AMD 5th Gen EPYC Linux benchmarks by Michael Larabel for a future article of EPYC 9655 / EPYC 9755 compared to Genoa EPYC 9654 and Intel Xeon Granite Rapids 6980P processors.
Xeon 6980P @ DDR5-6400 Processor: Intel Xeon 6980P @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 768GB, Disk: 960GB SAMSUNG MZ1L2960HCJR-00A07 + 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected
Xeon 6980P @ MRDIMM-8800 Changed Disk to 2 x 1920GB KIOXIA KCD8XPUG1T92 + 960GB SAMSUNG MZ1L2960HCJR-00A07 .
Xeon 6980P 2P @ DDR5-6400 Changed Processor to 2 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads) .
Changed Memory to 1520GB .
Changed Disk to 960GB SAMSUNG MZ1L2960HCJR-00A07 + 2 x 1920GB KIOXIA KCD8XPUG1T92 .
Xeon 6980P 2P @ MRDIMM-8800 Changed Motherboard to Intel BIRCHSTREAM (BHSDCRB1.IPC.0035.D44.2408292336 BIOS) .
Changed Disk to 2 x 1920GB KIOXIA KCD8XPUG1T92 + 960GB SAMSUNG MZ1L2960HCJR-00A07 .
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Security Change: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9654 Processor: AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads)Motherboard: AMD Titanite_4G (RTI1007B BIOS)Chipset: AMD Device 14a4Memory: 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEGDisk: 2 x 1920GB KIOXIA KCD8XPUG1T92Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9654 2P Changed Processor to 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads) .
Changed Memory to 1520GB .
EPYC 9655 Processor: AMD EPYC 9655 96-Core @ 2.60GHz (96 Cores / 192 Threads)Motherboard: AMD VOLCANO (RVOT1000D BIOS)Chipset: AMD Device 153aMemory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKCDisk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
EPYC 9655 2P Changed Processor to 2 x AMD EPYC 9655 96-Core @ 2.60GHz (192 Cores / 384 Threads) .
Changed Memory to 1520GB .
EPYC 9755 Changed Processor to AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads) .
Changed Memory to 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC .
EPYC 9755 2P Changed Processor to 2 x AMD EPYC 9755 128-Core @ 2.70GHz (256 Cores / 512 Threads) .
Changed Memory to 1520GB .
Changed Disk to Samsung SSD 980 500GB + 2 x 1920GB KIOXIA KCD8XPUG1T92 .
OpenVKL OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 1200 2400 3600 4800 6000 SE +/- 1.20, N = 3 SE +/- 8.67, N = 3 SE +/- 0.88, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 27.72, N = 3 SE +/- 43.45, N = 4 SE +/- 22.85, N = 3 SE +/- 8.19, N = 3 SE +/- 21.66, N = 3 2077 3335 2814 4634 3654 5663 3947 3908 3268 3291 MIN: 160 / MAX: 26161 MIN: 299 / MAX: 40960 MIN: 215 / MAX: 36394 MIN: 417 / MAX: 52082 MIN: 293 / MAX: 42376 MIN: 560 / MAX: 58963 MIN: 481 / MAX: 26338 MIN: 479 / MAX: 25430 MIN: 264 / MAX: 42594 MIN: 259 / MAX: 42493 Items / Sec Per Watt
OpenBenchmarking.org Items / Sec Per Watt, More Is Better OpenVKL 2.0.0 Benchmark: vklBenchmarkCPU ISPC EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3 6 9 12 15 7.601 9.341 9.156 7.647 7.574 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVKL 2.0.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 28.49 / Avg: 273.27 / Max: 332.24 Min: 42.34 / Avg: 301.24 / Max: 356.28 Min: 44.92 / Avg: 399.08 / Max: 477.59 Min: 49.38 / Avg: 427.36 / Max: 531.16 Min: 55.92 / Avg: 434.52 / Max: 535.03
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.
NAMD NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ns/day, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3 6 9 12 15 SE +/- 0.00537, N = 3 SE +/- 0.02927, N = 3 SE +/- 0.00164, N = 3 SE +/- 0.01771, N = 3 SE +/- 0.00697, N = 3 SE +/- 0.07369, N = 10 SE +/- 0.07262, N = 9 SE +/- 0.07599, N = 9 SE +/- 0.05786, N = 15 SE +/- 0.07833, N = 12 2.87877 5.27839 4.18891 7.93661 4.62277 9.33439 0.37009 0.37969 2.12510 1.90525 ns/day Per Watt
OpenBenchmarking.org ns/day Per Watt, More Is Better NAMD 3.0b6 Input: STMV with 1,066,628 Atoms EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0041 0.0082 0.0123 0.0164 0.0205 0.012 0.018 0.016 0.007 0.006 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAMD 3.0b6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 28.55 / Avg: 235.77 / Max: 330 Min: 41.83 / Avg: 235.16 / Max: 336.03 Min: 44.51 / Avg: 284.44 / Max: 425.63 Min: 49.15 / Avg: 311.15 / Max: 442.87 Min: 28.33 / Avg: 337.04 / Max: 455.76
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.
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 1024 CPU threads. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 16.1 Chess Benchmark EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 120M 240M 360M 480M 600M SE +/- 3170744.86, N = 15 SE +/- 2356843.91, N = 3 SE +/- 3587851.54, N = 15 SE +/- 4310907.78, N = 3 SE +/- 4338134.07, N = 15 SE +/- 7520081.68, N = 3 SE +/- 2910415.51, N = 15 SE +/- 5154575.31, N = 12 SE +/- 3585875.08, N = 15 SE +/- 4147707.14, N = 12 197708350 370751530 219189543 426839881 307343923 543944789 346175342 345790812 207794619 198271374 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver Nodes Per Second Per Watt
OpenBenchmarking.org Nodes Per Second Per Watt, More Is Better Stockfish 16.1 Chess Benchmark EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 150K 300K 450K 600K 750K 569277.48 668223.51 697627.07 432909.23 413612.73 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Stockfish 16.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 30.05 / Avg: 347.3 / Max: 373.1 Min: 42.3 / Avg: 328.02 / Max: 363.72 Min: 44.77 / Avg: 440.56 / Max: 487.21 Min: 51.7 / Avg: 480 / Max: 547.86 Min: 50.92 / Avg: 479.36 / Max: 541.75
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: X3D-benchmarking input.i3d EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 SE +/- 4.73, N = 3 SE +/- 3.26, N = 9 SE +/- 0.55, N = 3 SE +/- 1.75, N = 12 SE +/- 0.78, N = 3 SE +/- 4.41, N = 12 SE +/- 0.36, N = 3 SE +/- 0.36, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 466.55 248.87 201.85 117.97 199.84 159.85 81.41 68.62 170.91 143.37 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 30.46 / Avg: 296.94 / Max: 321.61 Min: 42.31 / Avg: 324.17 / Max: 343.18 Min: 44.86 / Avg: 401.65 / Max: 443.92 Min: 48.47 / Avg: 426.01 / Max: 464.59 Min: 50.4 / Avg: 458.4 / Max: 493.86
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50 100 150 200 250 SE +/- 0.34, N = 3 SE +/- 1.83, N = 3 SE +/- 0.03, N = 3 SE +/- 2.10, N = 3 SE +/- 0.52, N = 3 SE +/- 2.05, N = 3 SE +/- 2.02, N = 3 SE +/- 2.21, N = 4 SE +/- 1.45, N = 3 SE +/- 0.69, N = 3 140.01 161.90 240.07 238.49 246.24 210.75 178.53 180.57 223.12 234.72 images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.2063 0.4126 0.6189 0.8252 1.0315 0.487 0.917 0.730 0.592 0.598 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 30.39 / Avg: 287.56 / Max: 321.33 Min: 42.41 / Avg: 261.74 / Max: 287.47 Min: 45.08 / Avg: 337.16 / Max: 361.72 Min: 49.72 / Avg: 376.95 / Max: 425.38 Min: 55.61 / Avg: 392.45 / Max: 448.78
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 10 20 30 40 50 SE +/- 0.18, N = 15 SE +/- 0.84, N = 15 SE +/- 0.06, N = 3 SE +/- 0.53, N = 14 SE +/- 0.52, N = 15 SE +/- 1.05, N = 15 SE +/- 0.35, N = 15 SE +/- 0.44, N = 15 SE +/- 0.42, N = 15 SE +/- 0.44, N = 15 21.32 29.61 24.19 35.36 32.02 43.95 18.85 19.77 22.13 21.89 MIN: 18.08 / MAX: 26.9 MIN: 22.93 / MAX: 46.21 MIN: 21.58 / MAX: 32.81 MIN: 29.34 / MAX: 57.89 MIN: 26.48 / MAX: 43.04 MIN: 33.51 / MAX: 72.83 MIN: 11.1 / MAX: 44.53 MIN: 11.1 / MAX: 46.94 MIN: 16.42 / MAX: 35.75 MIN: 15.78 / MAX: 35.94 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.6 Scene: Orange Juice - Acceleration: CPU EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.018 0.036 0.054 0.072 0.09 0.072 0.080 0.074 0.049 0.048 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.54 / Avg: 296.6 / Max: 330.72 Min: 42.45 / Avg: 300.75 / Max: 347.52 Min: 45.04 / Avg: 431.61 / Max: 490.85 Min: 50.62 / Avg: 453.08 / Max: 540.71 Min: 52.8 / Avg: 453.43 / Max: 540.55
Result
OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 7 14 21 28 35 SE +/- 0.13, N = 3 SE +/- 0.12, N = 3 SE +/- 0.17, N = 15 SE +/- 0.51, N = 12 SE +/- 0.33, N = 15 SE +/- 0.95, N = 15 SE +/- 0.22, N = 15 SE +/- 0.23, N = 15 SE +/- 0.38, N = 15 SE +/- 0.35, N = 12 14.29 17.89 16.80 24.34 20.94 30.46 9.90 10.03 13.91 13.47 MIN: 13.78 / MAX: 17.04 MIN: 16.29 / MAX: 28.22 MIN: 15.67 / MAX: 20.23 MIN: 21.68 / MAX: 36.31 MIN: 19.5 / MAX: 27 MIN: 24.88 / MAX: 45.22 MIN: 6.7 / MAX: 24.04 MIN: 6.61 / MAX: 25.18 MIN: 11.25 / MAX: 23.63 MIN: 11.22 / MAX: 23.3 M samples/sec Per Watt
OpenBenchmarking.org M samples/sec Per Watt, More Is Better LuxCoreRender 2.6 Scene: DLSC - Acceleration: CPU EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0122 0.0244 0.0366 0.0488 0.061 0.048 0.054 0.048 0.030 0.029 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LuxCoreRender 2.6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.9 / Avg: 299.39 / Max: 326.71 Min: 42.45 / Avg: 312.93 / Max: 342.68 Min: 44.57 / Avg: 438.92 / Max: 482.64 Min: 46.71 / Avg: 459.42 / Max: 539.94 Min: 50.16 / Avg: 462.8 / Max: 540.07
Speedb Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Read While Writing EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 8M 16M 24M 32M 40M SE +/- 170909.18, N = 3 SE +/- 746932.76, N = 15 SE +/- 135475.45, N = 3 SE +/- 254480.91, N = 3 SE +/- 433421.14, N = 12 SE +/- 1204634.08, N = 15 SE +/- 419790.55, N = 15 SE +/- 597439.70, N = 15 SE +/- 299633.51, N = 12 SE +/- 310946.14, N = 15 18024993 30324596 15003965 26712002 18687897 34825934 35747722 37303792 19649049 18601575 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread Op/s Per Watt
OpenBenchmarking.org Op/s Per Watt, More Is Better Speedb 2.7 Test: Read While Writing EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 14K 28K 42K 56K 70K 63472.87 47929.33 46936.44 51389.74 46292.99 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Speedb 2.7 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 26.3 / Avg: 283.98 / Max: 305.25 Min: 42.29 / Avg: 313.04 / Max: 351.74 Min: 44.64 / Avg: 398.15 / Max: 497.59 Min: 50.62 / Avg: 382.35 / Max: 541.17 Min: 50.45 / Avg: 401.82 / Max: 540.54
ClickHouse ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 160 320 480 640 800 SE +/- 4.03, N = 3 SE +/- 10.00, N = 3 SE +/- 0.75, N = 3 SE +/- 2.38, N = 3 SE +/- 4.70, N = 3 SE +/- 8.02, N = 3 SE +/- 1.86, N = 3 SE +/- 4.00, N = 3 SE +/- 3.00, N = 6 SE +/- 3.43, N = 4 559.55 525.23 763.39 741.43 724.64 652.64 217.72 217.88 415.77 439.81 MIN: 57.03 / MAX: 5000 MIN: 81.86 / MAX: 5000 MIN: 69.36 / MAX: 8571.43 MIN: 105.26 / MAX: 7500 MIN: 85.11 / MAX: 6666.67 MIN: 118.81 / MAX: 6666.67 MIN: 40.16 / MAX: 3157.89 MIN: 38.36 / MAX: 3529.41 MIN: 66.23 / MAX: 4615.38 MIN: 68.42 / MAX: 4285.71 Queries Per Minute, Geo Mean Per Watt
OpenBenchmarking.org Queries Per Minute, Geo Mean Per Watt, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Third Run EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 1.0384 2.0768 3.1152 4.1536 5.192 4.053 4.615 4.431 2.946 2.909 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ClickHouse 22.12.3.5 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 28.3 / Avg: 138.04 / Max: 305.03 Min: 41.94 / Avg: 165.4 / Max: 302.89 Min: 44.35 / Avg: 163.53 / Max: 407.01 Min: 44.92 / Avg: 141.1 / Max: 386.84 Min: 50 / Avg: 151.17 / Max: 408.34
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, Second Run EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 160 320 480 640 800 SE +/- 3.14, N = 3 SE +/- 8.37, N = 3 SE +/- 5.05, N = 3 SE +/- 5.84, N = 3 SE +/- 5.27, N = 3 SE +/- 11.12, N = 3 SE +/- 1.13, N = 3 SE +/- 2.70, N = 3 SE +/- 4.34, N = 6 SE +/- 0.85, N = 4 562.50 529.80 755.69 735.48 729.56 651.59 213.64 213.72 410.44 435.75 MIN: 57.47 / MAX: 6666.67 MIN: 86.08 / MAX: 5454.55 MIN: 69.93 / MAX: 7500 MIN: 110.29 / MAX: 7500 MIN: 81.63 / MAX: 7500 MIN: 119.05 / MAX: 7500 MIN: 33.5 / MAX: 3333.33 MIN: 40.82 / MAX: 3529.41 MIN: 69.77 / MAX: 4615.38 MIN: 69.77 / MAX: 4615.38
OpenBenchmarking.org Queries Per Minute, Geo Mean, More Is Better ClickHouse 22.12.3.5 100M Rows Hits Dataset, First Run / Cold Cache EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 160 320 480 640 800 SE +/- 5.33, N = 3 SE +/- 6.05, N = 3 SE +/- 1.08, N = 3 SE +/- 2.73, N = 3 SE +/- 6.12, N = 3 SE +/- 4.93, N = 3 SE +/- 1.91, N = 3 SE +/- 2.77, N = 3 SE +/- 3.78, N = 6 SE +/- 4.86, N = 4 536.82 504.84 740.48 721.43 698.12 630.88 200.21 201.39 408.98 435.36 MIN: 56.6 / MAX: 6666.67 MIN: 81.97 / MAX: 4615.38 MIN: 68.57 / MAX: 8571.43 MIN: 107.91 / MAX: 7500 MIN: 80.86 / MAX: 6666.67 MIN: 109.89 / MAX: 6000 MIN: 31.35 / MAX: 2727.27 MIN: 30.35 / MAX: 2857.14 MIN: 66.74 / MAX: 4615.38 MIN: 62.24 / MAX: 5454.55
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50 100 150 200 250 SE +/- 0.66, N = 3 SE +/- 0.57, N = 3 SE +/- 1.14, N = 3 SE +/- 1.84, N = 3 SE +/- 0.65, N = 3 SE +/- 1.70, N = 3 SE +/- 0.21, N = 3 SE +/- 1.61, N = 3 SE +/- 1.06, N = 3 SE +/- 1.75, N = 3 138.11 133.87 210.14 184.47 203.33 158.64 126.62 122.40 180.26 186.94 images/sec Per Watt
OpenBenchmarking.org images/sec Per Watt, More Is Better TensorFlow 2.16.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.1924 0.3848 0.5772 0.7696 0.962 0.485 0.855 0.659 0.540 0.525 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better TensorFlow 2.16.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 29.3 / Avg: 284.71 / Max: 314.17 Min: 42.34 / Avg: 245.82 / Max: 264.32 Min: 44.84 / Avg: 308.73 / Max: 332.29 Min: 49.09 / Avg: 333.53 / Max: 378.38 Min: 50.93 / Avg: 356.04 / Max: 407.7
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: Chrysler Neon 1M EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 40 80 120 160 200 SE +/- 1.51, N = 8 SE +/- 0.71, N = 12 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.17, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 176.14 77.64 91.03 49.73 77.26 43.00 61.38 60.28 82.06 78.32 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2023.09.15 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.56 / Avg: 270.92 / Max: 332.67 Min: 42.65 / Avg: 296.94 / Max: 363.36 Min: 44.91 / Avg: 364.12 / Max: 489.25 Min: 49.81 / Avg: 370.13 / Max: 539.35 Min: 51.26 / Avg: 369.08 / Max: 540.56
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 900000M 1800000M 2700000M 3600000M 4500000M SE +/- 164763342.54, N = 3 SE +/- 337702856.52, N = 3 SE +/- 1295376232.10, N = 3 SE +/- 325870485.63, N = 3 SE +/- 679943093.73, N = 3 SE +/- 1040145141.77, N = 3 SE +/- 266676472.30, N = 3 SE +/- 2441895768.49, N = 3 SE +/- 316862649.33, N = 3 SE +/- 1079468156.27, N = 3 897288436123 1785006879067 1472835151827 2949554693370 2007365351470 3997224330763 3878078355230 3839570315567 1964597309167 1967069409960 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: AES-128-GCM EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 1000M 2000M 3000M 4000M 5000M 2686039538.13 4714124877.73 4699217928.95 4012206294.35 4013205956.76 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.74 / Avg: 334.06 / Max: 354.77 Min: 42.64 / Avg: 312.43 / Max: 329.11 Min: 44.65 / Avg: 427.17 / Max: 447.2 Min: 50.48 / Avg: 489.66 / Max: 539.94 Min: 50.8 / Avg: 490.15 / Max: 540.48
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300000M 600000M 900000M 1200000M 1500000M SE +/- 29295317.86, N = 3 SE +/- 6119305.11, N = 3 SE +/- 139220101.42, N = 3 SE +/- 567847363.95, N = 3 SE +/- 89801965.81, N = 3 SE +/- 1316278570.88, N = 3 SE +/- 774711882.62, N = 3 SE +/- 541993763.93, N = 3 SE +/- 174944331.36, N = 3 SE +/- 49597283.94, N = 3 350960998357 698925822223 615627362850 1221386705673 807009841427 1605650870013 986701602043 983054661587 497763896250 497225043487 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: ChaCha20-Poly1305 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 400M 800M 1200M 1600M 2000M 1061980440.86 1790086074.83 1746071268.12 1015831691.63 1013880039.90 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.82 / Avg: 330.48 / Max: 353.86 Min: 42.31 / Avg: 343.91 / Max: 362.03 Min: 44.65 / Avg: 462.19 / Max: 498.95 Min: 50.94 / Avg: 490.01 / Max: 540.48 Min: 51.48 / Avg: 490.42 / Max: 540.5
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 800000M 1600000M 2400000M 3200000M 4000000M SE +/- 818689705.82, N = 3 SE +/- 2225250504.62, N = 3 SE +/- 243566219.34, N = 3 SE +/- 3021247793.93, N = 3 SE +/- 2482404044.78, N = 3 SE +/- 2226119209.67, N = 3 SE +/- 4180336382.73, N = 3 SE +/- 1646468976.45, N = 3 SE +/- 2243461518.91, N = 3 SE +/- 654108493.84, N = 3 767696553667 1526505465813 1344599403087 2682968686683 1837765850747 3665896592633 3100362577873 3112294646850 1568111085887 1563790529240 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: AES-256-GCM EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 900M 1800M 2700M 3600M 4500M 2331206946.71 4358545440.70 4339501704.86 3197057120.80 3186709263.24 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.29 / Avg: 329.31 / Max: 350.94 Min: 42.27 / Avg: 308.5 / Max: 324.72 Min: 44.7 / Avg: 423.5 / Max: 443.31 Min: 50.69 / Avg: 490.49 / Max: 539.96 Min: 51.17 / Avg: 490.72 / Max: 540.43
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA512 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 30000M 60000M 90000M 120000M 150000M SE +/- 6285194.15, N = 3 SE +/- 37307640.51, N = 3 SE +/- 85304308.49, N = 3 SE +/- 334242164.38, N = 3 SE +/- 163780192.60, N = 3 SE +/- 587265222.90, N = 3 SE +/- 299324452.10, N = 3 SE +/- 123095714.53, N = 3 SE +/- 57519653.73, N = 3 SE +/- 73765633.28, N = 3 39627575497 78822257383 53901014490 107204759050 72359767240 144565915787 106427384107 105711340873 54542420633 54221405820 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: SHA512 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 40M 80M 120M 160M 200M 128564080.98 166891800.58 161764658.87 111142075.02 110629528.53 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.99 / Avg: 308.23 / Max: 338.17 Min: 42.32 / Avg: 322.97 / Max: 337.23 Min: 45.02 / Avg: 447.32 / Max: 471.81 Min: 51.04 / Avg: 490.75 / Max: 541.18 Min: 51.17 / Avg: 490.12 / Max: 539.94
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: SHA256 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80000M 160000M 240000M 320000M 400000M SE +/- 38601729.93, N = 3 SE +/- 210407867.05, N = 3 SE +/- 343661637.22, N = 3 SE +/- 182816536.21, N = 3 SE +/- 76407988.26, N = 3 SE +/- 666929568.64, N = 3 SE +/- 1048707846.36, N = 3 SE +/- 296061237.33, N = 3 SE +/- 208435661.63, N = 3 SE +/- 182381368.83, N = 3 126475137690 251645629887 137625591907 274972637600 186660393313 370780418480 300485773490 299610746847 153362715637 152704659163 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: SHA256 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90M 180M 270M 360M 450M 386445411.79 413951053.97 401864487.87 312750573.92 311566125.07 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.19 / Avg: 327.28 / Max: 361.5 Min: 42.42 / Avg: 332.47 / Max: 351.48 Min: 44.83 / Avg: 464.49 / Max: 492.11 Min: 50.79 / Avg: 490.37 / Max: 540.47 Min: 50.77 / Avg: 490.12 / Max: 539.97
Result
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 500000M 1000000M 1500000M 2000000M 2500000M SE +/- 151272595.84, N = 3 SE +/- 80233613.02, N = 3 SE +/- 211781187.22, N = 3 SE +/- 200687972.98, N = 3 SE +/- 507390352.95, N = 3 SE +/- 600986542.59, N = 3 SE +/- 719739801.83, N = 3 SE +/- 527088585.29, N = 3 SE +/- 114312823.74, N = 3 SE +/- 288670768.28, N = 3 503311021123 1001502634860 905409634213 1796116544717 1186359294450 2360488961000 1505124917340 1492693900400 761960960000 760875022490 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl byte/s Per Watt
OpenBenchmarking.org byte/s Per Watt, More Is Better OpenSSL 3.3 Algorithm: ChaCha20 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 600M 1200M 1800M 2400M 3000M 1510491450.86 2590512735.18 2532659749.39 1552821305.41 1552456968.84 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenSSL 3.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 30.31 / Avg: 333.21 / Max: 358.89 Min: 42.55 / Avg: 349.51 / Max: 368.35 Min: 44.99 / Avg: 468.42 / Max: 500.98 Min: 50.59 / Avg: 490.69 / Max: 541.01 Min: 50.42 / Avg: 490.11 / Max: 540.52
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 7 14 21 28 35 SE +/- 0.16, N = 14 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 15 SE +/- 0.64, N = 15 SE +/- 0.47, N = 15 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 16.32 23.12 11.20 11.37 10.73 11.21 29.61 30.02 12.97 12.92 MIN: 8.11 / MAX: 42.33 MIN: 10.62 / MAX: 67.83 MIN: 6.35 / MAX: 28.48 MIN: 7.75 / MAX: 45.15 MIN: 6.4 / MAX: 32.23 MIN: 7.52 / MAX: 54.87 MIN: 7.03 / MAX: 321.65 MIN: 6.85 / MAX: 313.69 MIN: 6.82 / MAX: 55.85 MIN: 7.06 / MAX: 56.43 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 29.75 / Avg: 315.18 / Max: 357.38 Min: 42.85 / Avg: 300.7 / Max: 326.4 Min: 44.91 / Avg: 397.17 / Max: 438.79 Min: 51.41 / Avg: 409.23 / Max: 468.4 Min: 51.35 / Avg: 428.39 / Max: 498.15
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3K 6K 9K 12K 15K SE +/- 67.22, N = 14 SE +/- 77.59, N = 3 SE +/- 10.75, N = 3 SE +/- 91.27, N = 3 SE +/- 33.49, N = 3 SE +/- 129.79, N = 15 SE +/- 67.53, N = 15 SE +/- 71.88, N = 15 SE +/- 92.39, N = 3 SE +/- 41.62, N = 3 5697.51 7810.65 8266.34 11384.88 10557.16 11713.40 5172.09 5212.74 9577.04 9585.13 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Timed Linux Kernel Compilation This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 6.8 Build: allmodconfig EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 SE +/- 0.49, N = 3 SE +/- 0.49, N = 3 SE +/- 0.40, N = 3 SE +/- 0.66, N = 3 SE +/- 0.88, N = 3 SE +/- 0.75, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.64, N = 3 SE +/- 0.43, N = 3 311.83 197.63 194.47 117.47 201.76 115.55 131.13 132.52 171.53 173.91 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Linux Kernel Compilation 6.8 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.23 / Avg: 282.28 / Max: 331.17 Min: 41.83 / Avg: 306.09 / Max: 360.29 Min: 44.41 / Avg: 383.82 / Max: 473.43 Min: 43.98 / Avg: 382.69 / Max: 540.51 Min: 49.02 / Avg: 387.13 / Max: 540.51
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 28.07 47.53 42.20 74.50 54.40 89.80 72.07 72.48 57.02 57.20 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 3.1 Benchmark: particle_volume/scivis/real_time EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0394 0.0788 0.1182 0.1576 0.197 0.107 0.151 0.144 0.175 0.169 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 3.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 28.04 / Avg: 261.28 / Max: 302.78 Min: 42.57 / Avg: 279.1 / Max: 323.77 Min: 44.78 / Avg: 376.84 / Max: 448.56 Min: 49.89 / Avg: 325.73 / Max: 423.03 Min: 51.82 / Avg: 339.42 / Max: 440.9
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 30 60 90 120 150 SE +/- 2.90, N = 15 SE +/- 0.44, N = 15 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.54, N = 15 SE +/- 0.53, N = 12 SE +/- 0.63, N = 6 SE +/- 0.28, N = 3 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 157.45 63.98 69.72 32.63 87.14 37.25 62.30 61.49 47.05 43.82 MIN: 52.3 / MAX: 282.08 MIN: 39.78 / MAX: 114.18 MIN: 33.74 / MAX: 128.03 MIN: 27.36 / MAX: 67.99 MIN: 35.35 / MAX: 200.15 MIN: 27.7 / MAX: 102.96 MIN: 30.34 / MAX: 380.81 MIN: 30.56 / MAX: 381.35 MIN: 31.24 / MAX: 91.93 MIN: 28.4 / MAX: 92.09 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 28.22 / Avg: 304.28 / Max: 347.63 Min: 42.46 / Avg: 321.76 / Max: 347.42 Min: 44.83 / Avg: 386.55 / Max: 442.75 Min: 49.9 / Avg: 377.27 / Max: 417.38 Min: 51.1 / Avg: 403.73 / Max: 451.34
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 400 800 1200 1600 2000 SE +/- 7.13, N = 15 SE +/- 5.47, N = 15 SE +/- 0.53, N = 3 SE +/- 3.94, N = 3 SE +/- 4.77, N = 15 SE +/- 26.17, N = 12 SE +/- 10.41, N = 6 SE +/- 4.65, N = 3 SE +/- 1.77, N = 3 SE +/- 0.64, N = 3 306.27 750.11 686.91 1470.13 733.80 1720.93 1026.29 1039.62 679.12 729.23 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Timed Gem5 Compilation This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 23.0.1 Time To Compile EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 40 80 120 160 200 SE +/- 2.24, N = 4 SE +/- 0.72, N = 3 SE +/- 1.17, N = 3 SE +/- 0.25, N = 3 SE +/- 1.52, N = 3 SE +/- 1.40, N = 3 SE +/- 1.00, N = 3 SE +/- 1.03, N = 3 SE +/- 1.05, N = 3 SE +/- 1.12, N = 3 185.30 164.90 126.33 112.43 128.13 120.47 155.72 154.82 156.27 159.67 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Gem5 Compilation 23.0.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.61 / Avg: 170.81 / Max: 332.22 Min: 42.05 / Avg: 176.53 / Max: 363.06 Min: 44.36 / Avg: 195.45 / Max: 485.43 Min: 44.49 / Avg: 188.29 / Max: 541.07 Min: 48.83 / Avg: 194.2 / Max: 539.96
LAMMPS Molecular Dynamics Simulator LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.13, N = 3 SE +/- 0.52, N = 3 SE +/- 0.22, N = 3 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.34, N = 3 SE +/- 0.33, N = 3 SE +/- 0.44, N = 3 SE +/- 0.17, N = 3 42.51 57.10 56.10 75.79 67.78 80.00 93.66 93.74 68.27 67.37 1. (CXX) g++ options: -O3 -lm -ldl ns/day Per Watt
OpenBenchmarking.org ns/day Per Watt, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0378 0.0756 0.1134 0.1512 0.189 0.133 0.168 0.147 0.144 0.142 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 29.12 / Avg: 318.64 / Max: 329.98 Min: 42.2 / Avg: 334.89 / Max: 355.48 Min: 44.34 / Avg: 461.94 / Max: 488.08 Min: 44.43 / Avg: 473.95 / Max: 535.12 Min: 48.95 / Avg: 475.09 / Max: 534.43
Timed Node.js Compilation This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 21.7.2 Time To Compile EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 40 80 120 160 200 SE +/- 0.59, N = 3 SE +/- 0.18, N = 3 SE +/- 0.12, N = 3 SE +/- 0.33, N = 3 SE +/- 0.21, N = 3 SE +/- 0.43, N = 3 SE +/- 0.81, N = 3 SE +/- 0.72, N = 3 SE +/- 0.74, N = 3 SE +/- 1.69, N = 3 164.02 118.90 118.70 84.49 109.56 88.81 138.20 133.70 166.77 168.77 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Node.js Compilation 21.7.2 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.13 / Avg: 242.47 / Max: 351.76 Min: 42.12 / Avg: 265.76 / Max: 361.51 Min: 44.54 / Avg: 304.19 / Max: 485.17 Min: 43.76 / Avg: 293.44 / Max: 541.92 Min: 49.25 / Avg: 299.08 / Max: 541.63
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200 400 600 800 1000 SE +/- 2.28, N = 3 SE +/- 0.38, N = 3 SE +/- 0.88, N = 3 SE +/- 2.66, N = 3 SE +/- 1.03, N = 3 SE +/- 2.35, N = 3 SE +/- 0.97, N = 3 SE +/- 0.86, N = 3 SE +/- 2.22, N = 3 SE +/- 0.68, N = 3 529.80 529.03 870.03 871.91 795.83 794.75 522.45 525.49 520.58 519.28 Score Per Watt
OpenBenchmarking.org Score Per Watt, More Is Better Numpy Benchmark EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3 6 9 12 15 5.359 9.739 8.603 5.752 5.442 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Numpy Benchmark CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 Min: 26.33 / Avg: 98.86 / Max: 103.35 Min: 42.08 / Avg: 89.34 / Max: 96.9 Min: 44.4 / Avg: 92.5 / Max: 99.71 Min: 43.63 / Avg: 90.51 / Max: 114.4 Min: 44.51 / Avg: 95.41 / Max: 122.26
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 28.10 47.61 42.13 74.20 54.39 89.40 72.33 72.21 57.34 57.30 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 3.1 Benchmark: particle_volume/ao/real_time EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.032 0.064 0.096 0.128 0.16 0.096 0.135 0.127 0.142 0.136 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 3.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 28.62 / Avg: 291.85 / Max: 303.75 Min: 42.6 / Avg: 311.63 / Max: 323.28 Min: 45.02 / Avg: 429.8 / Max: 449.29 Min: 50.6 / Avg: 404.88 / Max: 428.27 Min: 51.33 / Avg: 420.69 / Max: 446.54
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 8K 16K 24K 32K 40K SE +/- 117.32, N = 3 SE +/- 290.50, N = 3 SE +/- 672.73, N = 15 SE +/- 242.08, N = 3 SE +/- 912.79, N = 15 SE +/- 1719.77, N = 15 SE +/- 193.00, N = 3 SE +/- 118.76, N = 3 SE +/- 126.20, N = 3 SE +/- 145.49, N = 3 14207.7 26702.7 14312.3 31649.3 19873.0 36154.1 29584.2 30133.8 15178.8 15106.7 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 6.21 Variant: GhostRider - Hash Count: 1M EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 11 22 33 44 55 46.69 44.50 46.77 38.41 36.76 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Xmrig 6.21 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 30.21 / Avg: 304.31 / Max: 328.13 Min: 42.04 / Avg: 321.63 / Max: 347.4 Min: 44.9 / Avg: 424.95 / Max: 482.49 Min: 45.98 / Avg: 395.18 / Max: 435.93 Min: 49.73 / Avg: 411 / 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 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.135 0.27 0.405 0.54 0.675 SE +/- 0.01, N = 3 SE +/- 0.00, N = 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 4 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 0.48 0.35 0.32 0.20 0.48 0.19 0.45 0.45 0.60 0.60 MIN: 0.22 / MAX: 18.92 MIN: 0.32 / MAX: 81.66 MIN: 0.13 / MAX: 22.72 MIN: 0.16 / MAX: 31.17 MIN: 0.13 / MAX: 26.24 MIN: 0.17 / MAX: 37.73 MIN: 0.22 / MAX: 100.75 MIN: 0.24 / MAX: 62.73 MIN: 0.21 / MAX: 30.59 MIN: 0.22 / MAX: 25.88 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 60 120 180 240 300 Min: 26.97 / Avg: 310.58 / Max: 341.7 Min: 42.77 / Avg: 250.56 / Max: 268.51 Min: 45.01 / Avg: 337.44 / Max: 363.58 Min: 50.42 / Avg: 246.22 / Max: 266.54 Min: 51.09 / Avg: 257.75 / Max: 276.01
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50K 100K 150K 200K 250K SE +/- 205.87, N = 3 SE +/- 1922.38, N = 15 SE +/- 658.72, N = 3 SE +/- 2494.88, N = 4 SE +/- 1255.01, N = 3 SE +/- 2329.77, N = 3 SE +/- 633.69, N = 15 SE +/- 731.62, N = 3 SE +/- 358.48, N = 3 SE +/- 841.95, N = 3 133779.62 172688.50 173358.47 210660.46 190777.83 213655.87 79733.12 78708.75 119060.13 118934.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
RocksDB This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Op/s, More Is Better RocksDB 9.0 Test: Random Read EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300M 600M 900M 1200M 1500M SE +/- 610621.13, N = 3 SE +/- 599126.55, N = 3 SE +/- 4322874.61, N = 3 SE +/- 3941921.08, N = 3 SE +/- 5260460.78, N = 3 SE +/- 3614882.10, N = 3 SE +/- 6485473.88, N = 3 SE +/- 22025814.96, N = 15 SE +/- 2092957.08, N = 3 SE +/- 15289875.69, N = 15 409272949 815145110 577215374 1155058979 786896580 1573803038 1403285563 1353034879 734025723 675346299 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread Op/s Per Watt
OpenBenchmarking.org Op/s Per Watt, More Is Better RocksDB 9.0 Test: Random Read EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 400K 800K 1200K 1600K 2000K 1523041.95 1918650.38 1894471.54 1557954.63 1430621.07 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better RocksDB 9.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 24.72 / Avg: 268.72 / Max: 291.05 Min: 42.37 / Avg: 300.84 / Max: 323.06 Min: 44.54 / Avg: 415.36 / Max: 446.18 Min: 49.52 / Avg: 471.15 / Max: 541.05 Min: 51.05 / Avg: 472.07 / Max: 541.17
Timed Godot Game Engine Compilation This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Timed Godot Game Engine Compilation 4.0 Time To Compile EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 30 60 90 120 150 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.21, N = 3 SE +/- 0.74, N = 3 SE +/- 0.10, N = 3 SE +/- 0.68, N = 3 SE +/- 1.21, N = 3 SE +/- 1.19, N = 3 SE +/- 0.22, N = 3 SE +/- 0.77, N = 3 111.69 102.58 84.13 76.43 83.29 81.68 102.87 98.75 103.40 105.02 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Timed Godot Game Engine Compilation 4.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 24.79 / Avg: 188.63 / Max: 336.96 Min: 42 / Avg: 202.77 / Max: 359.86 Min: 44.54 / Avg: 220.41 / Max: 490.55 Min: 44.44 / Avg: 221.2 / Max: 529.28 Min: 48.59 / Avg: 227.28 / Max: 536.13
QMCPACK QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. QMCPACK is an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids. QMCPACK is supported by the U.S. Department of Energy. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: Li2_STO_ae EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.54, N = 3 SE +/- 0.23, N = 3 SE +/- 0.22, N = 3 SE +/- 0.27, N = 3 SE +/- 0.27, N = 3 SE +/- 0.23, N = 3 SE +/- 0.93, N = 3 SE +/- 0.29, N = 3 SE +/- 1.23, N = 3 SE +/- 0.41, N = 3 108.02 102.98 82.21 75.90 79.02 75.25 88.06 86.54 86.64 86.86 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better QMCPACK 3.17.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.38 / Avg: 316.1 / Max: 334.43 Min: 42.83 / Avg: 322.06 / Max: 343.94 Min: 44.91 / Avg: 441.83 / Max: 480.46 Min: 50.21 / Avg: 464.47 / Max: 540.46 Min: 50.89 / Avg: 463.87 / Max: 540.59
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Barbershop - Compute: CPU-Only EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 30 60 90 120 150 SE +/- 0.25, N = 3 SE +/- 0.02, N = 3 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.52, N = 3 SE +/- 0.22, N = 3 SE +/- 0.46, N = 3 SE +/- 0.02, N = 3 139.25 79.05 116.47 61.50 86.62 46.90 66.26 65.54 113.27 114.81 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.59 / Avg: 319.36 / Max: 343.48 Min: 42.77 / Avg: 334.06 / Max: 355.46 Min: 45.07 / Avg: 446.04 / Max: 487.04 Min: 49.37 / Avg: 442.05 / Max: 541 Min: 52.29 / Avg: 465.5 / Max: 540.53
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 11K 22K 33K 44K 55K SE +/- 231.95, N = 3 SE +/- 756.08, N = 15 SE +/- 11.68, N = 3 SE +/- 31.56, N = 3 SE +/- 32.92, N = 3 SE +/- 13.58, N = 3 SE +/- 51.00, N = 3 SE +/- 31.95, N = 3 SE +/- 65.17, N = 3 SE +/- 213.42, N = 3 50019 27943 35888 16987 23981 12482 14521 14507 31924 32247 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.71 / Avg: 254.04 / Max: 331.67 Min: 42.72 / Avg: 263.34 / Max: 342.15 Min: 44.74 / Avg: 395.07 / Max: 468.24 Min: 50.62 / Avg: 340.37 / Max: 539.47 Min: 53.63 / Avg: 343.33 / Max: 540.37
OpenRadioss OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better OpenRadioss 2023.09.15 Model: INIVOL and Fluid Structure Interaction Drop Container EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.57, N = 3 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.36, N = 3 SE +/- 0.35, N = 3 SE +/- 0.31, N = 3 SE +/- 0.24, N = 3 100.24 85.89 79.20 65.61 73.67 64.06 91.67 88.08 81.23 83.64 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenRadioss 2023.09.15 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 27.14 / Avg: 303.45 / Max: 345.2 Min: 42.97 / Avg: 322.59 / Max: 360.97 Min: 44.92 / Avg: 423.73 / Max: 488.83 Min: 49.58 / Avg: 428.78 / Max: 535.12 Min: 51.29 / Avg: 432.48 / Max: 536.02
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.
Speedb Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Op/s, More Is Better Speedb 2.7 Test: Random Read EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300M 600M 900M 1200M 1500M SE +/- 66268.38, N = 3 SE +/- 955915.20, N = 3 SE +/- 696066.18, N = 3 SE +/- 1997067.74, N = 3 SE +/- 707549.54, N = 3 SE +/- 5308547.71, N = 3 SE +/- 31475546.69, N = 15 SE +/- 4617898.31, N = 3 SE +/- 1257570.05, N = 3 SE +/- 3885781.01, N = 3 428557054 857687179 607769650 1199871918 822102828 1562695431 1413177491 1473705641 770071573 761457970 1. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread Op/s Per Watt
OpenBenchmarking.org Op/s Per Watt, More Is Better Speedb 2.7 Test: Random Read EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 400K 800K 1200K 1600K 2000K 1563545.14 1998985.07 1969975.35 1634064.97 1616258.76 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Speedb 2.7 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.2 / Avg: 274.09 / Max: 293.61 Min: 42.33 / Avg: 304.04 / Max: 324.55 Min: 45.34 / Avg: 417.32 / Max: 445.74 Min: 49.92 / Avg: 471.26 / Max: 540.53 Min: 51.32 / Avg: 471.12 / Max: 541
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 5K 10K 15K 20K 25K SE +/- 5.55, N = 3 SE +/- 27.79, N = 3 SE +/- 14.29, N = 3 SE +/- 11.68, N = 3 SE +/- 14.19, N = 3 SE +/- 5.04, N = 3 SE +/- 27.39, N = 3 SE +/- 1.86, N = 3 SE +/- 26.96, N = 3 SE +/- 37.03, N = 3 22305 12427 16295 8448 11982 6225 7293 7208 13760 14034 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.99 / Avg: 273.01 / Max: 332.14 Min: 42.64 / Avg: 281.54 / Max: 342.6 Min: 44.72 / Avg: 371.8 / Max: 469.86 Min: 50.58 / Avg: 426.55 / Max: 539.48 Min: 52.9 / Avg: 428.6 / Max: 542.32
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 4K 8K 12K 16K 20K SE +/- 44.33, N = 3 SE +/- 32.74, N = 3 SE +/- 19.97, N = 3 SE +/- 10.60, N = 3 SE +/- 3.71, N = 3 SE +/- 7.13, N = 3 SE +/- 7.55, N = 3 SE +/- 24.33, N = 3 SE +/- 13.57, N = 3 SE +/- 60.24, N = 3 18896 10428 13834 7149 10154 5265 6189 6073 11528 11720 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.03 / Avg: 265.51 / Max: 331.71 Min: 42.74 / Avg: 299.14 / Max: 339.33 Min: 44.74 / Avg: 358.18 / Max: 462.19 Min: 50.13 / Avg: 384.99 / Max: 538.78 Min: 54.43 / Avg: 389.52 / Max: 540.84
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 9K 18K 27K 36K 45K SE +/- 42.05, N = 3 SE +/- 109.43, N = 3 SE +/- 52.17, N = 3 SE +/- 16.68, N = 3 SE +/- 39.68, N = 3 SE +/- 6.94, N = 3 SE +/- 28.11, N = 3 SE +/- 38.35, N = 3 SE +/- 63.14, N = 3 SE +/- 104.51, N = 3 43290 20750 30966 14290 20379 10551 12346 12139 23066 23664 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 30.06 / Avg: 244.64 / Max: 330.87 Min: 42.52 / Avg: 248.91 / Max: 338.62 Min: 44.85 / Avg: 385.39 / Max: 463.91 Min: 50.45 / Avg: 415.19 / Max: 538.48 Min: 51.48 / Avg: 419.61 / Max: 540.64
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.77, N = 7 SE +/- 0.44, N = 3 SE +/- 0.20, N = 3 SE +/- 0.04, N = 3 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 SE +/- 0.36, N = 3 SE +/- 0.49, N = 3 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 91.16 48.43 56.98 32.13 57.57 34.07 45.99 46.18 32.12 30.93 MIN: 43.59 / MAX: 136.45 MIN: 36.56 / MAX: 119.12 MIN: 27.41 / MAX: 98.07 MIN: 23.03 / MAX: 169.79 MIN: 34.99 / MAX: 106.02 MIN: 25.56 / MAX: 407.44 MIN: 18.62 / MAX: 990.48 MIN: 18.46 / MAX: 904.84 MIN: 22.18 / MAX: 664.17 MIN: 19.37 / MAX: 810.1 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 29.13 / Avg: 323.9 / Max: 362.47 Min: 42.71 / Avg: 326.55 / Max: 357.14 Min: 44.75 / Avg: 437.08 / Max: 487.92 Min: 51.04 / Avg: 388.55 / Max: 437.69 Min: 50.97 / Avg: 412.06 / Max: 468.09
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 400 800 1200 1600 2000 SE +/- 4.59, N = 7 SE +/- 8.96, N = 3 SE +/- 3.01, N = 3 SE +/- 1.75, N = 3 SE +/- 2.99, N = 3 SE +/- 5.84, N = 3 SE +/- 10.90, N = 3 SE +/- 14.42, N = 3 SE +/- 11.20, N = 3 SE +/- 9.55, N = 3 525.88 990.16 840.05 1491.95 1109.75 1875.78 1389.52 1383.84 987.91 1026.33 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Memcached Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3M 6M 9M 12M 15M SE +/- 29027.89, N = 3 SE +/- 83562.82, N = 3 SE +/- 51257.47, N = 3 SE +/- 32915.29, N = 3 SE +/- 136953.60, N = 3 SE +/- 5635.45, N = 3 SE +/- 10219.58, N = 3 SE +/- 21107.34, N = 3 SE +/- 13783.64, N = 3 SE +/- 37824.28, N = 4 8220895.45 8498306.78 12513777.69 13798695.25 13316660.10 13914824.32 1959201.17 1931166.09 3122810.84 3064341.26 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre Ops/sec Per Watt
OpenBenchmarking.org Ops/sec Per Watt, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 10K 20K 30K 40K 50K 31074.26 47921.24 37790.62 10606.19 9868.67 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Memcached 1.6.19 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 26.63 / Avg: 264.56 / Max: 307.16 Min: 42.16 / Avg: 261.13 / Max: 299.83 Min: 44.51 / Avg: 352.38 / Max: 408.97 Min: 49.18 / Avg: 294.43 / Max: 347.68 Min: 50.57 / Avg: 310.51 / Max: 364.64
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 110 220 330 440 550 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.26, N = 3 SE +/- 0.04, N = 3 SE +/- 0.54, N = 3 SE +/- 0.01, N = 3 SE +/- 0.25, N = 3 SE +/- 0.68, N = 3 SE +/- 0.38, N = 3 SE +/- 0.26, N = 3 510.10 253.63 331.17 163.97 329.53 159.81 242.19 238.36 234.32 227.99 MIN: 263.11 / MAX: 527.97 MIN: 208.02 / MAX: 272.56 MIN: 259.06 / MAX: 360.41 MIN: 149.81 / MAX: 234.24 MIN: 165.13 / MAX: 354.63 MIN: 147.41 / MAX: 204.24 MIN: 155.74 / MAX: 682.88 MIN: 153.42 / MAX: 908.3 MIN: 180.69 / MAX: 1204.33 MIN: 160.06 / MAX: 683.01 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 28.86 / Avg: 317.58 / Max: 349.47 Min: 42.85 / Avg: 279.14 / Max: 302.27 Min: 45.09 / Avg: 364.93 / Max: 401.2 Min: 49.98 / Avg: 423.9 / Max: 505.35 Min: 56.14 / Avg: 429.46 / Max: 517.98
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200 400 600 800 1000 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 SE +/- 0.32, N = 3 SE +/- 0.05, N = 3 SE +/- 1.00, N = 3 SE +/- 3.46, N = 3 SE +/- 0.96, N = 3 SE +/- 0.58, N = 3 93.99 188.74 144.65 292.34 193.80 399.96 1054.42 1071.81 545.57 560.60 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, 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 9.47 5.20 7.68 4.19 7.22 4.03 12.06 11.92 11.30 11.08 MIN: 5.96 / MAX: 23.01 MIN: 4.52 / MAX: 23.03 MIN: 4.09 / MAX: 22.61 MIN: 3.32 / MAX: 17.36 MIN: 4.48 / MAX: 26.34 MIN: 3.15 / MAX: 22.43 MIN: 9.4 / MAX: 163.59 MIN: 9.31 / MAX: 107.51 MIN: 10.34 / MAX: 55.87 MIN: 9.64 / MAX: 39 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.5 / Avg: 315.59 / Max: 344.89 Min: 42.52 / Avg: 263.09 / Max: 284.96 Min: 45.18 / Avg: 355.67 / Max: 388.83 Min: 50.86 / Avg: 445.96 / Max: 535.27 Min: 51.27 / Avg: 448.22 / Max: 538.68
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 5K 10K 15K 20K 25K SE +/- 25.68, N = 3 SE +/- 6.56, N = 3 SE +/- 18.33, N = 3 SE +/- 31.28, N = 3 SE +/- 8.58, N = 3 SE +/- 16.96, N = 3 SE +/- 50.72, N = 3 SE +/- 26.87, N = 3 SE +/- 3.46, N = 3 SE +/- 10.44, N = 3 5024.32 9203.19 6173.61 11417.02 8730.88 15858.87 21076.39 21314.01 11295.66 11530.82 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Intel OSPRay is a portable ray-tracing engine for high-performance, high-fidelity scientific visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Items Per Second, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 SE +/- 0.44, N = 3 SE +/- 0.20, N = 3 SE +/- 0.22, N = 3 30.61 52.67 41.25 77.53 55.18 98.51 74.72 73.80 51.07 49.93 Items Per Second Per Watt
OpenBenchmarking.org Items Per Second Per Watt, More Is Better OSPRay 3.1 Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0302 0.0604 0.0906 0.1208 0.151 0.112 0.134 0.130 0.119 0.114 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay 3.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 29.59 / Avg: 273.92 / Max: 319.11 Min: 42.71 / Avg: 307.55 / Max: 338.05 Min: 44.73 / Avg: 425.84 / Max: 476.99 Min: 50.79 / Avg: 429.35 / Max: 500.74 Min: 51.73 / Avg: 436.62 / Max: 504.41
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 SE +/- 0.58, N = 3 SE +/- 0.67, N = 3 SE +/- 2.08, N = 3 SE +/- 3.56, N = 5 SE +/- 0.58, N = 3 SE +/- 2.65, N = 3 SE +/- 1.20, N = 3 SE +/- 0.67, N = 3 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 160 178 284 334 313 339 216 218 225 226 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.43 Operation: Noise-Gaussian EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.3519 0.7038 1.0557 1.4076 1.7595 1.041 1.564 1.505 1.138 1.067 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.43 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 40 80 120 160 200 Min: 29.47 / Avg: 153.63 / Max: 171.14 Min: 42.65 / Avg: 181.64 / Max: 199.6 Min: 44.65 / Avg: 207.96 / Max: 234.1 Min: 49.05 / Avg: 197.66 / Max: 217.92 Min: 51.88 / Avg: 211.75 / Max: 232.35
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 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 14 28 42 56 70 SE +/- 0.11, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.12, N = 3 SE +/- 0.33, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 27.46 14.30 19.95 9.75 19.36 9.43 60.33 57.04 52.81 50.33 MIN: 14.03 / MAX: 53.11 MIN: 11.91 / MAX: 38.94 MIN: 10.11 / MAX: 40.96 MIN: 7.8 / MAX: 32.13 MIN: 9.99 / MAX: 44.41 MIN: 7.81 / MAX: 38.18 MIN: 38.43 / MAX: 261.34 MIN: 37.85 / MAX: 326.3 MIN: 36.91 / MAX: 122.76 MIN: 37.22 / MAX: 109.7 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 30.63 / Avg: 302.4 / Max: 328.21 Min: 42.84 / Avg: 273.09 / Max: 294.13 Min: 44.81 / Avg: 372.19 / Max: 403.45 Min: 50.4 / Avg: 451.83 / Max: 524.72 Min: 52.56 / Avg: 451.13 / Max: 529.9
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 1500 3000 4500 6000 7500 SE +/- 6.85, N = 3 SE +/- 3.90, N = 3 SE +/- 0.98, N = 3 SE +/- 3.52, N = 3 SE +/- 2.87, N = 3 SE +/- 31.92, N = 3 SE +/- 7.81, N = 3 SE +/- 25.95, N = 3 SE +/- 3.06, N = 3 SE +/- 2.03, N = 3 1743.49 3353.73 2393.86 4918.44 3287.43 6777.56 4209.65 4443.01 2421.94 2541.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Helsing Helsing is an open-source POSIX vampire number generator. This test profile measures the time it takes to generate vampire numbers between varying numbers of digits. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 14 28 42 56 70 SE +/- 0.10, N = 3 SE +/- 0.38, N = 5 SE +/- 0.26, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.29, N = 3 SE +/- 0.67, N = 15 SE +/- 0.72, N = 12 SE +/- 0.19, N = 3 SE +/- 0.46, N = 3 62.17 33.68 59.29 29.99 43.06 22.80 29.48 30.49 44.40 45.55 1. (CC) gcc options: -O2 -pthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Helsing 1.0-beta CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.89 / Avg: 322.19 / Max: 348.84 Min: 42.65 / Avg: 287.02 / Max: 311.43 Min: 44.89 / Avg: 388.84 / Max: 429.71 Min: 50.73 / Avg: 459.53 / Max: 533.78 Min: 50.54 / Avg: 454.16 / Max: 541.57
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.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 1.3455 2.691 4.0365 5.382 6.7275 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 +/- 0.00, N = 3 5.85 5.98 3.95 3.89 3.88 3.79 5.46 5.46 5.10 5.10 MIN: 2.67 / MAX: 22.66 MIN: 4.9 / MAX: 26.69 MIN: 1.73 / MAX: 17.81 MIN: 2.88 / MAX: 19.02 MIN: 1.55 / MAX: 24.23 MIN: 2.86 / MAX: 24.24 MIN: 3.97 / MAX: 67.93 MIN: 4.02 / MAX: 73.01 MIN: 4.7 / MAX: 22.87 MIN: 4.6 / MAX: 22.76 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 31.29 / Avg: 316.48 / Max: 340.73 Min: 42.6 / Avg: 285.84 / Max: 305.8 Min: 45.13 / Avg: 382.72 / Max: 411.46 Min: 50.7 / Avg: 415.62 / Max: 456.89 Min: 56.91 / Avg: 430.07 / Max: 474.35
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 14K 28K 42K 56K 70K SE +/- 2.59, N = 3 SE +/- 46.87, N = 3 SE +/- 6.01, N = 3 SE +/- 128.37, N = 3 SE +/- 0.83, N = 3 SE +/- 46.18, N = 3 SE +/- 61.32, N = 3 SE +/- 50.12, N = 3 SE +/- 15.69, N = 3 SE +/- 4.85, N = 3 16038.90 31974.88 23288.26 49343.56 31655.57 67364.91 45630.30 45797.09 25053.26 25053.90 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300 600 900 1200 1500 SE +/- 1.00, N = 3 SE +/- 0.58, N = 3 SE +/- 0.00, N = 3 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.20, N = 3 SE +/- 1.15, N = 3 1391 780 1025 532 753 395 463 460 862 876 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 31.26 / Avg: 263.32 / Max: 331.82 Min: 42.48 / Avg: 282.11 / Max: 344.08 Min: 44.84 / Avg: 373.57 / Max: 459.86 Min: 50.29 / Avg: 393.5 / Max: 537.03 Min: 54.28 / Avg: 395.82 / Max: 538.42
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 4 8 12 16 20 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 +/- 0.03, N = 3 8.58 4.46 5.84 2.92 5.62 2.82 14.51 14.19 13.16 13.04 MIN: 3.84 / MAX: 27.82 MIN: 3.61 / MAX: 26.57 MIN: 2.3 / MAX: 25.04 MIN: 2.03 / MAX: 17.91 MIN: 2.01 / MAX: 29.21 MIN: 1.97 / MAX: 26.07 MIN: 10.91 / MAX: 126.72 MIN: 11.14 / MAX: 123.21 MIN: 11.96 / MAX: 44.38 MIN: 12 / MAX: 44.37 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.58 / Avg: 315.71 / Max: 340.19 Min: 42.47 / Avg: 292.63 / Max: 314.67 Min: 44.81 / Avg: 395.5 / Max: 423.47 Min: 50.22 / Avg: 461.32 / Max: 532.12 Min: 56.41 / Avg: 462.01 / Max: 538.84
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 5K 10K 15K 20K 25K SE +/- 8.39, N = 3 SE +/- 4.21, N = 3 SE +/- 13.26, N = 3 SE +/- 8.73, N = 3 SE +/- 2.97, N = 3 SE +/- 7.61, N = 3 SE +/- 12.80, N = 3 SE +/- 8.06, N = 3 SE +/- 7.26, N = 3 SE +/- 21.55, N = 3 5528.15 10708.91 8123.12 16407.95 11232.26 22683.50 17592.41 17994.95 9720.53 9800.26 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OSPRay Studio Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OSPRay Studio 1.0 Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300 600 900 1200 1500 SE +/- 0.58, N = 3 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 2.08, N = 3 SE +/- 0.88, N = 3 SE +/- 1.15, N = 3 SE +/- 2.08, N = 3 1180 661 869 451 639 333 395 389 723 735 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OSPRay Studio 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.72 / Avg: 259.52 / Max: 331.33 Min: 42.74 / Avg: 279.58 / Max: 339.88 Min: 44.79 / Avg: 371.81 / Max: 463.5 Min: 50.04 / Avg: 392.21 / Max: 538.08 Min: 50.86 / Avg: 393.04 / Max: 539.77
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 10.09 10.17 6.64 6.44 6.61 6.28 2.68 2.67 2.80 2.79 MIN: 4.29 / MAX: 26.52 MIN: 8.74 / MAX: 41.95 MIN: 2.3 / MAX: 23.89 MIN: 5.4 / MAX: 24.33 MIN: 2.25 / MAX: 28.15 MIN: 4.82 / MAX: 54.92 MIN: 1.82 / MAX: 138.07 MIN: 1.82 / MAX: 85.05 MIN: 1.99 / MAX: 53.73 MIN: 1.97 / MAX: 92.8 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better OpenVINO 2024.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 28.34 / Avg: 326.4 / Max: 351.05 Min: 42.68 / Avg: 275.14 / Max: 295.2 Min: 44.8 / Avg: 363.16 / Max: 388.4 Min: 50.62 / Avg: 378.87 / Max: 411.81 Min: 51.32 / Avg: 390.04 / Max: 433.77
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 15K 30K 45K 60K 75K SE +/- 4.46, N = 3 SE +/- 147.69, N = 3 SE +/- 5.45, N = 3 SE +/- 18.16, N = 3 SE +/- 13.14, N = 3 SE +/- 16.35, N = 3 SE +/- 443.75, N = 3 SE +/- 146.17, N = 3 SE +/- 105.63, N = 3 SE +/- 39.06, N = 3 9356.71 18666.16 13972.57 29775.21 18679.36 40729.82 72221.47 72116.63 43376.11 43386.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
GPAW GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.21, N = 3 SE +/- 0.29, N = 15 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.41, N = 3 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 SE +/- 0.24, N = 3 34.87 25.84 27.19 23.77 23.82 26.79 88.84 87.51 30.42 30.47 1. (CC) gcc options: -shared -lxc -lblas -lmpi CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GPAW 23.6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.47 / Avg: 300.58 / Max: 350.83 Min: 42.62 / Avg: 307.5 / Max: 363.64 Min: 44.6 / Avg: 396.62 / Max: 491.51 Min: 50.35 / Avg: 386.97 / Max: 532.61 Min: 51.11 / Avg: 393.06 / Max: 538.23
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 120 240 360 480 600 SE +/- 0.00, N = 3 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 SE +/- 1.53, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.20, N = 3 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 173 262 320 475 403 555 374 351 307 302 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.43 Operation: Sharpen EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.2673 0.5346 0.8019 1.0692 1.3365 0.674 1.188 1.170 0.808 0.765 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.43 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 28.8 / Avg: 256.57 / Max: 278.61 Min: 42.43 / Avg: 269.34 / Max: 287.68 Min: 44.97 / Avg: 344.34 / Max: 371.89 Min: 50.13 / Avg: 379.87 / Max: 410.76 Min: 50.97 / Avg: 395 / Max: 429.71
Result
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 130 260 390 520 650 SE +/- 0.33, N = 3 SE +/- 1.20, N = 3 SE +/- 0.00, N = 3 SE +/- 2.08, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 1.53, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 264 368 364 520 455 590 376 362 415 409 1. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp Iterations Per Minute Per Watt
OpenBenchmarking.org Iterations Per Minute Per Watt, More Is Better GraphicsMagick 1.3.43 Operation: Enhanced EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.3197 0.6394 0.9591 1.2788 1.5985 1.067 1.421 1.405 1.116 1.053 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GraphicsMagick 1.3.43 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 80 160 240 320 400 Min: 26.64 / Avg: 247.53 / Max: 267.87 Min: 42.37 / Avg: 256.1 / Max: 275.52 Min: 44.73 / Avg: 323.89 / Max: 350.4 Min: 45.35 / Avg: 371.79 / Max: 402.11 Min: 51.69 / Avg: 388.59 / Max: 431.59
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 30K 60K 90K 120K 150K SE +/- 1853.72, N = 3 SE +/- 2386.93, N = 4 SE +/- 380.83, N = 3 SE +/- 1202.40, N = 3 SE +/- 438.43, N = 3 SE +/- 818.00, N = 3 SE +/- 1048.51, N = 3 SE +/- 594.12, N = 12 SE +/- 382.37, N = 3 SE +/- 981.85, N = 3 46233.7 86757.7 59791.1 114525.0 74093.3 143952.0 123498.0 126296.0 69589.8 68109.1 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 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50 100 150 200 250 188.14 209.31 207.54 185.54 175.15 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASKAP 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 29.47 / Avg: 245.74 / Max: 336.85 Min: 41.95 / Avg: 285.65 / Max: 357.68 Min: 45.02 / Avg: 357.02 / Max: 474.43 Min: 44.21 / Avg: 375.07 / Max: 528.33 Min: 49.26 / Avg: 388.87 / Max: 513.68
OpenBenchmarking.org Mpix/sec, More Is Better ASKAP 1.0 Test: tConvolve MPI - Degridding EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 30K 60K 90K 120K 150K SE +/- 189.10, N = 3 SE +/- 882.91, N = 4 SE +/- 328.80, N = 3 SE +/- 1206.67, N = 3 SE +/- 395.30, N = 3 SE +/- 790.67, N = 3 SE +/- 1398.33, N = 3 SE +/- 1657.92, N = 12 SE +/- 419.72, N = 3 SE +/- 777.47, N = 3 42172.4 81025.8 55898.8 106165.0 70762.8 140735.0 109084.0 106388.0 55247.6 57532.6 1. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200K 400K 600K 800K 1000K SE +/- 86.78, N = 3 SE +/- 713.18, N = 3 SE +/- 414.37, N = 3 SE +/- 310.97, N = 3 SE +/- 401.79, N = 3 SE +/- 706.04, N = 3 SE +/- 6898.59, N = 3 SE +/- 5872.24, N = 3 SE +/- 1975.23, N = 3 SE +/- 3274.43, N = 3 294183.2 593246.9 341991.7 690813.6 465436.8 943189.3 851172.5 852757.7 431602.4 421964.3 1. (CXX) g++ options: -O3 -march=native -fPIE -pie MFLOPS Per Watt
OpenBenchmarking.org MFLOPS Per Watt, More Is Better QuantLib 1.32 Configuration: Multi-Threaded EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200 400 600 800 1000 930.70 1136.47 1146.37 945.41 919.86 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better QuantLib 1.32 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.93 / Avg: 316.09 / Max: 352.6 Min: 41.91 / Avg: 300.92 / Max: 345.93 Min: 44.39 / Avg: 406.01 / Max: 482.98 Min: 44 / Avg: 456.53 / Max: 542.18 Min: 45.66 / Avg: 458.73 / Max: 541.01
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3M 6M 9M 12M 15M SE +/- 10132.66, N = 3 SE +/- 2306.54, N = 3 SE +/- 8964.82, N = 3 SE +/- 47498.43, N = 3 SE +/- 10789.95, N = 3 SE +/- 18916.54, N = 3 SE +/- 91145.15, N = 15 SE +/- 16938.33, N = 3 SE +/- 1719.10, N = 3 SE +/- 11988.52, N = 3 3926265.28 7975907.45 4550652.10 8395282.21 6042366.34 12443517.84 9430899.09 9614029.98 5133862.58 4548209.67 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 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3K 6K 9K 12K 15K 13254.14 14303.03 14585.74 12456.43 10811.88 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Coremark 1.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 26.88 / Avg: 296.23 / Max: 351.89 Min: 41.78 / Avg: 318.16 / Max: 348.06 Min: 44.74 / Avg: 414.27 / Max: 479.84 Min: 44.16 / Avg: 412.15 / Max: 528.16 Min: 44.08 / Avg: 420.67 / Max: 538.7
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300K 600K 900K 1200K 1500K SE +/- 111.53, N = 3 SE +/- 15794.26, N = 3 SE +/- 257.58, N = 3 SE +/- 17629.29, N = 3 SE +/- 276.36, N = 3 SE +/- 11779.84, N = 6 SE +/- 34967.05, N = 3 SE +/- 29199.31, N = 3 SE +/- 600.77, N = 3 SE +/- 1467.64, N = 3 642626 1033277 626600 1016040 846736 1342537 1182009 1294985 745557 740026 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 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 500 1000 1500 2000 2500 2434.84 2211.88 2269.16 1869.24 1810.40 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better 7-Zip Compression 22.01 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.34 / Avg: 263.93 / Max: 352.58 Min: 42.49 / Avg: 283.29 / Max: 363.19 Min: 44.66 / Avg: 373.15 / Max: 482.77 Min: 50.09 / Avg: 398.86 / Max: 541.55 Min: 52.26 / Avg: 408.77 / Max: 540.5
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300K 600K 900K 1200K 1500K SE +/- 719.89, N = 3 SE +/- 6869.20, N = 3 SE +/- 660.09, N = 3 SE +/- 6132.86, N = 3 SE +/- 3530.77, N = 3 SE +/- 12021.47, N = 6 SE +/- 9035.03, N = 3 SE +/- 4862.49, N = 3 SE +/- 1083.44, N = 3 SE +/- 6455.42, N = 3 549500 761734 762891 1078506 908159 1246609 915439 871812 709705 744325 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: WPA PSK EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 500K 1000K 1500K 2000K 2500K SE +/- 921.74, N = 3 SE +/- 1333.33, N = 3 SE +/- 1855.92, N = 3 SE +/- 18489.19, N = 6 SE +/- 1201.85, N = 3 SE +/- 33780.81, N = 14 SE +/- 23067.53, N = 3 SE +/- 9291.57, N = 3 SE +/- 2201.98, N = 3 SE +/- 3153.44, N = 3 643475 1253333 1039333 2001500 1361333 2560000 1686667 1719000 925672 907937 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2 Real C/S Per Watt
OpenBenchmarking.org Real C/S Per Watt, More Is Better John The Ripper 2023.03.14 Test: WPA PSK EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 700 1400 2100 2800 3500 2017.72 3348.48 3396.83 2083.45 2046.21 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better John The Ripper 2023.03.14 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.6 / Avg: 318.91 / Max: 365.41 Min: 42.38 / Avg: 310.39 / Max: 352.3 Min: 44.91 / Avg: 400.77 / Max: 455.82 Min: 51 / Avg: 444.3 / Max: 536.53 Min: 51.12 / Avg: 443.72 / Max: 539.69
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 12 24 36 48 60 SE +/- 0.04, N = 3 SE +/- 0.21, N = 4 SE +/- 0.05, N = 3 SE +/- 0.17, N = 4 SE +/- 0.09, N = 4 SE +/- 0.35, N = 4 SE +/- 0.19, N = 15 SE +/- 0.16, N = 15 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 28.01 40.96 31.90 51.68 39.14 52.45 20.72 21.08 27.32 27.28 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0297 0.0594 0.0891 0.1188 0.1485 0.108 0.132 0.123 0.093 0.087 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 28.73 / Avg: 258.29 / Max: 311.87 Min: 42.43 / Avg: 240.84 / Max: 292.89 Min: 45.28 / Avg: 318.43 / Max: 407.96 Min: 44.79 / Avg: 293.73 / Max: 386.63 Min: 50.17 / Avg: 313.03 / Max: 396.84
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: bcrypt EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 130K 260K 390K 520K 650K SE +/- 20.00, N = 3 SE +/- 710.46, N = 3 SE +/- 23.62, N = 3 SE +/- 4890.26, N = 4 SE +/- 45.32, N = 3 SE +/- 3998.65, N = 3 SE +/- 4966.19, N = 15 SE +/- 3581.87, N = 3 SE +/- 845.21, N = 3 SE +/- 3541.04, N = 3 166541 320527 237739 455597 323000 599893 443548 482948 265106 260166 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2 Real C/S Per Watt
OpenBenchmarking.org Real C/S Per Watt, More Is Better John The Ripper 2023.03.14 Test: bcrypt EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200 400 600 800 1000 606.47 789.71 782.32 593.58 584.24
Result
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 130K 260K 390K 520K 650K SE +/- 38.33, N = 3 SE +/- 3455.48, N = 3 SE +/- 7.33, N = 3 SE +/- 1429.13, N = 3 SE +/- 53.35, N = 3 SE +/- 3529.91, N = 3 SE +/- 5523.43, N = 4 SE +/- 5262.08, N = 3 SE +/- 280.31, N = 3 SE +/- 2952.36, N = 15 166541 316492 237823 460416 323010 609008 451601 479368 264265 256471 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2 Real C/S Per Watt
OpenBenchmarking.org Real C/S Per Watt, More Is Better John The Ripper 2023.03.14 Test: Blowfish EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200 400 600 800 1000 605.49 792.83 778.22 591.59 576.71 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better John The Ripper 2023.03.14 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P Xeon 6980P - DDR5-6400 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.03 / Avg: 274.61 / Max: 310.69 Min: 42.33 / Avg: 301.05 / Max: 337.82 Min: 44.63 / Avg: 415.07 / Max: 468.23 Min: 50.75 / Avg: 445.3 / Max: 539.78 Min: 50.42 / Avg: 446.62 / Max: 539.55 Min: 51.81 / Avg: 446.7 / Max: 539.8 Min: 51.25 / Avg: 444.72 / Max: 540.41
Pennant Pennant is an application focused on hydrodynamics on general unstructured meshes in 2D. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.8448 1.6896 2.5344 3.3792 4.224 SE +/- 0.115723, N = 15 SE +/- 0.063684, N = 15 SE +/- 0.087065, N = 15 SE +/- 0.032998, N = 15 SE +/- 0.045208, N = 15 SE +/- 0.002996, N = 5 SE +/- 0.011251, N = 15 SE +/- 0.019165, N = 15 SE +/- 0.018745, N = 6 SE +/- 0.018539, N = 15 3.754835 2.312977 3.136517 1.869350 2.761260 1.472970 1.313149 1.336274 2.005280 2.004903 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 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.07 / Avg: 170.76 / Max: 330.73 Min: 42.45 / Avg: 171.37 / Max: 339.93 Min: 44.55 / Avg: 210.49 / Max: 475.61 Min: 49.62 / Avg: 197.07 / Max: 536.58 Min: 50.43 / Avg: 204.7 / Max: 539.09
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.01, N = 4 SE +/- 0.50, N = 5 SE +/- 0.03, N = 4 SE +/- 0.47, N = 14 SE +/- 0.06, N = 5 SE +/- 0.63, N = 9 SE +/- 0.66, N = 15 SE +/- 0.72, N = 15 SE +/- 0.20, N = 4 SE +/- 0.25, N = 15 38.90 61.07 44.40 70.65 53.42 78.12 31.89 32.24 39.21 39.25 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0464 0.0928 0.1392 0.1856 0.232 0.169 0.206 0.195 0.148 0.140 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 28.16 / Avg: 229.8 / Max: 294.04 Min: 42.25 / Avg: 215.53 / Max: 278.11 Min: 44.71 / Avg: 273.76 / Max: 377.94 Min: 43.73 / Avg: 264.48 / Max: 382.76 Min: 49.68 / Avg: 281.35 / Max: 396.67
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 57 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 2000M 4000M 6000M 8000M 10000M SE +/- 2618735.91, N = 3 SE +/- 60380193.59, N = 3 SE +/- 7992983.03, N = 3 SE +/- 38320157.16, N = 3 SE +/- 6331139.97, N = 3 SE +/- 15230561.38, N = 3 SE +/- 112123547.93, N = 3 SE +/- 68230620.86, N = 9 SE +/- 32823213.33, N = 3 SE +/- 20137223.69, N = 3 5266466667 7411866667 6204633333 8926633333 8151900000 8179100000 8179400000 8550488889 7167500000 7064533333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 57 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 4M 8M 12M 16M 20M 17475938.77 20917606.81 19710155.44 15953254.33 15799318.46 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 30.72 / Avg: 301.36 / Max: 345.8 Min: 42.67 / Avg: 296.62 / Max: 337.92 Min: 44.84 / Avg: 413.59 / Max: 472.3 Min: 50.81 / Avg: 449.28 / Max: 540.58 Min: 51.66 / Avg: 447.14 / Max: 541.36
LAMMPS Molecular Dynamics Simulator LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 16 32 48 64 80 SE +/- 0.14, N = 11 SE +/- 0.39, N = 7 SE +/- 0.32, N = 15 SE +/- 0.29, N = 7 SE +/- 0.31, N = 10 SE +/- 0.27, N = 5 SE +/- 1.61, N = 15 SE +/- 0.57, N = 15 SE +/- 0.84, N = 15 SE +/- 0.47, N = 15 36.15 50.12 45.22 66.54 55.79 72.71 71.95 71.54 51.72 49.93 1. (CXX) g++ options: -O3 -lm -ldl ns/day Per Watt
OpenBenchmarking.org ns/day Per Watt, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: Rhodopsin Protein EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.1004 0.2008 0.3012 0.4016 0.502 0.372 0.444 0.446 0.355 0.319 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 26.87 / Avg: 97.2 / Max: 234.7 Min: 42.03 / Avg: 101.77 / Max: 272.71 Min: 44.53 / Avg: 125.04 / Max: 352.94 Min: 36.54 / Avg: 145.82 / Max: 356.35 Min: 49.49 / Avg: 156.52 / Max: 370.27
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.19, N = 6 SE +/- 0.01, N = 3 SE +/- 0.30, N = 3 SE +/- 0.04, N = 3 SE +/- 0.25, N = 3 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 12.51 20.23 17.63 29.47 22.73 34.38 33.12 32.67 21.09 20.55 1. (CXX) g++ options: -O3 -lm Ns Per Day Per Watt
OpenBenchmarking.org Ns Per Day Per Watt, More Is Better GROMACS 2024 Implementation: MPI CPU - Input: water_GMX50_bare EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0149 0.0298 0.0447 0.0596 0.0745 0.048 0.066 0.065 0.063 0.061 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better GROMACS 2024 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.69 / Avg: 260.21 / Max: 348.03 Min: 42.17 / Avg: 266.41 / Max: 347.59 Min: 44.64 / Avg: 349.18 / Max: 487.22 Min: 49.47 / Avg: 333.31 / Max: 537.53 Min: 52.92 / Avg: 338.43 / Max: 540.14
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 512 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 500M 1000M 1500M 2000M 2500M SE +/- 1047748.91, N = 3 SE +/- 2338327.99, N = 3 SE +/- 1997498.44, N = 3 SE +/- 4363612.16, N = 3 SE +/- 1305118.13, N = 3 SE +/- 7718376.34, N = 3 SE +/- 17442399.25, N = 4 SE +/- 14895674.24, N = 3 SE +/- 14143824.72, N = 3 SE +/- 6349365.67, N = 3 1158166667 1199966667 1953600000 2102033333 2487400000 2524100000 1592425000 1615266667 1573933333 1553766667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 512 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 1.4M 2.8M 4.2M 5.6M 7M 4367851.07 6449178.39 5913583.74 4094043.94 3872275.00 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 26.08 / Avg: 265.16 / Max: 303.52 Min: 42.5 / Avg: 302.92 / Max: 347.46 Min: 45.02 / Avg: 420.62 / Max: 484.72 Min: 50.28 / Avg: 384.44 / Max: 494.51 Min: 51.51 / Avg: 401.25 / Max: 509.08
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Pabellon Barcelona - Compute: CPU-Only EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 11 22 33 44 55 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 4 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 48.88 26.35 40.68 20.64 29.75 15.37 20.58 19.95 37.12 37.76 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 30.54 / Avg: 312.47 / Max: 346.36 Min: 42.6 / Avg: 299.89 / Max: 333.57 Min: 44.67 / Avg: 395 / Max: 457.96 Min: 49.68 / Avg: 439.22 / Max: 539.91 Min: 51.16 / Avg: 441.6 / Max: 540.03
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3 6 9 12 15 SE +/- 0.052975, N = 7 SE +/- 0.040626, N = 15 SE +/- 0.054129, N = 15 SE +/- 0.042880, N = 15 SE +/- 0.073388, N = 15 SE +/- 0.020936, N = 15 SE +/- 0.001234, N = 3 SE +/- 0.007459, N = 3 SE +/- 0.014420, N = 4 SE +/- 0.029559, N = 4 5.916458 3.408337 5.478708 3.021763 4.393606 2.329222 6.449588 6.437402 8.968728 9.151189 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 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 26.98 / Avg: 200.64 / Max: 329.21 Min: 42.51 / Avg: 209.04 / Max: 339.71 Min: 44.51 / Avg: 248.94 / Max: 471.46 Min: 45.95 / Avg: 308.83 / Max: 535.66 Min: 50.54 / Avg: 318.84 / Max: 537.88
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 512 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 800M 1600M 2400M 3200M 4000M SE +/- 520683.31, N = 3 SE +/- 11753202.87, N = 3 SE +/- 1659651.90, N = 3 SE +/- 26473907.49, N = 3 SE +/- 3925274.23, N = 3 SE +/- 1800000.00, N = 3 SE +/- 10019370.13, N = 3 SE +/- 3437214.63, N = 3 SE +/- 3590728.80, N = 3 SE +/- 5751811.31, N = 3 1362166667 2129533333 2152766667 3561366667 2855466667 2980400000 2839933333 2934633333 2327500000 2301200000 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 512 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 1.6M 3.2M 4.8M 6.4M 8M 4853033.94 7245928.17 7237709.10 5269561.61 5186961.59 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.69 / Avg: 280.68 / Max: 320.8 Min: 42.56 / Avg: 297.1 / Max: 338.79 Min: 45.35 / Avg: 394.53 / Max: 450.68 Min: 50.69 / Avg: 441.69 / Max: 540.03 Min: 51.54 / Avg: 443.65 / Max: 540.73
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 2000M 4000M 6000M 8000M 10000M SE +/- 1066998.75, N = 3 SE +/- 8808919.44, N = 3 SE +/- 4068843.09, N = 3 SE +/- 18981834.93, N = 3 SE +/- 6342005.91, N = 3 SE +/- 6625553.97, N = 3 SE +/- 8494773.54, N = 3 SE +/- 47352853.80, N = 3 SE +/- 4984066.09, N = 3 SE +/- 8646191.73, N = 3 2282802000 4324930333 3076739667 5961230333 3177082000 6201018333 6583859667 8546625667 3395003333 4483678333 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 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3M 6M 9M 12M 15M 9442032.07 11562385.40 9501967.55 9949199.16 12678857.70 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Algebraic Multi-Grid Benchmark 1.2 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 23.58 / Avg: 241.77 / Max: 304.95 Min: 41.9 / Avg: 266.1 / Max: 338.05 Min: 44.44 / Avg: 334.36 / Max: 438.6 Min: 44.26 / Avg: 341.23 / Max: 490.12 Min: 44.54 / Avg: 353.63 / Max: 508.45
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 32 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 2000M 4000M 6000M 8000M 10000M SE +/- 1419311.26, N = 3 SE +/- 46730658.51, N = 3 SE +/- 6065476.07, N = 3 SE +/- 49681015.82, N = 3 SE +/- 14339494.80, N = 3 SE +/- 10838870.38, N = 3 SE +/- 23764329.01, N = 3 SE +/- 31563973.84, N = 3 SE +/- 9930480.57, N = 3 SE +/- 13819109.15, N = 3 5271933333 7513333333 6327600000 9093100000 8494733333 8570166667 7354300000 7439266667 6891466667 6852066667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid samples/s Per Watt
OpenBenchmarking.org samples/s Per Watt, More Is Better Liquid-DSP 1.6 Threads: 256 - Buffer Length: 256 - Filter Length: 32 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 4M 8M 12M 16M 20M 17844515.21 20685459.05 20115931.63 15435164.83 15259867.89 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Liquid-DSP 1.6 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 30.54 / Avg: 295.44 / Max: 336.72 Min: 42.53 / Avg: 305.9 / Max: 344.23 Min: 45.19 / Avg: 422.29 / Max: 487.56 Min: 49.91 / Avg: 446.48 / Max: 527 Min: 50.85 / Avg: 449.03 / Max: 538.09
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 60 120 180 240 300 SE +/- 0.02, N = 4 SE +/- 1.58, N = 15 SE +/- 0.07, N = 5 SE +/- 1.69, N = 15 SE +/- 0.14, N = 5 SE +/- 3.59, N = 15 SE +/- 2.56, N = 4 SE +/- 2.16, N = 4 SE +/- 0.87, N = 4 SE +/- 1.15, N = 4 113.28 175.60 148.79 220.17 191.78 248.77 296.45 295.11 188.80 186.81 MIN: 111.7 / MAX: 116.19 MIN: 154.41 / MAX: 194.22 MIN: 146.45 / MAX: 152.13 MIN: 192.38 / MAX: 242.25 MIN: 188.36 / MAX: 196.2 MIN: 183.45 / MAX: 296.21 MIN: 255.3 / MAX: 342.81 MIN: 251.9 / MAX: 342.7 MIN: 178.76 / MAX: 200.12 MIN: 173.28 / MAX: 197.67 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon Obj EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.2441 0.4882 0.7323 0.9764 1.2205 0.693 0.892 1.085 1.069 1.013 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 4.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 28.7 / Avg: 163.54 / Max: 333.81 Min: 42.41 / Avg: 166.72 / Max: 351.88 Min: 44.63 / Avg: 176.74 / Max: 465.19 Min: 49.43 / Avg: 176.65 / Max: 536.36 Min: 50.19 / Avg: 184.47 / Max: 536.75
miniBUDE MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 110 220 330 440 550 SE +/- 0.93, N = 3 SE +/- 0.08, N = 3 SE +/- 1.70, N = 3 SE +/- 5.30, N = 15 SE +/- 3.07, N = 4 SE +/- 8.91, N = 15 SE +/- 3.20, N = 3 SE +/- 0.86, N = 3 SE +/- 2.16, N = 3 SE +/- 1.89, N = 3 171.77 291.28 268.21 430.12 386.18 485.50 294.14 291.98 226.84 223.19 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm Billion Interactions/s Per Watt
OpenBenchmarking.org Billion Interactions/s Per Watt, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.2446 0.4892 0.7338 0.9784 1.223 0.605 0.948 1.087 0.529 0.514 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better miniBUDE 20210901 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.02 / Avg: 283.82 / Max: 328.33 Min: 41.98 / Avg: 282.8 / Max: 341.81 Min: 44.68 / Avg: 355.42 / Max: 459.93 Min: 49.31 / Avg: 428 / Max: 540.04 Min: 50.83 / Avg: 434.53 / Max: 540.79
OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3K 6K 9K 12K 15K SE +/- 23.15, N = 3 SE +/- 2.03, N = 3 SE +/- 42.42, N = 3 SE +/- 132.52, N = 15 SE +/- 76.86, N = 4 SE +/- 222.68, N = 15 SE +/- 79.93, N = 3 SE +/- 21.42, N = 3 SE +/- 53.91, N = 3 SE +/- 47.20, N = 3 4294.28 7281.96 6705.15 10753.05 9654.58 12137.49 7353.40 7299.51 5670.88 5579.78 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
Kvazaar This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 SE +/- 0.07, N = 4 SE +/- 0.56, N = 5 SE +/- 0.06, N = 4 SE +/- 0.40, N = 5 SE +/- 0.01, N = 5 SE +/- 0.64, N = 6 SE +/- 0.50, N = 15 SE +/- 0.30, N = 3 SE +/- 0.05, N = 4 SE +/- 0.16, N = 4 39.58 61.11 44.93 72.38 53.95 78.79 31.92 32.34 39.66 39.68 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0473 0.0946 0.1419 0.1892 0.2365 0.181 0.210 0.197 0.152 0.141 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Kvazaar 2.2 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 26.12 / Avg: 219.12 / Max: 294.65 Min: 42.71 / Avg: 213.69 / Max: 276.07 Min: 44.59 / Avg: 273.65 / Max: 377.98 Min: 45.5 / Avg: 260.91 / Max: 344.81 Min: 50.94 / Avg: 280.96 / Max: 364.53
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Classroom - Compute: CPU-Only EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 9 18 27 36 45 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 4 SE +/- 0.10, N = 4 SE +/- 0.10, N = 4 SE +/- 0.20, N = 3 SE +/- 0.09, N = 3 40.26 21.12 32.67 16.61 24.00 12.32 15.82 15.65 28.85 29.30 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 31.02 / Avg: 300.94 / Max: 333.76 Min: 42.64 / Avg: 302.84 / Max: 340.23 Min: 44.79 / Avg: 395.56 / Max: 467.14 Min: 49.69 / Avg: 433.41 / Max: 540.25 Min: 51.27 / Avg: 437.26 / Max: 541.3
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Exhaustive EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 5 10 15 20 25 SE +/- 0.0002, N = 3 SE +/- 0.0218, N = 3 SE +/- 0.0012, N = 3 SE +/- 0.0874, N = 15 SE +/- 0.0004, N = 3 SE +/- 0.1679, N = 4 SE +/- 0.1937, N = 4 SE +/- 0.2367, N = 4 SE +/- 0.0133, N = 3 SE +/- 0.0350, N = 3 5.6301 10.6018 7.1053 13.0322 9.6576 17.5040 18.9042 19.0719 10.1423 9.9139 1. (CXX) g++ options: -O3 -flto -pthread MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.7 Preset: Exhaustive EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0068 0.0136 0.0204 0.0272 0.034 0.021 0.028 0.030 0.029 0.028 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.7 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 29.24 / Avg: 271.69 / Max: 338.26 Min: 42.62 / Avg: 256.32 / Max: 324.48 Min: 44.69 / Avg: 318.58 / Max: 450.37 Min: 49.56 / Avg: 347.76 / Max: 540.56 Min: 51.56 / Avg: 348.75 / Max: 541.58
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 30 60 90 120 150 SE +/- 0.56, N = 5 SE +/- 0.40, N = 5 SE +/- 0.62, N = 6 SE +/- 1.00, N = 6 SE +/- 1.10, N = 7 SE +/- 1.17, N = 6 SE +/- 0.72, N = 15 SE +/- 0.75, N = 15 SE +/- 0.26, N = 5 SE +/- 0.87, N = 5 87.99 86.34 107.42 109.18 118.16 120.23 73.73 73.03 79.71 79.77 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.1881 0.3762 0.5643 0.7524 0.9405 0.653 0.836 0.778 0.583 0.558 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 2.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50 100 150 200 250 Min: 28.36 / Avg: 134.72 / Max: 238.02 Min: 42.16 / Avg: 128.56 / Max: 218.27 Min: 44.49 / Avg: 151.86 / Max: 281.96 Min: 43.41 / Avg: 136.67 / Max: 235.15 Min: 45.33 / Avg: 143.06 / Max: 250.09
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 60 120 180 240 300 SE +/- 4.38, N = 15 SE +/- 4.23, N = 15 SE +/- 6.06, N = 15 SE +/- 6.77, N = 15 SE +/- 7.58, N = 15 SE +/- 7.82, N = 15 SE +/- 4.16, N = 15 SE +/- 4.79, N = 15 SE +/- 0.88, N = 7 SE +/- 3.86, N = 15 172.88 167.22 249.29 250.39 271.92 275.70 154.57 156.73 176.50 174.71 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 13 - Input: Bosphorus 4K EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.56 1.12 1.68 2.24 2.8 1.644 2.489 2.353 1.648 1.543 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 2.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50 100 150 200 250 Min: 25.79 / Avg: 105.15 / Max: 208.71 Min: 42.16 / Avg: 100.15 / Max: 228.05 Min: 44.43 / Avg: 115.57 / Max: 288.05 Min: 43.68 / Avg: 107.1 / Max: 218.44 Min: 44.7 / Avg: 113.22 / Max: 224.37
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.
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Very Thorough EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 7 14 21 28 35 SE +/- 0.0006, N = 3 SE +/- 0.1965, N = 3 SE +/- 0.0010, N = 3 SE +/- 0.0798, N = 4 SE +/- 0.0025, N = 3 SE +/- 0.2272, N = 4 SE +/- 0.3048, N = 6 SE +/- 0.1749, N = 4 SE +/- 0.0406, N = 3 SE +/- 0.0590, N = 3 9.1844 17.0098 11.5757 21.3961 15.7195 27.7865 30.9109 31.2552 16.6745 16.4289 1. (CXX) g++ options: -O3 -flto -pthread MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.7 Preset: Very Thorough EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0113 0.0226 0.0339 0.0452 0.0565 0.034 0.045 0.050 0.049 0.047 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.7 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 25.96 / Avg: 270.94 / Max: 337.98 Min: 42.39 / Avg: 254.74 / Max: 323.1 Min: 44.52 / Avg: 317.5 / Max: 448.44 Min: 44.51 / Avg: 342.26 / Max: 539.9 Min: 50.48 / Avg: 349.22 / Max: 541.59
Result
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.7 Preset: Thorough EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 40 80 120 160 200 SE +/- 0.01, N = 4 SE +/- 0.73, N = 15 SE +/- 0.01, N = 5 SE +/- 0.97, N = 15 SE +/- 0.02, N = 6 SE +/- 1.05, N = 6 SE +/- 0.20, N = 5 SE +/- 0.71, N = 5 SE +/- 0.08, N = 5 SE +/- 0.16, N = 5 65.30 105.41 81.68 130.02 110.04 169.75 163.96 162.26 115.01 114.11 1. (CXX) g++ options: -O3 -flto -pthread MT/s Per Watt
OpenBenchmarking.org MT/s Per Watt, More Is Better ASTC Encoder 4.7 Preset: Thorough EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.1217 0.2434 0.3651 0.4868 0.6085 0.338 0.458 0.541 0.537 0.532 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better ASTC Encoder 4.7 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 28.71 / Avg: 193.35 / Max: 335.29 Min: 42.15 / Avg: 178.31 / Max: 319.1 Min: 44.54 / Avg: 203.27 / Max: 437.24 Min: 43.99 / Avg: 214.28 / Max: 523.16 Min: 47.61 / Avg: 214.37 / Max: 519.61
uvg266 uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.23, N = 4 SE +/- 0.05, N = 3 SE +/- 0.26, N = 5 SE +/- 0.04, N = 4 SE +/- 0.30, N = 5 SE +/- 0.20, N = 3 SE +/- 0.19, N = 3 SE +/- 0.06, N = 3 SE +/- 0.20, N = 3 31.44 42.03 35.95 54.24 43.85 53.27 20.98 21.05 30.13 29.97 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.0342 0.0684 0.1026 0.1368 0.171 0.150 0.152 0.140 0.104 0.099 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better uvg266 0.4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 29.07 / Avg: 209.83 / Max: 311.67 Min: 42.47 / Avg: 236.03 / Max: 292.84 Min: 44.64 / Avg: 313.89 / Max: 407.23 Min: 49.23 / Avg: 291.06 / Max: 362.18 Min: 51.36 / Avg: 304.14 / Max: 387.73
NAS Parallel Benchmarks NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. This test profile offers selecting the different NPB tests/problems and varying problem sizes. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 3K 6K 9K 12K 15K SE +/- 17.53, N = 5 SE +/- 76.70, N = 10 SE +/- 41.67, N = 6 SE +/- 91.78, N = 15 SE +/- 55.66, N = 6 SE +/- 106.77, N = 5 SE +/- 72.69, N = 3 SE +/- 84.81, N = 3 SE +/- 52.01, N = 5 SE +/- 41.85, N = 5 5229.41 10139.69 7042.53 13161.52 8647.62 15104.57 14608.88 15317.80 8393.32 9381.50 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 9 18 27 36 45 29.67 36.75 40.04 38.54 41.04 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 25.79 / Avg: 176.27 / Max: 304.26 Min: 42.42 / Avg: 191.65 / Max: 344.45 Min: 44.5 / Avg: 215.99 / Max: 421.15 Min: 45.57 / Avg: 217.8 / Max: 485.18 Min: 50.55 / Avg: 228.62 / Max: 511.3
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Junkshop - Compute: CPU-Only EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.02, N = 4 SE +/- 0.02, N = 3 SE +/- 0.02, N = 5 SE +/- 0.03, N = 4 SE +/- 0.04, N = 5 SE +/- 0.09, N = 10 SE +/- 0.11, N = 4 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 21.02 12.87 16.55 9.61 12.71 7.74 11.58 11.59 15.97 16.01 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 16.01 / Avg: 272.23 / Max: 337.39 Min: 42.81 / Avg: 286.93 / Max: 368.7 Min: 45 / Avg: 350.75 / Max: 492.13 Min: 50.93 / Avg: 369.78 / Max: 541.5 Min: 52.19 / Avg: 375.95 / Max: 540.44
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100K 200K 300K 400K 500K SE +/- 1153.71, N = 15 SE +/- 2707.72, N = 14 SE +/- 1820.15, N = 15 SE +/- 3226.17, N = 15 SE +/- 1302.88, N = 15 SE +/- 3807.41, N = 15 SE +/- 361.11, N = 3 SE +/- 965.50, N = 3 SE +/- 890.04, N = 6 SE +/- 794.43, N = 7 116725.04 194942.32 144599.38 237346.22 167026.93 361767.36 387445.06 451798.00 196892.69 240025.24 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 300 600 900 1200 1500 1070.68 1272.73 1197.56 1339.29 1510.91 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 Min: 27.57 / Avg: 109.02 / Max: 286.49 Min: 42.13 / Avg: 113.61 / Max: 329.46 Min: 44.37 / Avg: 139.47 / Max: 413.95 Min: 44.11 / Avg: 147.01 / Max: 404.55 Min: 50.22 / Avg: 158.86 / Max: 390.81
Primesieve Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e13 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 6 12 18 24 30 SE +/- 0.021, N = 3 SE +/- 0.013, N = 4 SE +/- 0.010, N = 3 SE +/- 0.031, N = 4 SE +/- 0.017, N = 3 SE +/- 0.013, N = 5 SE +/- 0.075, N = 4 SE +/- 0.044, N = 4 SE +/- 0.092, N = 3 SE +/- 0.184, N = 3 24.237 12.631 24.215 12.477 17.968 9.289 11.714 11.664 22.470 22.778 1. (CXX) g++ options: -O3 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Primesieve 12.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 28.63 / Avg: 313.43 / Max: 370.81 Min: 42.16 / Avg: 267.77 / Max: 344.07 Min: 44.62 / Avg: 342.49 / Max: 459.6 Min: 49.71 / Avg: 429.04 / Max: 540.64 Min: 50.3 / Avg: 432.08 / Max: 540.03
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 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200K 400K 600K 800K 1000K SE +/- 789.76, N = 5 SE +/- 4162.49, N = 6 SE +/- 1611.44, N = 6 SE +/- 3426.11, N = 6 SE +/- 5529.34, N = 15 SE +/- 6146.84, N = 5 SE +/- 1419.65, N = 3 SE +/- 4483.01, N = 3 SE +/- 1363.65, N = 5 SE +/- 537.94, N = 5 269047.28 472931.04 315803.13 589945.23 385558.53 835481.40 781325.16 771659.52 477450.80 474870.04 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 400 800 1200 1600 2000 1333.71 1431.33 1391.90 1944.59 1848.26 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 26.14 / Avg: 201.73 / Max: 306.76 Min: 42.56 / Avg: 220.64 / Max: 341.42 Min: 44.78 / Avg: 277 / Max: 487.21 Min: 49.35 / Avg: 245.53 / Max: 522.72 Min: 51.13 / Avg: 256.93 / Max: 523.54
srsRAN Project srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Mbps, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Thread EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50 100 150 200 250 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 SE +/- 0.00, N = 4 SE +/- 0.00, N = 4 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 112.2 112.2 224.5 224.5 183.3 183.3 129.4 129.3 129.5 129.2 MIN: 79.3 MIN: 79.3 MIN: 158.7 MIN: 158.7 MIN: 105.8 MIN: 105.8 MIN: 105.7 / MAX: 129.5 MIN: 105.6 / MAX: 129.4 MIN: 105.7 MIN: 105.5 1. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl Mbps Per Watt
OpenBenchmarking.org Mbps Per Watt, More Is Better srsRAN Project 23.10.1-20240325 Test: PUSCH Processor Benchmark, Throughput Thread EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.6523 1.3046 1.9569 2.6092 3.2615 1.257 2.899 2.215 1.662 1.520 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better srsRAN Project 23.10.1-20240325 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 20 40 60 80 100 Min: 27.03 / Avg: 89.27 / Max: 101.62 Min: 42.42 / Avg: 77.44 / Max: 91.96 Min: 44.7 / Avg: 82.75 / Max: 94.11 Min: 44.77 / Avg: 77.9 / Max: 86.18 Min: 50.61 / Avg: 84.98 / Max: 95.24
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: SP.C EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90K 180K 270K 360K 450K SE +/- 72.03, N = 4 SE +/- 1929.89, N = 5 SE +/- 367.39, N = 5 SE +/- 2950.53, N = 5 SE +/- 878.07, N = 5 SE +/- 1941.42, N = 4 SE +/- 2163.37, N = 3 SE +/- 3507.67, N = 3 SE +/- 386.44, N = 4 SE +/- 475.06, N = 5 125191.11 256584.67 154462.83 329784.54 194853.91 317246.03 407367.97 425941.29 225918.92 263762.92 1. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6 Total Mop/s Per Watt
OpenBenchmarking.org Total Mop/s Per Watt, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.C EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 200 400 600 800 1000 547.32 619.92 644.42 862.73 974.34 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better NAS Parallel Benchmarks 3.4 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 26 / Avg: 228.74 / Max: 319.02 Min: 42.27 / Avg: 249.16 / Max: 352.04 Min: 44.76 / Avg: 302.37 / Max: 488.19 Min: 45.25 / Avg: 261.87 / Max: 477.32 Min: 50.69 / Avg: 271.53 / Max: 516.16
Blender Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: Fishy Cat - Compute: CPU-Only EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 5 10 15 20 25 SE +/- 0.11, N = 3 SE +/- 0.05, N = 4 SE +/- 0.11, N = 3 SE +/- 0.03, N = 5 SE +/- 0.01, N = 4 SE +/- 0.02, N = 6 SE +/- 0.04, N = 5 SE +/- 0.06, N = 5 SE +/- 0.07, N = 4 SE +/- 0.13, N = 3 20.15 11.25 16.80 9.01 12.50 6.91 9.85 9.75 15.49 15.87 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 30.77 / Avg: 277.68 / Max: 346.38 Min: 42.52 / Avg: 267.31 / Max: 340.55 Min: 44.85 / Avg: 338.57 / Max: 471.87 Min: 49.78 / Avg: 377.81 / Max: 540.78 Min: 51.25 / Avg: 377.63 / Max: 540.35
Result
OpenBenchmarking.org Seconds, Fewer Is Better Blender 4.1 Blend File: BMW27 - Compute: CPU-Only EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 4 8 12 16 20 SE +/- 0.07, N = 4 SE +/- 0.02, N = 5 SE +/- 0.05, N = 4 SE +/- 0.01, N = 6 SE +/- 0.01, N = 5 SE +/- 0.02, N = 7 SE +/- 0.04, N = 6 SE +/- 0.03, N = 6 SE +/- 0.02, N = 4 SE +/- 0.03, N = 4 15.96 8.61 12.97 6.66 9.46 5.10 6.55 6.45 10.88 11.03 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Blender 4.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 27.61 / Avg: 264.26 / Max: 339.47 Min: 42.53 / Avg: 254.72 / Max: 335.42 Min: 44.7 / Avg: 317.62 / Max: 461.24 Min: 50.36 / Avg: 356.9 / Max: 540.66 Min: 52.21 / Avg: 358.27 / Max: 541.03
SVT-AV1 This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 60 120 180 240 300 SE +/- 0.80, N = 7 SE +/- 1.88, N = 15 SE +/- 1.90, N = 9 SE +/- 1.78, N = 15 SE +/- 2.17, N = 9 SE +/- 1.67, N = 9 SE +/- 1.20, N = 7 SE +/- 1.38, N = 15 SE +/- 0.97, N = 7 SE +/- 0.87, N = 7 178.52 171.22 258.61 253.99 281.59 283.54 160.33 161.64 179.14 180.58 1. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better SVT-AV1 2.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.5729 1.1458 1.7187 2.2916 2.8645 1.714 2.546 2.421 1.662 1.604 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better SVT-AV1 2.0 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 50 100 150 200 250 Min: 25.96 / Avg: 104.16 / Max: 214.25 Min: 42.3 / Avg: 101.59 / Max: 233.45 Min: 44.48 / Avg: 116.33 / Max: 294.81 Min: 43.74 / Avg: 107.81 / Max: 226.55 Min: 44.66 / Avg: 112.56 / Max: 226.81
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 70 140 210 280 350 SE +/- 0.03, N = 6 SE +/- 1.54, N = 8 SE +/- 0.11, N = 8 SE +/- 2.22, N = 15 SE +/- 0.06, N = 8 SE +/- 2.29, N = 15 SE +/- 2.41, N = 9 SE +/- 1.59, N = 9 SE +/- 0.56, N = 8 SE +/- 0.37, N = 8 132.49 185.71 173.00 262.06 223.21 305.13 341.83 344.27 217.71 218.33 MIN: 130.77 / MAX: 135.13 MIN: 154.13 / MAX: 227.12 MIN: 170.04 / MAX: 176.59 MIN: 209.29 / MAX: 297.79 MIN: 219.93 / MAX: 227.73 MIN: 222.07 / MAX: 356.87 MIN: 287.85 / MAX: 403.73 MIN: 289.86 / MAX: 404.39 MIN: 205.59 / MAX: 231.05 MIN: 206.31 / MAX: 231.64 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Asian Dragon EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.2171 0.4342 0.6513 0.8684 1.0855 0.735 0.872 0.965 0.831 0.824 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 4.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 28.26 / Avg: 180.38 / Max: 335.4 Min: 42.45 / Avg: 198.36 / Max: 353.12 Min: 44.72 / Avg: 231.42 / Max: 467.75 Min: 50.08 / Avg: 261.98 / Max: 536.02 Min: 50.81 / Avg: 264.82 / Max: 536.59
Result
OpenBenchmarking.org Frames Per Second, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 60 120 180 240 300 SE +/- 0.08, N = 6 SE +/- 0.43, N = 7 SE +/- 0.03, N = 7 SE +/- 1.81, N = 8 SE +/- 0.11, N = 8 SE +/- 2.40, N = 15 SE +/- 0.38, N = 8 SE +/- 0.57, N = 8 SE +/- 0.21, N = 7 SE +/- 0.27, N = 7 110.53 176.21 136.80 229.69 179.45 287.53 262.10 260.81 162.98 161.81 MIN: 107.72 / MAX: 115.26 MIN: 163.69 / MAX: 195.97 MIN: 133.41 / MAX: 142.65 MIN: 202.63 / MAX: 249.19 MIN: 175.01 / MAX: 186.64 MIN: 212.32 / MAX: 329.07 MIN: 227.47 / MAX: 315.15 MIN: 220.89 / MAX: 311.03 MIN: 156.25 / MAX: 173.86 MIN: 153.51 / MAX: 173.4 Frames Per Second Per Watt
OpenBenchmarking.org Frames Per Second Per Watt, More Is Better Embree 4.3 Binary: Pathtracer ISPC - Model: Crown EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.1575 0.315 0.4725 0.63 0.7875 0.499 0.634 0.700 0.557 0.546 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Embree 4.3 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 90 180 270 360 450 Min: 27.85 / Avg: 221.71 / Max: 341.98 Min: 42.52 / Avg: 215.65 / Max: 352.12 Min: 44.46 / Avg: 256.25 / Max: 473.57 Min: 45.16 / Avg: 292.53 / Max: 534.34 Min: 50.04 / Avg: 296.53 / Max: 535.58
Primesieve Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve primarily benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 12.1 Length: 1e12 EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.4631 0.9262 1.3893 1.8524 2.3155 SE +/- 0.003, N = 11 SE +/- 0.005, N = 12 SE +/- 0.004, N = 11 SE +/- 0.004, N = 12 SE +/- 0.004, N = 12 SE +/- 0.006, N = 13 SE +/- 0.004, N = 12 SE +/- 0.007, N = 13 SE +/- 0.009, N = 11 SE +/- 0.007, N = 11 2.058 1.242 2.042 1.196 1.553 1.067 1.152 1.117 1.982 1.992 1. (CXX) g++ options: -O3 CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Primesieve 12.1 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 26.05 / Avg: 142.51 / Max: 369.88 Min: 42.23 / Avg: 130.22 / Max: 315.11 Min: 44.74 / Avg: 147.17 / Max: 431.8 Min: 50.88 / Avg: 204.31 / Max: 541.32 Min: 50.77 / Avg: 203.34 / Max: 534.41
Parallel BZIP2 Compression This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.
Result
OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.13 FreeBSD-13.0-RELEASE-amd64-memstick.img Compression EPYC 9654 EPYC 9654 2P EPYC 9655 EPYC 9655 2P EPYC 9755 EPYC 9755 2P Xeon 6980P 2P @ DDR5-6400 Xeon 6980P 2P @ MRDIMM-8800 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 0.3202 0.6404 0.9606 1.2808 1.601 SE +/- 0.014512, N = 15 SE +/- 0.019468, N = 15 SE +/- 0.014837, N = 15 SE +/- 0.011000, N = 15 SE +/- 0.010948, N = 15 SE +/- 0.006187, N = 15 SE +/- 0.021554, N = 15 SE +/- 0.012727, N = 15 SE +/- 0.017482, N = 15 SE +/- 0.013373, N = 15 1.422954 1.126329 1.131325 0.892009 0.934896 0.787357 1.012839 0.960310 1.147614 1.131788 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread CPU Power Consumption
OpenBenchmarking.org Watts, Fewer Is Better Parallel BZIP2 Compression 1.1.13 CPU Power Consumption Monitor EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 60 120 180 240 300 Min: 26.03 / Avg: 87.61 / Max: 297.16 Min: 42.35 / Avg: 89.62 / Max: 271.21 Min: 44.54 / Avg: 97.48 / Max: 318.96 Min: 44.22 / Avg: 104.19 / Max: 320.86 Min: 49.71 / Avg: 107.9 / Max: 332.59
CPU Power Consumption Monitor OpenBenchmarking.org Watts CPU Power Consumption Monitor Phoronix Test Suite System Monitoring EPYC 9654 EPYC 9655 EPYC 9755 Xeon 6980P @ DDR5-6400 Xeon 6980P @ MRDIMM-8800 100 200 300 400 500 Min: 14.69 / Avg: 244.69 / Max: 373.1 Min: 41.04 / Avg: 253.26 / Max: 371.62 Min: 44.19 / Avg: 324.1 / Max: 500.98 Min: 26.45 / Avg: 322.46 / Max: 547.86 Min: 25.15 / Avg: 331.79 / Max: 542.32
Xeon 6980P @ DDR5-6400 Processor: Intel Xeon 6980P @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 768GB, Disk: 960GB SAMSUNG MZ1L2960HCJR-00A07 + 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 7 October 2024 11:48 by user phoronix.
Xeon 6980P @ MRDIMM-8800 Processor: Intel Xeon 6980P @ 3.90GHz (128 Cores / 256 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 768GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92 + 960GB SAMSUNG MZ1L2960HCJR-00A07, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 26 September 2024 19:03 by user phoronix.
Xeon 6980P 2P @ DDR5-6400 Processor: 2 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads), Motherboard: Intel AvenueCity v0.01 (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 1520GB, Disk: 960GB SAMSUNG MZ1L2960HCJR-00A07 + 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: Not affected; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 30 September 2024 21:00 by user phoronix.
Xeon 6980P 2P @ MRDIMM-8800 Processor: 2 x Intel Xeon 6980P @ 3.90GHz (256 Cores / 512 Threads), Motherboard: Intel BIRCHSTREAM (BHSDCRB1.IPC.0035.D44.2408292336 BIOS), Chipset: Intel Ice Lake IEH, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92 + 960GB SAMSUNG MZ1L2960HCJR-00A07, Graphics: ASPEED, Network: Intel I210 + 2 x Intel 10-Gigabit X540-AT2
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: intel_pstate performance (EPP: performance) - CPU Microcode: 0x10002f0Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 25 September 2024 11:57 by user phoronix.
EPYC 9654 Processor: AMD EPYC 9654 96-Core @ 2.40GHz (96 Cores / 192 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 12 x 64GB DDR5-4800MT/s Samsung M321R8GA0BB0-CQKEG, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 13 May 2024 14:14 by user phoronix.
EPYC 9654 2P Processor: 2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads), Motherboard: AMD Titanite_4G (RTI1007B BIOS), Chipset: AMD Device 14a4, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.9.0-060900rc3-generic (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa101144Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 14 May 2024 15:08 by user phoronix.
EPYC 9655 Processor: AMD EPYC 9655 96-Core @ 2.60GHz (96 Cores / 192 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 24 October 2024 20:58 by user phoronix.
EPYC 9655 2P Processor: 2 x AMD EPYC 9655 96-Core @ 2.60GHz (192 Cores / 384 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 1520GB, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 23 October 2024 01:56 by user phoronix.
EPYC 9755 Processor: AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 26 September 2024 15:49 by user phoronix.
EPYC 9755 2P Processor: 2 x AMD EPYC 9755 128-Core @ 2.70GHz (256 Cores / 512 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 1520GB, Disk: Samsung SSD 980 500GB + 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe
OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -vProcessor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)Python Notes: Python 3.12.2Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 28 September 2024 02:00 by user phoronix.