106.62 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LULESH 2.0.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 130.79 / Avg: 430.36 / Max: 575.52 Min: 21.99 / Avg: 156.77 / Max: 257.64 Min: 19.23 / Avg: 157.77 / Max: 259.4 Min: 43.03 / Avg: 347.28 / Max: 551.83 Min: 44.34 / Avg: 343.91 / Max: 543.05 Min: 43.24 / Avg: 167.92 / Max: 252.37 Min: 88.38 / Avg: 365.31 / Max: 519.75 Min: 54.54 / Avg: 383.97 / Max: 606.7 Min: 51.18 / Avg: 370.24 / Max: 565.14 Min: 27.27 / Avg: 174.94 / Max: 284.76 Min: 26.38 / Avg: 170.04 / Max: 276.56 Min: 109.66 / Avg: 419.88 / Max: 566.82 Min: 60.26 / Avg: 205.27 / Max: 283.41 Min: 59.27 / Avg: 205.52 / Max: 278.2 Min: 75.98 / Avg: 380.57 / Max: 553.84 Min: 34.44 / Avg: 181.43 / Max: 266.35 Min: 78.12 / Avg: 363.15 / Max: 533.02 Min: 35.85 / Avg: 175.11 / Max: 259.65 Min: 37.56 / Avg: 170.21 / Max: 219.52 Min: 81.71 / Avg: 356.38 / Max: 452.76
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
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 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.2453 0.4906 0.7359 0.9812 1.2265 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 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 +/- 0.02, N = 12 SE +/- 0.01, N = 15 SE +/- 0.01, N = 15 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 0.59 0.37 0.36 0.35 0.35 0.77 0.79 0.36 0.36 0.43 0.45 0.57 0.60 0.63 0.96 0.90 1.01 0.98 1.04 1.09 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2022.2.dev CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 135.32 / Avg: 512.09 / Max: 580.17 Min: 22.08 / Avg: 302.73 / Max: 328.63 Min: 18.5 / Avg: 308.09 / Max: 334.64 Min: 43.68 / Avg: 454.26 / Max: 507.97 Min: 43.62 / Avg: 457.9 / Max: 508.57 Min: 43.39 / Avg: 255.48 / Max: 281.38 Min: 88.32 / Avg: 517.53 / Max: 554.19 Min: 54.13 / Avg: 517.78 / Max: 573.3 Min: 48.89 / Avg: 497.91 / Max: 540.84 Min: 27.3 / Avg: 347.78 / Max: 379.53 Min: 26.37 / Avg: 308.56 / Max: 334.71 Min: 113.83 / Avg: 502.56 / Max: 570.22 Min: 59.94 / Avg: 252.2 / Max: 285.34 Min: 58.06 / Avg: 256.79 / Max: 290.84 Min: 74.17 / Avg: 526.25 / Max: 573.13 Min: 34.71 / Avg: 252.7 / Max: 276.03 Min: 77.73 / Avg: 465.77 / Max: 513.35 Min: 36.01 / Avg: 223.91 / Max: 249.93 Min: 38.18 / Avg: 215.86 / Max: 229.98 Min: 81.1 / Avg: 429 / Max: 460.02
POV-Ray This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4 8 12 16 20 SE +/- 0.048, N = 4 SE +/- 0.037, N = 5 SE +/- 0.025, N = 5 SE +/- 0.024, N = 6 SE +/- 0.035, N = 6 SE +/- 0.014, N = 4 SE +/- 0.060, N = 5 SE +/- 0.042, N = 15 SE +/- 0.041, N = 15 SE +/- 0.032, N = 5 SE +/- 0.034, N = 5 SE +/- 0.104, N = 4 SE +/- 0.034, N = 3 SE +/- 0.090, N = 3 SE +/- 0.043, N = 5 SE +/- 0.022, N = 4 SE +/- 0.039, N = 5 SE +/- 0.060, N = 4 SE +/- 0.036, N = 4 SE +/- 0.035, N = 5 9.544 7.445 7.145 5.733 5.851 13.369 8.233 5.673 6.035 6.578 7.178 9.930 17.434 15.841 7.183 9.667 7.298 9.695 10.506 7.689 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -R/usr/lib -lSDL -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better POV-Ray 3.7.0.7 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 133.93 / Avg: 375.99 / Max: 581.49 Min: 22.17 / Avg: 164.82 / Max: 322.47 Min: 21.46 / Avg: 178.58 / Max: 373.56 Min: 42.83 / Avg: 269.51 / Max: 731.89 Min: 42.53 / Avg: 257.21 / Max: 637.75 Min: 43.34 / Avg: 186.66 / Max: 278.64 Min: 87.65 / Avg: 327.15 / Max: 557.48 Min: 50.41 / Avg: 286.67 / Max: 817.72 Min: 51.69 / Avg: 267.51 / Max: 649.82 Min: 25.87 / Avg: 178.98 / Max: 409.5 Min: 25.81 / Avg: 161.18 / Max: 329.69 Min: 114.98 / Avg: 366.02 / Max: 568.37 Min: 58.25 / Avg: 209.25 / Max: 284.09 Min: 62.12 / Avg: 208.69 / Max: 290.23 Min: 74.81 / Avg: 254.49 / Max: 553.83 Min: 34.5 / Avg: 159.09 / Max: 268.26 Min: 76.47 / Avg: 253.07 / Max: 550.75 Min: 36.28 / Avg: 159.61 / Max: 270.68 Min: 37.84 / Avg: 147.59 / Max: 230.3 Min: 81.26 / Avg: 247.57 / Max: 460.74
PJSIP PJSIP is a free and open source multimedia communication library written in C language implementing standard based protocols such as SIP, SDP, RTP, STUN, TURN, and ICE. It combines signaling protocol (SIP) with rich multimedia framework and NAT traversal functionality into high level API that is portable and suitable for almost any type of systems ranging from desktops, embedded systems, to mobile handsets. This test profile is making use of pjsip-perf with both the client/server on teh system. More details on the PJSIP benchmark at https://www.pjsip.org/high-performance-sip.htm Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20K 40K 60K 80K 100K SE +/- 321.08, N = 3 SE +/- 306.04, N = 3 SE +/- 685.00, N = 3 SE +/- 758.24, N = 15 SE +/- 839.32, N = 15 SE +/- 142.06, N = 3 SE +/- 368.57, N = 15 SE +/- 871.18, N = 5 SE +/- 299.00, N = 3 SE +/- 260.59, N = 3 SE +/- 278.58, N = 3 SE +/- 304.29, N = 15 SE +/- 449.23, N = 3 SE +/- 359.80, N = 9 SE +/- 1274.54, N = 15 SE +/- 445.63, N = 3 SE +/- 734.76, N = 15 SE +/- 317.58, N = 3 SE +/- 377.55, N = 3 SE +/- 821.92, N = 15 43053 89733 89834 84745 83661 42830 29445 83007 86749 87728 87898 43807 44605 43449 67128 71208 66415 72333 74389 68314 1. (CC) gcc options: -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2 Responses Per Second Per Watt
OpenBenchmarking.org Responses Per Second Per Watt, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200 400 600 800 1000 165.48 1062.67 1057.90 474.52 467.76 434.51 139.16 397.17 417.79 887.11 885.84 178.44 273.45 266.27 442.29 889.04 424.64 868.87 835.63 412.31 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PJSIP 2.11 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 Min: 131.37 / Avg: 260.17 / Max: 287.62 Min: 21.32 / Avg: 84.44 / Max: 98.74 Min: 20.91 / Avg: 84.92 / Max: 99.36 Min: 41.71 / Avg: 178.59 / Max: 203.97 Min: 43.24 / Avg: 178.86 / Max: 203.83 Min: 42.41 / Avg: 98.57 / Max: 111.05 Min: 87.89 / Avg: 211.59 / Max: 232.89 Min: 51.71 / Avg: 209 / Max: 237.16 Min: 52.21 / Avg: 207.64 / Max: 235.47 Min: 25.12 / Avg: 98.89 / Max: 114.19 Min: 25.59 / Avg: 99.23 / Max: 113.49 Min: 109.63 / Avg: 245.51 / Max: 274.15 Min: 60.08 / Avg: 163.12 / Max: 176.74 Min: 61.39 / Avg: 163.18 / Max: 176.59 Min: 74.39 / Avg: 151.77 / Max: 186.44 Min: 33.81 / Avg: 80.1 / Max: 90.05 Min: 77.02 / Avg: 156.4 / Max: 190.98 Min: 35.51 / Avg: 83.25 / Max: 95.16 Min: 37.42 / Avg: 89.02 / Max: 102.04 Min: 80.87 / Avg: 165.69 / Max: 208.81
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org sssp median_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130M 260M 390M 520M 650M 284444000 351607000 354905000 488130000 454926000 203644000 268136000 600906000 539862000 412741000 417648000 269303000 197386000 204473000 298987000 288658000 356857000 265868000 233676000 336248000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
WebP2 Image Encode This is a test of Google's libwebp2 library with the WebP2 image encode utility and using a sample 6000x4000 pixel JPEG image as the input, similar to the WebP/libwebp test profile. WebP2 is currently experimental and under heavy development as ultimately the successor to WebP. WebP2 supports 10-bit HDR, more efficienct lossy compression, improved lossless compression, animation support, and full multi-threading support compared to WebP. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 75, Compression Effort 7 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.1913 0.3826 0.5739 0.7652 0.9565 SE +/- 0.00, N = 3 SE +/- 0.00, N = 13 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 +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 4 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.53 0.72 0.72 0.84 0.85 0.37 0.59 0.83 0.83 0.83 0.78 0.51 0.28 0.32 0.66 0.52 0.64 0.48 0.48 0.63 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl MP/s Per Watt
OpenBenchmarking.org MP/s Per Watt, More Is Better WebP2 Image Encode 20220823 Encode Settings: Quality 75, Compression Effort 7 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0007 0.0014 0.0021 0.0028 0.0035 0.001 0.003 0.003 0.002 0.002 0.002 0.001 0.002 0.002 0.003 0.003 0.001 0.001 0.001 0.002 0.002 0.002 0.002 0.003 0.002 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better WebP2 Image Encode 20220823 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 131.68 / Avg: 443.9 / Max: 580.87 Min: 20.4 / Avg: 231.48 / Max: 328.04 Min: 21.03 / Avg: 239.87 / Max: 353.77 Min: 40.23 / Avg: 367.86 / Max: 560.04 Min: 43.07 / Avg: 369.82 / Max: 559.57 Min: 42.13 / Avg: 230.16 / Max: 281.54 Min: 88.8 / Avg: 412.03 / Max: 554.68 Min: 52 / Avg: 396.58 / Max: 598.31 Min: 51.53 / Avg: 400.73 / Max: 594.71 Min: 26.69 / Avg: 268.87 / Max: 409.42 Min: 24.31 / Avg: 238.35 / Max: 323.82 Min: 112.77 / Avg: 441.89 / Max: 568.77 Min: 55.34 / Avg: 238.29 / Max: 283.41 Min: 56.99 / Avg: 242.78 / Max: 289.69 Min: 74.16 / Avg: 361.54 / Max: 550.41 Min: 33.7 / Avg: 213.88 / Max: 286.72 Min: 75.98 / Avg: 314.48 / Max: 456.11 Min: 35.64 / Avg: 197.34 / Max: 264.05 Min: 37.61 / Avg: 190.89 / Max: 230.43 Min: 80.52 / Avg: 336.84 / Max: 460.58
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 16 32 48 64 80 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.31, N = 3 47.47 35.66 36.98 73.51 70.05 24.26 47.43 49.10 42.69
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.
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 16 32 48 64 80 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.26, N = 3 SE +/- 0.47, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.36, N = 3 47.56 35.69 36.96 73.12 69.62 24.22 47.56 48.98 42.52
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 18.8 Time To Compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 60 120 180 240 300 SE +/- 0.54, N = 3 SE +/- 0.32, N = 3 SE +/- 0.03, N = 3 SE +/- 0.11, N = 3 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.27, N = 3 SE +/- 0.37, N = 3 SE +/- 0.16, N = 3 SE +/- 0.18, N = 3 SE +/- 0.32, N = 3 SE +/- 0.78, N = 3 SE +/- 0.15, N = 3 SE +/- 0.32, N = 3 SE +/- 0.22, N = 3 SE +/- 0.42, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.27, N = 3 SE +/- 0.26, N = 3 173.99 133.20 132.32 99.65 100.26 229.17 152.42 95.41 98.51 117.06 123.43 178.62 279.48 257.12 130.04 177.63 135.21 186.25 203.23 141.32 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Node.js Compilation 18.8 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 127.17 / Avg: 400.19 / Max: 582.04 Min: 21.57 / Avg: 203.36 / Max: 327.49 Min: 20.05 / Avg: 208.9 / Max: 361.53 Min: 41.73 / Avg: 355.09 / Max: 740.01 Min: 43.84 / Avg: 345.22 / Max: 654.88 Min: 42.83 / Avg: 234.75 / Max: 285.07 Min: 82.25 / Avg: 392.97 / Max: 559.35 Min: 52.69 / Avg: 386.44 / Max: 821.1 Min: 51.89 / Avg: 357.37 / Max: 679.25 Min: 27.17 / Avg: 232.07 / Max: 409.59 Min: 24.5 / Avg: 205.89 / Max: 339.55 Min: 119.17 / Avg: 403.16 / Max: 570.85 Min: 55.81 / Avg: 232.64 / Max: 284.96 Min: 58.23 / Avg: 230 / Max: 291.15 Min: 73.89 / Avg: 330.81 / Max: 576.88 Min: 34.14 / Avg: 201.21 / Max: 286.87 Min: 77.22 / Avg: 328.92 / Max: 568.55 Min: 35.89 / Avg: 199.8 / Max: 286.29 Min: 37.7 / Avg: 176.8 / Max: 229.69 Min: 80.77 / Avg: 311.43 / Max: 461.56
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org bfs max_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300M 600M 900M 1200M 1500M 877292000 822265000 817075000 1297530000 1192870000 550370000 597565000 1594850000 1437570000 881729000 906613000 838693000 680026000 717132000 611172000 732471000 725689000 686802000 546314000 728499000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
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 2.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.09, N = 4 SE +/- 0.20, N = 5 SE +/- 0.12, N = 5 SE +/- 0.31, N = 6 SE +/- 0.40, N = 6 SE +/- 0.10, N = 4 SE +/- 0.08, N = 4 SE +/- 0.30, N = 5 SE +/- 0.55, N = 5 SE +/- 0.53, N = 15 SE +/- 0.51, N = 6 SE +/- 0.06, N = 4 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.61, N = 5 SE +/- 0.06, N = 4 SE +/- 0.41, N = 15 SE +/- 0.08, N = 4 SE +/- 0.10, N = 4 SE +/- 0.42, N = 15 39.82 62.33 62.13 74.70 73.37 37.46 50.01 71.57 71.57 77.05 76.67 40.10 29.36 27.55 55.08 41.75 56.98 39.08 37.05 55.77 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 2.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0923 0.1846 0.2769 0.3692 0.4615 0.104 0.389 0.393 0.294 0.290 0.187 0.143 0.257 0.259 0.409 0.410 0.107 0.128 0.126 0.186 0.249 0.197 0.251 0.232 0.180 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 80 160 240 320 400 Min: 136.2 / Avg: 381.82 / Max: 465.28 Min: 21.98 / Avg: 160.05 / Max: 223.92 Min: 20.28 / Avg: 158.23 / Max: 225.51 Min: 43.73 / Avg: 253.89 / Max: 378.95 Min: 40.93 / Avg: 252.77 / Max: 373.73 Min: 43.87 / Avg: 200.12 / Max: 247.36 Min: 88.1 / Avg: 350.2 / Max: 458.33 Min: 53.38 / Avg: 278.55 / Max: 418.27 Min: 50.38 / Avg: 276.51 / Max: 408.2 Min: 27.18 / Avg: 188.33 / Max: 283.23 Min: 25.11 / Avg: 186.9 / Max: 278.56 Min: 117.71 / Avg: 374.95 / Max: 454.5 Min: 58.76 / Avg: 228.9 / Max: 267.72 Min: 59.54 / Avg: 218.08 / Max: 257.15 Min: 75.19 / Avg: 296.85 / Max: 402.04 Min: 34.23 / Avg: 167.4 / Max: 214.45 Min: 77.28 / Avg: 289 / Max: 392.09 Min: 36.13 / Avg: 156 / Max: 194.26 Min: 37.87 / Avg: 159.71 / Max: 200.29 Min: 81.09 / Avg: 309.49 / Max: 420.23
Graph500 This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org bfs median_TEPS, More Is Better Graph500 3.0 Scale: 26 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 300M 600M 900M 1200M 1500M 844030000 799869000 797394000 1238540000 1115180000 538025000 576137000 1479590000 1342540000 863368000 887314000 806551000 646764000 703700000 591513000 716376000 696955000 676555000 531725000 713016000 1. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi
Neural Magic DeepSparse Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 6 12 18 24 30 SE +/- 0.0748, N = 3 SE +/- 0.0441, N = 3 SE +/- 0.0141, N = 3 SE +/- 0.1144, N = 3 SE +/- 0.0509, N = 3 SE +/- 0.0482, N = 3 SE +/- 0.2644, N = 6 SE +/- 0.0122, N = 3 SE +/- 0.0277, N = 3 12.9658 10.7833 10.7061 10.9903 10.9209 25.3025 26.6528 9.7375 9.8328 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 70 140 210 280 350 Min: 133.81 / Avg: 316.31 / Max: 383 Min: 21.73 / Avg: 187.51 / Max: 229.03 Min: 19.2 / Avg: 188.49 / Max: 229.38 Min: 40.49 / Avg: 269.65 / Max: 332.45 Min: 43.17 / Avg: 269.01 / Max: 332.98 Min: 43.15 / Avg: 201.49 / Max: 271.55 Min: 88.11 / Avg: 282.39 / Max: 359.38 Min: 26.72 / Avg: 233.47 / Max: 294.42 Min: 26.9 / Avg: 226.78 / Max: 285.11
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 20 40 60 80 100 SE +/- 0.44, N = 3 SE +/- 0.38, N = 3 SE +/- 0.12, N = 3 SE +/- 0.94, N = 3 SE +/- 0.43, N = 3 SE +/- 0.08, N = 3 SE +/- 0.36, N = 6 SE +/- 0.13, N = 3 SE +/- 0.29, N = 3 77.08 92.68 93.34 90.94 91.50 39.51 37.51 102.65 101.65
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 5.18 Build: defconfig Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 11 22 33 44 55 SE +/- 0.42, N = 3 SE +/- 0.32, N = 3 SE +/- 0.24, N = 5 SE +/- 0.18, N = 7 SE +/- 0.17, N = 7 SE +/- 0.42, N = 3 SE +/- 0.32, N = 4 SE +/- 0.15, N = 9 SE +/- 0.16, N = 9 SE +/- 0.23, N = 5 SE +/- 0.26, N = 5 SE +/- 0.42, N = 3 SE +/- 0.41, N = 3 SE +/- 0.42, N = 3 SE +/- 0.22, N = 7 SE +/- 0.36, N = 4 SE +/- 0.23, N = 7 SE +/- 0.41, N = 4 SE +/- 0.47, N = 3 SE +/- 0.25, N = 7 29.95 24.73 23.88 18.79 19.14 40.42 27.69 18.23 19.00 22.51 23.61 30.63 46.67 43.38 24.15 31.92 24.67 32.61 35.86 26.12 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Linux Kernel Compilation 5.18 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 133.98 / Avg: 339.92 / Max: 581.16 Min: 21.02 / Avg: 152.82 / Max: 319 Min: 20.4 / Avg: 167.28 / Max: 354.28 Min: 43.1 / Avg: 279.54 / Max: 736.44 Min: 38.99 / Avg: 270.17 / Max: 647.7 Min: 42.91 / Avg: 188.06 / Max: 277.74 Min: 89.02 / Avg: 313.58 / Max: 562.82 Min: 53.47 / Avg: 310.09 / Max: 819.32 Min: 49.09 / Avg: 290.92 / Max: 664.72 Min: 26.36 / Avg: 181.21 / Max: 409.58 Min: 23.18 / Avg: 163.79 / Max: 330.29 Min: 122.95 / Avg: 336.46 / Max: 570.14 Min: 58.74 / Avg: 201.8 / Max: 284.42 Min: 58.83 / Avg: 197.2 / Max: 291 Min: 74.39 / Avg: 255.49 / Max: 573.15 Min: 34.09 / Avg: 157.73 / Max: 286.61 Min: 77.85 / Avg: 259.77 / Max: 572.79 Min: 35.57 / Avg: 158.79 / Max: 286.31 Min: 37.63 / Avg: 144.15 / Max: 230.08 Min: 80.79 / Avg: 251.35 / Max: 460.74
Timed MPlayer Compilation This test times how long it takes to build the MPlayer open-source media player program. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.5 Time To Compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4 8 12 16 20 SE +/- 0.021, N = 4 SE +/- 0.014, N = 5 SE +/- 0.022, N = 5 SE +/- 0.030, N = 6 SE +/- 0.024, N = 6 SE +/- 0.037, N = 4 SE +/- 0.046, N = 5 SE +/- 0.018, N = 6 SE +/- 0.029, N = 6 SE +/- 0.016, N = 5 SE +/- 0.006, N = 5 SE +/- 0.047, N = 4 SE +/- 0.064, N = 3 SE +/- 0.060, N = 3 SE +/- 0.025, N = 5 SE +/- 0.056, N = 4 SE +/- 0.058, N = 5 SE +/- 0.034, N = 4 SE +/- 0.018, N = 4 SE +/- 0.044, N = 5 11.835 9.162 8.947 7.676 7.795 14.419 10.384 7.493 7.697 8.414 8.765 11.910 18.012 16.645 9.939 12.204 10.097 12.594 13.623 10.396 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed MPlayer Compilation 1.5 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 134.06 / Avg: 330.52 / Max: 581.27 Min: 21.69 / Avg: 141.63 / Max: 327.13 Min: 21.42 / Avg: 146.87 / Max: 366.37 Min: 43.58 / Avg: 237.88 / Max: 726.52 Min: 42.4 / Avg: 231.07 / Max: 660.92 Min: 43.16 / Avg: 175.13 / Max: 279.18 Min: 87.71 / Avg: 285.16 / Max: 560.38 Min: 53.49 / Avg: 263.96 / Max: 816.81 Min: 51.24 / Avg: 247.18 / Max: 683.64 Min: 27.09 / Avg: 154.89 / Max: 409.43 Min: 27 / Avg: 142.25 / Max: 340.9 Min: 62.15 / Avg: 323.78 / Max: 569.94 Min: 56.33 / Avg: 195.33 / Max: 284.1 Min: 61 / Avg: 192.31 / Max: 290.59 Min: 74.48 / Avg: 225.27 / Max: 573.03 Min: 34.1 / Avg: 139.3 / Max: 286.64 Min: 77.63 / Avg: 219.96 / Max: 570.7 Min: 35.77 / Avg: 141.1 / Max: 285.59 Min: 37.68 / Avg: 132.6 / Max: 230.06 Min: 80.8 / Avg: 223.55 / Max: 460.78
Neural Magic DeepSparse Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 3 6 9 12 15 SE +/- 0.0553, N = 3 SE +/- 0.0022, N = 3 SE +/- 0.0035, N = 3 SE +/- 0.0039, N = 3 SE +/- 0.0045, N = 3 SE +/- 0.0238, N = 3 SE +/- 0.0139, N = 3 SE +/- 0.0082, N = 3 SE +/- 0.0029, N = 3 8.3483 5.2790 5.2608 5.2659 5.3134 11.7404 11.8133 5.0062 5.1960 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 70 140 210 280 350 Min: 129.44 / Avg: 335.13 / Max: 378.21 Min: 22.2 / Avg: 227.49 / Max: 265.56 Min: 16.21 / Avg: 226.91 / Max: 267.4 Min: 43.34 / Avg: 310.25 / Max: 371.84 Min: 43.83 / Avg: 317.1 / Max: 369.16 Min: 43.11 / Avg: 207.6 / Max: 247.94 Min: 88.07 / Avg: 287.91 / Max: 323.02 Min: 26.4 / Avg: 253.98 / Max: 325.25 Min: 23.02 / Avg: 241.78 / Max: 286.68
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 40 80 120 160 200 SE +/- 0.79, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.33, N = 3 SE +/- 0.11, N = 3 119.63 189.26 189.93 189.73 188.04 85.14 84.60 199.58 192.31
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/. 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 2022.10.13 Model: Cell Phone Drop Test Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.20, N = 3 33.27 23.13 22.78 16.64 17.48 38.93 27.69 20.40 23.09 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 120 240 360 480 600 Min: 125.07 / Avg: 439.94 / Max: 580.9 Min: 21.42 / Avg: 238.55 / Max: 326.97 Min: 20.27 / Avg: 243.71 / Max: 338.22 Min: 42.4 / Avg: 433.7 / Max: 709.66 Min: 44.38 / Avg: 415.47 / Max: 669.17 Min: 43.88 / Avg: 228.06 / Max: 280.25 Min: 88.74 / Avg: 418.02 / Max: 553.1 Min: 27.6 / Avg: 274.65 / Max: 409.63 Min: 24.77 / Avg: 240.4 / Max: 341.46
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 19.62 26.44 26.58 26.39 26.11 16.37 16.02 37.25 35.57
Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 14 28 42 56 70 SE +/- 0.21, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 50.96 37.82 37.62 37.88 38.29 61.07 62.43 26.84 28.11 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 70 140 210 280 350 Min: 129.68 / Avg: 311.58 / Max: 383.65 Min: 21.84 / Avg: 214.02 / Max: 280.13 Min: 20.86 / Avg: 215.98 / Max: 282.93 Min: 43.73 / Avg: 299.48 / Max: 387.06 Min: 43.36 / Avg: 295.57 / Max: 380.59 Min: 42.94 / Avg: 194.04 / Max: 259.69 Min: 88.54 / Avg: 277.88 / Max: 337.63 Min: 27.44 / Avg: 254.33 / Max: 352.35 Min: 26.97 / Avg: 224.11 / Max: 299.57
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 19.59 26.44 26.49 26.28 26.14 16.35 16.01 37.15 35.66
Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 14 28 42 56 70 SE +/- 0.25, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 51.05 37.81 37.74 38.04 38.25 61.16 62.44 26.91 28.04 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 70 140 210 280 350 Min: 127.66 / Avg: 305.85 / Max: 381.35 Min: 21.82 / Avg: 215.49 / Max: 281.06 Min: 21.81 / Avg: 215.87 / Max: 282.73 Min: 43.83 / Avg: 298.15 / Max: 386.92 Min: 43.26 / Avg: 294.37 / Max: 380.9 Min: 43.14 / Avg: 196.87 / Max: 263.44 Min: 88.87 / Avg: 278.82 / Max: 334.06 Min: 25.45 / Avg: 254.33 / Max: 349.9 Min: 26.32 / Avg: 222.02 / Max: 298.56
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/. 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 2022.10.13 Model: INIVOL and Fluid Structure Interaction Drop Container Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 40 80 120 160 200 SE +/- 0.26, N = 3 SE +/- 0.15, N = 3 SE +/- 0.30, N = 3 SE +/- 0.35, N = 3 SE +/- 0.15, N = 3 SE +/- 0.61, N = 3 SE +/- 0.27, N = 3 SE +/- 0.13, N = 3 SE +/- 0.49, N = 3 147.10 117.49 117.81 88.54 87.78 198.12 138.72 90.85 103.59 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 120 240 360 480 600 Min: 126.3 / Avg: 507.61 / Max: 581.35 Min: 21.79 / Avg: 284 / Max: 322.64 Min: 17.72 / Avg: 283.78 / Max: 322.76 Min: 44.1 / Avg: 537.93 / Max: 664.36 Min: 42.79 / Avg: 535.57 / Max: 645.05 Min: 43.64 / Avg: 272.49 / Max: 286.41 Min: 87.5 / Avg: 509.82 / Max: 549.32 Min: 27.39 / Avg: 358.52 / Max: 409.1 Min: 26.43 / Avg: 292.49 / Max: 336.66
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 40 80 120 160 200 SE +/- 0.15, N = 3 SE +/- 0.47, N = 3 SE +/- 0.28, N = 3 SE +/- 0.60, N = 3 SE +/- 0.29, N = 3 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.52, N = 3 SE +/- 0.35, N = 3 100.39 172.18 172.26 168.25 167.07 95.40 92.60 196.20 189.88
Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 3 6 9 12 15 SE +/- 0.0147, N = 3 SE +/- 0.0160, N = 3 SE +/- 0.0095, N = 3 SE +/- 0.0211, N = 3 SE +/- 0.0103, N = 3 SE +/- 0.0135, N = 3 SE +/- 0.0170, N = 3 SE +/- 0.0133, N = 3 SE +/- 0.0098, N = 3 9.9536 5.8020 5.7994 5.9369 5.9782 10.4761 10.7861 5.0933 5.2631 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 60 120 180 240 300 Min: 131.41 / Avg: 320.21 / Max: 362.39 Min: 21.74 / Avg: 196.31 / Max: 237.17 Min: 20.3 / Avg: 201.78 / Max: 237.23 Min: 42.28 / Avg: 280.29 / Max: 341.84 Min: 43.78 / Avg: 293.85 / Max: 342.43 Min: 42.87 / Avg: 208.09 / Max: 243.75 Min: 87.95 / Avg: 284.65 / Max: 321.37 Min: 27.18 / Avg: 229.16 / Max: 286.36 Min: 26.8 / Avg: 213.26 / Max: 271.38
Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 40 80 120 160 200 SE +/- 1.18, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.27, N = 3 SE +/- 0.35, N = 3 SE +/- 0.15, N = 3 SE +/- 0.10, N = 3 183.88 97.09 89.13 91.94 101.51 161.37 171.91 111.75 119.41 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 140 280 420 560 700 Min: 135.98 / Avg: 455.44 / Max: 581.53 Min: 20.8 / Avg: 256.31 / Max: 322.81 Min: 18.85 / Avg: 296.96 / Max: 381.94 Min: 43.71 / Avg: 579.1 / Max: 790.55 Min: 42.05 / Avg: 491.63 / Max: 653.29 Min: 43.18 / Avg: 199.09 / Max: 279.93 Min: 88.67 / Avg: 373.55 / Max: 564.28 Min: 25.06 / Avg: 301.53 / Max: 394.95 Min: 27.15 / Avg: 267.47 / Max: 335.54
Timed LLVM Compilation This test times how long it takes to build the LLVM compiler stack. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 13.0 Build System: Unix Makefiles Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 70 140 210 280 350 SE +/- 0.98, N = 3 SE +/- 0.36, N = 3 SE +/- 0.82, N = 3 SE +/- 0.46, N = 3 SE +/- 0.41, N = 3 SE +/- 2.85, N = 4 SE +/- 1.43, N = 3 SE +/- 0.24, N = 3 SE +/- 0.11, N = 3 SE +/- 1.36, N = 3 SE +/- 0.19, N = 3 SE +/- 1.50, N = 3 SE +/- 3.72, N = 3 SE +/- 1.62, N = 3 SE +/- 0.32, N = 3 SE +/- 0.91, N = 3 SE +/- 0.30, N = 3 SE +/- 1.42, N = 3 SE +/- 0.65, N = 3 SE +/- 0.08, N = 3 222.62 180.48 178.75 159.93 159.74 274.03 199.54 157.88 158.69 167.35 171.12 223.51 324.08 295.90 201.37 232.08 210.12 244.61 258.75 212.67 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed LLVM Compilation 13.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 128.3 / Avg: 382.32 / Max: 583.63 Min: 21.93 / Avg: 176.32 / Max: 319.65 Min: 20.26 / Avg: 178.95 / Max: 341.1 Min: 44.16 / Avg: 295.39 / Max: 696.58 Min: 42.55 / Avg: 292.88 / Max: 632.93 Min: 43.18 / Avg: 218.97 / Max: 284.37 Min: 83.58 / Avg: 364.78 / Max: 562.97 Min: 51.4 / Avg: 330.89 / Max: 817.6 Min: 52.54 / Avg: 321.74 / Max: 649.54 Min: 25.78 / Avg: 198.89 / Max: 409.53 Min: 27.04 / Avg: 186.68 / Max: 326.25 Min: 111.85 / Avg: 382.45 / Max: 571.1 Min: 58.57 / Avg: 225.58 / Max: 285.31 Min: 57.37 / Avg: 223.86 / Max: 291.08 Min: 73.14 / Avg: 283.86 / Max: 574.83 Min: 34.45 / Avg: 182.02 / Max: 286.79 Min: 76.69 / Avg: 278.68 / Max: 572.92 Min: 36.14 / Avg: 177.59 / Max: 286.48 Min: 38.07 / Avg: 167.11 / Max: 230.75 Min: 81.02 / Avg: 285.86 / Max: 460.4
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.25, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 23.93 41.63 42.87 83.26 82.01 6.67 11.10 109.78 102.38 53.51 50.06 21.84 10.82 12.05 17.41 10.36 16.01 9.74 8.97 15.80 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2K 4K 6K 8K 10K SE +/- 2.48, N = 3 SE +/- 3.40, N = 3 SE +/- 13.95, N = 3 SE +/- 4.40, N = 3 SE +/- 1.39, N = 3 SE +/- 0.44, N = 3 SE +/- 0.56, N = 3 SE +/- 7.95, N = 3 SE +/- 1.33, N = 3 SE +/- 5.11, N = 3 SE +/- 10.61, N = 3 SE +/- 0.33, N = 3 SE +/- 0.24, N = 3 SE +/- 0.30, N = 3 SE +/- 0.77, N = 3 SE +/- 0.12, N = 3 SE +/- 1.76, N = 3 SE +/- 1.50, N = 3 SE +/- 1.20, N = 3 SE +/- 1.87, N = 3 1112.38 2847.39 2880.48 6310.01 6063.84 776.79 1497.62 8084.61 7435.72 3414.62 3426.69 1027.01 522.87 551.20 2336.77 1204.49 2173.49 1060.63 945.34 1904.67 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
BRL-CAD BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
VGR Performance Metric
Xeon Platinum 8380: The test quit with a non-zero exit status. E: ERROR: Could not find the BRL-CAD raytracer
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2K 4K 6K 8K 10K SE +/- 2.45, N = 3 SE +/- 2.02, N = 3 SE +/- 1.00, N = 3 SE +/- 0.65, N = 3 SE +/- 4.40, N = 3 SE +/- 0.17, N = 3 SE +/- 5.10, N = 3 SE +/- 7.19, N = 3 SE +/- 5.49, N = 3 SE +/- 2.77, N = 3 SE +/- 0.56, N = 3 SE +/- 1.08, N = 3 SE +/- 1.88, N = 3 SE +/- 1.45, N = 3 SE +/- 0.36, N = 3 SE +/- 0.31, N = 3 SE +/- 2.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.66, N = 3 SE +/- 4.19, N = 3 2408.31 4165.02 4279.78 8198.28 8090.58 770.45 1488.56 10858.90 9979.66 5329.57 5004.25 2186.18 1118.62 1234.66 2407.71 1195.39 2136.93 1126.90 1029.06 1909.81 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
oneDNN Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.7 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 1.0595 2.119 3.1785 4.238 5.2975 SE +/- 0.003087, N = 7 SE +/- 0.001053, N = 7 SE +/- 0.000790, N = 7 SE +/- 0.002384, N = 15 SE +/- 0.002017, N = 7 SE +/- 0.003312, N = 7 SE +/- 0.001212, N = 7 SE +/- 0.001518, N = 7 SE +/- 0.001543, N = 7 SE +/- 0.001660, N = 7 SE +/- 0.011150, N = 7 SE +/- 0.004466, N = 7 2.127880 0.400531 0.397186 0.352990 0.359965 0.386561 0.441567 0.375184 0.394456 2.387430 4.708860 4.101210 MIN: 2.03 MIN: 2.21 MIN: 4.29 MIN: 3.98 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.7 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 100 200 300 400 500 Min: 138.94 / Avg: 394.75 / Max: 578.91 Min: 21.85 / Avg: 177.85 / Max: 313.85 Min: 19.06 / Avg: 178.46 / Max: 324.09 Min: 41.77 / Avg: 298.43 / Max: 554.93 Min: 39.01 / Avg: 293.79 / Max: 538.93 Min: 51.3 / Avg: 330.35 / Max: 573.45 Min: 53.38 / Avg: 307.49 / Max: 518.93 Min: 25.94 / Avg: 185.55 / Max: 332.52 Min: 24.95 / Avg: 171.78 / Max: 313.76 Min: 113.13 / Avg: 378.9 / Max: 569.7 Min: 60.23 / Avg: 189.39 / Max: 284.75 Min: 60.87 / Avg: 194.24 / Max: 290.92 Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
EPYC 75F3 2P: The test run did not produce a result.
EPYC 75F3: The test run did not produce a result.
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 5K 10K 15K 20K 25K SE +/- 22.44, N = 3 SE +/- 3.17, N = 3 SE +/- 2.84, N = 3 SE +/- 13.29, N = 3 SE +/- 13.90, N = 3 SE +/- 0.09, N = 3 SE +/- 0.84, N = 3 SE +/- 17.72, N = 3 SE +/- 46.02, N = 3 SE +/- 2.97, N = 3 SE +/- 2.62, N = 3 SE +/- 2.01, N = 3 SE +/- 0.47, N = 3 SE +/- 6.16, N = 3 SE +/- 1.68, N = 3 SE +/- 1.99, N = 3 SE +/- 2.09, N = 3 SE +/- 0.60, N = 3 SE +/- 1.31, N = 3 SE +/- 1.67, N = 3 9597.93 8228.70 8512.58 16421.67 16203.41 1811.34 3788.71 21859.02 19812.09 10601.83 9842.93 8569.85 4023.35 4465.68 5735.05 2664.49 5931.55 2756.76 2458.72 5276.79 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
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 Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20K 40K 60K 80K 100K SE +/- 37.10, N = 3 SE +/- 158.23, N = 3 SE +/- 270.04, N = 3 SE +/- 307.17, N = 3 SE +/- 509.24, N = 3 SE +/- 131.90, N = 3 SE +/- 431.65, N = 3 SE +/- 721.42, N = 3 SE +/- 0.00, N = 3 SE +/- 223.70, N = 3 SE +/- 383.40, N = 3 SE +/- 61.83, N = 3 SE +/- 30.05, N = 3 SE +/- 19.57, N = 3 SE +/- 307.17, N = 3 SE +/- 0.00, N = 3 SE +/- 153.43, N = 3 SE +/- 137.18, N = 3 SE +/- 64.10, N = 3 SE +/- 370.23, N = 3 17075.80 31647.30 31335.50 62047.30 60853.90 20316.20 39616.30 88708.80 83966.60 46081.40 42366.70 14994.50 7391.67 8766.09 62354.40 32294.80 44039.50 22333.20 20056.10 39243.60 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
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.
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 SE +/- 0.22, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 82.00 80.62 83.27 158.29 156.27 18.35 37.01 212.43 194.03 103.49 96.87 73.30 38.48 42.69 54.96 27.04 57.38 27.67 24.58 50.20 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200 400 600 800 1000 SE +/- 1.24, N = 3 SE +/- 0.82, N = 3 SE +/- 0.27, N = 3 SE +/- 1.35, N = 3 SE +/- 0.64, N = 3 SE +/- 0.19, N = 3 SE +/- 0.39, N = 3 SE +/- 1.17, N = 3 SE +/- 0.69, N = 3 SE +/- 0.50, N = 3 SE +/- 0.51, N = 3 SE +/- 0.97, N = 3 SE +/- 0.24, N = 3 SE +/- 0.14, N = 3 SE +/- 0.69, N = 3 SE +/- 0.06, N = 3 SE +/- 1.09, N = 3 SE +/- 0.27, N = 3 SE +/- 0.18, N = 3 SE +/- 1.23, N = 3 230.22 449.76 470.91 808.16 792.53 89.82 174.06 1037.28 973.45 590.08 547.98 205.84 123.56 140.24 275.03 140.19 254.03 131.27 116.91 223.15 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20K 40K 60K 80K 100K SE +/- 84.38, N = 3 SE +/- 0.00, N = 3 SE +/- 219.20, N = 3 SE +/- 438.43, N = 3 SE +/- 696.55, N = 3 SE +/- 316.90, N = 3 SE +/- 526.29, N = 3 SE +/- 1025.23, N = 3 SE +/- 460.77, N = 3 SE +/- 277.50, N = 3 SE +/- 626.96, N = 3 SE +/- 82.76, N = 3 SE +/- 40.72, N = 3 SE +/- 0.00, N = 3 SE +/- 610.89, N = 3 SE +/- 364.13, N = 3 SE +/- 160.07, N = 3 SE +/- 85.47, N = 3 SE +/- 183.61, N = 3 SE +/- 133.20, N = 3 19582.50 37485.10 37265.90 74093.30 71171.80 22500.10 43745.30 98935.00 93531.70 51341.30 47485.20 17349.30 8603.52 10092.10 66651.40 34048.40 44983.20 23153.20 20855.80 41026.90 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 EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 39.09 191.79 192.09 175.59 169.26 113.78 107.91 187.80 188.91 208.69 202.01 35.56 35.30 40.15 152.74 162.65 117.40 122.94 108.59 102.60 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASKAP 1.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 128.65 / Avg: 501.03 / Max: 579.76 Min: 22.18 / Avg: 195.45 / Max: 299.88 Min: 20.02 / Avg: 194 / Max: 319.13 Min: 43.7 / Avg: 421.98 / Max: 655.85 Min: 42.81 / Avg: 420.49 / Max: 631.59 Min: 43.56 / Avg: 197.75 / Max: 268.97 Min: 88.38 / Avg: 405.39 / Max: 544.09 Min: 54.76 / Avg: 526.81 / Max: 812.57 Min: 52.99 / Avg: 495.12 / Max: 670.39 Min: 26.68 / Avg: 246.01 / Max: 401.53 Min: 27.02 / Avg: 235.06 / Max: 330.27 Min: 114.43 / Avg: 487.9 / Max: 567.21 Min: 59.2 / Avg: 243.75 / Max: 284.88 Min: 62.72 / Avg: 251.36 / Max: 288.53 Min: 75.11 / Avg: 436.36 / Max: 556.83 Min: 34.56 / Avg: 209.34 / Max: 271.48 Min: 77.23 / Avg: 383.18 / Max: 560.93 Min: 36.11 / Avg: 188.33 / Max: 279.43 Min: 38.11 / Avg: 192.06 / Max: 224.14 Min: 82.63 / Avg: 399.87 / Max: 456.42
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 3.0 Algorithm: SHA256 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 60000M 120000M 180000M 240000M 300000M SE +/- 282889949.77, N = 3 SE +/- 88674415.22, N = 3 SE +/- 113242158.65, N = 3 SE +/- 540081125.64, N = 3 SE +/- 145742816.61, N = 3 SE +/- 87203247.94, N = 3 SE +/- 4248731.03, N = 3 SE +/- 281531389.95, N = 3 SE +/- 584082922.27, N = 3 SE +/- 91643095.12, N = 3 SE +/- 380252901.09, N = 3 SE +/- 23310559.35, N = 3 SE +/- 42250028.06, N = 3 SE +/- 65833761.08, N = 3 SE +/- 112290036.56, N = 3 SE +/- 66727027.10, N = 3 SE +/- 22229383.18, N = 3 SE +/- 10744204.26, N = 3 SE +/- 28092099.50, N = 3 SE +/- 401898644.45, N = 3 57267221813 103690964737 103745920213 205338727447 205408037813 45499341367 90974009323 284499818607 251511273853 143163470057 125979444607 51417167977 25151039647 28538883087 146456411990 74013930600 148797141130 74358249567 65206014577 128616636900 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.0 Algorithm: SHA256 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 80M 160M 240M 320M 400M 108841118.53 338684812.02 323674263.25 305453461.58 327935256.48 170831087.71 176556662.45 364018269.52 393970052.62 366567582.34 394313977.85 98800981.68 96726680.36 107679709.78 271280767.13 278365751.00 294464855.67 295613823.05 289517518.41 285018945.31 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 125.15 / Avg: 526.15 / Max: 581.23 Min: 21.93 / Avg: 306.16 / Max: 349.46 Min: 21.46 / Avg: 320.53 / Max: 378.1 Min: 43.81 / Avg: 672.24 / Max: 782 Min: 43.45 / Avg: 626.37 / Max: 697.99 Min: 43.62 / Avg: 266.34 / Max: 286.58 Min: 87.24 / Avg: 515.27 / Max: 550.57 Min: 54.32 / Avg: 781.55 / Max: 819.43 Min: 52.37 / Avg: 638.4 / Max: 705.78 Min: 26.7 / Avg: 390.55 / Max: 409.42 Min: 24.52 / Avg: 319.49 / Max: 355.12 Min: 116.52 / Avg: 520.41 / Max: 569.12 Min: 57.89 / Avg: 260.02 / Max: 284.3 Min: 59.24 / Avg: 265.03 / Max: 290.49 Min: 73.29 / Avg: 539.87 / Max: 574.58 Min: 34.53 / Avg: 265.89 / Max: 286.58 Min: 76.74 / Avg: 505.31 / Max: 550.19 Min: 36.11 / Avg: 251.54 / Max: 273.58 Min: 38.6 / Avg: 225.22 / Max: 230.29 Min: 80.92 / Avg: 451.26 / Max: 460.57
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/. 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 2022.10.13 Model: Rubber O-Ring Seal Installation Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 20 40 60 80 100 SE +/- 0.58, N = 12 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.09, N = 3 SE +/- 0.27, N = 3 SE +/- 1.42, N = 3 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 82.63 50.14 50.28 79.99 80.06 68.30 99.41 61.52 66.81 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 100 200 300 400 500 Min: 130.74 / Avg: 487.91 / Max: 580.28 Min: 22.22 / Avg: 253.58 / Max: 299.53 Min: 20.69 / Avg: 251.94 / Max: 303.14 Min: 43.28 / Avg: 500.83 / Max: 574.85 Min: 43.49 / Avg: 501.89 / Max: 574.15 Min: 44.16 / Avg: 244.68 / Max: 276.22 Min: 88.77 / Avg: 461.79 / Max: 530.88 Min: 27.41 / Avg: 332.85 / Max: 391.82 Min: 26.51 / Avg: 281.67 / Max: 324.07
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 3.2.3 Time To Compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 14 28 42 56 70 SE +/- 0.27, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.38, N = 4 SE +/- 0.31, N = 3 SE +/- 0.10, N = 3 SE +/- 0.28, N = 3 SE +/- 0.38, N = 4 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.18, N = 3 SE +/- 0.22, N = 3 SE +/- 0.20, N = 3 SE +/- 0.14, N = 3 SE +/- 0.30, N = 3 SE +/- 0.13, N = 3 SE +/- 0.53, N = 3 SE +/- 0.12, N = 3 SE +/- 0.13, N = 3 SE +/- 0.53, N = 3 45.77 34.53 34.20 32.97 32.60 52.24 40.67 33.34 33.78 32.45 33.26 44.68 63.05 59.20 38.99 42.81 43.07 45.40 47.92 43.53 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Godot Game Engine Compilation 3.2.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 126.52 / Avg: 356.72 / Max: 568.9 Min: 21.98 / Avg: 161.7 / Max: 320.92 Min: 20.64 / Avg: 164.78 / Max: 354.01 Min: 43.66 / Avg: 267.38 / Max: 681.44 Min: 42.78 / Avg: 264.78 / Max: 637.4 Min: 42.68 / Avg: 200.86 / Max: 277.93 Min: 88.22 / Avg: 328.12 / Max: 556.53 Min: 52.8 / Avg: 296.56 / Max: 734.53 Min: 54.4 / Avg: 287.63 / Max: 576.15 Min: 27.17 / Avg: 181.35 / Max: 409.9 Min: 26.62 / Avg: 171.05 / Max: 335.83 Min: 106.83 / Avg: 352.3 / Max: 567.34 Min: 55.69 / Avg: 206.41 / Max: 284.72 Min: 55.18 / Avg: 204.57 / Max: 291.04 Min: 73.92 / Avg: 270.73 / Max: 574.51 Min: 34.17 / Avg: 171.46 / Max: 286.64 Min: 76.85 / Avg: 261.48 / Max: 565.75 Min: 35.75 / Avg: 170.03 / Max: 283.92 Min: 37.52 / Avg: 157.55 / Max: 228.8 Min: 81.69 / Avg: 265.06 / Max: 458.38
Neural Magic DeepSparse OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 20 40 60 80 100 SE +/- 0.39, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.23, N = 3 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.21, N = 3 51.59 89.03 89.10 88.05 88.20 51.46 49.04 89.50 87.52
Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 19.38 11.23 11.22 11.35 11.33 19.42 20.38 11.17 11.42 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 70 140 210 280 350 Min: 131.15 / Avg: 308.01 / Max: 368.32 Min: 21.09 / Avg: 186.65 / Max: 255.13 Min: 20.89 / Avg: 194.54 / Max: 254.32 Min: 43.69 / Avg: 282.06 / Max: 358.8 Min: 43.67 / Avg: 280.56 / Max: 359.94 Min: 42.18 / Avg: 189.09 / Max: 251.9 Min: 88.77 / Avg: 271.99 / Max: 341.36 Min: 26.93 / Avg: 212.22 / Max: 309.2 Min: 24.87 / Avg: 201.01 / Max: 287.34
Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 2 4 6 8 10 SE +/- 0.0151, N = 3 SE +/- 0.0046, N = 3 SE +/- 0.0116, N = 3 SE +/- 0.0077, N = 3 SE +/- 0.0072, N = 3 SE +/- 0.0078, N = 3 SE +/- 0.0024, N = 3 SE +/- 0.0062, N = 3 SE +/- 0.0115, N = 3 4.4379 3.9577 3.9067 3.9080 3.8941 6.9706 7.0245 5.1923 5.1998 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 70 140 210 280 350 Min: 124.99 / Avg: 333.28 / Max: 371.53 Min: 21.54 / Avg: 188.1 / Max: 213.23 Min: 21.26 / Avg: 189.39 / Max: 214.52 Min: 24.32 / Avg: 280.37 / Max: 319.3 Min: 42.7 / Avg: 272.68 / Max: 318.9 Min: 42.82 / Avg: 205.6 / Max: 241.96 Min: 88.83 / Avg: 292.35 / Max: 321.97 Min: 27.34 / Avg: 206.78 / Max: 238.73 Min: 25.49 / Avg: 200.64 / Max: 231.52
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 60 120 180 240 300 SE +/- 0.77, N = 3 SE +/- 0.30, N = 3 SE +/- 0.76, N = 3 SE +/- 0.50, N = 3 SE +/- 0.47, N = 3 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 SE +/- 0.23, N = 3 SE +/- 0.43, N = 3 224.92 252.55 255.83 255.74 256.65 143.41 142.28 192.52 192.24
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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 9 18 27 36 45 39.47 22.84 22.85 22.29 21.93 28.29 24.44 31.67 23.19 25.94 30.94 37.18 35.64 30.64 28.94 31.56 34.49 -lfoamToVTK -ldynamicMesh -lfileFormats -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfoamToVTK -ldynamicMesh -lfileFormats -lfoamToVTK -ldynamicMesh -lfileFormats -lfoamToVTK -ldynamicMesh -lfileFormats -lfoamToVTK -ldynamicMesh -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Medium Mesh Size - Mesh Time Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 40 80 120 160 200 175.08 102.78 110.84 106.44 109.42 143.31 131.09 129.44 120.42 131.29 156.83 177.06 173.54 147.74 126.71 154.21 161.85 -lfoamToVTK -ldynamicMesh -lfileFormats -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfiniteVolume -lmeshTools -lparallel -lregionModels -lfoamToVTK -ldynamicMesh -lfileFormats -lfoamToVTK -ldynamicMesh -lfileFormats -lfoamToVTK -ldynamicMesh -lfileFormats -lfoamToVTK -ldynamicMesh -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -llagrangian -lgenericPatchFields -lOpenFOAM -ldl -lm
Etcpak Etcpack is the self-proclaimed "fastest ETC compressor on the planet" with focused on providing open-source, very fast ETC and S3 texture compression support. The test profile uses a 8K x 8K game texture as a sample input. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Mpx/s, More Is Better Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: ETC2 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2K 4K 6K 8K 10K SE +/- 42.29, N = 8 SE +/- 16.14, N = 9 SE +/- 18.91, N = 9 SE +/- 28.22, N = 9 SE +/- 26.45, N = 9 SE +/- 8.39, N = 9 SE +/- 18.81, N = 9 SE +/- 47.66, N = 9 SE +/- 70.12, N = 9 SE +/- 79.32, N = 15 SE +/- 97.61, N = 15 SE +/- 44.69, N = 8 SE +/- 4.50, N = 9 SE +/- 4.01, N = 8 SE +/- 24.69, N = 8 SE +/- 7.06, N = 9 SE +/- 38.74, N = 8 SE +/- 10.29, N = 9 SE +/- 12.27, N = 9 SE +/- 34.64, N = 8 5779.84 8966.41 8976.89 8825.79 8902.85 7919.46 7726.46 9232.75 9305.67 9335.76 9257.88 6238.49 6170.39 5532.15 6926.20 6990.00 6678.40 6689.61 6694.85 6628.31 1. (CXX) g++ options: -O3 -march=native -std=c++11 -lpthread Mpx/s Per Watt
OpenBenchmarking.org Mpx/s Per Watt, More Is Better Etcpak 1.0 Benchmark: Multi-Threaded - Configuration: ETC2 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30 60 90 120 150 23.81 122.44 126.37 66.84 67.13 72.17 38.87 61.21 60.77 111.96 110.63 28.29 45.23 40.91 44.23 81.19 40.01 72.67 69.89 37.48 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Etcpak 1.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 70 140 210 280 350 Min: 133.57 / Avg: 242.75 / Max: 380.52 Min: 21.22 / Avg: 73.23 / Max: 178.03 Min: 20.02 / Avg: 71.04 / Max: 178.42 Min: 42.23 / Avg: 132.05 / Max: 279.05 Min: 42.7 / Avg: 132.61 / Max: 273.97 Min: 41.96 / Avg: 109.74 / Max: 254.38 Min: 88.74 / Avg: 198.78 / Max: 379.25 Min: 51.75 / Avg: 150.85 / Max: 315.02 Min: 52.38 / Avg: 153.14 / Max: 313.59 Min: 26.68 / Avg: 83.38 / Max: 204.87 Min: 24.69 / Avg: 83.68 / Max: 207.27 Min: 109.06 / Avg: 220.53 / Max: 355.46 Min: 57.27 / Avg: 136.44 / Max: 264.14 Min: 59.92 / Avg: 135.23 / Max: 243.45 Min: 74.59 / Avg: 156.59 / Max: 285.62 Min: 33.87 / Avg: 86.09 / Max: 179.73 Min: 77.16 / Avg: 166.93 / Max: 303.15 Min: 35.69 / Avg: 92.06 / Max: 192.91 Min: 37.35 / Avg: 95.79 / Max: 200.16 Min: 81.05 / Avg: 176.86 / Max: 324.67
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 21.2 Time To Compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 SE +/- 2.02, N = 3 SE +/- 1.10, N = 12 SE +/- 1.25, N = 3 SE +/- 0.87, N = 3 SE +/- 1.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.43, N = 3 SE +/- 0.87, N = 3 SE +/- 0.76, N = 3 SE +/- 0.21, N = 3 SE +/- 2.00, N = 3 SE +/- 1.75, N = 6 SE +/- 0.31, N = 3 SE +/- 1.27, N = 3 SE +/- 0.34, N = 3 SE +/- 1.36, N = 12 SE +/- 0.84, N = 3 SE +/- 2.33, N = 3 SE +/- 2.24, N = 3 SE +/- 1.63, N = 3 183.95 150.77 148.97 134.83 135.99 188.03 157.73 135.26 137.08 141.44 146.31 183.40 225.74 211.95 154.93 178.79 161.44 188.63 196.93 162.23 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Gem5 Compilation 21.2 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 126.27 / Avg: 315.66 / Max: 582.29 Min: 21.77 / Avg: 146.97 / Max: 320.83 Min: 17.95 / Avg: 150.17 / Max: 345 Min: 43.43 / Avg: 263.73 / Max: 692.37 Min: 43.16 / Avg: 259.79 / Max: 642.48 Min: 43.06 / Avg: 196.59 / Max: 281.55 Min: 88.92 / Avg: 304.43 / Max: 558.29 Min: 53.27 / Avg: 294.05 / Max: 823.2 Min: 52.01 / Avg: 284.85 / Max: 657.67 Min: 26.82 / Avg: 164.82 / Max: 409.76 Min: 27.27 / Avg: 151.58 / Max: 329.9 Min: 111.08 / Avg: 317.74 / Max: 570.63 Min: 55.07 / Avg: 197.36 / Max: 285.17 Min: 56.06 / Avg: 191.54 / Max: 290.93 Min: 75.65 / Avg: 240.69 / Max: 574.01 Min: 32.85 / Avg: 149.99 / Max: 286.92 Min: 77.16 / Avg: 245.03 / Max: 569.41 Min: 35.78 / Avg: 149.88 / Max: 285.66 Min: 37.74 / Avg: 140.02 / Max: 228.85 Min: 81.06 / Avg: 242.96 / Max: 458.88
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 5.73 6.65 6.60 6.65 6.66 4.67 4.66 6.57 6.49 6.55 6.57 6.10 6.10 5.69 4.08 4.08 4.06 4.04 4.29 4.29 1. (CXX) g++ options: -O3 GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: TopTweet Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0207 0.0414 0.0621 0.0828 0.1035 0.028 0.092 0.091 0.038 0.039 0.056 0.029 0.032 0.032 0.074 0.074 0.031 0.060 0.055 0.031 0.062 0.029 0.057 0.057 0.029 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 135.01 / Avg: 208.1 / Max: 223.39 Min: 21.7 / Avg: 72.34 / Max: 77.99 Min: 20.36 / Avg: 72.85 / Max: 78.09 Min: 43.23 / Avg: 174.16 / Max: 183.18 Min: 43.09 / Avg: 172.71 / Max: 182.17 Min: 42.05 / Avg: 83.19 / Max: 87.82 Min: 88.41 / Avg: 160.2 / Max: 168.54 Min: 53.22 / Avg: 205.68 / Max: 215.31 Min: 52.12 / Avg: 204.52 / Max: 214.64 Min: 26.7 / Avg: 88.44 / Max: 92.49 Min: 25.31 / Avg: 88.4 / Max: 92.33 Min: 116.92 / Avg: 193.88 / Max: 210.78 Min: 59.85 / Avg: 102.43 / Max: 106 Min: 57.49 / Avg: 104.12 / Max: 111.34 Min: 73.93 / Avg: 132.45 / Max: 138.68 Min: 34.04 / Avg: 65.71 / Max: 67.79 Min: 76.57 / Avg: 138.59 / Max: 145.56 Min: 35.48 / Avg: 70.67 / Max: 72.8 Min: 37.39 / Avg: 74.72 / Max: 78.7 Min: 81.04 / Avg: 149 / Max: 157.2
Neural Magic DeepSparse Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 13 26 39 52 65 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.11, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 48.47 37.89 36.35 36.73 39.55 59.31 59.72 42.29 47.25 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 120 240 360 480 600 Min: 125.11 / Avg: 487.54 / Max: 581.39 Min: 21.19 / Avg: 255.49 / Max: 292.65 Min: 21.29 / Avg: 286.24 / Max: 328.41 Min: 43.92 / Avg: 578.95 / Max: 691.46 Min: 43.69 / Avg: 507.86 / Max: 597.89 Min: 43.03 / Avg: 240.1 / Max: 279.77 Min: 89.83 / Avg: 474.64 / Max: 562.58 Min: 26.89 / Avg: 323.54 / Max: 376.67 Min: 26.48 / Avg: 264.19 / Max: 303.66
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 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 5.69 6.95 6.91 6.93 6.92 4.83 4.84 6.87 6.86 6.83 6.82 6.10 6.04 5.69 4.24 4.24 4.24 4.24 4.45 4.45 1. (CXX) g++ options: -O3 GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0216 0.0432 0.0648 0.0864 0.108 0.027 0.096 0.094 0.040 0.040 0.058 0.030 0.033 0.033 0.077 0.077 0.031 0.059 0.055 0.032 0.064 0.030 0.060 0.060 0.030 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 134.89 / Avg: 208.56 / Max: 222.12 Min: 21.35 / Avg: 72.28 / Max: 75.55 Min: 19.85 / Avg: 73.14 / Max: 78.46 Min: 42.81 / Avg: 174.36 / Max: 182.53 Min: 39.24 / Avg: 172.08 / Max: 182.29 Min: 42.24 / Avg: 83.77 / Max: 86.35 Min: 88.47 / Avg: 160.49 / Max: 168.18 Min: 52.2 / Avg: 205.81 / Max: 215.38 Min: 52.59 / Avg: 205.38 / Max: 214.76 Min: 26.54 / Avg: 88.2 / Max: 92.25 Min: 25.29 / Avg: 88.54 / Max: 92.5 Min: 109.76 / Avg: 194.73 / Max: 209.65 Min: 60.21 / Avg: 102.22 / Max: 105.67 Min: 57.86 / Avg: 103.52 / Max: 107.03 Min: 73.67 / Avg: 132.74 / Max: 139.23 Min: 33.88 / Avg: 65.85 / Max: 69.16 Min: 76.83 / Avg: 139.1 / Max: 145.95 Min: 17.91 / Avg: 70.7 / Max: 72.89 Min: 37.49 / Avg: 74.76 / Max: 77.14 Min: 81.08 / Avg: 148.86 / Max: 156.14
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1.287 2.574 3.861 5.148 6.435 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 +/- 0.00, N = 3 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 +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 4.73 5.70 5.72 5.72 5.70 4.05 4.06 5.67 5.67 5.66 5.67 5.03 5.03 4.74 3.54 3.56 3.54 3.56 3.74 3.72 1. (CXX) g++ options: -O3 GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: PartialTweets Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0178 0.0356 0.0534 0.0712 0.089 0.023 0.079 0.079 0.033 0.033 0.049 0.025 0.028 0.028 0.064 0.064 0.026 0.049 0.046 0.027 0.054 0.025 0.050 0.050 0.025 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 136.48 / Avg: 206.98 / Max: 218.51 Min: 21.83 / Avg: 72.09 / Max: 75.77 Min: 20.16 / Avg: 72.06 / Max: 75.39 Min: 43.35 / Avg: 173.99 / Max: 182.31 Min: 42.54 / Avg: 174.22 / Max: 182.38 Min: 42.1 / Avg: 83.39 / Max: 87.6 Min: 89.42 / Avg: 160.85 / Max: 168.85 Min: 53.33 / Avg: 205.68 / Max: 214.9 Min: 53.42 / Avg: 205.12 / Max: 214.45 Min: 26.11 / Avg: 88.42 / Max: 92.3 Min: 26.95 / Avg: 88.22 / Max: 92.15 Min: 102.64 / Avg: 192.09 / Max: 202.72 Min: 60.74 / Avg: 101.98 / Max: 106.12 Min: 57.37 / Avg: 103.16 / Max: 106.24 Min: 74.59 / Avg: 132.51 / Max: 138.73 Min: 34.03 / Avg: 65.87 / Max: 67.93 Min: 77.57 / Avg: 139.57 / Max: 146.21 Min: 35.7 / Avg: 70.78 / Max: 72.83 Min: 37.42 / Avg: 74.83 / Max: 77.17 Min: 83.15 / Avg: 149.4 / Max: 157.5
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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 UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.28, N = 4 SE +/- 0.29, N = 4 SE +/- 0.36, N = 4 SE +/- 2.78, N = 4 SE +/- 0.31, N = 3 SE +/- 0.07, N = 3 SE +/- 0.31, N = 4 SE +/- 0.17, N = 4 SE +/- 0.09, N = 4 SE +/- 2.60, N = 4 SE +/- 1.94, N = 4 SE +/- 0.29, N = 3 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 71.4 95.9 95.9 95.6 93.4 68.1 68.1 94.4 94.9 94.5 92.2 77.4 78.0 72.6 59.9 59.8 59.5 59.6 62.8 62.5 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm UE Mb/s Per Watt
OpenBenchmarking.org UE Mb/s Per Watt, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.3373 0.6746 1.0119 1.3492 1.6865 0.357 1.499 1.478 0.631 0.613 0.889 0.455 0.523 0.531 1.225 1.182 0.420 0.817 0.747 0.478 0.978 0.451 0.906 0.906 0.446 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN 22.04.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 132.51 / Avg: 199.83 / Max: 213.96 Min: 21.7 / Avg: 63.98 / Max: 76.76 Min: 17.85 / Avg: 64.89 / Max: 76.88 Min: 43.36 / Avg: 151.54 / Max: 180.98 Min: 42.34 / Avg: 152.26 / Max: 180.93 Min: 42.08 / Avg: 76.57 / Max: 85.03 Min: 88.29 / Avg: 149.79 / Max: 166.37 Min: 51.89 / Avg: 180.33 / Max: 213.74 Min: 51.87 / Avg: 178.83 / Max: 213.15 Min: 26.52 / Avg: 77.16 / Max: 90.83 Min: 26.8 / Avg: 78.01 / Max: 91.02 Min: 114.03 / Avg: 184.25 / Max: 201.15 Min: 54.46 / Avg: 95.49 / Max: 103.41 Min: 61.29 / Avg: 97.25 / Max: 104.24 Min: 74.04 / Avg: 125.28 / Max: 137.44 Min: 33.81 / Avg: 61.15 / Max: 66.67 Min: 76.51 / Avg: 131.91 / Max: 145.35 Min: 35.54 / Avg: 65.76 / Max: 71.32 Min: 37.15 / Avg: 69.35 / Max: 75.78 Min: 80.38 / Avg: 140.11 / Max: 151.5
Node.js Express HTTP Load Test A Node.js Express server with a Node-based loadtest client for facilitating HTTP benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2K 4K 6K 8K 10K SE +/- 32.04, N = 4 SE +/- 39.98, N = 4 SE +/- 27.20, N = 4 SE +/- 74.87, N = 5 SE +/- 36.28, N = 4 SE +/- 9.06, N = 3 SE +/- 58.66, N = 3 SE +/- 73.54, N = 6 SE +/- 62.92, N = 8 SE +/- 17.64, N = 4 SE +/- 11.05, N = 4 SE +/- 48.12, N = 4 SE +/- 30.67, N = 4 SE +/- 18.16, N = 4 SE +/- 43.93, N = 15 SE +/- 16.70, N = 3 SE +/- 40.61, N = 15 SE +/- 19.43, N = 3 SE +/- 14.88, N = 3 SE +/- 42.80, N = 15 6245 7846 7884 7500 7453 5971 5280 7474 7508 7780 7829 6778 7085 6671 4899 5175 4912 5236 5438 5019 Requests Per Second Per Watt
OpenBenchmarking.org Requests Per Second Per Watt, More Is Better Node.js Express HTTP Load Test Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30 60 90 120 150 29.78 118.71 117.73 49.27 49.72 68.22 28.39 41.33 41.50 96.98 97.18 35.36 65.02 61.04 33.75 77.82 31.93 73.06 71.08 29.98 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Node.js Express HTTP Load Test CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 136.22 / Avg: 209.7 / Max: 224.65 Min: 21.86 / Avg: 66.1 / Max: 82.72 Min: 21 / Avg: 66.97 / Max: 83.08 Min: 43.73 / Avg: 152.22 / Max: 187.39 Min: 43.7 / Avg: 149.91 / Max: 187.2 Min: 42.69 / Avg: 87.53 / Max: 104.35 Min: 88.72 / Avg: 185.97 / Max: 215.21 Min: 53.35 / Avg: 180.83 / Max: 221.58 Min: 49.8 / Avg: 180.93 / Max: 221.24 Min: 26 / Avg: 80.23 / Max: 97.72 Min: 26.38 / Avg: 80.56 / Max: 98.17 Min: 110.5 / Avg: 191.67 / Max: 211.66 Min: 58.19 / Avg: 108.96 / Max: 128.41 Min: 59.69 / Avg: 109.29 / Max: 124.42 Min: 75.29 / Avg: 145.16 / Max: 172.68 Min: 34.2 / Avg: 66.5 / Max: 74.63 Min: 76.85 / Avg: 153.86 / Max: 186.41 Min: 35.71 / Avg: 71.66 / Max: 82.39 Min: 37.77 / Avg: 76.51 / Max: 87.64 Min: 80.22 / Avg: 167.42 / Max: 201.41
Neural Magic DeepSparse Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 40 80 120 160 200 SE +/- 0.02, N = 3 SE +/- 0.23, N = 3 SE +/- 0.18, N = 3 SE +/- 0.41, N = 3 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 SE +/- 0.23, N = 3 SE +/- 0.50, N = 3 SE +/- 0.55, N = 3 181.75 121.43 113.41 114.56 125.42 155.47 159.54 142.33 151.40 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 140 280 420 560 700 Min: 132.36 / Avg: 420.89 / Max: 580.87 Min: 22.03 / Avg: 225.38 / Max: 316.16 Min: 19.98 / Avg: 261.67 / Max: 370.06 Min: 40.88 / Avg: 523.3 / Max: 776.83 Min: 42.76 / Avg: 449.87 / Max: 641.95 Min: 42.81 / Avg: 201.85 / Max: 279.68 Min: 89.23 / Avg: 400.04 / Max: 561.58 Min: 26.87 / Avg: 264.06 / Max: 373.36 Min: 24.61 / Avg: 239.01 / Max: 327.95
Build2 This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.28, N = 3 SE +/- 0.20, N = 3 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.23, N = 3 SE +/- 0.23, N = 3 SE +/- 0.05, N = 3 SE +/- 0.20, N = 3 SE +/- 0.19, N = 3 SE +/- 0.27, N = 3 SE +/- 0.21, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 64.55 50.86 50.71 48.49 48.32 64.89 56.16 48.73 48.78 49.53 50.60 62.48 75.89 74.72 59.37 63.13 60.86 65.56 67.29 60.77 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Build2 0.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 128.49 / Avg: 319.13 / Max: 582.29 Min: 21.84 / Avg: 137.39 / Max: 317.73 Min: 20.81 / Avg: 138.81 / Max: 343.42 Min: 42.38 / Avg: 243.3 / Max: 696.36 Min: 42.34 / Avg: 241.21 / Max: 629.98 Min: 42.54 / Avg: 180.99 / Max: 278.12 Min: 88.66 / Avg: 285.56 / Max: 561.36 Min: 51.46 / Avg: 274.49 / Max: 816.18 Min: 49.85 / Avg: 267.53 / Max: 636.07 Min: 27.07 / Avg: 153.41 / Max: 409.44 Min: 26.87 / Avg: 144.89 / Max: 327.26 Min: 109.61 / Avg: 313.27 / Max: 570.73 Min: 57.1 / Avg: 196.35 / Max: 285.28 Min: 58.01 / Avg: 189.88 / Max: 290.84 Min: 73.78 / Avg: 226.18 / Max: 573.11 Min: 34.1 / Avg: 138.72 / Max: 286.59 Min: 76.6 / Avg: 226.21 / Max: 572.06 Min: 35.74 / Avg: 138.39 / Max: 286.64 Min: 37.43 / Avg: 134.69 / Max: 230.41 Min: 80.62 / Avg: 232.51 / Max: 462.15
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 21.0 Time To Compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.15, N = 3 SE +/- 0.19, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 26.83 20.79 20.57 19.80 19.81 26.16 22.75 19.94 20.25 20.38 20.77 26.09 30.80 31.01 24.54 26.38 24.95 26.87 27.75 24.62 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Mesa Compilation 21.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 130.96 / Avg: 293.77 / Max: 581.85 Min: 21.76 / Avg: 124.79 / Max: 325.4 Min: 19.47 / Avg: 127.58 / Max: 356.71 Min: 43.85 / Avg: 213.06 / Max: 740.35 Min: 40.4 / Avg: 219.12 / Max: 656.04 Min: 43.23 / Avg: 169.47 / Max: 281.3 Min: 89.15 / Avg: 264.09 / Max: 554.49 Min: 51.94 / Avg: 249.1 / Max: 810.56 Min: 52.15 / Avg: 242.2 / Max: 672.46 Min: 26.93 / Avg: 137.93 / Max: 409.56 Min: 25.33 / Avg: 119.96 / Max: 335.44 Min: 107.91 / Avg: 291.37 / Max: 569.88 Min: 60.44 / Avg: 185.96 / Max: 284.57 Min: 57.56 / Avg: 178.5 / Max: 290.45 Min: 75.84 / Avg: 202.82 / Max: 572.96 Min: 34.4 / Avg: 124.62 / Max: 286.6 Min: 76.66 / Avg: 206.95 / Max: 572.74 Min: 36.06 / Avg: 128.69 / Max: 286.4 Min: 37.89 / Avg: 125.57 / Max: 230.1 Min: 81.36 / Avg: 213.53 / Max: 460.09
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 0.1193 0.2386 0.3579 0.4772 0.5965 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 0.41 0.53 0.53 0.52 0.52 0.41 0.48 0.52 0.52 0.44 0.34 0.35 0.43 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better AOM AV1 3.5 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 0.0009 0.0018 0.0027 0.0036 0.0045 0.001 0.004 0.004 0.002 0.002 0.002 0.002 0.002 0.002 0.001 0.002 0.002 0.002 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better AOM AV1 3.5 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 100 200 300 400 500 Min: 130.88 / Avg: 328.33 / Max: 581.04 Min: 22.2 / Avg: 141.36 / Max: 326.15 Min: 19.56 / Avg: 145.67 / Max: 372.16 Min: 41.58 / Avg: 244.6 / Max: 504.29 Min: 43.44 / Avg: 245.7 / Max: 499.03 Min: 42.61 / Avg: 179.52 / Max: 281.33 Min: 88.42 / Avg: 295.47 / Max: 563.48 Min: 50.86 / Avg: 278.38 / Max: 538.25 Min: 52.32 / Avg: 273.29 / Max: 497.78 Min: 110.98 / Avg: 321.55 / Max: 569.62 Min: 58.92 / Avg: 197.9 / Max: 283.85 Min: 60.17 / Avg: 194.47 / Max: 290.05 Min: 73.58 / Avg: 230.03 / Max: 492.33
Neural Magic DeepSparse Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.17, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.26, N = 3 88.67 61.38 57.40 58.53 64.12 78.86 81.01 71.96 76.60 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 120 240 360 480 600 Min: 136.56 / Avg: 467.32 / Max: 555.96 Min: 22.07 / Avg: 240.74 / Max: 285.36 Min: 20.82 / Avg: 280.43 / Max: 336.45 Min: 44.86 / Avg: 576.77 / Max: 703.86 Min: 42.42 / Avg: 480.63 / Max: 585.47 Min: 43.01 / Avg: 235.69 / Max: 281.09 Min: 89.35 / Avg: 461.82 / Max: 564.86 Min: 27.31 / Avg: 282.47 / Max: 341.11 Min: 26.67 / Avg: 253.5 / Max: 299.43
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/. 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 2022.10.13 Model: Bird Strike on Windshield Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 40 80 120 160 200 SE +/- 0.94, N = 3 SE +/- 0.17, N = 3 SE +/- 0.31, N = 3 SE +/- 0.19, N = 3 SE +/- 0.22, N = 3 SE +/- 0.40, N = 3 SE +/- 1.23, N = 3 SE +/- 0.79, N = 3 SE +/- 0.70, N = 3 141.93 109.32 108.19 166.46 165.94 141.46 128.95 111.28 119.94 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 120 240 360 480 600 Min: 132.69 / Avg: 519.73 / Max: 581.19 Min: 21.52 / Avg: 287.91 / Max: 331.05 Min: 18.8 / Avg: 288.2 / Max: 325.45 Min: 44.35 / Avg: 557.21 / Max: 695.92 Min: 44.73 / Avg: 549.4 / Max: 677.34 Min: 43.17 / Avg: 267.53 / Max: 286.44 Min: 88.72 / Avg: 500.4 / Max: 550.63 Min: 27.43 / Avg: 365.17 / Max: 406.32 Min: 26.8 / Avg: 307.92 / Max: 344.54
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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 SE +/- 1.53, N = 3 SE +/- 0.88, N = 3 SE +/- 0.79, N = 3 SE +/- 2.27, N = 3 SE +/- 1.62, N = 3 SE +/- 2.49, N = 3 SE +/- 1.36, N = 3 SE +/- 1.36, N = 3 SE +/- 1.32, N = 3 SE +/- 0.08, N = 3 SE +/- 1.13, N = 3 SE +/- 0.48, N = 3 SE +/- 0.65, N = 3 SE +/- 0.26, N = 3 SE +/- 1.81, N = 3 SE +/- 1.00, N = 3 SE +/- 0.72, N = 3 SE +/- 2.62, N = 3 SE +/- 1.09, N = 3 SE +/- 0.91, N = 3 389.89 592.89 593.13 591.08 592.13 529.07 525.03 584.26 586.86 583.50 585.06 412.16 415.99 398.58 488.61 492.43 455.68 466.89 486.42 479.53 Score Per Watt
OpenBenchmarking.org Score Per Watt, More Is Better Numpy Benchmark Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2 4 6 8 10 1.869 7.931 7.923 3.343 3.321 6.279 3.222 2.772 2.792 6.462 6.473 2.098 4.024 3.826 3.634 7.382 3.229 6.521 6.420 3.169 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Numpy Benchmark CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 126.56 / Avg: 208.56 / Max: 222.92 Min: 21.7 / Avg: 74.76 / Max: 81.54 Min: 18.13 / Avg: 74.86 / Max: 79.25 Min: 42.09 / Avg: 176.81 / Max: 183.26 Min: 43.49 / Avg: 178.27 / Max: 185.56 Min: 41.85 / Avg: 84.27 / Max: 105.69 Min: 88.03 / Avg: 162.97 / Max: 203.04 Min: 53.47 / Avg: 210.74 / Max: 218.8 Min: 50.38 / Avg: 210.21 / Max: 217.88 Min: 24.93 / Avg: 90.29 / Max: 95.62 Min: 26.12 / Avg: 90.38 / Max: 95.49 Min: 113.18 / Avg: 196.43 / Max: 209.83 Min: 57.22 / Avg: 103.37 / Max: 107.94 Min: 60.4 / Avg: 104.18 / Max: 109 Min: 73.77 / Avg: 134.47 / Max: 141.68 Min: 33.7 / Avg: 66.7 / Max: 70.89 Min: 76.12 / Avg: 141.13 / Max: 164.75 Min: 35.54 / Avg: 71.6 / Max: 92.18 Min: 37.34 / Avg: 75.77 / Max: 96.56 Min: 81.03 / Avg: 151.34 / Max: 172.86
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 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 500M 1000M 1500M 2000M 2500M SE +/- 3667121.18, N = 3 SE +/- 3481538.61, N = 3 SE +/- 5660683.12, N = 3 SE +/- 3540872.46, N = 3 SE +/- 1123981.02, N = 3 SE +/- 2702468.01, N = 3 SE +/- 5138849.85, N = 3 SE +/- 3401960.22, N = 3 SE +/- 2804955.93, N = 3 SE +/- 4493328.39, N = 3 SE +/- 9321659.37, N = 3 SE +/- 2318045.15, N = 3 SE +/- 4351755.71, N = 3 SE +/- 2321158.71, N = 3 SE +/- 2140353.03, N = 3 SE +/- 959745.34, N = 3 SE +/- 1713994.68, N = 3 SE +/- 5453744.89, N = 3 SE +/- 1331665.62, N = 3 SE +/- 3291571.73, N = 3 1696333333 2319266667 2308200000 2311866667 2317400000 1856000000 1949233333 2281500000 2282066667 2284300000 2268800000 1770300000 1568333333 1552466667 1670933333 1679333333 1598066667 1590000000 1591600000 1594933333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 3M 6M 9M 12M 15M 4038613.77 12274571.61 12275909.24 8183090.91 8168735.78 8005262.08 5589199.52 7271115.82 7251773.02 11091025.94 11144939.01 4285492.58 6800601.68 6583025.47 6376830.64 8819629.13 6686638.50 9283308.78 8967002.78 6260744.87 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 2021.01.31 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 90 180 270 360 450 Min: 134.18 / Avg: 420.03 / Max: 480.63 Min: 21.11 / Avg: 188.95 / Max: 223.22 Min: 20.41 / Avg: 188.03 / Max: 223.68 Min: 42.93 / Avg: 282.52 / Max: 334.36 Min: 37.88 / Avg: 283.69 / Max: 335.17 Min: 42.05 / Avg: 232.15 / Max: 279.42 Min: 89.1 / Avg: 348.75 / Max: 414.32 Min: 52.57 / Avg: 313.78 / Max: 369.73 Min: 50.6 / Avg: 314.69 / Max: 369.68 Min: 26.94 / Avg: 205.96 / Max: 242.34 Min: 25.47 / Avg: 203.57 / Max: 241.34 Min: 113.16 / Avg: 413.09 / Max: 480.4 Min: 54.19 / Avg: 230.62 / Max: 284.26 Min: 59.32 / Avg: 235.83 / Max: 290.61 Min: 74.6 / Avg: 262.03 / Max: 304.05 Min: 33.68 / Avg: 190.41 / Max: 224.02 Min: 76.78 / Avg: 238.99 / Max: 275.06 Min: 35.6 / Avg: 171.28 / Max: 200.16 Min: 37.24 / Avg: 177.5 / Max: 210.14 Min: 80.18 / Avg: 254.75 / Max: 294.61
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 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 +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 169 115 114 115 114 143 143 117 116 116 116 160 160 169 164 163 163 164 156 156 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 135.27 / Avg: 205.02 / Max: 225.41 Min: 21.48 / Avg: 68.57 / Max: 77.75 Min: 16.26 / Avg: 67.85 / Max: 77.78 Min: 43.14 / Avg: 160.42 / Max: 181.96 Min: 42.67 / Avg: 160.86 / Max: 182.05 Min: 41.95 / Avg: 79.28 / Max: 85.16 Min: 89.04 / Avg: 156.87 / Max: 169.95 Min: 52.63 / Avg: 192.01 / Max: 214.99 Min: 52.87 / Avg: 191.11 / Max: 217.17 Min: 26.93 / Avg: 82.93 / Max: 92.4 Min: 22.52 / Avg: 82.22 / Max: 92.11 Min: 111.08 / Avg: 190.88 / Max: 207.47 Min: 58.78 / Avg: 99.3 / Max: 105.42 Min: 60.79 / Avg: 101.21 / Max: 107.03 Min: 73.89 / Avg: 128.46 / Max: 139.02 Min: 33.87 / Avg: 63.36 / Max: 67.4 Min: 76.47 / Avg: 134.87 / Max: 145.38 Min: 35.43 / Avg: 67.42 / Max: 71.79 Min: 37.55 / Avg: 71.48 / Max: 76.12 Min: 81.08 / Avg: 143.89 / Max: 155.21
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.9383 1.8766 2.8149 3.7532 4.6915 SE +/- 0.00, 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 +/- 0.00, 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 +/- 0.00, 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 2.83 4.17 4.17 4.16 4.15 3.24 3.24 4.11 4.10 4.11 4.10 3.01 3.06 2.91 2.84 2.84 2.84 2.84 2.98 2.98 1. (CXX) g++ options: -O3 GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: Kostya Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0126 0.0252 0.0378 0.0504 0.063 0.013 0.056 0.056 0.024 0.024 0.032 0.018 0.020 0.020 0.046 0.046 0.015 0.029 0.027 0.019 0.036 0.018 0.033 0.032 0.018 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 135.99 / Avg: 212.16 / Max: 224.09 Min: 21.17 / Avg: 74.45 / Max: 80.36 Min: 21.12 / Avg: 73.84 / Max: 77.85 Min: 43.27 / Avg: 174.86 / Max: 184.67 Min: 42.56 / Avg: 175.11 / Max: 184.79 Min: 42.05 / Avg: 101.69 / Max: 106.87 Min: 88.12 / Avg: 178.58 / Max: 187.46 Min: 53.71 / Avg: 206.56 / Max: 217.13 Min: 50.98 / Avg: 206.37 / Max: 217.45 Min: 26.21 / Avg: 89.8 / Max: 94.64 Min: 26.9 / Avg: 89.92 / Max: 94.55 Min: 116.24 / Avg: 196.64 / Max: 214.71 Min: 59.58 / Avg: 105.01 / Max: 109.43 Min: 59.43 / Avg: 106.26 / Max: 110.79 Min: 74.58 / Avg: 145.94 / Max: 153.16 Min: 33.86 / Avg: 79.6 / Max: 83.79 Min: 76.41 / Avg: 154.56 / Max: 163.12 Min: 35.68 / Avg: 86.68 / Max: 91.48 Min: 37.37 / Avg: 92.14 / Max: 96.92 Min: 80.91 / Avg: 166.36 / Max: 175.3
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.22, N = 12 SE +/- 0.13, N = 15 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 9.56 13.91 13.98 12.74 12.56 11.46 10.59 12.78 13.17 9.85 9.57 9.75 10.61 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 0.0236 0.0472 0.0708 0.0944 0.118 0.031 0.105 0.105 0.055 0.054 0.061 0.035 0.048 0.050 0.033 0.049 0.051 0.044 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better AOM AV1 3.5 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 70 140 210 280 350 Min: 137.05 / Avg: 312.07 / Max: 377.52 Min: 21.66 / Avg: 132.83 / Max: 170.86 Min: 20.5 / Avg: 132.74 / Max: 170.66 Min: 43.68 / Avg: 230.11 / Max: 273.01 Min: 43.34 / Avg: 230.88 / Max: 278.19 Min: 42.41 / Avg: 188.47 / Max: 227.44 Min: 88.92 / Avg: 306.81 / Max: 372.93 Min: 51.7 / Avg: 265.26 / Max: 312.61 Min: 46.09 / Avg: 264.13 / Max: 306.07 Min: 117.12 / Avg: 302.72 / Max: 370.97 Min: 60.94 / Avg: 194.6 / Max: 239.52 Min: 61.08 / Avg: 191.78 / Max: 238.51 Min: 75.13 / Avg: 241.4 / Max: 287.06
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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 UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 SE +/- 0.43, N = 3 SE +/- 0.27, N = 3 SE +/- 0.35, N = 3 SE +/- 0.47, N = 3 SE +/- 0.37, N = 3 SE +/- 0.15, N = 3 SE +/- 0.12, N = 3 SE +/- 0.20, N = 14 SE +/- 0.19, N = 3 SE +/- 0.17, N = 3 SE +/- 0.12, N = 3 SE +/- 1.30, N = 3 SE +/- 0.60, N = 3 SE +/- 0.22, N = 3 SE +/- 0.43, N = 3 SE +/- 0.19, N = 3 SE +/- 0.20, N = 12 SE +/- 0.37, N = 3 120.7 160.4 160.9 159.6 160.1 147.0 147.5 158.1 158.6 158.4 158.5 132.3 133.7 110.2 128.4 129.8 128.5 128.1 135.4 134.6 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm UE Mb/s Per Watt
OpenBenchmarking.org UE Mb/s Per Watt, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.5337 1.0674 1.6011 2.1348 2.6685 0.597 2.284 2.372 0.970 0.977 1.823 0.945 0.812 0.816 1.895 1.903 0.696 1.363 1.100 0.995 2.030 0.956 1.886 1.867 0.932 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN 22.04.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 133.59 / Avg: 202.32 / Max: 218.7 Min: 21.55 / Avg: 70.22 / Max: 77.45 Min: 18.54 / Avg: 67.83 / Max: 74.7 Min: 43.53 / Avg: 164.56 / Max: 181.52 Min: 41.2 / Avg: 163.83 / Max: 181.34 Min: 42.03 / Avg: 80.63 / Max: 85.98 Min: 88.6 / Avg: 156.11 / Max: 168.93 Min: 52.35 / Avg: 194.71 / Max: 215.11 Min: 49.13 / Avg: 194.4 / Max: 213.64 Min: 14.66 / Avg: 83.6 / Max: 91.52 Min: 25.9 / Avg: 83.31 / Max: 91.64 Min: 115.09 / Avg: 190.22 / Max: 208.88 Min: 57.29 / Avg: 98.1 / Max: 103.25 Min: 59.65 / Avg: 100.14 / Max: 104.53 Min: 74.15 / Avg: 129.03 / Max: 138.28 Min: 33.84 / Avg: 63.93 / Max: 67.63 Min: 70.25 / Avg: 134.48 / Max: 145.5 Min: 18.19 / Avg: 67.92 / Max: 72.1 Min: 37.26 / Avg: 72.52 / Max: 76.83 Min: 80.38 / Avg: 144.44 / Max: 153.95
Neural Magic DeepSparse Result
OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.1 Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 30 60 90 120 150 SE +/- 0.24, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 SE +/- 0.27, N = 3 SE +/- 0.23, N = 3 SE +/- 0.09, N = 3 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 SE +/- 0.19, N = 3 119.75 87.56 82.29 82.26 89.81 116.77 119.11 95.85 107.01 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Neural Magic DeepSparse 1.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 130 260 390 520 650 Min: 135.36 / Avg: 478.65 / Max: 579.53 Min: 21.63 / Avg: 260.68 / Max: 305.96 Min: 20.65 / Avg: 294.07 / Max: 349.21 Min: 43.43 / Avg: 600.4 / Max: 734.21 Min: 43.56 / Avg: 520.95 / Max: 623.77 Min: 42.82 / Avg: 232.23 / Max: 274.5 Min: 88.96 / Avg: 463.81 / Max: 560.21 Min: 27.15 / Avg: 334.29 / Max: 399.83 Min: 26.95 / Avg: 271.74 / Max: 318.14
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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 UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 SE +/- 0.24, N = 3 SE +/- 0.68, N = 4 SE +/- 0.65, N = 4 SE +/- 0.57, N = 4 SE +/- 0.81, N = 4 SE +/- 1.02, N = 4 SE +/- 0.44, N = 4 SE +/- 0.36, N = 4 SE +/- 0.84, N = 4 SE +/- 0.38, N = 4 SE +/- 0.15, N = 4 SE +/- 0.07, N = 3 SE +/- 0.79, N = 15 SE +/- 0.70, N = 13 SE +/- 0.21, N = 4 SE +/- 0.26, N = 4 SE +/- 0.99, N = 3 SE +/- 0.44, N = 3 SE +/- 0.28, N = 4 SE +/- 0.55, N = 4 116.1 168.1 169.0 168.7 168.0 157.8 158.5 166.3 165.2 166.6 166.6 125.2 126.4 118.1 138.3 138.6 138.0 137.3 146.0 145.1 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm UE Mb/s Per Watt
OpenBenchmarking.org UE Mb/s Per Watt, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.6093 1.2186 1.8279 2.4372 3.0465 0.580 2.589 2.708 1.118 1.121 2.081 1.072 0.937 0.927 2.165 2.162 0.679 1.322 1.209 1.120 2.291 1.068 2.111 2.127 1.049 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN 22.04.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 129.83 / Avg: 200.1 / Max: 222.62 Min: 21.61 / Avg: 64.93 / Max: 77.18 Min: 20.57 / Avg: 62.41 / Max: 74.52 Min: 42.96 / Avg: 150.88 / Max: 181.33 Min: 42.21 / Avg: 149.9 / Max: 181.09 Min: 42.12 / Avg: 75.82 / Max: 85.72 Min: 88.27 / Avg: 147.86 / Max: 167.25 Min: 51.01 / Avg: 177.4 / Max: 214.05 Min: 51.65 / Avg: 178.27 / Max: 217.87 Min: 26.87 / Avg: 76.94 / Max: 91.4 Min: 25.36 / Avg: 77.07 / Max: 91.37 Min: 107.85 / Avg: 184.33 / Max: 206.36 Min: 55.94 / Avg: 95.63 / Max: 103.02 Min: 56.34 / Avg: 97.69 / Max: 104.82 Min: 74.25 / Avg: 123.63 / Max: 137.9 Min: 33.79 / Avg: 60.51 / Max: 66.93 Min: 76.27 / Avg: 129.19 / Max: 146.23 Min: 35.49 / Avg: 65.03 / Max: 72.01 Min: 37.52 / Avg: 68.63 / Max: 76.56 Min: 80.85 / Avg: 138.32 / Max: 155.66
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/. 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 2022.10.13 Model: Bumper Beam Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 20 40 60 80 100 SE +/- 0.26, N = 3 SE +/- 0.26, N = 3 SE +/- 0.27, N = 3 SE +/- 0.14, N = 3 SE +/- 0.32, N = 3 SE +/- 0.17, N = 3 SE +/- 0.60, N = 3 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 86.21 71.10 71.04 72.59 73.13 90.79 100.54 69.37 73.76 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2022.10.13 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 - Power EPYC 9654 120 240 360 480 600 Min: 136.3 / Avg: 512.35 / Max: 581.65 Min: 21.94 / Avg: 305.45 / Max: 333.25 Min: 20.74 / Avg: 305.44 / Max: 333.93 Min: 42.26 / Avg: 630.1 / Max: 698.17 Min: 42.76 / Avg: 613.49 / Max: 677.6 Min: 43.54 / Avg: 244.7 / Max: 261.21 Min: 87.77 / Avg: 491.96 / Max: 524.29 Min: 27.49 / Avg: 376.68 / Max: 409.43 Min: 26.44 / Avg: 314.7 / Max: 344.38
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd 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 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 800 1600 2400 3200 4000 SE +/- 6.09, N = 3 SE +/- 40.76, N = 3 SE +/- 5.81, N = 3 SE +/- 30.54, N = 12 SE +/- 18.13, N = 12 SE +/- 47.75, N = 3 SE +/- 13.14, N = 15 SE +/- 21.16, N = 12 SE +/- 11.04, N = 15 SE +/- 39.99, N = 3 SE +/- 1.24, N = 3 SE +/- 15.95, N = 3 SE +/- 1.66, N = 3 SE +/- 3.78, N = 3 SE +/- 17.82, N = 4 SE +/- 44.74, N = 3 SE +/- 10.83, N = 15 SE +/- 12.82, N = 3 SE +/- 13.08, N = 3 SE +/- 12.57, N = 15 2731.2 3926.0 3837.0 3843.5 3870.9 3754.7 3727.8 3779.6 3797.6 3852.8 3798.1 2828.9 2982.5 2815.9 3343.3 3378.4 3336.6 3328.4 3538.0 3492.2 1. (CC) gcc options: -O3 -pthread -lz -llzma MB/s Per Watt
OpenBenchmarking.org MB/s Per Watt, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 11 22 33 44 55 11.49 46.38 45.39 21.17 21.42 32.74 18.37 17.69 17.82 38.95 38.46 12.78 21.72 20.66 20.85 38.80 18.87 35.51 35.76 18.43 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Zstd Compression 1.5.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 Min: 136.9 / Avg: 237.75 / Max: 292.92 Min: 21.73 / Avg: 84.65 / Max: 110.98 Min: 20.83 / Avg: 84.54 / Max: 110.85 Min: 43.17 / Avg: 181.54 / Max: 217.28 Min: 40.75 / Avg: 180.68 / Max: 217.17 Min: 42.53 / Avg: 114.69 / Max: 157.24 Min: 82.97 / Avg: 202.97 / Max: 284.52 Min: 50.13 / Avg: 213.69 / Max: 252.36 Min: 49.62 / Avg: 213.09 / Max: 251.98 Min: 26.93 / Avg: 98.92 / Max: 128.55 Min: 25.63 / Avg: 98.75 / Max: 128.26 Min: 108.21 / Avg: 221.34 / Max: 280.03 Min: 61.38 / Avg: 137.3 / Max: 191.01 Min: 57.88 / Avg: 136.32 / Max: 188.61 Min: 74.02 / Avg: 160.32 / Max: 225.8 Min: 34.05 / Avg: 87.07 / Max: 124.79 Min: 76.98 / Avg: 176.8 / Max: 233.97 Min: 35.65 / Avg: 93.73 / Max: 121.62 Min: 37.27 / Avg: 98.93 / Max: 126.81 Min: 80.43 / Avg: 189.44 / Max: 256.97
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 6 12 18 24 30 SE +/- 0.19, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 SE +/- 0.19, N = 11 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.23, N = 7 SE +/- 0.35, N = 3 SE +/- 0.22, N = 4 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.18, N = 15 19.09 26.60 26.38 25.37 25.17 22.49 20.95 24.83 24.96 19.43 19.88 19.15 19.76 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better AOM AV1 3.5 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 0.0556 0.1112 0.1668 0.2224 0.278 0.069 0.246 0.247 0.125 0.124 0.148 0.082 0.105 0.106 0.075 0.119 0.115 0.096 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better AOM AV1 3.5 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P 50 100 150 200 250 Min: 129.22 / Avg: 275.05 / Max: 306.08 Min: 21.24 / Avg: 107.99 / Max: 130.29 Min: 19.2 / Avg: 106.98 / Max: 128.08 Min: 43.1 / Avg: 202.36 / Max: 236.99 Min: 41.26 / Avg: 202.56 / Max: 233.71 Min: 42.7 / Avg: 152.29 / Max: 184.56 Min: 89.1 / Avg: 255.62 / Max: 300.32 Min: 50.69 / Avg: 235.43 / Max: 268.83 Min: 51.12 / Avg: 234.79 / Max: 267.35 Min: 111.68 / Avg: 260.05 / Max: 300.94 Min: 59.84 / Avg: 167.61 / Max: 199.43 Min: 59.86 / Avg: 165.92 / Max: 194.97 Min: 75.37 / Avg: 205.32 / Max: 243.21
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: json_loads Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 22.6 16.3 16.3 16.4 16.5 19.6 19.5 16.6 16.5 16.7 16.6 21.4 21.4 22.6 22.5 22.3 22.3 22.5 21.3 21.5 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 131.53 / Avg: 198.09 / Max: 215.87 Min: 21.66 / Avg: 69.76 / Max: 77.71 Min: 19.81 / Avg: 69.59 / Max: 77.79 Min: 41.65 / Avg: 164.13 / Max: 182.07 Min: 44.35 / Avg: 164.3 / Max: 181.89 Min: 41.99 / Avg: 76.68 / Max: 85.45 Min: 87.87 / Avg: 151.36 / Max: 170.71 Min: 49.79 / Avg: 196.03 / Max: 214.66 Min: 51.59 / Avg: 195.15 / Max: 214.63 Min: 26.69 / Avg: 84.49 / Max: 92.13 Min: 25.82 / Avg: 84.68 / Max: 91.97 Min: 114.18 / Avg: 186.87 / Max: 206.5 Min: 55.86 / Avg: 96.45 / Max: 104.3 Min: 56.59 / Avg: 98.1 / Max: 105.26 Min: 74.6 / Avg: 124.91 / Max: 136.87 Min: 33.88 / Avg: 61.18 / Max: 66.73 Min: 76.42 / Avg: 131.03 / Max: 144.71 Min: 35.66 / Avg: 65.28 / Max: 72.97 Min: 37.16 / Avg: 71.48 / Max: 82.84 Min: 80.86 / Avg: 140.41 / Max: 154.71
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.44, N = 3 SE +/- 0.23, N = 3 SE +/- 0.31, N = 3 SE +/- 1.36, N = 15 SE +/- 1.46, N = 3 SE +/- 1.10, N = 3 SE +/- 1.67, N = 14 SE +/- 0.61, N = 3 SE +/- 0.35, N = 3 SE +/- 1.03, N = 3 SE +/- 0.23, N = 3 SE +/- 0.94, N = 3 SE +/- 0.15, N = 3 SE +/- 0.20, N = 3 SE +/- 0.98, N = 7 SE +/- 0.83, N = 3 SE +/- 1.28, N = 15 SE +/- 0.88, N = 5 SE +/- 0.79, N = 3 SE +/- 0.89, N = 15 86.2 103.3 102.1 102.9 103.3 95.1 94.7 107.8 108.4 107.3 106.1 87.1 83.7 82.4 107.6 103.6 80.1 85.0 84.8 82.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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 UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 SE +/- 3.20, N = 3 SE +/- 0.13, N = 3 SE +/- 0.23, N = 3 SE +/- 0.00, N = 3 SE +/- 0.26, N = 3 SE +/- 0.52, N = 3 SE +/- 0.22, N = 3 SE +/- 0.58, N = 3 SE +/- 0.19, N = 3 SE +/- 0.29, N = 3 SE +/- 0.54, N = 3 SE +/- 0.17, N = 3 SE +/- 2.02, N = 3 SE +/- 1.56, N = 3 SE +/- 0.17, N = 3 SE +/- 0.33, N = 3 SE +/- 0.23, N = 3 SE +/- 0.66, N = 3 SE +/- 0.30, N = 3 SE +/- 0.63, N = 3 125.7 169.3 169.1 168.9 168.5 156.1 154.9 166.7 166.1 166.4 166.2 138.9 137.3 135.2 137.0 136.4 136.0 135.8 143.3 142.2 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm UE Mb/s Per Watt
OpenBenchmarking.org UE Mb/s Per Watt, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.5528 1.1056 1.6584 2.2112 2.764 0.618 2.369 2.457 1.017 1.019 1.923 0.986 0.842 0.843 2.134 1.962 0.724 1.388 1.341 1.053 2.136 0.998 1.979 1.966 0.979 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN 22.04.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 135.54 / Avg: 203.54 / Max: 218.98 Min: 21.85 / Avg: 71.46 / Max: 77.18 Min: 20.42 / Avg: 68.83 / Max: 77.16 Min: 43.31 / Avg: 166.11 / Max: 181.44 Min: 43.43 / Avg: 165.32 / Max: 181.32 Min: 41.97 / Avg: 81.17 / Max: 85.83 Min: 88.57 / Avg: 157.02 / Max: 168.15 Min: 52.86 / Avg: 197.95 / Max: 214.21 Min: 52.03 / Avg: 196.94 / Max: 213.64 Min: 26.21 / Avg: 77.97 / Max: 91.43 Min: 23.85 / Avg: 84.71 / Max: 91.46 Min: 114.14 / Avg: 191.78 / Max: 211.72 Min: 53.42 / Avg: 98.94 / Max: 103.81 Min: 59.78 / Avg: 100.82 / Max: 109.68 Min: 73.98 / Avg: 130.07 / Max: 138.7 Min: 33.74 / Avg: 63.86 / Max: 67.01 Min: 76.35 / Avg: 136.3 / Max: 145.85 Min: 35.49 / Avg: 68.62 / Max: 72.02 Min: 37.26 / Avg: 72.89 / Max: 76.48 Min: 80.76 / Avg: 145.31 / Max: 153.81
DaCapo Benchmark This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 900 1800 2700 3600 4500 SE +/- 13.65, N = 7 SE +/- 19.41, N = 8 SE +/- 12.71, N = 8 SE +/- 18.24, N = 8 SE +/- 21.16, N = 8 SE +/- 9.91, N = 7 SE +/- 32.86, N = 7 SE +/- 22.93, N = 8 SE +/- 24.10, N = 8 SE +/- 16.67, N = 8 SE +/- 19.92, N = 8 SE +/- 26.05, N = 7 SE +/- 16.15, N = 7 SE +/- 21.78, N = 7 SE +/- 31.80, N = 7 SE +/- 13.60, N = 7 SE +/- 35.81, N = 8 SE +/- 7.99, N = 7 SE +/- 11.39, N = 7 SE +/- 15.85, N = 7 3855 3205 3171 3321 3302 3566 3706 3395 3380 3219 3240 3659 3646 3830 4248 4053 4217 4125 4088 4076 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better DaCapo Benchmark 9.12-MR1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 50 100 150 200 250 Min: 131.17 / Avg: 204.72 / Max: 299.57 Min: 21.72 / Avg: 56.99 / Max: 110.43 Min: 19.45 / Avg: 55.8 / Max: 108.76 Min: 41.56 / Avg: 123.33 / Max: 217.94 Min: 43.36 / Avg: 124.11 / Max: 216.01 Min: 42.33 / Avg: 77.45 / Max: 149.11 Min: 87.39 / Avg: 160.26 / Max: 271.47 Min: 52.83 / Avg: 149.65 / Max: 253.79 Min: 50.64 / Avg: 147.9 / Max: 253.67 Min: 26.9 / Avg: 68.44 / Max: 126.41 Min: 26.15 / Avg: 68.09 / Max: 127.98 Min: 113.13 / Avg: 184.27 / Max: 266.64 Min: 55.84 / Avg: 104.29 / Max: 186.33 Min: 58.16 / Avg: 104.56 / Max: 187.89 Min: 73.8 / Avg: 131.96 / Max: 218.39 Min: 33.96 / Avg: 61.06 / Max: 114.91 Min: 76.65 / Avg: 139.08 / Max: 223.65 Min: 35.57 / Avg: 64.38 / Max: 118.36 Min: 37.25 / Avg: 67.56 / Max: 121.29 Min: 81.79 / Avg: 148.58 / Max: 235.13
Timed Wasmer Compilation This test times how long it takes to compile Wasmer. Wasmer is written in the Rust programming language and is a WebAssembly runtime implementation that supports WASI and EmScripten. This test profile builds Wasmer with the Cranelift and Singlepast compiler features enabled. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.3 Time To Compile Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 12 24 36 48 60 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.12, N = 3 SE +/- 0.14, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.32, N = 3 48.33 40.10 40.18 40.86 40.72 46.08 45.82 41.44 41.09 40.41 40.45 46.74 47.41 48.69 50.33 49.68 53.11 52.90 52.02 51.35 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Wasmer Compilation 2.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 90 180 270 360 450 Min: 134.08 / Avg: 279.54 / Max: 491.85 Min: 21.99 / Avg: 105.32 / Max: 220.33 Min: 19.11 / Avg: 105.1 / Max: 212.77 Min: 42.68 / Avg: 203.38 / Max: 339.56 Min: 42.34 / Avg: 203.65 / Max: 319.15 Min: 42.39 / Avg: 143.61 / Max: 275.56 Min: 88.42 / Avg: 246.1 / Max: 432.42 Min: 52.34 / Avg: 235.97 / Max: 370.6 Min: 52.39 / Avg: 235.6 / Max: 377.24 Min: 27.07 / Avg: 120.66 / Max: 238.88 Min: 21.66 / Avg: 119.91 / Max: 222.03 Min: 110.33 / Avg: 262.87 / Max: 478.44 Min: 59.69 / Avg: 172.49 / Max: 284.16 Min: 59.28 / Avg: 167.21 / Max: 282.9 Min: 74 / Avg: 188.13 / Max: 351.84 Min: 33.95 / Avg: 107.22 / Max: 245.95 Min: 76.93 / Avg: 192.47 / Max: 339.32 Min: 35.66 / Avg: 107.47 / Max: 204.36 Min: 37.44 / Avg: 113.51 / Max: 221.96 Min: 81.53 / Avg: 206.64 / Max: 367.83
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.2858 0.5716 0.8574 1.1432 1.429 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 0.96 1.27 1.26 1.27 1.27 1.12 1.12 1.25 1.25 1.25 1.25 1.00 1.02 0.97 0.98 0.98 0.98 0.98 1.03 1.03 1. (CXX) g++ options: -O3 GB/s Per Watt
OpenBenchmarking.org GB/s Per Watt, More Is Better simdjson 2.0 Throughput Test: LargeRandom Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0041 0.0082 0.0123 0.0164 0.0205 0.005 0.018 0.017 0.007 0.007 0.012 0.007 0.006 0.006 0.014 0.014 0.005 0.010 0.009 0.007 0.014 0.007 0.012 0.012 0.007 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better simdjson 2.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 134.18 / Avg: 209.26 / Max: 222.32 Min: 21.08 / Avg: 72.25 / Max: 76.39 Min: 20.55 / Avg: 74.6 / Max: 79.12 Min: 43.18 / Avg: 173 / Max: 183.49 Min: 43.04 / Avg: 171.39 / Max: 183.05 Min: 42.19 / Avg: 94.65 / Max: 101.05 Min: 89.21 / Avg: 170.95 / Max: 181.44 Min: 49.96 / Avg: 203.62 / Max: 215.86 Min: 53.08 / Avg: 203.36 / Max: 216.68 Min: 26.49 / Avg: 87.9 / Max: 93.36 Min: 23.37 / Avg: 87.89 / Max: 93.17 Min: 109.73 / Avg: 192.92 / Max: 211.69 Min: 58.05 / Avg: 102.64 / Max: 106.94 Min: 60.74 / Avg: 103.93 / Max: 108.15 Min: 74.13 / Avg: 137.33 / Max: 146.05 Min: 33.82 / Avg: 71.68 / Max: 77.46 Min: 75.85 / Avg: 147.03 / Max: 158.24 Min: 35.55 / Avg: 78.7 / Max: 85 Min: 37.36 / Avg: 84.07 / Max: 90.23 Min: 81.06 / Avg: 157.54 / Max: 168
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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 Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40M 80M 120M 160M 200M SE +/- 218581.28, N = 3 SE +/- 592546.29, N = 3 SE +/- 550757.05, N = 3 SE +/- 1211518.79, N = 3 SE +/- 688799.28, N = 3 SE +/- 876229.30, N = 3 SE +/- 1646207.76, N = 3 SE +/- 520683.31, N = 3 SE +/- 1841496.98, N = 3 SE +/- 1212530.99, N = 11 SE +/- 2007485.99, N = 3 SE +/- 520683.31, N = 3 SE +/- 581186.53, N = 3 SE +/- 523874.45, N = 3 SE +/- 1046835.32, N = 9 SE +/- 1757207.38, N = 3 SE +/- 1074873.19, N = 15 SE +/- 961718.04, N = 15 SE +/- 1264695.92, N = 7 SE +/- 1229303.58, N = 15 136166667 164566667 166800000 164166667 166666667 148066667 147700000 163766667 158633333 161236364 162000000 143266667 143166667 135233333 130344444 128766667 127480000 130106667 134557143 136493333 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm Samples / Second Per Watt
OpenBenchmarking.org Samples / Second Per Watt, More Is Better srsRAN 22.04.1 Test: OFDM_Test Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 500K 1000K 1500K 2000K 2500K 668180.55 2288251.04 2397264.95 989602.37 1006148.09 1764993.40 929541.54 832424.52 812282.24 1886910.71 1894513.02 748225.14 1427669.20 1330622.55 993107.27 1967922.41 921714.30 1833553.37 1794758.13 926976.10 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN 22.04.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 131.7 / Avg: 203.79 / Max: 227.39 Min: 21.51 / Avg: 71.92 / Max: 79.51 Min: 20.75 / Avg: 69.58 / Max: 76.91 Min: 42.73 / Avg: 165.89 / Max: 183.58 Min: 40.56 / Avg: 165.65 / Max: 183.59 Min: 42 / Avg: 83.89 / Max: 90.31 Min: 88.25 / Avg: 158.9 / Max: 171.86 Min: 53 / Avg: 196.73 / Max: 216.98 Min: 52.51 / Avg: 195.29 / Max: 215.92 Min: 25.22 / Avg: 85.45 / Max: 93.85 Min: 26.32 / Avg: 85.51 / Max: 93.7 Min: 112.89 / Avg: 191.48 / Max: 214.6 Min: 55.71 / Avg: 100.28 / Max: 106.42 Min: 60.87 / Avg: 101.63 / Max: 106.71 Min: 74.25 / Avg: 131.25 / Max: 140.7 Min: 33.78 / Avg: 65.43 / Max: 69.53 Min: 76.28 / Avg: 138.31 / Max: 149.21 Min: 35.55 / Avg: 70.96 / Max: 75.47 Min: 37.17 / Avg: 74.97 / Max: 80.05 Min: 79.81 / Avg: 147.25 / Max: 157.24
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.17, N = 3 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 SE +/- 0.20, N = 3 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 SE +/- 0.27, N = 3 SE +/- 0.12, N = 3 SE +/- 0.15, N = 3 SE +/- 0.21, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.25, N = 3 111.0 87.0 86.8 87.3 86.6 91.9 91.2 89.5 90.1 87.4 88.2 104.0 104.0 110.0 103.0 103.0 105.0 103.0 101.0 98.2 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 131.97 / Avg: 201.97 / Max: 222.88 Min: 21.06 / Avg: 70.19 / Max: 77.9 Min: 19.67 / Avg: 69.97 / Max: 77.98 Min: 43.17 / Avg: 164.74 / Max: 182.26 Min: 43.64 / Avg: 165.38 / Max: 181.96 Min: 42.11 / Avg: 79.96 / Max: 86.86 Min: 87.84 / Avg: 157.95 / Max: 175.44 Min: 52.44 / Avg: 196.59 / Max: 214.93 Min: 51.34 / Avg: 196.51 / Max: 214.89 Min: 26.65 / Avg: 84.81 / Max: 92.42 Min: 24.7 / Avg: 84.9 / Max: 92.67 Min: 116.12 / Avg: 188.1 / Max: 205.05 Min: 56.69 / Avg: 96.54 / Max: 107.64 Min: 58.82 / Avg: 97.73 / Max: 105.2 Min: 73.32 / Avg: 126.08 / Max: 137.28 Min: 33.91 / Avg: 61.37 / Max: 67.33 Min: 75.88 / Avg: 130.7 / Max: 144.97 Min: 35.48 / Avg: 65.23 / Max: 71.84 Min: 37.31 / Avg: 71.39 / Max: 76.17 Min: 80.62 / Avg: 145.64 / Max: 163.23
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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.
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 30 60 90 120 150 SE +/- 0.30, N = 3 SE +/- 0.06, N = 4 SE +/- 0.45, N = 4 SE +/- 0.44, N = 4 SE +/- 0.23, N = 4 SE +/- 0.78, N = 3 SE +/- 0.23, N = 3 SE +/- 0.40, N = 4 SE +/- 0.44, N = 4 SE +/- 0.42, N = 4 SE +/- 0.34, N = 4 SE +/- 1.43, N = 4 SE +/- 0.20, N = 3 SE +/- 0.20, N = 3 SE +/- 0.21, N = 3 SE +/- 0.24, N = 3 SE +/- 0.26, N = 3 SE +/- 0.06, N = 3 SE +/- 0.23, N = 3 SE +/- 0.23, N = 3 111.3 141.9 141.6 141.0 141.7 138.2 139.1 138.8 139.3 139.8 139.4 123.0 122.0 113.1 121.9 121.7 121.8 121.6 127.5 127.8 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200K 400K 600K 800K 1000K SE +/- 1645.39, N = 3 SE +/- 4409.84, N = 3 SE +/- 9166.50, N = 3 SE +/- 1751.73, N = 3 SE +/- 9437.20, N = 4 SE +/- 2116.45, N = 3 SE +/- 3058.25, N = 3 SE +/- 3619.22, N = 3 SE +/- 7390.85, N = 3 SE +/- 1659.67, N = 3 SE +/- 5980.59, N = 3 SE +/- 987.27, N = 3 SE +/- 5721.95, N = 3 SE +/- 924.75, N = 3 SE +/- 1434.53, N = 3 SE +/- 1748.53, N = 3 SE +/- 1449.54, N = 3 SE +/- 9346.50, N = 3 SE +/- 3252.22, N = 3 SE +/- 2398.01, N = 3 816968 855637 862102 849730 876214 793816 802341 846790 847129 843411 843665 866491 859511 816743 696203 697059 691655 702291 730550 730528 Score Per Watt
OpenBenchmarking.org Score Per Watt, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 3K 6K 9K 12K 15K 4053.33 12571.74 12652.56 5292.64 5482.17 10166.46 5261.11 4463.56 4470.82 10168.51 10335.56 4665.07 8917.25 8247.04 5486.97 11211.83 5187.57 10616.91 10412.21 5132.40 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PHPBench 0.8.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 135.3 / Avg: 201.55 / Max: 218.09 Min: 21.34 / Avg: 68.06 / Max: 77.66 Min: 20.28 / Avg: 68.14 / Max: 77.75 Min: 43.32 / Avg: 160.55 / Max: 181.86 Min: 43.07 / Avg: 159.83 / Max: 181.93 Min: 42 / Avg: 78.08 / Max: 84.68 Min: 88.74 / Avg: 152.5 / Max: 166.53 Min: 52.68 / Avg: 189.71 / Max: 214.54 Min: 52.3 / Avg: 189.48 / Max: 214.19 Min: 26.81 / Avg: 82.94 / Max: 92.05 Min: 25.43 / Avg: 81.63 / Max: 91.76 Min: 109.53 / Avg: 185.74 / Max: 200.93 Min: 55.75 / Avg: 96.39 / Max: 104.14 Min: 60.56 / Avg: 99.03 / Max: 105.37 Min: 74.2 / Avg: 126.88 / Max: 137.94 Min: 33.79 / Avg: 62.17 / Max: 67.13 Min: 76.39 / Avg: 133.33 / Max: 145.13 Min: 35.63 / Avg: 66.15 / Max: 71.2 Min: 37.39 / Avg: 70.16 / Max: 76.23 Min: 80.61 / Avg: 142.34 / Max: 154.85
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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 200 400 600 800 1000 SE +/- 10.13, N = 6 SE +/- 3.84, N = 3 SE +/- 1.15, N = 3 SE +/- 3.93, N = 3 SE +/- 2.33, N = 3 SE +/- 0.88, N = 3 SE +/- 8.88, N = 3 SE +/- 4.33, N = 3 SE +/- 5.61, N = 3 SE +/- 6.08, N = 3 SE +/- 6.01, N = 3 SE +/- 1.45, N = 3 SE +/- 1.53, N = 3 SE +/- 0.58, N = 3 SE +/- 1.76, N = 3 SE +/- 2.03, N = 3 SE +/- 2.33, N = 3 SE +/- 12.19, N = 4 SE +/- 3.18, N = 3 SE +/- 7.57, N = 3 1052 849 849 846 844 901 887 862 864 864 855 986 983 1042 1018 1016 1016 1018 969 970 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyBench 2018-02-16 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 130.05 / Avg: 199.48 / Max: 220.06 Min: 21.7 / Avg: 66.02 / Max: 75.51 Min: 18.93 / Avg: 65.72 / Max: 75.71 Min: 43.06 / Avg: 158.91 / Max: 182.03 Min: 43.09 / Avg: 156.73 / Max: 181.95 Min: 42.23 / Avg: 77.99 / Max: 84.89 Min: 87.7 / Avg: 150.86 / Max: 166.66 Min: 50.33 / Avg: 186.76 / Max: 214.96 Min: 22.26 / Avg: 186.45 / Max: 214.19 Min: 26.59 / Avg: 80.7 / Max: 92.09 Min: 24.5 / Avg: 80.63 / Max: 92.03 Min: 115.94 / Avg: 186.71 / Max: 200.53 Min: 56.8 / Avg: 96.04 / Max: 103.34 Min: 60.12 / Avg: 97.58 / Max: 103.99 Min: 73.35 / Avg: 125.86 / Max: 137.7 Min: 33.99 / Avg: 62.51 / Max: 68.02 Min: 76.85 / Avg: 132.72 / Max: 145.75 Min: 35.52 / Avg: 66.89 / Max: 73.44 Min: 37.42 / Avg: 70.41 / Max: 76.43 Min: 80.95 / Avg: 139.63 / Max: 153.33
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN 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 UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 SE +/- 0.21, N = 15 SE +/- 0.81, N = 3 SE +/- 0.66, N = 3 SE +/- 0.41, N = 3 SE +/- 0.54, N = 3 SE +/- 0.20, N = 3 SE +/- 0.31, N = 3 SE +/- 0.23, N = 3 SE +/- 0.51, N = 3 SE +/- 0.88, N = 3 SE +/- 0.58, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 SE +/- 0.29, N = 3 SE +/- 0.40, N = 3 SE +/- 0.44, N = 3 SE +/- 0.30, N = 3 SE +/- 0.52, N = 3 SE +/- 0.21, N = 3 140.9 175.1 175.6 175.5 174.0 165.9 164.3 173.1 173.2 172.1 172.8 147.1 146.6 142.3 144.3 144.2 143.8 142.8 152.6 151.8 1. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -ldl -lpthread -lm UE Mb/s Per Watt
OpenBenchmarking.org UE Mb/s Per Watt, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.6084 1.2168 1.8252 2.4336 3.042 0.703 2.704 2.669 1.139 1.133 2.145 1.098 0.942 0.945 2.171 2.189 0.791 1.523 1.448 1.152 2.350 1.090 2.161 2.191 1.083 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN 22.04.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 104.13 / Avg: 200.42 / Max: 219.57 Min: 21.28 / Avg: 64.76 / Max: 74.48 Min: 19.49 / Avg: 65.8 / Max: 77.13 Min: 43.31 / Avg: 154.02 / Max: 181.07 Min: 41.27 / Avg: 153.59 / Max: 180.95 Min: 41.9 / Avg: 77.32 / Max: 85.71 Min: 88.28 / Avg: 149.67 / Max: 167.46 Min: 47.51 / Avg: 183.68 / Max: 214.04 Min: 43.29 / Avg: 183.33 / Max: 213.32 Min: 26.13 / Avg: 79.29 / Max: 91.37 Min: 26.72 / Avg: 78.95 / Max: 91.32 Min: 116.85 / Avg: 186.01 / Max: 202.41 Min: 56.14 / Avg: 96.24 / Max: 104.97 Min: 59.92 / Avg: 98.29 / Max: 104.6 Min: 74.28 / Avg: 125.24 / Max: 138.01 Min: 33.75 / Avg: 61.36 / Max: 66.81 Min: 76.67 / Avg: 131.89 / Max: 145.28 Min: 35.55 / Avg: 66.07 / Max: 72.38 Min: 37.25 / Avg: 69.64 / Max: 76.61 Min: 80.19 / Avg: 140.17 / Max: 153.61
PyPerformance PyPerformance is the reference Python performance benchmark suite. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 44.3 36.0 36.0 35.7 35.8 36.8 36.9 36.2 36.1 36.5 36.3 41.9 41.8 44.3 42.1 42.1 41.8 42.2 39.9 39.8 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better PyPerformance 1.0.0 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 128.48 / Avg: 202.28 / Max: 216.51 Min: 21.3 / Avg: 70.55 / Max: 77.7 Min: 17.15 / Avg: 70.04 / Max: 77.77 Min: 43.67 / Avg: 165.19 / Max: 182.08 Min: 44.54 / Avg: 165.35 / Max: 181.8 Min: 42.2 / Avg: 82.38 / Max: 90.66 Min: 87.66 / Avg: 158.68 / Max: 172.62 Min: 49.17 / Avg: 197.01 / Max: 214.99 Min: 52.34 / Avg: 196.32 / Max: 214.46 Min: 25.54 / Avg: 85.24 / Max: 92.27 Min: 24.9 / Avg: 84.71 / Max: 92.14 Min: 112.94 / Avg: 192.01 / Max: 211.02 Min: 56.57 / Avg: 99.48 / Max: 104.84 Min: 58.85 / Avg: 100.81 / Max: 106.03 Min: 73.65 / Avg: 130.54 / Max: 141.09 Min: 33.85 / Avg: 65.62 / Max: 70.4 Min: 76.21 / Avg: 137.34 / Max: 148.4 Min: 35.55 / Avg: 69.94 / Max: 75.31 Min: 37.36 / Avg: 74.08 / Max: 81.17 Min: 40.73 / Avg: 146.23 / Max: 159.48
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 1.21 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 700 1400 2100 2800 3500 SE +/- 16.97, N = 3 SE +/- 31.02, N = 3 SE +/- 31.45, N = 3 SE +/- 22.61, N = 3 SE +/- 2.89, N = 3 SE +/- 29.32, N = 3 SE +/- 0.95, N = 3 SE +/- 24.81, N = 9 SE +/- 5.62, N = 3 SE +/- 30.22, N = 3 SE +/- 35.26, N = 3 SE +/- 18.13, N = 3 SE +/- 23.48, N = 3 SE +/- 17.79, N = 3 SE +/- 25.83, N = 3 SE +/- 22.27, N = 3 SE +/- 27.55, N = 5 SE +/- 24.99, N = 3 SE +/- 25.97, N = 3 SE +/- 25.70, N = 3 2514.7 3075.1 3089.5 3059.9 3106.4 3047.1 3094.0 3030.6 3049.8 3043.0 3028.2 2666.3 2664.8 2521.7 2668.0 2694.3 2689.6 2684.7 2827.5 2830.5 1. (CXX) g++ options: -O3 -march=native -rdynamic MFLOPS Per Watt
OpenBenchmarking.org MFLOPS Per Watt, More Is Better QuantLib 1.21 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 10 20 30 40 50 12.39 45.12 44.17 19.03 19.31 38.66 20.05 15.63 15.86 36.62 36.50 14.17 26.89 25.28 20.98 42.68 19.86 39.86 39.50 19.69 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better QuantLib 1.21 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 40 80 120 160 200 Min: 134.45 / Avg: 202.91 / Max: 219.51 Min: 21.66 / Avg: 68.15 / Max: 75.51 Min: 19.2 / Avg: 69.95 / Max: 78.23 Min: 43.8 / Avg: 160.8 / Max: 179.88 Min: 43.21 / Avg: 160.88 / Max: 179.82 Min: 42.05 / Avg: 78.82 / Max: 84.67 Min: 88.51 / Avg: 154.39 / Max: 168.16 Min: 51.68 / Avg: 193.87 / Max: 215.29 Min: 49.37 / Avg: 192.26 / Max: 214.6 Min: 26.72 / Avg: 83.09 / Max: 92.33 Min: 24.4 / Avg: 82.95 / Max: 92.16 Min: 110.79 / Avg: 188.15 / Max: 203.21 Min: 55.85 / Avg: 99.1 / Max: 105.23 Min: 58.84 / Avg: 99.76 / Max: 105.76 Min: 66.9 / Avg: 127.18 / Max: 138.89 Min: 33.79 / Avg: 63.12 / Max: 67.3 Min: 76.68 / Avg: 135.45 / Max: 146.26 Min: 35.42 / Avg: 67.35 / Max: 71.82 Min: 37.45 / Avg: 71.58 / Max: 77 Min: 80.46 / Avg: 143.79 / Max: 157.86
WebP2 Image Encode OpenBenchmarking.org Watts, Fewer Is Better WebP2 Image Encode 20220823 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 90 180 270 360 450 Min: 132.1 / Avg: 270.74 / Max: 510.03 Min: 20.87 / Avg: 70.29 / Max: 201.63 Min: 16.16 / Avg: 67.27 / Max: 200.66 Min: 41.49 / Avg: 133.41 / Max: 322.48 Min: 41.59 / Avg: 130.1 / Max: 319.48 Min: 41.88 / Avg: 94.45 / Max: 249.32 Min: 88.23 / Avg: 178.53 / Max: 398.49 Min: 52.12 / Avg: 153.04 / Max: 350.04 Min: 49.67 / Avg: 154.93 / Max: 353.94 Min: 26.52 / Avg: 83.72 / Max: 233.39 Min: 25.13 / Avg: 82.85 / Max: 220.37 Min: 105.81 / Avg: 250.52 / Max: 498.31 Min: 55.42 / Avg: 130.44 / Max: 283.74 Min: 57.78 / Avg: 138.45 / Max: 287.62 Min: 73.91 / Avg: 149.74 / Max: 323.44 Min: 33.77 / Avg: 83.79 / Max: 224.42 Min: 75.94 / Avg: 146.55 / Max: 297.33 Min: 35.61 / Avg: 83.58 / Max: 209.48 Min: 37.18 / Avg: 85.41 / Max: 202.89 Min: 79.81 / Avg: 157.99 / Max: 323.15
OpenBenchmarking.org MP/s Per Watt, More Is Better WebP2 Image Encode 20220823 Encode Settings: Default Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0392 0.0784 0.1176 0.1568 0.196 0.029 0.167 0.174 0.076 0.079 0.109 0.049 0.067 0.064 0.144 0.140 0.032 0.069 0.059 0.057 0.114 0.057 0.109 0.108 0.052
Result
OpenBenchmarking.org MP/s, More Is Better WebP2 Image Encode 20220823 Encode Settings: Default Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 3 6 9 12 15 SE +/- 0.06, N = 15 SE +/- 0.19, N = 15 SE +/- 0.17, N = 15 SE +/- 0.20, N = 15 SE +/- 0.21, N = 15 SE +/- 0.09, N = 15 SE +/- 0.12, N = 15 SE +/- 0.20, N = 15 SE +/- 0.15, N = 15 SE +/- 0.18, N = 15 SE +/- 0.10, N = 15 SE +/- 0.07, N = 9 SE +/- 0.07, N = 10 SE +/- 0.04, N = 9 SE +/- 0.16, N = 15 SE +/- 0.13, N = 15 SE +/- 0.13, N = 15 SE +/- 0.09, N = 15 SE +/- 0.11, N = 15 SE +/- 0.18, N = 15 7.96 11.76 11.69 10.15 10.34 10.30 8.77 10.21 9.96 12.06 11.60 8.05 9.01 8.16 8.56 9.55 8.32 9.14 9.21 8.25 1. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl MP/s Per Watt
OpenBenchmarking.org MP/s Per Watt, More Is Better WebP2 Image Encode 20220823 Encode Settings: Default Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.0392 0.0784 0.1176 0.1568 0.196 0.029 0.167 0.174 0.076 0.079 0.109 0.049 0.067 0.064 0.144 0.140 0.032 0.069 0.059 0.057 0.114 0.057 0.109 0.108 0.052 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better WebP2 Image Encode 20220823 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 90 180 270 360 450 Min: 132.1 / Avg: 270.74 / Max: 510.03 Min: 20.87 / Avg: 70.29 / Max: 201.63 Min: 16.16 / Avg: 67.27 / Max: 200.66 Min: 41.49 / Avg: 133.41 / Max: 322.48 Min: 41.59 / Avg: 130.1 / Max: 319.48 Min: 41.88 / Avg: 94.45 / Max: 249.32 Min: 88.23 / Avg: 178.53 / Max: 398.49 Min: 52.12 / Avg: 153.04 / Max: 350.04 Min: 49.67 / Avg: 154.93 / Max: 353.94 Min: 26.52 / Avg: 83.72 / Max: 233.39 Min: 25.13 / Avg: 82.85 / Max: 220.37 Min: 105.81 / Avg: 250.52 / Max: 498.31 Min: 55.42 / Avg: 130.44 / Max: 283.74 Min: 57.78 / Avg: 138.45 / Max: 287.62 Min: 73.91 / Avg: 149.74 / Max: 323.44 Min: 33.77 / Avg: 83.79 / Max: 224.42 Min: 75.94 / Avg: 146.55 / Max: 297.33 Min: 35.61 / Avg: 83.58 / Max: 209.48 Min: 37.18 / Avg: 85.41 / Max: 202.89 Min: 79.81 / Avg: 157.99 / Max: 323.15
CPU Power Consumption Monitor OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 150 300 450 600 750 Min: 73.9 / Avg: 431.65 / Max: 583.63 Min: 10.82 / Avg: 221.23 / Max: 355.01 Min: 15 / Avg: 234.13 / Max: 404.97 Min: 21.9 / Avg: 420.09 / Max: 816.8 Min: 21.75 / Avg: 366.87 / Max: 697.99 Min: 41.77 / Avg: 216.76 / Max: 286.74 Min: 44.29 / Avg: 388.91 / Max: 568.18 Min: 29.18 / Avg: 443.82 / Max: 833.55 Min: 22.26 / Avg: 361.53 / Max: 707.31 Min: 13.57 / Avg: 256.57 / Max: 415.76 Min: 13.46 / Avg: 223.35 / Max: 363.54 Min: 55.85 / Avg: 410.13 / Max: 571.36 Min: 37.91 / Avg: 225.19 / Max: 286.34 Min: 31.32 / Avg: 223.73 / Max: 293.02 Min: 38.36 / Avg: 336.85 / Max: 578.83 Min: 17.66 / Avg: 193.18 / Max: 291.19 Min: 38.66 / Avg: 332 / Max: 573.72 Min: 17.91 / Avg: 169.5 / Max: 286.78 Min: 19.29 / Avg: 158.59 / Max: 231.88 Min: 79.43 / Avg: 211.35 / Max: 460.63
ebizzy OpenBenchmarking.org Watts, Fewer Is Better ebizzy 0.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 133.51 / Avg: 476.25 / Max: 581.88 Min: 21.89 / Avg: 232.97 / Max: 277.3 Min: 18.28 / Avg: 311.19 / Max: 372.03 Min: 42.03 / Avg: 631.31 / Max: 767.46 Min: 43.33 / Avg: 481.07 / Max: 577.37 Min: 42.62 / Avg: 224.4 / Max: 265.28 Min: 89.69 / Avg: 452.29 / Max: 549.22 Min: 54.63 / Avg: 609.68 / Max: 750.06 Min: 46.44 / Avg: 488.18 / Max: 604.99 Min: 26.54 / Avg: 300.39 / Max: 357.13 Min: 26.33 / Avg: 246.52 / Max: 293.17 Min: 114.67 / Avg: 466.7 / Max: 570.84 Min: 57.15 / Avg: 231.39 / Max: 285.46 Min: 62.8 / Avg: 237.52 / Max: 290.91 Min: 74.96 / Avg: 423.84 / Max: 505.86 Min: 34.28 / Avg: 208.24 / Max: 246.4 Min: 78.29 / Avg: 412.01 / Max: 496.95 Min: 35.81 / Avg: 206.51 / Max: 245.66 Min: 37.65 / Avg: 195.84 / Max: 230.29 Min: 82.07 / Avg: 391.19 / Max: 461.45
OpenBenchmarking.org Records/s Per Watt, More Is Better ebizzy 0.3 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4K 8K 12K 16K 20K 3934.54 17226.24 15325.41 9220.48 11212.27 8986.90 6341.70 9400.07 10754.94 15548.27 17391.21 3513.76 4207.04 4709.47 7385.23 12415.08 7429.47 11357.36 12223.91 8056.04
Result
OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 1.2M 2.4M 3.6M 4.8M 6M SE +/- 26102.71, N = 3 SE +/- 41834.71, N = 15 SE +/- 38422.79, N = 13 SE +/- 105603.89, N = 15 SE +/- 108149.58, N = 15 SE +/- 18399.25, N = 7 SE +/- 61589.71, N = 15 SE +/- 121230.32, N = 15 SE +/- 133651.04, N = 12 SE +/- 53379.81, N = 15 SE +/- 56812.23, N = 15 SE +/- 19665.52, N = 12 SE +/- 8108.16, N = 3 SE +/- 7489.45, N = 3 SE +/- 63488.17, N = 15 SE +/- 3596.86, N = 3 SE +/- 67846.42, N = 15 SE +/- 31247.78, N = 13 SE +/- 18666.48, N = 3 SE +/- 8983.85, N = 3 1872541 4013193 4769106 5820948 5393882 2016627 2868278 5731049 5250316 4670562 4287200 1639889 973463 1118582 3130176 2585316 3061051 2345395 2393917 3151425 1. (CC) gcc options: -pthread -lpthread -O3 -march=native Records/s Per Watt
OpenBenchmarking.org Records/s Per Watt, More Is Better ebizzy 0.3 Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4K 8K 12K 16K 20K 3934.54 17226.24 15325.41 9220.48 11212.27 8986.90 6341.70 9400.07 10754.94 15548.27 17391.21 3513.76 4207.04 4709.47 7385.23 12415.08 7429.47 11357.36 12223.91 8056.04 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ebizzy 0.3 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 130 260 390 520 650 Min: 133.51 / Avg: 476.25 / Max: 581.88 Min: 21.89 / Avg: 232.97 / Max: 277.3 Min: 18.28 / Avg: 311.19 / Max: 372.03 Min: 42.03 / Avg: 631.31 / Max: 767.46 Min: 43.33 / Avg: 481.07 / Max: 577.37 Min: 42.62 / Avg: 224.4 / Max: 265.28 Min: 89.69 / Avg: 452.29 / Max: 549.22 Min: 54.63 / Avg: 609.68 / Max: 750.06 Min: 46.44 / Avg: 488.18 / Max: 604.99 Min: 26.54 / Avg: 300.39 / Max: 357.13 Min: 26.33 / Avg: 246.52 / Max: 293.17 Min: 114.67 / Avg: 466.7 / Max: 570.84 Min: 57.15 / Avg: 231.39 / Max: 285.46 Min: 62.8 / Avg: 237.52 / Max: 290.91 Min: 74.96 / Avg: 423.84 / Max: 505.86 Min: 34.28 / Avg: 208.24 / Max: 246.4 Min: 78.29 / Avg: 412.01 / Max: 496.95 Min: 35.81 / Avg: 206.51 / Max: 245.66 Min: 37.65 / Avg: 195.84 / Max: 230.29 Min: 82.07 / Avg: 391.19 / Max: 461.45
oneDNN OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 132.35 / Avg: 365.98 / Max: 540.89 Min: 21.82 / Avg: 162.41 / Max: 286.89 Min: 18.4 / Avg: 176 / Max: 333.69 Min: 43.51 / Avg: 280.81 / Max: 537.42 Min: 40.23 / Avg: 275.53 / Max: 514.15 Min: 42.78 / Avg: 180.13 / Max: 277.72 Min: 89.11 / Avg: 314.43 / Max: 508.41 Min: 50.87 / Avg: 305.48 / Max: 505.31 Min: 51.96 / Avg: 288.57 / Max: 456.99 Min: 27.13 / Avg: 167.65 / Max: 295.22 Min: 26.8 / Avg: 158.47 / Max: 286.83 Min: 116.16 / Avg: 339.23 / Max: 540.54 Min: 58.33 / Avg: 187.92 / Max: 285.25 Min: 60.52 / Avg: 191.45 / Max: 290.97 Min: 75.02 / Avg: 308.1 / Max: 572.87 Min: 34.15 / Avg: 167.6 / Max: 269.49 Min: 77.35 / Avg: 280.84 / Max: 490.19 Min: 36.01 / Avg: 152.43 / Max: 241.75 Min: 37.9 / Avg: 147.54 / Max: 230.36 Min: 82.02 / Avg: 291.06 / Max: 460.21
Result
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 0.4459 0.8918 1.3377 1.7836 2.2295 SE +/- 0.001485, N = 7 SE +/- 0.000753, N = 7 SE +/- 0.001154, N = 7 SE +/- 0.001500, N = 7 SE +/- 0.002218, N = 15 SE +/- 0.004588, N = 7 SE +/- 0.028000, N = 15 SE +/- 0.002765, N = 15 SE +/- 0.000899, N = 7 SE +/- 0.001008, N = 7 SE +/- 0.001346, N = 7 SE +/- 0.002389, N = 7 SE +/- 0.001212, N = 7 SE +/- 0.001800, N = 7 SE +/- 0.035324, N = 15 SE +/- 0.018656, N = 12 SE +/- 0.030182, N = 15 SE +/- 0.002404, N = 7 SE +/- 0.001820, N = 7 SE +/- 0.028672, N = 15 1.227510 0.280237 0.261029 0.282014 0.289708 1.604200 1.298430 0.341806 0.381155 0.281104 0.285820 1.981630 1.499960 1.403060 0.714856 0.933818 0.796595 1.577660 1.595740 0.793824 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better oneDNN 2.6 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 100 200 300 400 500 Min: 132.35 / Avg: 365.98 / Max: 540.89 Min: 21.82 / Avg: 162.41 / Max: 286.89 Min: 18.4 / Avg: 176 / Max: 333.69 Min: 43.51 / Avg: 280.81 / Max: 537.42 Min: 40.23 / Avg: 275.53 / Max: 514.15 Min: 42.78 / Avg: 180.13 / Max: 277.72 Min: 89.11 / Avg: 314.43 / Max: 508.41 Min: 50.87 / Avg: 305.48 / Max: 505.31 Min: 51.96 / Avg: 288.57 / Max: 456.99 Min: 27.13 / Avg: 167.65 / Max: 295.22 Min: 26.8 / Avg: 158.47 / Max: 286.83 Min: 116.16 / Avg: 339.23 / Max: 540.54 Min: 58.33 / Avg: 187.92 / Max: 285.25 Min: 60.52 / Avg: 191.45 / Max: 290.97 Min: 75.02 / Avg: 308.1 / Max: 572.87 Min: 34.15 / Avg: 167.6 / Max: 269.49 Min: 77.35 / Avg: 280.84 / Max: 490.19 Min: 36.01 / Avg: 152.43 / Max: 241.75 Min: 37.9 / Avg: 147.54 / Max: 230.36 Min: 82.02 / Avg: 291.06 / Max: 460.21
NAS Parallel Benchmarks OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 129.31 / Avg: 412.35 / Max: 564.07 Min: 21.86 / Avg: 155.36 / Max: 278.04 Min: 19.73 / Avg: 154.65 / Max: 279.54 Min: 41.53 / Avg: 265.85 / Max: 569.98 Min: 41.2 / Avg: 260.06 / Max: 549.34 Min: 43.25 / Avg: 179.08 / Max: 260.37 Min: 88.59 / Avg: 338.08 / Max: 546.81 Min: 52.77 / Avg: 289.69 / Max: 613.7 Min: 50.25 / Avg: 278 / Max: 574.66 Min: 27.18 / Avg: 171.33 / Max: 306.38 Min: 25.76 / Avg: 167.73 / Max: 292.41 Min: 112.17 / Avg: 409.49 / Max: 548.23 Min: 61.16 / Avg: 221.5 / Max: 271.85 Min: 61.42 / Avg: 214.32 / Max: 277.23 Min: 75.37 / Avg: 315.78 / Max: 548.53 Min: 34.59 / Avg: 183.56 / Max: 278.02 Min: 76.9 / Avg: 308.1 / Max: 520.1 Min: 36.11 / Avg: 173.06 / Max: 256.08 Min: 37.98 / Avg: 163.33 / Max: 222.6 Min: 81.88 / Avg: 294.63 / Max: 451.81
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 7 14 21 28 35 6.786 31.400 31.657 30.096 29.570 14.748 13.054 27.759 27.680 28.844 29.146 7.062 9.895 10.611 16.357 15.461 15.351 15.572 16.363 16.168
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 2K 4K 6K 8K 10K SE +/- 8.39, N = 4 SE +/- 13.30, N = 5 SE +/- 8.06, N = 5 SE +/- 146.90, N = 15 SE +/- 127.97, N = 15 SE +/- 28.14, N = 3 SE +/- 11.17, N = 5 SE +/- 190.79, N = 15 SE +/- 138.87, N = 15 SE +/- 18.47, N = 5 SE +/- 24.99, N = 5 SE +/- 12.95, N = 4 SE +/- 3.06, N = 3 SE +/- 4.23, N = 3 SE +/- 42.90, N = 15 SE +/- 34.33, N = 4 SE +/- 75.53, N = 15 SE +/- 15.95, N = 4 SE +/- 10.18, N = 4 SE +/- 74.45, N = 15 2798.30 4878.23 4895.84 8001.12 7690.07 2641.00 4413.49 8041.38 7694.93 4941.75 4888.52 2891.84 2191.66 2274.13 5165.19 2838.04 4729.63 2695.00 2672.58 4763.44 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 4.1.4 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 7 14 21 28 35 6.786 31.400 31.657 30.096 29.570 14.748 13.054 27.759 27.680 28.844 29.146 7.062 9.895 10.611 16.357 15.461 15.351 15.572 16.363 16.168 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 110 220 330 440 550 Min: 129.31 / Avg: 412.35 / Max: 564.07 Min: 21.86 / Avg: 155.36 / Max: 278.04 Min: 19.73 / Avg: 154.65 / Max: 279.54 Min: 41.53 / Avg: 265.85 / Max: 569.98 Min: 41.2 / Avg: 260.06 / Max: 549.34 Min: 43.25 / Avg: 179.08 / Max: 260.37 Min: 88.59 / Avg: 338.08 / Max: 546.81 Min: 52.77 / Avg: 289.69 / Max: 613.7 Min: 50.25 / Avg: 278 / Max: 574.66 Min: 27.18 / Avg: 171.33 / Max: 306.38 Min: 25.76 / Avg: 167.73 / Max: 292.41 Min: 112.17 / Avg: 409.49 / Max: 548.23 Min: 61.16 / Avg: 221.5 / Max: 271.85 Min: 61.42 / Avg: 214.32 / Max: 277.23 Min: 75.37 / Avg: 315.78 / Max: 548.53 Min: 34.59 / Avg: 183.56 / Max: 278.02 Min: 76.9 / Avg: 308.1 / Max: 520.1 Min: 36.11 / Avg: 173.06 / Max: 256.08 Min: 37.98 / Avg: 163.33 / Max: 222.6 Min: 81.88 / Avg: 294.63 / Max: 451.81
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 122.48 / Avg: 459.67 / Max: 581.5 Min: 21.62 / Avg: 236.44 / Max: 317.87 Min: 21.71 / Avg: 230.79 / Max: 300.9 Min: 43.17 / Avg: 424.19 / Max: 670.3 Min: 43.16 / Avg: 423.95 / Max: 660.91 Min: 42.51 / Avg: 229.99 / Max: 274.73 Min: 88.75 / Avg: 432.21 / Max: 545.6 Min: 52.68 / Avg: 493.62 / Max: 819.03 Min: 51.82 / Avg: 403.27 / Max: 671.24 Min: 26.16 / Avg: 299.08 / Max: 409.41 Min: 25.34 / Avg: 237.4 / Max: 323.86 Min: 111.68 / Avg: 449.71 / Max: 570.3 Min: 59.44 / Avg: 242.86 / Max: 285.08 Min: 59.75 / Avg: 245.23 / Max: 290.78 Min: 74.54 / Avg: 449.43 / Max: 573.91 Min: 34.18 / Avg: 248.55 / Max: 286.58 Min: 77.27 / Avg: 396.58 / Max: 518.88 Min: 35.94 / Avg: 217.35 / Max: 256.47 Min: 37.61 / Avg: 199.56 / Max: 230.17 Min: 81.25 / Avg: 371.92 / Max: 461.44
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 11 22 33 44 55 18.81 36.52 38.51 38.54 38.21 14.08 14.75 44.01 49.90 41.13 47.75 18.38 17.22 18.91 22.08 22.10 26.06 24.39 24.41 25.10
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 5K 10K 15K 20K 25K SE +/- 114.34, N = 15 SE +/- 165.09, N = 15 SE +/- 21.62, N = 4 SE +/- 406.67, N = 15 SE +/- 571.15, N = 12 SE +/- 12.27, N = 3 SE +/- 66.24, N = 15 SE +/- 666.94, N = 12 SE +/- 249.56, N = 15 SE +/- 324.02, N = 12 SE +/- 56.69, N = 4 SE +/- 91.51, N = 3 SE +/- 58.00, N = 15 SE +/- 51.61, N = 15 SE +/- 269.85, N = 15 SE +/- 35.17, N = 3 SE +/- 85.20, N = 9 SE +/- 10.07, N = 3 SE +/- 5.07, N = 3 SE +/- 108.23, N = 15 8647.74 8634.10 8887.57 16347.89 16197.05 3238.91 6374.82 21722.65 20121.23 12299.79 11335.94 8264.36 4181.13 4636.72 9921.73 5491.62 10333.19 5300.77 4871.16 9336.77 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 4.1.4 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 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 11 22 33 44 55 18.81 36.52 38.51 38.54 38.21 14.08 14.75 44.01 49.90 41.13 47.75 18.38 17.22 18.91 22.08 22.10 26.06 24.39 24.41 25.10 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 122.48 / Avg: 459.67 / Max: 581.5 Min: 21.62 / Avg: 236.44 / Max: 317.87 Min: 21.71 / Avg: 230.79 / Max: 300.9 Min: 43.17 / Avg: 424.19 / Max: 670.3 Min: 43.16 / Avg: 423.95 / Max: 660.91 Min: 42.51 / Avg: 229.99 / Max: 274.73 Min: 88.75 / Avg: 432.21 / Max: 545.6 Min: 52.68 / Avg: 493.62 / Max: 819.03 Min: 51.82 / Avg: 403.27 / Max: 671.24 Min: 26.16 / Avg: 299.08 / Max: 409.41 Min: 25.34 / Avg: 237.4 / Max: 323.86 Min: 111.68 / Avg: 449.71 / Max: 570.3 Min: 59.44 / Avg: 242.86 / Max: 285.08 Min: 59.75 / Avg: 245.23 / Max: 290.78 Min: 74.54 / Avg: 449.43 / Max: 573.91 Min: 34.18 / Avg: 248.55 / Max: 286.58 Min: 77.27 / Avg: 396.58 / Max: 518.88 Min: 35.94 / Avg: 217.35 / Max: 256.47 Min: 37.61 / Avg: 199.56 / Max: 230.17 Min: 81.25 / Avg: 371.92 / Max: 461.44
Pennant OpenBenchmarking.org Watts, Fewer Is Better Pennant 1.0.1 CPU Power Consumption Monitor Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 129.69 / Avg: 371.27 / Max: 581.86 Min: 19.8 / Avg: 156.27 / Max: 311.63 Min: 19.8 / Avg: 160.33 / Max: 318.28 Min: 42.46 / Avg: 258.74 / Max: 664.84 Min: 41.74 / Avg: 247.65 / Max: 622.17 Min: 42.89 / Avg: 185.1 / Max: 276.13 Min: 88.76 / Avg: 312.94 / Max: 546.78 Min: 51.79 / Avg: 307.67 / Max: 818.81 Min: 50.53 / Avg: 270.65 / Max: 636.18 Min: 26.62 / Avg: 195.6 / Max: 409.46 Min: 24.46 / Avg: 158.29 / Max: 316.6 Min: 107.58 / Avg: 378.32 / Max: 568.51 Min: 60.1 / Avg: 220.02 / Max: 284.79 Min: 55.77 / Avg: 218.87 / Max: 290.86 Min: 41.91 / Avg: 279.27 / Max: 567.9 Min: 34.44 / Avg: 165.77 / Max: 278.34 Min: 76.87 / Avg: 259.93 / Max: 497.86 Min: 35.99 / Avg: 153.97 / Max: 253.07 Min: 37.71 / Avg: 151.24 / Max: 230.33 Min: 80.97 / Avg: 258.52 / Max: 460.75
Result
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig Xeon Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 4 8 12 16 20 SE +/- 0.006909, N = 7 SE +/- 0.084956, N = 15 SE +/- 0.056585, N = 15 SE +/- 0.045794, N = 15 SE +/- 0.062550, N = 15 SE +/- 0.014185, N = 5 SE +/- 0.032179, N = 15 SE +/- 0.042439, N = 15 SE +/- 0.050393, N = 15 SE +/- 0.122551, N = 15 SE +/- 0.088305, N = 15 SE +/- 0.010589, N = 6 SE +/- 0.017254, N = 4 SE +/- 0.023873, N = 4 SE +/- 0.038831, N = 15 SE +/- 0.046366, N = 15 SE +/- 0.083507, N = 15 SE +/- 0.039217, N = 15 SE +/- 0.065779, N = 15 SE +/- 0.094749, N = 12 4.845815 4.023470 3.919148 2.375619 2.374382 8.277237 4.396425 2.146766 2.422264 3.382516 3.763021 6.488374 13.754940 12.006820 3.300578 5.419712 3.484325 5.812808 6.100938 3.631628 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 Platinum 8380 2P EPYC 9554 EPYC 9554 - Power EPYC 9554 2P - Power EPYC 9554 2P EPYC 75F3 EPYC 75F3 2P EPYC 9654 2P - Power EPYC 9654 2P EPYC 9654 - Power EPYC 9654 Xeon Platinum 8362 2P Xeon Platinum 8362 Xeon Platinum 8380 EPYC 7773X 2P EPYC 7773X EPYC 7763 2P EPYC 7763 EPYC 7713 EPYC 7713 2P 140 280 420 560 700 Min: 129.69 / Avg: 371.27 / Max: 581.86 Min: 19.8 / Avg: 156.27 / Max: 311.63 Min: 19.8 / Avg: 160.33 / Max: 318.28 Min: 42.46 / Avg: 258.74 / Max: 664.84 Min: 41.74 / Avg: 247.65 / Max: 622.17 Min: 42.89 / Avg: 185.1 / Max: 276.13 Min: 88.76 / Avg: 312.94 / Max: 546.78 Min: 51.79 / Avg: 307.67 / Max: 818.81 Min: 50.53 / Avg: 270.65 / Max: 636.18 Min: 26.62 / Avg: 195.6 / Max: 409.46 Min: 24.46 / Avg: 158.29 / Max: 316.6 Min: 107.58 / Avg: 378.32 / Max: 568.51 Min: 60.1 / Avg: 220.02 / Max: 284.79 Min: 55.77 / Avg: 218.87 / Max: 290.86 Min: 41.91 / Avg: 279.27 / Max: 567.9 Min: 34.44 / Avg: 165.77 / Max: 278.34 Min: 76.87 / Avg: 259.93 / Max: 497.86 Min: 35.99 / Avg: 153.97 / Max: 253.07 Min: 37.71 / Avg: 151.24 / Max: 230.33 Min: 80.97 / Avg: 258.52 / Max: 460.75
EPYC 7713 2P Processor: 2 x AMD EPYC 7713 64-Core @ 2.00GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 6 September 2022 15:02 by user phoronix.
EPYC 7713 Processor: AMD EPYC 7713 64-Core @ 2.00GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 10 September 2022 13:08 by user phoronix.
EPYC 7763 Processor: AMD EPYC 7763 64-Core @ 2.45GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 16 September 2022 13:42 by user phoronix.
EPYC 7763 2P Processor: 2 x AMD EPYC 7763 64-Core @ 2.45GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 18 September 2022 19:45 by user phoronix.
EPYC 7773X Processor: AMD EPYC 7773X 64-Core @ 2.20GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001229Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 19 September 2022 18:19 by user phoronix.
EPYC 7773X 2P Processor: 2 x AMD EPYC 7773X 64-Core @ 2.20GHz (128 Cores / 256 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001229Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 22 September 2022 11:14 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: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xd000375Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 30 September 2022 20:14 by user phoronix.
Xeon Platinum 8362 Processor: Intel Xeon Platinum 8362 @ 3.60GHz (32 Cores / 64 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Ice Lake IEH, Memory: 256GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xd000375Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 4 October 2022 07:14 by user phoronix.
Xeon Platinum 8362 2P Processor: 2 x Intel Xeon Platinum 8362 @ 3.60GHz (64 Cores / 128 Threads), Motherboard: Intel M50CYP2SB2U (SE5C6200.86B.0022.D08.2103221623 BIOS), Chipset: Intel Ice Lake IEH, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xd000375Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 5 October 2022 06:27 by user phoronix.
EPYC 9654 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 15 October 2022 20:32 by user phoronix.
EPYC 9654 - Power Processor: AMD EPYC 9654 96-Core @ 3.71GHz (96 Cores / 192 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 768GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 16 October 2022 16:30 by user phoronix.
EPYC 9654 2P 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 22 October 2022 01:47 by user phoronix.
EPYC 9654 2P - Power Processor: 2 x AMD EPYC 9654 96-Core @ 3.71GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 23 October 2022 21:22 by user phoronix.
EPYC 75F3 2P Processor: 2 x AMD EPYC 75F3 32-Core @ 2.95GHz (64 Cores / 128 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 512GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 27 October 2022 20:42 by user phoronix.
EPYC 75F3 Processor: AMD EPYC 75F3 32-Core @ 2.95GHz (32 Cores / 64 Threads), Motherboard: AMD DAYTONA_X (RYM1009B BIOS), Chipset: AMD Starship/Matisse, Memory: 256GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Mellanox MT27710
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xa001173Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 28 October 2022 16:43 by user phoronix.
EPYC 9554 2P 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 31 October 2022 16:10 by user phoronix.
EPYC 9554 2P - Power Processor: 2 x AMD EPYC 9554 64-Core @ 3.76GHz (128 Cores / 256 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 1 November 2022 14:12 by user phoronix.
EPYC 9554 - Power 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 2 November 2022 04:15 by user phoronix.
EPYC 9554 Processor: AMD EPYC 9554 64-Core @ 3.76GHz (64 Cores / 128 Threads), Motherboard: AMD Titanite_4G (RTI1002E BIOS), Chipset: AMD Device 14a4, Memory: 768GB, Disk: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VGA HDMI, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: amd-pstate performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 2 November 2022 18:27 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: 3841GB Micron_9300_MTFDHAL3T8TDP, Graphics: ASPEED, Monitor: VE228, Network: 2 x Intel X710 for 10GBASE-T + 2 x Intel E810-C for QSFP
OS: Ubuntu 22.10, Kernel: 6.0.0-060000rc3daily20220904-generic (x86_64), Desktop: GNOME Shell, Display Server: X Server 1.21.1.3, Vulkan: 1.3.211, Compiler: GCC 12.2.0, 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-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-12-Wbc0TK/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-Wbc0TK/gcc-12-12.2.0/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: 0xd000375Java Notes: OpenJDK Runtime Environment (build 11.0.16+8-post-Ubuntu-0ubuntu1)Python Notes: Python 3.10.6Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 4 November 2022 14:06 by user phoronix.