24Core

2 x AMD EPYC 7F72 24-Core testing with a Supermicro H11DSU-iN (2.1b BIOS) and llvmpipe 504GB on Ubuntu 20.04 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2007101-NI-24CORE67309
Jump To Table - Results

Statistics

Remove Outliers Before Calculating Averages

Graph Settings

Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs
Condense Test Profiles With Multiple Version Results Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
2 x AMD EPYC 7F72 24-Core
July 09 2020
  8 Hours, 13 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

2 x AMD EPYC 7F72 24-Core

Processor: 2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads), Motherboard: Supermicro H11DSU-iN (2.1b BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 2 x 3841GB Micron_9200_MTFDHAL3T8TCT, Graphics: llvmpipe 504GB, Network: 4 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.4.0-40-generic (x86_64), Desktop: GNOME Shell 3.36.2, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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 -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301038
Python Notes: Python 3.8.2
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

24CoreOpenBenchmarking.orgPhoronix Test Suite2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads)Supermicro H11DSU-iN (2.1b BIOS)AMD Starship/Matisse504GB2 x 3841GB Micron_9200_MTFDHAL3T8TCTllvmpipe 504GB4 x Intel I350Ubuntu 20.045.4.0-40-generic (x86_64)GNOME Shell 3.36.2X Server 1.20.8modesetting 1.20.83.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits)GCC 9.3.0ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution24Core BenchmarksSystem Logs- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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 -v - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301038- Python 3.8.2- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

24Coreblender: Pabellon Barcelona - OpenCLblender: Fishy Cat - OpenCLbuild-gcc: Time To Compileblender: Barbershop - OpenCLblender: BMW27 - OpenCLfftw: Float + SSE - 2D FFT Size 2048fftw: Float + SSE - 2D FFT Size 4096onednn: IP Batch All - f32 - CPUmlpack: scikit_linearridgeregressionnumpy: blender: Classroom - OpenCLbuild-llvm: Time To Compilefftw: Stock - 2D FFT Size 4096onednn: Recurrent Neural Network Training - f32 - CPUsvt-av1: Enc Mode 0 - 1080pblender: Barbershop - CPU-Onlygeekbench: CPU Multi Core - Horizon Detectiongeekbench: CPU Multi Core - Face Detectiongeekbench: CPU Multi Core - Gaussian Blurgeekbench: CPU Multi Coremlpack: scikit_svmbyte: Dhrystone 2byte: Floating-Point Arithmeticbyte: Integer Arithmeticbyte: Register Arithmeticblender: Pabellon Barcelona - CPU-Onlyonednn: Deconvolution Batch deconv_1d - f32 - CPUnpb: BT.Cblender: Classroom - CPU-Onlyv-ray: CPUbuild-linux-kernel: Time To Compileonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUblender: Fishy Cat - CPU-Onlystockfish: Total Timeonednn: IP Batch All - u8s8f32 - CPUgeekbench: CPU Single Core - Horizon Detectiongeekbench: CPU Single Core - Face Detectiongeekbench: CPU Single Core - Gaussian Blurgeekbench: CPU Single Coreredis: SETredis: GETfftw: Stock - 2D FFT Size 2048stream: Copyredis: LPOPredis: LPUSHredis: SADDsysbench: Memorygromacs: Water Benchmarkblender: BMW27 - CPU-Onlyonednn: Recurrent Neural Network Inference - f32 - CPUnamd: ATPase Simulation - 327,506 Atomsnpb: EP.Dembree: Pathtracer ISPC - Asian Dragon Objembree: Pathtracer - Asian Dragon Objonednn: Convolution Batch Shapes Auto - u8s8f32 - CPUfftw: Float + SSE - 2D FFT Size 1024pybench: Total For Average Test Timesembree: Pathtracer - Asian Dragononednn: Deconvolution Batch deconv_1d - u8s8f32 - CPUonednn: IP Batch 1D - f32 - CPUonednn: IP Batch 1D - u8s8f32 - CPUopenssl: RSA 4096-bit Performanceembree: Pathtracer ISPC - Crowny-cruncher: Calculating 500M Pi Digitsembree: Pathtracer - Crownsvt-av1: Enc Mode 4 - 1080ppovray: Trace Timex265: H.265 1080p Video Encodingnpb: LU.Cembree: Pathtracer ISPC - Asian Dragonsysbench: CPUnpb: FT.Cc-ray: Total Time - 4K, 16 Rays Per Pixelonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUfftw: Stock - 2D FFT Size 1024onednn: Deconvolution Batch deconv_3d - f32 - CPUonednn: Convolution Batch Shapes Auto - f32 - CPUfftw: Float + SSE - 2D FFT Size 512svt-av1: Enc Mode 8 - 1080pfftw: Float + SSE - 1D FFT Size 2048fftw: Float + SSE - 1D FFT Size 4096fftw: Stock - 1D FFT Size 4096fftw: Float + SSE - 2D FFT Size 256fftw: Stock - 2D FFT Size 512fftw: Stock - 1D FFT Size 2048fftw: Float + SSE - 1D FFT Size 512fftw: Float + SSE - 1D FFT Size 1024fftw: Stock - 2D FFT Size 128fftw: Float + SSE - 2D FFT Size 128npb: SP.Bsvt-vp9: Visual Quality Optimized - Bosphorus 1080pfftw: Stock - 1D FFT Size 1024svt-vp9: VMAF Optimized - Bosphorus 1080pfftw: Float + SSE - 1D FFT Size 32fftw: Stock - 2D FFT Size 256fftw: Stock - 2D FFT Size 64fftw: Float + SSE - 1D FFT Size 256fftw: Float + SSE - 1D FFT Size 128onednn: Deconvolution Batch deconv_3d - u8s8f32 - CPUsvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080px264: H.264 Video Encodingfftw: Float + SSE - 2D FFT Size 64npb: EP.Cfftw: Stock - 1D FFT Size 512fftw: Float + SSE - 1D FFT Size 64fftw: Stock - 1D FFT Size 64npb: MG.Cfftw: Stock - 1D FFT Size 128fftw: Stock - 1D FFT Size 256lammps: Rhodopsin Proteinfftw: Stock - 2D FFT Size 32fftw: Float + SSE - 2D FFT Size 32fftw: Stock - 1D FFT Size 32stream: Triadstream: Addstream: Scale2 x AMD EPYC 7F72 24-Core1005.74968.60727.009505.44371.37284581686319.3931208.29343.27209.74202.9395788.9432.1210.113164.26292.26472.71.574064726.4439057758.9111115.162.26958143148.6786.155620325.0350.48876158.941174577558.8786725.99.2069.511191551535.961878718.286373.8167365.31418979.191370019.671747641.583109595.03695.54236.46176.0020.411523999.8132.753634.72684.2731737390107839.68461.854241.528182.7981012991.843.172511.50245.93948.62511.03657.71168485.1137.988992719.140966684.4611.8510.7524976764.62.439760.8558433644864.85451012482017471.4367587396.77691.144669488867632.339096101356.36288.117957.8324.12132057368.38175.433200229841.38501333.09196.45397103906.987776.7180248934.087308.047314.37744.423.7479530.0390489610.7192261.6191065.1180732.9OpenBenchmarking.org

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Pabellon Barcelona - Compute: OpenCL2 x AMD EPYC 7F72 24-Core2004006008001000SE +/- 4.89, N = 31005.74
MinAvgMax2 x AMD EPYC 7F72 24-Core249737153846OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.550.762.1OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core235.0365.3424.3OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor1102203304405501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 49189 Joules per run.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Fishy Cat - Compute: OpenCL2 x AMD EPYC 7F72 24-Core2004006008001000SE +/- 1.82, N = 3968.60
MinAvgMax2 x AMD EPYC 7F72 24-Core180136903809OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core33.945.662.0OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core238.6334.4373.3OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor1002003004005001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 43254 Joules per run.

Timed GCC Compilation

This test times how long it takes to build the GNU Compiler Collection (GCC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 9.3.0Time To Compile2 x AMD EPYC 7F72 24-Core160320480640800SE +/- 0.21, N = 3727.01
MinAvgMax2 x AMD EPYC 7F72 24-Core243735363756OpenBenchmarking.orgMegahertz, More Is BetterTimed GCC Compilation 9.3.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core36.646.467.3OpenBenchmarking.orgCelsius, Fewer Is BetterTimed GCC Compilation 9.3.0CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core240364712OpenBenchmarking.orgWatts, Fewer Is BetterTimed GCC Compilation 9.3.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 35425 Joules per run.

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Barbershop - Compute: OpenCL2 x AMD EPYC 7F72 24-Core110220330440550SE +/- 2.14, N = 3505.44
MinAvgMax2 x AMD EPYC 7F72 24-Core180136883836OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core38.157.866.3OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core240.8456.4552.8OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 30882 Joules per run.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: BMW27 - Compute: OpenCL2 x AMD EPYC 7F72 24-Core80160240320400SE +/- 1.44, N = 3371.37
MinAvgMax2 x AMD EPYC 7F72 24-Core180236973902OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core37.050.458.4OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core237.2352.8400.2OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor1102203304405501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 17525 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 20482 x AMD EPYC 7F72 24-Core6K12K18K24K30KSE +/- 452.18, N = 12284581. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 20482 x AMD EPYC 7F72 24-Core2040608010090.04
MinAvgMax2 x AMD EPYC 7F72 24-Core180036533814OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.336.550.3OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core237.0316.1335.1OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 4030 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 40962 x AMD EPYC 7F72 24-Core4K8K12K16K20KSE +/- 40.58, N = 3168631. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 40962 x AMD EPYC 7F72 24-Core122436486052.21
MinAvgMax2 x AMD EPYC 7F72 24-Core369537063806OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.834.334.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core235.9323.0334.8OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 15612 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core510152025SE +/- 0.19, N = 1519.39MIN: 16.111. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core184136434005OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor11002200330044005500
MinAvgMax2 x AMD EPYC 7F72 24-Core32.853.062.3OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core237464636OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 3708 Joules per run.

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregression2 x AMD EPYC 7F72 24-Core50100150200250SE +/- 0.32, N = 3208.29
MinAvgMax2 x AMD EPYC 7F72 24-Core181836753769OpenBenchmarking.orgMegahertz, More Is BetterMlpack BenchmarkCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core33.842.248.8OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkCPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core243.9324.0332.1OpenBenchmarking.orgWatts, Fewer Is BetterMlpack BenchmarkSystem Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 11666 Joules per run.

Numpy Benchmark

This is a test to obtain the general Numpy performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark2 x AMD EPYC 7F72 24-Core70140210280350SE +/- 2.31, N = 3343.27
OpenBenchmarking.orgScore Per Watt, More Is BetterNumpy Benchmark2 x AMD EPYC 7F72 24-Core0.24530.49060.73590.98121.22651.09
MinAvgMax2 x AMD EPYC 7F72 24-Core180136513712OpenBenchmarking.orgMegahertz, More Is BetterNumpy BenchmarkCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.035.741.6OpenBenchmarking.orgCelsius, Fewer Is BetterNumpy BenchmarkCPU Temperature Monitor1122334455
MinAvgMax2 x AMD EPYC 7F72 24-Core238.2315.7336.6OpenBenchmarking.orgWatts, Fewer Is BetterNumpy BenchmarkSystem Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 11364 Joules per run.

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Classroom - Compute: OpenCL2 x AMD EPYC 7F72 24-Core50100150200250SE +/- 0.81, N = 3209.74
MinAvgMax2 x AMD EPYC 7F72 24-Core207236953882OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core43.568.174.8OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core241526639OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 15092 Joules per run.

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 10.0Time To Compile2 x AMD EPYC 7F72 24-Core4080120160200SE +/- 2.19, N = 3202.94
MinAvgMax2 x AMD EPYC 7F72 24-Core180136013763OpenBenchmarking.orgMegahertz, More Is BetterTimed LLVM Compilation 10.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core39.460.873.1OpenBenchmarking.orgCelsius, Fewer Is BetterTimed LLVM Compilation 10.0CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core236507723OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 10.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 15218 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 40962 x AMD EPYC 7F72 24-Core12002400360048006000SE +/- 8.42, N = 35788.91. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 40962 x AMD EPYC 7F72 24-Core4812162017.89
MinAvgMax2 x AMD EPYC 7F72 24-Core369537013706OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core42.649.956.5OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core234.4323.5340.6OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 8519 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core90180270360450SE +/- 4.74, N = 15432.12MIN: 396.981. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180136123756OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.055.266.8OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core235.8477.4610.7OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2578 Joules per run.

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080p2 x AMD EPYC 7F72 24-Core0.02540.05080.07620.10160.127SE +/- 0.000, N = 30.1131. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 0 - Input: 1080p2 x AMD EPYC 7F72 24-Core
MinAvgMax2 x AMD EPYC 7F72 24-Core247736913834OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 0.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core37.652.362.3OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core238.4342.9561.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 8574 Joules per run.

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Barbershop - Compute: CPU-Only2 x AMD EPYC 7F72 24-Core4080120160200SE +/- 0.26, N = 3164.26
MinAvgMax2 x AMD EPYC 7F72 24-Core180135323754OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core33.567.676.8OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core238596691OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 14298 Joules per run.

Geekbench

This is a benchmark of Geekbench 5 Pro. The test profile automates the execution of Geekbench 5 under the Phoronix Test Suite, assuming you have a valid license key for Geekbench 5 Pro. This test will not work without a valid license key for Geekbench Pro. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGpixels/sec, More Is BetterGeekbench 5.0Test: CPU Multi Core - Horizon Detection2 x AMD EPYC 7F72 24-Core60120180240300SE +/- 291.12, N = 3292.26
OpenBenchmarking.orgGpixels/sec Per Watt, More Is BetterGeekbench 5.0Test: CPU Multi Core - Horizon Detection2 x AMD EPYC 7F72 24-Core0.1530.3060.4590.6120.7650.68
MinAvgMax2 x AMD EPYC 7F72 24-Core227036993851OpenBenchmarking.orgMegahertz, More Is BetterGeekbench 5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core40.855.071.4OpenBenchmarking.orgCelsius, Fewer Is BetterGeekbench 5.0CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core236429694OpenBenchmarking.orgWatts, Fewer Is BetterGeekbench 5.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 7872 Joules per run.

OpenBenchmarking.orgimages/sec, More Is BetterGeekbench 5.0Test: CPU Multi Core - Face Detection2 x AMD EPYC 7F72 24-Core100200300400500SE +/- 3.64, N = 3472.7

OpenBenchmarking.orgMpixels/sec, More Is BetterGeekbench 5.0Test: CPU Multi Core - Gaussian Blur2 x AMD EPYC 7F72 24-Core0.35330.70661.05991.41321.7665SE +/- 0.06, N = 31.57

OpenBenchmarking.orgScore, More Is BetterGeekbench 5.0Test: CPU Multi Core2 x AMD EPYC 7F72 24-Core9K18K27K36K45KSE +/- 610.72, N = 340647

Mlpack Benchmark

Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svm2 x AMD EPYC 7F72 24-Core612182430SE +/- 0.80, N = 1226.44
MinAvgMax2 x AMD EPYC 7F72 24-Core180035333707OpenBenchmarking.orgMegahertz, More Is BetterMlpack BenchmarkCPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core41.043.848.0OpenBenchmarking.orgCelsius, Fewer Is BetterMlpack BenchmarkCPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core232.6314.0348.9OpenBenchmarking.orgWatts, Fewer Is BetterMlpack BenchmarkSystem Power Consumption Monitor1002003004005001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1465 Joules per run.

BYTE Unix Benchmark

This is a test of BYTE. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 22 x AMD EPYC 7F72 24-Core8M16M24M32M40MSE +/- 133031.37, N = 339057758.9
OpenBenchmarking.orgLPS Per Watt, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 22 x AMD EPYC 7F72 24-Core30K60K90K120K150K142296.25
MinAvgMax2 x AMD EPYC 7F72 24-Core180027743717OpenBenchmarking.orgMegahertz, More Is BetterBYTE Unix Benchmark 3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.834.639.5OpenBenchmarking.orgCelsius, Fewer Is BetterBYTE Unix Benchmark 3.6CPU Temperature Monitor1122334455
MinAvgMax2 x AMD EPYC 7F72 24-Core231.2274.5315.7OpenBenchmarking.orgWatts, Fewer Is BetterBYTE Unix Benchmark 3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 4575 Joules per run.

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Floating-Point Arithmetic2 x AMD EPYC 7F72 24-Core0.2250.450.6750.91.1251
OpenBenchmarking.orgLPS Per Watt, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Floating-Point Arithmetic2 x AMD EPYC 7F72 24-Core
MinAvgMax2 x AMD EPYC 7F72 24-Core180026913710OpenBenchmarking.orgMegahertz, More Is BetterBYTE Unix Benchmark 3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.033.134.0OpenBenchmarking.orgCelsius, Fewer Is BetterBYTE Unix Benchmark 3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core232.1274.7311.7OpenBenchmarking.orgWatts, Fewer Is BetterBYTE Unix Benchmark 3.6System Power Consumption Monitor80160240320400

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Integer Arithmetic2 x AMD EPYC 7F72 24-Core0.2250.450.6750.91.1251
OpenBenchmarking.orgLPS Per Watt, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Integer Arithmetic2 x AMD EPYC 7F72 24-Core
MinAvgMax2 x AMD EPYC 7F72 24-Core180028203712OpenBenchmarking.orgMegahertz, More Is BetterBYTE Unix Benchmark 3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.334.537.5OpenBenchmarking.orgCelsius, Fewer Is BetterBYTE Unix Benchmark 3.6CPU Temperature Monitor1122334455
MinAvgMax2 x AMD EPYC 7F72 24-Core231.3274.5311.7OpenBenchmarking.orgWatts, Fewer Is BetterBYTE Unix Benchmark 3.6System Power Consumption Monitor80160240320400

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Register Arithmetic2 x AMD EPYC 7F72 24-Core0.2250.450.6750.91.1251
OpenBenchmarking.orgLPS Per Watt, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Register Arithmetic2 x AMD EPYC 7F72 24-Core
MinAvgMax2 x AMD EPYC 7F72 24-Core180028793709OpenBenchmarking.orgMegahertz, More Is BetterBYTE Unix Benchmark 3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.334.537.3OpenBenchmarking.orgCelsius, Fewer Is BetterBYTE Unix Benchmark 3.6CPU Temperature Monitor1122334455
MinAvgMax2 x AMD EPYC 7F72 24-Core230.6275.3310.6OpenBenchmarking.orgWatts, Fewer Is BetterBYTE Unix Benchmark 3.6System Power Consumption Monitor80160240320400

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Pabellon Barcelona - Compute: CPU-Only2 x AMD EPYC 7F72 24-Core306090120150SE +/- 0.44, N = 3115.16
MinAvgMax2 x AMD EPYC 7F72 24-Core180134003808OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core30.869.176.6OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core236620671OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 9916 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.51071.02141.53212.04282.5535SE +/- 0.02617, N = 152.26958MIN: 1.841. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180135293700OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.949.557.6OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core236.8443.9583.0OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1420 Joules per run.

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C2 x AMD EPYC 7F72 24-Core30K60K90K120K150KSE +/- 3344.56, N = 13143148.671. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C2 x AMD EPYC 7F72 24-Core50100150200250233.29
MinAvgMax2 x AMD EPYC 7F72 24-Core180134544180OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor11002200330044005500
MinAvgMax2 x AMD EPYC 7F72 24-Core46.366.070.4OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core224614713OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2124 Joules per run.

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Classroom - Compute: CPU-Only2 x AMD EPYC 7F72 24-Core20406080100SE +/- 0.22, N = 386.15
MinAvgMax2 x AMD EPYC 7F72 24-Core180232913695OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.070.176.5OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core234604642OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 7247 Joules per run.

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPU2 x AMD EPYC 7F72 24-Core12K24K36K48K60KSE +/- 162.05, N = 356203
OpenBenchmarking.orgKsamples Per Watt, More Is BetterChaos Group V-RAY 4.10.07Mode: CPU2 x AMD EPYC 7F72 24-Core2040608010096.32
MinAvgMax2 x AMD EPYC 7F72 24-Core249436463711OpenBenchmarking.orgMegahertz, More Is BetterChaos Group V-RAY 4.10.07CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core42.164.069.6OpenBenchmarking.orgCelsius, Fewer Is BetterChaos Group V-RAY 4.10.07CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core239583663OpenBenchmarking.orgWatts, Fewer Is BetterChaos Group V-RAY 4.10.07System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 5251 Joules per run.

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compile2 x AMD EPYC 7F72 24-Core612182430SE +/- 0.26, N = 825.04
MinAvgMax2 x AMD EPYC 7F72 24-Core197634203704OpenBenchmarking.orgMegahertz, More Is BetterTimed Linux Kernel Compilation 5.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core43.556.264.4OpenBenchmarking.orgCelsius, Fewer Is BetterTimed Linux Kernel Compilation 5.4CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core238467701OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 5.4System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2219 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.110.220.330.440.55SE +/- 0.006372, N = 150.488761MIN: 0.421. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180133323708OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core35.550.158.8OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core229.4437.5580.8OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 933 Joules per run.

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Fishy Cat - Compute: CPU-Only2 x AMD EPYC 7F72 24-Core1326395265SE +/- 0.19, N = 358.94
MinAvgMax2 x AMD EPYC 7F72 24-Core224235423827OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core37.467.577.4OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core237564671OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 4697 Joules per run.

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time2 x AMD EPYC 7F72 24-Core30M60M90M120M150MSE +/- 935897.61, N = 31174577551. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 9Total Time2 x AMD EPYC 7F72 24-Core40K80K120K160K200K178778.93
MinAvgMax2 x AMD EPYC 7F72 24-Core247735533694OpenBenchmarking.orgMegahertz, More Is BetterStockfish 9CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core46.569.876.3OpenBenchmarking.orgCelsius, Fewer Is BetterStockfish 9CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core234657703OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 9System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 5256 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch All - Data Type: u8s8f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core246810SE +/- 0.06082, N = 38.87867MIN: 8.311. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core367536993708OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core40.355.764.9OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core240453640OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 3626 Joules per run.

Geekbench

This is a benchmark of Geekbench 5 Pro. The test profile automates the execution of Geekbench 5 under the Phoronix Test Suite, assuming you have a valid license key for Geekbench 5 Pro. This test will not work without a valid license key for Geekbench Pro. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGpixels/sec, More Is BetterGeekbench 5.0Test: CPU Single Core - Horizon Detection2 x AMD EPYC 7F72 24-Core612182430SE +/- 0.03, N = 325.9
OpenBenchmarking.orgGpixels/sec Per Watt, More Is BetterGeekbench 5.0Test: CPU Single Core - Horizon Detection2 x AMD EPYC 7F72 24-Core0.02030.04060.06090.08120.10150.09
MinAvgMax2 x AMD EPYC 7F72 24-Core180034013708OpenBenchmarking.orgMegahertz, More Is BetterGeekbench 5.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.038.151.8OpenBenchmarking.orgCelsius, Fewer Is BetterGeekbench 5.0CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core241.3282.8323.2OpenBenchmarking.orgWatts, Fewer Is BetterGeekbench 5.0System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2168 Joules per run.

OpenBenchmarking.orgimages/sec, More Is BetterGeekbench 5.0Test: CPU Single Core - Face Detection2 x AMD EPYC 7F72 24-Core3691215SE +/- 0.01, N = 39.20

OpenBenchmarking.orgMpixels/sec, More Is BetterGeekbench 5.0Test: CPU Single Core - Gaussian Blur2 x AMD EPYC 7F72 24-Core1530456075SE +/- 0.46, N = 369.5

OpenBenchmarking.orgScore, More Is BetterGeekbench 5.0Test: CPU Single Core2 x AMD EPYC 7F72 24-Core2004006008001000SE +/- 0.88, N = 31119

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SET2 x AMD EPYC 7F72 24-Core300K600K900K1200K1500KSE +/- 33093.57, N = 151551535.961. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 5.0.5Test: SET2 x AMD EPYC 7F72 24-Core140028004200560070006451.57
MinAvgMax2 x AMD EPYC 7F72 24-Core180020443697OpenBenchmarking.orgMegahertz, More Is BetterRedis 5.0.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core27.027.628.8OpenBenchmarking.orgCelsius, Fewer Is BetterRedis 5.0.5CPU Temperature Monitor918273645
MinAvgMax2 x AMD EPYC 7F72 24-Core232.3240.5293.6OpenBenchmarking.orgWatts, Fewer Is BetterRedis 5.0.5System Power Consumption Monitor701402102803501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 465 Joules per run.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GET2 x AMD EPYC 7F72 24-Core400K800K1200K1600K2000KSE +/- 49665.92, N = 151878718.281. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 5.0.5Test: GET2 x AMD EPYC 7F72 24-Core2K4K6K8K10K7816.27
MinAvgMax2 x AMD EPYC 7F72 24-Core180120683703OpenBenchmarking.orgMegahertz, More Is BetterRedis 5.0.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core26.527.031.9OpenBenchmarking.orgCelsius, Fewer Is BetterRedis 5.0.5CPU Temperature Monitor918273645
MinAvgMax2 x AMD EPYC 7F72 24-Core229.0240.4289.0OpenBenchmarking.orgWatts, Fewer Is BetterRedis 5.0.5System Power Consumption Monitor701402102803501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 481 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 20482 x AMD EPYC 7F72 24-Core14002800420056007000SE +/- 16.99, N = 36373.81. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 20482 x AMD EPYC 7F72 24-Core51015202520.33
MinAvgMax2 x AMD EPYC 7F72 24-Core180236153706OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.635.035.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core236.9313.5326.3OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2299 Joules per run.

Stream

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy2 x AMD EPYC 7F72 24-Core40K80K120K160K200KSE +/- 3251.50, N = 25167365.31. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgMB/s Per Watt, More Is BetterStream 2013-01-17Type: Copy2 x AMD EPYC 7F72 24-Core80160240320400387.61
MinAvgMax2 x AMD EPYC 7F72 24-Core180133893757OpenBenchmarking.orgMegahertz, More Is BetterStream 2013-01-17CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.942.346.4OpenBenchmarking.orgCelsius, Fewer Is BetterStream 2013-01-17CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core234.7431.8619.8OpenBenchmarking.orgWatts, Fewer Is BetterStream 2013-01-17System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 605 Joules per run.

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOP2 x AMD EPYC 7F72 24-Core300K600K900K1200K1500KSE +/- 59187.07, N = 131418979.191. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 5.0.5Test: LPOP2 x AMD EPYC 7F72 24-Core130026003900520065005955.69
MinAvgMax2 x AMD EPYC 7F72 24-Core180021453697OpenBenchmarking.orgMegahertz, More Is BetterRedis 5.0.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core26.827.127.5OpenBenchmarking.orgCelsius, Fewer Is BetterRedis 5.0.5CPU Temperature Monitor816243240
MinAvgMax2 x AMD EPYC 7F72 24-Core232.2238.3247.4OpenBenchmarking.orgWatts, Fewer Is BetterRedis 5.0.5System Power Consumption Monitor601201802403001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 458 Joules per run.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSH2 x AMD EPYC 7F72 24-Core300K600K900K1200K1500KSE +/- 26148.61, N = 121370019.671. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 5.0.5Test: LPUSH2 x AMD EPYC 7F72 24-Core120024003600480060005637.44
MinAvgMax2 x AMD EPYC 7F72 24-Core180019623702OpenBenchmarking.orgMegahertz, More Is BetterRedis 5.0.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core26.526.827.3OpenBenchmarking.orgCelsius, Fewer Is BetterRedis 5.0.5CPU Temperature Monitor816243240
MinAvgMax2 x AMD EPYC 7F72 24-Core233.0243.0301.8OpenBenchmarking.orgWatts, Fewer Is BetterRedis 5.0.5System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 466 Joules per run.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADD2 x AMD EPYC 7F72 24-Core400K800K1200K1600K2000KSE +/- 47396.92, N = 121747641.581. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second Per Watt, More Is BetterRedis 5.0.5Test: SADD2 x AMD EPYC 7F72 24-Core160032004800640080007301.15
MinAvgMax2 x AMD EPYC 7F72 24-Core180020823697OpenBenchmarking.orgMegahertz, More Is BetterRedis 5.0.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core27.027.227.6OpenBenchmarking.orgCelsius, Fewer Is BetterRedis 5.0.5CPU Temperature Monitor918273645
MinAvgMax2 x AMD EPYC 7F72 24-Core232.5239.4290.6OpenBenchmarking.orgWatts, Fewer Is BetterRedis 5.0.5System Power Consumption Monitor701402102803501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 459 Joules per run.

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: Memory2 x AMD EPYC 7F72 24-Core700K1400K2100K2800K3500KSE +/- 88433.92, N = 123109595.041. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second Per Watt, More Is BetterSysbench 2018-07-28Test: Memory2 x AMD EPYC 7F72 24-Core2K4K6K8K10K8467.85
MinAvgMax2 x AMD EPYC 7F72 24-Core206635643709OpenBenchmarking.orgMegahertz, More Is BetterSysbench 2018-07-28CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core36.038.640.0OpenBenchmarking.orgCelsius, Fewer Is BetterSysbench 2018-07-28CPU Temperature Monitor1122334455
MinAvgMax2 x AMD EPYC 7F72 24-Core236.4367.2421.0OpenBenchmarking.orgWatts, Fewer Is BetterSysbench 2018-07-28System Power Consumption Monitor1102203304405501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 643 Joules per run.

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020.1Water Benchmark2 x AMD EPYC 7F72 24-Core1.2472.4943.7414.9886.235SE +/- 0.019, N = 35.5421. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2020.1Water Benchmark2 x AMD EPYC 7F72 24-Core0.00230.00460.00690.00920.01150.01
MinAvgMax2 x AMD EPYC 7F72 24-Core180134663805OpenBenchmarking.orgMegahertz, More Is BetterGROMACS 2020.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.461.769.3OpenBenchmarking.orgCelsius, Fewer Is BetterGROMACS 2020.1CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core232602680OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2020.1System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 3210 Joules per run.

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: BMW27 - Compute: CPU-Only2 x AMD EPYC 7F72 24-Core816243240SE +/- 0.01, N = 336.46
MinAvgMax2 x AMD EPYC 7F72 24-Core180134303710OpenBenchmarking.orgMegahertz, More Is BetterBlender 2.82CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core48.367.473.3OpenBenchmarking.orgCelsius, Fewer Is BetterBlender 2.82CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core242557655OpenBenchmarking.orgWatts, Fewer Is BetterBlender 2.82System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2972 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core4080120160200SE +/- 2.86, N = 3176.00MIN: 151.921. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180135643710OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.445.355.8OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core239.8419.0545.4OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2235 Joules per run.

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.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13ATPase Simulation - 327,506 Atoms2 x AMD EPYC 7F72 24-Core0.09260.18520.27780.37040.463SE +/- 0.00032, N = 30.41152
MinAvgMax2 x AMD EPYC 7F72 24-Core180134373700OpenBenchmarking.orgMegahertz, More Is BetterNAMD 2.13CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core28.364.772.3OpenBenchmarking.orgCelsius, Fewer Is BetterNAMD 2.13CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core235624700OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 2.13System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 3326 Joules per run.

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D2 x AMD EPYC 7F72 24-Core9001800270036004500SE +/- 8.55, N = 33999.811. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D2 x AMD EPYC 7F72 24-Core2468107.75
MinAvgMax2 x AMD EPYC 7F72 24-Core247536483837OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core35.657.864.0OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core242.3516.4568.1OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2754 Joules per run.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon Obj2 x AMD EPYC 7F72 24-Core816243240SE +/- 0.16, N = 332.75MIN: 31.97 / MAX: 35.05
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon Obj2 x AMD EPYC 7F72 24-Core0.01580.03160.04740.06320.0790.07
MinAvgMax2 x AMD EPYC 7F72 24-Core369837033731OpenBenchmarking.orgMegahertz, More Is BetterEmbree 3.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core43.454.360.3OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core237437640OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 2040 Joules per run.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon Obj2 x AMD EPYC 7F72 24-Core816243240SE +/- 0.05, N = 334.73MIN: 34.06 / MAX: 36.79
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon Obj2 x AMD EPYC 7F72 24-Core0.0180.0360.0540.0720.090.08
MinAvgMax2 x AMD EPYC 7F72 24-Core247436103732OpenBenchmarking.orgMegahertz, More Is BetterEmbree 3.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core40.053.059.4OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core241428638OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1855 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.96151.9232.88453.8464.8075SE +/- 0.21555, N = 154.27317MIN: 2.931. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180133843706OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core36.550.958.4OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core236.5413.1573.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 551 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 10242 x AMD EPYC 7F72 24-Core8K16K24K32K40KSE +/- 30.51, N = 3373901. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 10242 x AMD EPYC 7F72 24-Core306090120150121.48
MinAvgMax2 x AMD EPYC 7F72 24-Core180134273709OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.543.750.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core239.2307.8316.4OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1231 Joules per run.

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Times2 x AMD EPYC 7F72 24-Core2004006008001000SE +/- 6.51, N = 31078
MinAvgMax2 x AMD EPYC 7F72 24-Core180135303711OpenBenchmarking.orgMegahertz, More Is BetterPyBench 2018-02-16CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core47.151.755.1OpenBenchmarking.orgCelsius, Fewer Is BetterPyBench 2018-02-16CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core241.1304.0317.7OpenBenchmarking.orgWatts, Fewer Is BetterPyBench 2018-02-16System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1216 Joules per run.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon2 x AMD EPYC 7F72 24-Core918273645SE +/- 0.12, N = 439.68MIN: 38.7 / MAX: 41.65
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Asian Dragon2 x AMD EPYC 7F72 24-Core0.01580.03160.04740.06320.0790.07
MinAvgMax2 x AMD EPYC 7F72 24-Core212435433719OpenBenchmarking.orgMegahertz, More Is BetterEmbree 3.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.452.260.8OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core254558648OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1394 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.41720.83441.25161.66882.086SE +/- 0.00452, N = 31.85424MIN: 1.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180134893700OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core37.355.362.3OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core237.6464.1616.6OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1392 Joules per run.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.34380.68761.03141.37521.719SE +/- 0.00907, N = 41.52818MIN: 1.291. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core223934193708OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core33.846.756.3OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core235.8431.1591.7OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1078 Joules per run.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: IP Batch 1D - Data Type: u8s8f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.62961.25921.88882.51843.148SE +/- 0.01627, N = 42.79810MIN: 2.391. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core369636993700OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core37.047.051.0OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core234.9407.4486.0OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1302603905206501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1019 Joules per run.

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x AMD EPYC 7F72 24-Core3K6K9K12K15KSE +/- 22.63, N = 312991.81. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgSigns Per Second Per Watt, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x AMD EPYC 7F72 24-Core61218243024.64
MinAvgMax2 x AMD EPYC 7F72 24-Core369837003700OpenBenchmarking.orgMegahertz, More Is BetterOpenSSL 1.1.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core48.563.171.8OpenBenchmarking.orgCelsius, Fewer Is BetterOpenSSL 1.1.1CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core236527663OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 1.1.1System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1582 Joules per run.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Crown2 x AMD EPYC 7F72 24-Core1020304050SE +/- 0.29, N = 443.17MIN: 40.79 / MAX: 44.78
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Crown2 x AMD EPYC 7F72 24-Core0.0180.0360.0540.0720.090.08
MinAvgMax2 x AMD EPYC 7F72 24-Core275735693696OpenBenchmarking.orgMegahertz, More Is BetterEmbree 3.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core52.461.766.8OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core231556692OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1252 Joules per run.

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.8.9503Calculating 500M Pi Digits2 x AMD EPYC 7F72 24-Core3691215SE +/- 0.09, N = 411.50
MinAvgMax2 x AMD EPYC 7F72 24-Core180134993705OpenBenchmarking.orgMegahertz, More Is BetterY-Cruncher 0.7.8.9503CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core41.356.170.1OpenBenchmarking.orgCelsius, Fewer Is BetterY-Cruncher 0.7.8.9503CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core235467677OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.7.8.9503System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1167 Joules per run.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Crown2 x AMD EPYC 7F72 24-Core1020304050SE +/- 0.12, N = 445.94MIN: 44.62 / MAX: 47.76
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer - Model: Crown2 x AMD EPYC 7F72 24-Core0.01580.03160.04740.06320.0790.07
MinAvgMax2 x AMD EPYC 7F72 24-Core183332683671OpenBenchmarking.orgMegahertz, More Is BetterEmbree 3.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core39.359.765.9OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core244623696OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1245 Joules per run.

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080p2 x AMD EPYC 7F72 24-Core246810SE +/- 0.114, N = 48.6251. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 4 - Input: 1080p2 x AMD EPYC 7F72 24-Core0.00450.0090.01350.0180.02250.02
MinAvgMax2 x AMD EPYC 7F72 24-Core180232383742OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 0.8CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core35.554.664.0OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core237404671OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1009 Joules per run.

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time2 x AMD EPYC 7F72 24-Core3691215SE +/- 0.02, N = 411.041. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
MinAvgMax2 x AMD EPYC 7F72 24-Core243834773710OpenBenchmarking.orgMegahertz, More Is BetterPOV-Ray 3.7.0.7CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.857.367.4OpenBenchmarking.orgCelsius, Fewer Is BetterPOV-Ray 3.7.0.7CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core238446639OpenBenchmarking.orgWatts, Fewer Is BetterPOV-Ray 3.7.0.7System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 893 Joules per run.

x265

This is a simple test of the x265 encoder run on the CPU with a sample 1080p video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video Encoding2 x AMD EPYC 7F72 24-Core1326395265SE +/- 0.43, N = 557.711. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx265 3.1.2H.265 1080p Video Encoding2 x AMD EPYC 7F72 24-Core0.03830.07660.11490.15320.19150.17
MinAvgMax2 x AMD EPYC 7F72 24-Core180135583845OpenBenchmarking.orgMegahertz, More Is Betterx265 3.1.2CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.447.952.6OpenBenchmarking.orgCelsius, Fewer Is Betterx265 3.1.2CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core233.6332.1428.8OpenBenchmarking.orgWatts, Fewer Is Betterx265 3.1.2System Power Consumption Monitor1102203304405501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 664 Joules per run.

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C2 x AMD EPYC 7F72 24-Core40K80K120K160K200KSE +/- 1185.50, N = 4168485.111. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C2 x AMD EPYC 7F72 24-Core80160240320400374.34
MinAvgMax2 x AMD EPYC 7F72 24-Core180135043793OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core39.654.460.1OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core238450663OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 900 Joules per run.

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon2 x AMD EPYC 7F72 24-Core918273645SE +/- 0.05, N = 337.99MIN: 37.29 / MAX: 40
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 3.9.0Binary: Pathtracer ISPC - Model: Asian Dragon2 x AMD EPYC 7F72 24-Core0.01580.03160.04740.06320.0790.07
MinAvgMax2 x AMD EPYC 7F72 24-Core283135913700OpenBenchmarking.orgMegahertz, More Is BetterEmbree 3.9.0CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core41.857.963.3OpenBenchmarking.orgCelsius, Fewer Is BetterEmbree 3.9.0CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core236514652OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 3.9.0System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1543 Joules per run.

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPU2 x AMD EPYC 7F72 24-Core20K40K60K80K100KSE +/- 26.00, N = 592719.141. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
OpenBenchmarking.orgEvents Per Second Per Watt, More Is BetterSysbench 2018-07-28Test: CPU2 x AMD EPYC 7F72 24-Core50100150200250244.87
MinAvgMax2 x AMD EPYC 7F72 24-Core370037003703OpenBenchmarking.orgMegahertz, More Is BetterSysbench 2018-07-28CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core44.646.948.8OpenBenchmarking.orgCelsius, Fewer Is BetterSysbench 2018-07-28CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core237.9378.6466.8OpenBenchmarking.orgWatts, Fewer Is BetterSysbench 2018-07-28System Power Consumption Monitor1202403604806001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 682 Joules per run.

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.C2 x AMD EPYC 7F72 24-Core14K28K42K56K70KSE +/- 731.63, N = 766684.461. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.C2 x AMD EPYC 7F72 24-Core4080120160200169.77
MinAvgMax2 x AMD EPYC 7F72 24-Core217735183726OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core41.858.564.9OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core239393699OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 561 Joules per run.

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel2 x AMD EPYC 7F72 24-Core3691215SE +/- 0.01, N = 411.851. (CC) gcc options: -lm -lpthread -O3
MinAvgMax2 x AMD EPYC 7F72 24-Core226234983702OpenBenchmarking.orgMegahertz, More Is BetterC-Ray 1.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core54.970.675.3OpenBenchmarking.orgCelsius, Fewer Is BetterC-Ray 1.1CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core239447652OpenBenchmarking.orgWatts, Fewer Is BetterC-Ray 1.1System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 894 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.16930.33860.50790.67720.8465SE +/- 0.003275, N = 40.752497MIN: 0.721. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180132773700OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core38.856.464.1OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor20406080100
MinAvgMax2 x AMD EPYC 7F72 24-Core238.2461.6621.7OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 1039 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 10242 x AMD EPYC 7F72 24-Core14002800420056007000SE +/- 26.48, N = 46764.61. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 10242 x AMD EPYC 7F72 24-Core51015202522.40
MinAvgMax2 x AMD EPYC 7F72 24-Core180128563702OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.136.043.1OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1224364860
MinAvgMax2 x AMD EPYC 7F72 24-Core231.9301.9317.2OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 679 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.54891.09781.64672.19562.7445SE +/- 0.09005, N = 152.43976MIN: 1.961. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180131653696OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core43.548.654.8OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core233.3362.4611.4OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 338 Joules per run.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.19260.38520.57780.77040.963SE +/- 0.006983, N = 70.855843MIN: 0.761. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180031093712OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.149.254.6OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core236.0416.8578.2OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 595 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 5122 x AMD EPYC 7F72 24-Core8K16K24K32K40KSE +/- 76.91, N = 7364481. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 5122 x AMD EPYC 7F72 24-Core306090120150126.55
MinAvgMax2 x AMD EPYC 7F72 24-Core180230113704OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.344.649.1OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core235.0288.0314.8OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 370 Joules per run.

SVT-AV1

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-AV1 CPU-based multi-threaded video encoder for the AV1 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080p2 x AMD EPYC 7F72 24-Core1428425670SE +/- 0.62, N = 564.851. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080p2 x AMD EPYC 7F72 24-Core0.04050.0810.12150.1620.20250.18
MinAvgMax2 x AMD EPYC 7F72 24-Core180131674009OpenBenchmarking.orgMegahertz, More Is BetterSVT-AV1 0.8CPU Peak Freq (Highest CPU Core Frequency) Monitor11002200330044005500
MinAvgMax2 x AMD EPYC 7F72 24-Core31.851.057.3OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-AV1 0.8CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core240.3353.3559.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 0.8System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 565 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 20482 x AMD EPYC 7F72 24-Core11K22K33K44K55KSE +/- 202.11, N = 7510121. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 20482 x AMD EPYC 7F72 24-Core4080120160200187.14
MinAvgMax2 x AMD EPYC 7F72 24-Core180133523705OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.333.033.4OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core236.6272.6315.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 350 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 40962 x AMD EPYC 7F72 24-Core10K20K30K40K50KSE +/- 302.15, N = 7482011. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 40962 x AMD EPYC 7F72 24-Core4080120160200170.69
MinAvgMax2 x AMD EPYC 7F72 24-Core180132813707OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.832.633.1OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core234.4282.4314.9OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 363 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 40962 x AMD EPYC 7F72 24-Core16003200480064008000SE +/- 11.10, N = 77471.41. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 40962 x AMD EPYC 7F72 24-Core61218243026.75
MinAvgMax2 x AMD EPYC 7F72 24-Core180133583708OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.533.434.0OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core235.2279.3315.6OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 359 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2562 x AMD EPYC 7F72 24-Core8K16K24K32K40KSE +/- 78.44, N = 7367581. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2562 x AMD EPYC 7F72 24-Core306090120150128.00
MinAvgMax2 x AMD EPYC 7F72 24-Core180130203722OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core41.145.749.9OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core247.1287.2316.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 369 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 5122 x AMD EPYC 7F72 24-Core16003200480064008000SE +/- 6.60, N = 87396.71. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 5122 x AMD EPYC 7F72 24-Core61218243026.18
MinAvgMax2 x AMD EPYC 7F72 24-Core180226823707OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.033.234.0OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core233.6282.5313.3OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 353 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 20482 x AMD EPYC 7F72 24-Core16003200480064008000SE +/- 6.89, N = 87691.11. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 20482 x AMD EPYC 7F72 24-Core61218243026.20
MinAvgMax2 x AMD EPYC 7F72 24-Core180031873709OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.032.933.3OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core238.2293.6315.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 294 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 5122 x AMD EPYC 7F72 24-Core10K20K30K40K50KSE +/- 313.65, N = 8446691. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 5122 x AMD EPYC 7F72 24-Core4080120160200158.93
MinAvgMax2 x AMD EPYC 7F72 24-Core180130703712OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.543.847.3OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core233.6281.1315.4OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 316 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 10242 x AMD EPYC 7F72 24-Core10K20K30K40K50KSE +/- 324.08, N = 7488861. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 10242 x AMD EPYC 7F72 24-Core4080120160200170.33
MinAvgMax2 x AMD EPYC 7F72 24-Core180232303708OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core44.447.150.5OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core234.0287.0315.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 328 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1282 x AMD EPYC 7F72 24-Core16003200480064008000SE +/- 9.71, N = 87632.31. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1282 x AMD EPYC 7F72 24-Core61218243027.00
MinAvgMax2 x AMD EPYC 7F72 24-Core180126553709OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.843.748.6OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core231.5282.7315.1OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 353 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 1282 x AMD EPYC 7F72 24-Core8K16K24K32K40KSE +/- 69.82, N = 9390961. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 1282 x AMD EPYC 7F72 24-Core306090120150152.71
MinAvgMax2 x AMD EPYC 7F72 24-Core193635043704OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.031.832.3OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor918273645
MinAvgMax2 x AMD EPYC 7F72 24-Core232.3256.0304.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 256 Joules per run.

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B2 x AMD EPYC 7F72 24-Core20K40K60K80K100KSE +/- 991.27, N = 8101356.361. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B2 x AMD EPYC 7F72 24-Core4080120160200181.03
MinAvgMax2 x AMD EPYC 7F72 24-Core180123423674OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core38.051.858.4OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1632486480
MinAvgMax2 x AMD EPYC 7F72 24-Core235560727OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor20040060080010001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 630 Joules per run.

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080p2 x AMD EPYC 7F72 24-Core60120180240300SE +/- 1.86, N = 9288.111. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080p2 x AMD EPYC 7F72 24-Core0.23850.4770.71550.9541.19251.06
MinAvgMax2 x AMD EPYC 7F72 24-Core183233223705OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core45.947.749.1OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core235.6270.9414.4OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.1System Power Consumption Monitor1102203304405501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 271 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 10242 x AMD EPYC 7F72 24-Core2K4K6K8K10KSE +/- 5.59, N = 97957.81. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 10242 x AMD EPYC 7F72 24-Core71421283531.97
MinAvgMax2 x AMD EPYC 7F72 24-Core180230983705OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.832.933.5OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core234.6248.9295.0OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor701402102803501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 249 Joules per run.

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080p2 x AMD EPYC 7F72 24-Core70140210280350SE +/- 1.48, N = 9324.121. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080p2 x AMD EPYC 7F72 24-Core0.1620.3240.4860.6480.810.72
MinAvgMax2 x AMD EPYC 7F72 24-Core180126043625OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.038.740.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1CPU Temperature Monitor1122334455
MinAvgMax2 x AMD EPYC 7F72 24-Core241.4447.9535.3OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.1System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 448 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 322 x AMD EPYC 7F72 24-Core3K6K9K12K15KSE +/- 69.72, N = 9132051. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 322 x AMD EPYC 7F72 24-Core102030405043.04
MinAvgMax2 x AMD EPYC 7F72 24-Core180123063705OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core33.534.235.3OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core261.0306.8314.1OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 273 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2562 x AMD EPYC 7F72 24-Core16003200480064008000SE +/- 11.06, N = 97368.31. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2562 x AMD EPYC 7F72 24-Core71421283529.08
MinAvgMax2 x AMD EPYC 7F72 24-Core201432993705OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.933.333.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core232.8253.4312.4OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 225 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 642 x AMD EPYC 7F72 24-Core2K4K6K8K10KSE +/- 17.47, N = 98175.41. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 642 x AMD EPYC 7F72 24-Core81624324032.34
MinAvgMax2 x AMD EPYC 7F72 24-Core369637013707OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.833.133.5OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core232.4252.8315.4OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 253 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 2562 x AMD EPYC 7F72 24-Core7K14K21K28K35KSE +/- 191.87, N = 9332001. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 2562 x AMD EPYC 7F72 24-Core306090120150131.46
MinAvgMax2 x AMD EPYC 7F72 24-Core180232253705OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.532.833.5OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core237.0252.5285.3OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor701402102803501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 253 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 1282 x AMD EPYC 7F72 24-Core5K10K15K20K25KSE +/- 17.35, N = 10229841. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 1282 x AMD EPYC 7F72 24-Core2040608010097.00
MinAvgMax2 x AMD EPYC 7F72 24-Core369837033710OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core33.033.233.3OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core233.8237.0240.7OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor601201802403001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 237 Joules per run.

oneDNN

This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the oneAPI initiative. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 1.5Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 - Engine: CPU2 x AMD EPYC 7F72 24-Core0.31160.62320.93481.24641.558SE +/- 0.01247, N = 91.38501MIN: 1.241. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
MinAvgMax2 x AMD EPYC 7F72 24-Core180230483711OpenBenchmarking.orgMegahertz, More Is BetteroneDNN 1.5CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core45.549.253.5OpenBenchmarking.orgCelsius, Fewer Is BetteroneDNN 1.5CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core232.1347.4602.5OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 1.5System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 309 Joules per run.

SVT-VP9

This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p2 x AMD EPYC 7F72 24-Core70140210280350SE +/- 1.64, N = 9333.091. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p2 x AMD EPYC 7F72 24-Core0.26550.5310.79651.0621.32751.18
MinAvgMax2 x AMD EPYC 7F72 24-Core180132143782OpenBenchmarking.orgMegahertz, More Is BetterSVT-VP9 0.1CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core35.343.246.8OpenBenchmarking.orgCelsius, Fewer Is BetterSVT-VP9 0.1CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core234.6282.6519.6OpenBenchmarking.orgWatts, Fewer Is BetterSVT-VP9 0.1System Power Consumption Monitor1302603905206501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 251 Joules per run.

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video Encoding2 x AMD EPYC 7F72 24-Core4080120160200SE +/- 0.97, N = 9196.451. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betterx264 2019-12-17H.264 Video Encoding2 x AMD EPYC 7F72 24-Core0.12830.25660.38490.51320.64150.57
MinAvgMax2 x AMD EPYC 7F72 24-Core180131353705OpenBenchmarking.orgMegahertz, More Is Betterx264 2019-12-17CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core44.647.753.6OpenBenchmarking.orgCelsius, Fewer Is Betterx264 2019-12-17CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core237.9342.6496.3OpenBenchmarking.orgWatts, Fewer Is Betterx264 2019-12-17System Power Consumption Monitor1302603905206501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 305 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 642 x AMD EPYC 7F72 24-Core9K18K27K36K45KSE +/- 102.75, N = 10397101. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 642 x AMD EPYC 7F72 24-Core306090120150140.20
MinAvgMax2 x AMD EPYC 7F72 24-Core180128843709OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core40.344.751.5OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core232.6283.2315.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 255 Joules per run.

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C2 x AMD EPYC 7F72 24-Core8001600240032004000SE +/- 27.89, N = 103906.981. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C2 x AMD EPYC 7F72 24-Core2468107.68
MinAvgMax2 x AMD EPYC 7F72 24-Core180123473684OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core42.448.352.8OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core238.1508.4549.8OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor1402804205607001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 508 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 5122 x AMD EPYC 7F72 24-Core17003400510068008500SE +/- 13.18, N = 97776.71. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 5122 x AMD EPYC 7F72 24-Core61218243027.19
MinAvgMax2 x AMD EPYC 7F72 24-Core180020062500OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor6001200180024003000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.832.332.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core272.9286.1312.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 254 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 642 x AMD EPYC 7F72 24-Core4K8K12K16K20KSE +/- 28.46, N = 9180241. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 642 x AMD EPYC 7F72 24-Core153045607566.76
MinAvgMax2 x AMD EPYC 7F72 24-Core180128463711OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.833.333.8OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core236.8270.0315.1OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 240 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 642 x AMD EPYC 7F72 24-Core2K4K6K8K10KSE +/- 4.52, N = 98934.01. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 642 x AMD EPYC 7F72 24-Core81624324035.05
MinAvgMax2 x AMD EPYC 7F72 24-Core180029883703OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.332.833.3OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core233.9254.9313.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 227 Joules per run.

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.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C2 x AMD EPYC 7F72 24-Core20K40K60K80K100KSE +/- 602.22, N = 1087308.041. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C2 x AMD EPYC 7F72 24-Core4080120160200169.28
MinAvgMax2 x AMD EPYC 7F72 24-Core182829453701OpenBenchmarking.orgMegahertz, More Is BetterNAS Parallel Benchmarks 3.4CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core30.536.640.5OpenBenchmarking.orgCelsius, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Temperature Monitor1122334455
MinAvgMax2 x AMD EPYC 7F72 24-Core240.7515.8603.5OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4System Power Consumption Monitor1603204806408001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 516 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1282 x AMD EPYC 7F72 24-Core16003200480064008000SE +/- 26.90, N = 107314.31. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1282 x AMD EPYC 7F72 24-Core71421283529.19
MinAvgMax2 x AMD EPYC 7F72 24-Core180533073704OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core36.343.647.6OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1428425670
MinAvgMax2 x AMD EPYC 7F72 24-Core234.7250.5297.2OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor701402102803501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 225 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2562 x AMD EPYC 7F72 24-Core17003400510068008500SE +/- 13.27, N = 107744.41. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2562 x AMD EPYC 7F72 24-Core71421283528.68
MinAvgMax2 x AMD EPYC 7F72 24-Core180028163710OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.032.533.1OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core236.5270.0314.5OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 216 Joules per run.

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.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020Model: Rhodopsin Protein2 x AMD EPYC 7F72 24-Core612182430SE +/- 0.58, N = 1523.751. (CXX) g++ options: -O3 -rdynamic -ljpeg -lpng -lz -lfftw3 -lm
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020Model: Rhodopsin Protein2 x AMD EPYC 7F72 24-Core0.02030.04060.06090.08120.10150.09
MinAvgMax2 x AMD EPYC 7F72 24-Core207129203677OpenBenchmarking.orgMegahertz, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core34.047.252.6OpenBenchmarking.orgCelsius, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020CPU Temperature Monitor1530456075
MinAvgMax2 x AMD EPYC 7F72 24-Core234.0279.3414.6OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020System Power Consumption Monitor1102203304405501. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 242 Joules per run.

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 322 x AMD EPYC 7F72 24-Core2K4K6K8K10KSE +/- 32.63, N = 109530.01. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 322 x AMD EPYC 7F72 24-Core81624324035.20
MinAvgMax2 x AMD EPYC 7F72 24-Core180028323705OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.332.733.0OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core232.5270.7312.7OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 217 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 322 x AMD EPYC 7F72 24-Core8K16K24K32K40KSE +/- 16.95, N = 10390481. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 322 x AMD EPYC 7F72 24-Core306090120150154.60
MinAvgMax2 x AMD EPYC 7F72 24-Core206132903704OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core31.331.732.0OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor918273645
MinAvgMax2 x AMD EPYC 7F72 24-Core232.4252.6312.3OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 202 Joules per run.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 322 x AMD EPYC 7F72 24-Core2K4K6K8K10KSE +/- 4.31, N = 109610.71. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OpenBenchmarking.orgMflops Per Watt, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 322 x AMD EPYC 7F72 24-Core81624324036.76
MinAvgMax2 x AMD EPYC 7F72 24-Core180129893706OpenBenchmarking.orgMegahertz, More Is BetterFFTW 3.3.6CPU Peak Freq (Highest CPU Core Frequency) Monitor10002000300040005000
MinAvgMax2 x AMD EPYC 7F72 24-Core32.332.633.0OpenBenchmarking.orgCelsius, Fewer Is BetterFFTW 3.3.6CPU Temperature Monitor1020304050
MinAvgMax2 x AMD EPYC 7F72 24-Core231.9261.4315.3OpenBenchmarking.orgWatts, Fewer Is BetterFFTW 3.3.6System Power Consumption Monitor801602403204001. 2 x AMD EPYC 7F72 24-Core: Approximate power consumption of 209 Joules per run.

System Power Consumption Monitor

OpenBenchmarking.orgWattsSystem Power Consumption MonitorPhoronix Test Suite System Monitoring2 x AMD EPYC 7F72 24-Core130260390520650Min: 223.5 / Avg: 371.93 / Max: 726.9

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System Monitoring2 x AMD EPYC 7F72 24-Core1530456075Min: 26.5 / Avg: 46.19 / Max: 77.38

CPU Peak Freq (Highest CPU Core Frequency) Monitor

OpenBenchmarking.orgMegahertzCPU Peak Freq (Highest CPU Core Frequency) MonitorPhoronix Test Suite System Monitoring2 x AMD EPYC 7F72 24-Core7001400210028003500Min: 1800 / Avg: 3440.06 / Max: 4180

Meta Performance Per Watts

OpenBenchmarking.orgPerformance Per Watts, More Is BetterMeta Performance Per WattsPerformance Per Watts2 x AMD EPYC 7F72 24-Core110022003300440055005037.81

Stream

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triad2 x AMD EPYC 7F72 24-Core40K80K120K160K200KSE +/- 5530.22, N = 5192261.61. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add2 x AMD EPYC 7F72 24-Core40K80K120K160K200KSE +/- 3346.40, N = 5191065.11. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scale2 x AMD EPYC 7F72 24-Core40K80K120K160K200KSE +/- 850.33, N = 5180732.91. (CC) gcc options: -O3 -march=native -fopenmp

120 Results Shown

Blender:
  Pabellon Barcelona - OpenCL
  Fishy Cat - OpenCL
Timed GCC Compilation
Blender:
  Barbershop - OpenCL
  BMW27 - OpenCL
FFTW:
  Float + SSE - 2D FFT Size 2048
  Float + SSE - 2D FFT Size 4096
oneDNN
Mlpack Benchmark
Numpy Benchmark
Blender
Timed LLVM Compilation
FFTW
oneDNN
SVT-AV1
Blender
Geekbench:
  CPU Multi Core - Horizon Detection
  CPU Multi Core - Face Detection
  CPU Multi Core - Gaussian Blur
  CPU Multi Core
Mlpack Benchmark
BYTE Unix Benchmark:
  Dhrystone 2
  Floating-Point Arithmetic
  Integer Arithmetic
  Register Arithmetic
Blender
oneDNN
NAS Parallel Benchmarks
Blender
Chaos Group V-RAY
Timed Linux Kernel Compilation
oneDNN
Blender
Stockfish
oneDNN
Geekbench:
  CPU Single Core - Horizon Detection
  CPU Single Core - Face Detection
  CPU Single Core - Gaussian Blur
  CPU Single Core
Redis:
  SET
  GET
FFTW
Stream
Redis:
  LPOP
  LPUSH
  SADD
Sysbench
GROMACS
Blender
oneDNN
NAMD
NAS Parallel Benchmarks
Embree:
  Pathtracer ISPC - Asian Dragon Obj
  Pathtracer - Asian Dragon Obj
oneDNN
FFTW
PyBench
Embree
oneDNN:
  Deconvolution Batch deconv_1d - u8s8f32 - CPU
  IP Batch 1D - f32 - CPU
  IP Batch 1D - u8s8f32 - CPU
OpenSSL
Embree
Y-Cruncher
Embree
SVT-AV1
POV-Ray
x265
NAS Parallel Benchmarks
Embree
Sysbench
NAS Parallel Benchmarks
C-Ray
oneDNN
FFTW
oneDNN:
  Deconvolution Batch deconv_3d - f32 - CPU
  Convolution Batch Shapes Auto - f32 - CPU
FFTW
SVT-AV1
FFTW:
  Float + SSE - 1D FFT Size 2048
  Float + SSE - 1D FFT Size 4096
  Stock - 1D FFT Size 4096
  Float + SSE - 2D FFT Size 256
  Stock - 2D FFT Size 512
  Stock - 1D FFT Size 2048
  Float + SSE - 1D FFT Size 512
  Float + SSE - 1D FFT Size 1024
  Stock - 2D FFT Size 128
  Float + SSE - 2D FFT Size 128
NAS Parallel Benchmarks
SVT-VP9
FFTW
SVT-VP9
FFTW:
  Float + SSE - 1D FFT Size 32
  Stock - 2D FFT Size 256
  Stock - 2D FFT Size 64
  Float + SSE - 1D FFT Size 256
  Float + SSE - 1D FFT Size 128
oneDNN
SVT-VP9
x264
FFTW
NAS Parallel Benchmarks
FFTW:
  Stock - 1D FFT Size 512
  Float + SSE - 1D FFT Size 64
  Stock - 1D FFT Size 64
NAS Parallel Benchmarks
FFTW:
  Stock - 1D FFT Size 128
  Stock - 1D FFT Size 256
LAMMPS Molecular Dynamics Simulator
FFTW:
  Stock - 2D FFT Size 32
  Float + SSE - 2D FFT Size 32
  Stock - 1D FFT Size 32
System Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Celsius
    Megahertz
  Performance Per Watts:
    Performance Per Watts
Stream:
  Triad
  Add
  Scale

2 x AMD EPYC 7F72 24-Core

Processor: 2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads), Motherboard: Supermicro H11DSU-iN (2.1b BIOS), Chipset: AMD Starship/Matisse, Memory: 504GB, Disk: 2 x 3841GB Micron_9200_MTFDHAL3T8TCT, Graphics: llvmpipe 504GB, Network: 4 x Intel I350

OS: Ubuntu 20.04, Kernel: 5.4.0-40-generic (x86_64), Desktop: GNOME Shell 3.36.2, Display Server: X Server 1.20.8, Display Driver: modesetting 1.20.8, OpenGL: 3.3 Mesa 20.0.4 (LLVM 9.0.1 128 bits), Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1024x768

Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none,hsa --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 -v
Processor Notes: Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301038
Python Notes: Python 3.8.2
Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 9 July 2020 22:10 by user paul.