AMD EPYC 7F72 2P Linux 5.11 Perf Governor

2 x AMD EPYC 7F72 24-Core testing looking at CPU freq invariance on 5.11 with patch. CPU power consumption monitoring via AMD_Energy interface at 1 second polling. Additional data with CPUFreq performance governor included.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2102048-HA-AMDEPYC7F37
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

AV1 2 Tests
BLAS (Basic Linear Algebra Sub-Routine) Tests 3 Tests
C++ Boost Tests 2 Tests
C/C++ Compiler Tests 5 Tests
CPU Massive 12 Tests
Creator Workloads 6 Tests
Database Test Suite 2 Tests
Encoding 3 Tests
Fortran Tests 3 Tests
HPC - High Performance Computing 11 Tests
LAPACK (Linear Algebra Pack) Tests 2 Tests
Machine Learning 5 Tests
Molecular Dynamics 2 Tests
MPI Benchmarks 3 Tests
Multi-Core 11 Tests
NVIDIA GPU Compute 2 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 6 Tests
Python Tests 2 Tests
Renderers 2 Tests
Scientific Computing 4 Tests
Server 2 Tests
Server CPU Tests 8 Tests
Video Encoding 3 Tests
Common Workstation Benchmarks 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Clock Calculation Graphs Where Applicable

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

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
CPUFreq Performance
January 24 2021
  6 Hours, 39 Minutes
Linux 5.11 Git
January 22 2021
  5 Hours, 35 Minutes
Linux 5.11 Giovanni Patch
January 23 2021
  5 Hours, 41 Minutes
Linux 5.11 Rafael Patch
February 03 2021
  6 Hours, 39 Minutes
Invert Hiding All Results Option
  6 Hours, 8 Minutes

Only show results where is faster than
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):


AMD EPYC 7F72 2P Linux 5.11 Perf GovernorProcessorMotherboardChipsetMemoryDiskGraphicsNetworkMonitorOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch2 x AMD EPYC 7F72 24-Core @ 3.20GHz (48 Cores / 96 Threads)Supermicro H11DSi-NT v2.00 (2.1 BIOS)AMD Starship/Matisse16 x 8192 MB DDR4-3200MT/s HMA81GR7CJR8N-XN1000GB Western Digital WD_BLACK SN850 1TBASPEED2 x Intel 10G X550TUbuntu 20.105.11.0-rc4-max-boost-inv-patch (x86_64) 20210121GNOME Shell 3.38.1X Server 1.20.9modesetting 1.20.9GCC 10.2.0ext41920x10805.11.0-051100rc4daily20210122-generic (x86_64) 20210121VE2285.11.0-rc4-max-boost-inv-patch (x86_64) 202101212 x AMD EPYC 7F72 24-Core @ 3.71GHz (48 Cores / 96 Threads)5.11.0-rc6-phx (x86_64) 20210203aspeedOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,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 Disk Details- CPUFreq Performance, Linux 5.11 Git, Linux 5.11 Giovanni Patch: NONE / errors=remount-ro,relatime,rw / Block Size: 4096Processor Details- CPUFreq Performance: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0x8301034- Linux 5.11 Git: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034- Linux 5.11 Giovanni Patch: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034- Linux 5.11 Rafael Patch: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034Java Details- OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10)Python Details- Python 3.8.6Security Details- 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

CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael PatchResult OverviewPhoronix Test Suite100%111%123%134%Cpuminer-Optdav1dx265OSPrayLeelaChessZeroLAMMPS Molecular Dynamics SimulatorTimed GDB GNU Debugger CompilationInfluxDBDaCapo BenchmarkCLOMPRodiniaQMCPACKrav1eQuantum ESPRESSOoneDNNTTSIOD 3D RendererONNX RuntimeAI Benchmark AlphaRedisNAS Parallel BenchmarksOpenFOAMTensorFlow Lite

AMD EPYC 7F72 2P Linux 5.11 Perf Governorbuild-gdb: Time To Compilecpuminer-opt: Skeincoincpuminer-opt: LBC, LBRY Creditsdav1d: Summer Nature 4Kdav1d: Chimera 1080p 10-bitlammps: Rhodopsin Proteinnpb: LU.Connx: yolov4 - OpenMP CPUopenfoam: Motorbike 30Mopenfoam: Motorbike 60Mqe: AUSURF112qmcpack: simple-H2Orav1e: 10rav1e: 6rav1e: 5redis: SETai-benchmark: Device Inference Scoreai-benchmark: Device Training Scoreai-benchmark: Device AI Scoredacapobench: Jythondacapobench: Tradebeansdacapobench: Tradesoapospray: Magnetic Reconnection - Path Tracerospray: San Miguel - SciVisclomp: Static OMP Speedupinfluxdb: 4 - 10000 - 2,5000,1 - 10000influxdb: 64 - 10000 - 2,5000,1 - 10000lczero: BLASlczero: Eigenonednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: IP Shapes 3D - f32 - CPUonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUttsiod-renderer: Phong Rendering With Soft-Shadow Mappingrodinia: OpenMP CFD Solverrodinia: OpenMP Streamclustertensorflow-lite: Mobilenet Floattensorflow-lite: Mobilenet Quanttensorflow-lite: NASNet Mobiletensorflow-lite: SqueezeNettensorflow-lite: Inception ResNet V2tensorflow-lite: Inception V4x265: Bosphorus 1080px265: Bosphorus 4KCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch85.277522948194087363.33181.9524.639153770.5718518.29128.811249.0628.9713.1771.4461.0951454741.42177511332908474046714621333.3355.5647.4956189.41360163.0414744500.8675452.304670.8136280.514604665.4488.51010.43239981.941180.113284461347.273799381888762.2920.7597.641363784132477308.29130.6121.129147443.8617518.71129.671217.4931.1772.9021.3701.0451380890.2216971059275648975954517025052.6343.9807463.11231991.2410642840.9141982.405490.8813480.547674627.2089.25511.20946659.245083.918977165193.076572689464047.6618.6392.916364017139037317.45133.3723.787154376.7618118.30128.281171.0329.2813.0541.4081.0681427348.1017201067278747785591514825054.9747.8812193.61256112.1406144330.8637822.332900.8492480.521968655.2258.88210.33839523.541034.013404462195.473628581075049.4519.7493.098366648137557315.99133.6924.795154111.4318118.32129.051222.6029.0403.0451.3981.0641401394.3017131061277448435600516725054.9746.9812464.31264917.7352237490.8703512.311710.8238250.511809642.2518.95210.56740060.040544.113546762054.272445481547850.4319.93OpenBenchmarking.org

Timed GDB GNU Debugger Compilation

This test times how long it takes to build the GNU Debugger (GDB) in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch20406080100SE +/- 0.14, N = 3SE +/- 0.40, N = 3SE +/- 0.43, N = 3SE +/- 0.23, N = 385.2897.6492.9293.10
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To CompileCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch20406080100Min: 85.13 / Avg: 85.28 / Max: 85.56Min: 97.05 / Avg: 97.64 / Max: 98.41Min: 92.05 / Avg: 92.92 / Max: 93.37Min: 92.71 / Avg: 93.1 / Max: 93.5

Cpuminer-Opt

Cpuminer-Opt is a fork of cpuminer-multi that carries a wide range of CPU performance optimizations for measuring the potential cryptocurrency mining performance of the CPU/processor with a wide variety of cryptocurrencies. The benchmark reports the hash speed for the CPU mining performance for the selected cryptocurrency. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: SkeincoinCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch110K220K330K440K550KSE +/- 9614.65, N = 12SE +/- 3597.13, N = 15SE +/- 5604.68, N = 12SE +/- 2614.77, N = 135229483637843640173666481. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: SkeincoinCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch90K180K270K360K450KMin: 419180 / Avg: 522948.33 / Max: 540350Min: 316870 / Avg: 363784 / Max: 377150Min: 303220 / Avg: 364016.67 / Max: 377540Min: 338280 / Avg: 366648.46 / Max: 3747601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: LBC, LBRY CreditsCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch40K80K120K160K200KSE +/- 861.90, N = 3SE +/- 1036.73, N = 3SE +/- 1380.06, N = 3SE +/- 1545.00, N = 31940871324771390371375571. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.15.5Algorithm: LBC, LBRY CreditsCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch30K60K90K120K150KMin: 192690 / Avg: 194086.67 / Max: 195660Min: 130710 / Avg: 132476.67 / Max: 134300Min: 136670 / Avg: 139036.67 / Max: 141450Min: 134520 / Avg: 137556.67 / Max: 1395701. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

dav1d

Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Summer Nature 4KCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch80160240320400SE +/- 3.54, N = 15SE +/- 1.86, N = 3SE +/- 0.53, N = 3SE +/- 2.68, N = 3363.33308.29317.45315.99MIN: 186.32 / MAX: 403.05MIN: 163.13 / MAX: 334.13MIN: 173.69 / MAX: 340.43MIN: 157.61 / MAX: 340.721. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Summer Nature 4KCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch60120180240300Min: 333.89 / Avg: 363.33 / Max: 377.56Min: 304.76 / Avg: 308.29 / Max: 311.07Min: 316.41 / Avg: 317.45 / Max: 318.17Min: 310.62 / Avg: 315.99 / Max: 318.791. (CC) gcc options: -pthread

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Chimera 1080p 10-bitCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch4080120160200SE +/- 0.23, N = 3SE +/- 0.23, N = 3SE +/- 0.14, N = 3SE +/- 0.19, N = 3181.95130.61133.37133.69MIN: 125.32 / MAX: 275.36MIN: 90.23 / MAX: 199.74MIN: 92.59 / MAX: 205.11MIN: 92.24 / MAX: 206.311. (CC) gcc options: -pthread
OpenBenchmarking.orgFPS, More Is Betterdav1d 0.8.1Video Input: Chimera 1080p 10-bitCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch306090120150Min: 181.5 / Avg: 181.95 / Max: 182.28Min: 130.35 / Avg: 130.61 / Max: 131.07Min: 133.23 / Avg: 133.37 / Max: 133.65Min: 133.32 / Avg: 133.69 / Max: 133.91. (CC) gcc options: -pthread

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 29Oct2020Model: Rhodopsin ProteinCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch612182430SE +/- 0.19, N = 15SE +/- 0.23, N = 15SE +/- 0.17, N = 12SE +/- 0.16, N = 324.6421.1323.7924.801. (CXX) g++ options: -O3 -pthread -lm
OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 29Oct2020Model: Rhodopsin ProteinCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch612182430Min: 22.96 / Avg: 24.64 / Max: 25.7Min: 20.01 / Avg: 21.13 / Max: 23.09Min: 23 / Avg: 23.79 / Max: 25.06Min: 24.63 / Avg: 24.8 / Max: 25.111. (CXX) g++ options: -O3 -pthread -lm

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.CCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch30K60K90K120K150KSE +/- 121.33, N = 4SE +/- 1780.52, N = 15SE +/- 509.59, N = 4SE +/- 237.90, N = 3153770.57147443.86154376.76154111.431. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3
OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch30K60K90K120K150KMin: 153434.98 / Avg: 153770.57 / Max: 153998.55Min: 130785.22 / Avg: 147443.86 / Max: 153153.3Min: 153161.9 / Avg: 154376.76 / Max: 155556.23Min: 153807.4 / Avg: 154111.43 / Max: 154580.411. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz 2. Open MPI 4.0.3

ONNX Runtime

ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Zoo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch4080120160200SE +/- 2.62, N = 3SE +/- 1.60, N = 12SE +/- 1.86, N = 3SE +/- 1.86, N = 41851751811811. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.6Model: yolov4 - Device: OpenMP CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch306090120150Min: 181 / Avg: 185.17 / Max: 190Min: 166 / Avg: 174.58 / Max: 184.5Min: 177.5 / Avg: 181.17 / Max: 183.5Min: 175.5 / Avg: 180.5 / Max: 184.51. (CXX) g++ options: -fopenmp -ffunction-sections -fdata-sections -O3 -ldl -lrt

OpenFOAM

OpenFOAM is the leading free, open source software for computational fluid dynamics (CFD). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 30MCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch510152025SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.16, N = 318.2918.7118.3018.321. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 30MCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch510152025Min: 18.16 / Avg: 18.29 / Max: 18.48Min: 18.48 / Avg: 18.71 / Max: 18.96Min: 18.15 / Avg: 18.3 / Max: 18.42Min: 18.07 / Avg: 18.32 / Max: 18.611. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 60MCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch306090120150SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3128.81129.67128.28129.051. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 8Input: Motorbike 60MCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch20406080100Min: 128.69 / Avg: 128.81 / Max: 128.99Min: 129.52 / Avg: 129.67 / Max: 129.84Min: 128.2 / Avg: 128.28 / Max: 128.42Min: 128.97 / Avg: 129.05 / Max: 129.141. (CXX) g++ options: -std=c++11 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfoamToVTK -ldynamicMesh -llagrangian -lgenericPatchFields -lfileFormats -lOpenFOAM -ldl -lm

Quantum ESPRESSO

Quantum ESPRESSO is an integrated suite of Open-Source computer codes for electronic-structure calculations and materials modeling at the nanoscale. It is based on density-functional theory, plane waves, and pseudopotentials. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterQuantum ESPRESSO 6.7Input: AUSURF112CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch30060090012001500SE +/- 19.05, N = 9SE +/- 11.28, N = 3SE +/- 12.21, N = 4SE +/- 23.97, N = 61249.061217.491171.031222.601. (F9X) gfortran options: -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz
OpenBenchmarking.orgSeconds, Fewer Is BetterQuantum ESPRESSO 6.7Input: AUSURF112CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch2004006008001000Min: 1163.48 / Avg: 1249.06 / Max: 1316.52Min: 1194.93 / Avg: 1217.49 / Max: 1228.78Min: 1148.76 / Avg: 1171.03 / Max: 1205.51Min: 1172.6 / Avg: 1222.6 / Max: 1323.441. (F9X) gfortran options: -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz

QMCPACK

QMCPACK is a modern high-performance open-source Quantum Monte Carlo (QMC) simulation code making use of MPI for this benchmark of the H20 example code. QMCPACK is an open-source production level many-body ab initio Quantum Monte Carlo code for computing the electronic structure of atoms, molecules, and solids. QMCPACK is supported by the U.S. Department of Energy. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.10Input: simple-H2OCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch714212835SE +/- 0.06, N = 3SE +/- 0.53, N = 15SE +/- 0.08, N = 3SE +/- 0.04, N = 328.9731.1829.2829.041. (CXX) g++ options: -fopenmp -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -fomit-frame-pointer -ffast-math -pthread -lm
OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.10Input: simple-H2OCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch714212835Min: 28.9 / Avg: 28.97 / Max: 29.09Min: 29.13 / Avg: 31.18 / Max: 35.25Min: 29.11 / Avg: 29.28 / Max: 29.37Min: 28.99 / Avg: 29.04 / Max: 29.121. (CXX) g++ options: -fopenmp -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -fomit-frame-pointer -ffast-math -pthread -lm

rav1e

Xiph rav1e is a Rust-written AV1 video encoder. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 10CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch0.71481.42962.14442.85923.574SE +/- 0.018, N = 3SE +/- 0.016, N = 3SE +/- 0.008, N = 3SE +/- 0.011, N = 33.1772.9023.0543.045
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 10CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch246810Min: 3.15 / Avg: 3.18 / Max: 3.21Min: 2.87 / Avg: 2.9 / Max: 2.93Min: 3.04 / Avg: 3.05 / Max: 3.07Min: 3.02 / Avg: 3.05 / Max: 3.06

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 6CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch0.32540.65080.97621.30161.627SE +/- 0.001, N = 3SE +/- 0.002, N = 3SE +/- 0.003, N = 3SE +/- 0.002, N = 31.4461.3701.4081.398
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 6CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch246810Min: 1.45 / Avg: 1.45 / Max: 1.45Min: 1.37 / Avg: 1.37 / Max: 1.38Min: 1.4 / Avg: 1.41 / Max: 1.41Min: 1.4 / Avg: 1.4 / Max: 1.4

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 5CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch0.24640.49280.73920.98561.232SE +/- 0.003, N = 3SE +/- 0.001, N = 3SE +/- 0.001, N = 3SE +/- 0.002, N = 31.0951.0451.0681.064
OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.4Speed: 5CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch246810Min: 1.09 / Avg: 1.1 / Max: 1.1Min: 1.04 / Avg: 1.04 / Max: 1.05Min: 1.07 / Avg: 1.07 / Max: 1.07Min: 1.06 / Avg: 1.06 / Max: 1.07

Redis

Redis is an open-source in-memory data structure store, used as a database, cache, and message broker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch300K600K900K1200K1500KSE +/- 10017.79, N = 13SE +/- 10410.66, N = 15SE +/- 13176.39, N = 15SE +/- 15335.21, N = 51454741.421380890.221427348.101401394.301. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 6.0.9Test: SETCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch300K600K900K1200K1500KMin: 1381801.25 / Avg: 1454741.42 / Max: 1521606.75Min: 1271941 / Avg: 1380890.22 / Max: 1431871.62Min: 1355752.75 / Avg: 1427348.1 / Max: 1519526Min: 1373253.5 / Avg: 1401394.3 / Max: 1447843.621. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

AI Benchmark Alpha

AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference ScoreCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch4008001200160020001775169717201713

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training ScoreCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch20040060080010001133105910671061

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI ScoreCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch60012001800240030002908275627872774

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch10002000300040005000SE +/- 20.83, N = 6SE +/- 28.66, N = 18SE +/- 43.93, N = 6SE +/- 24.16, N = 44740489747784843
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch9001800270036004500Min: 4645 / Avg: 4740.33 / Max: 4787Min: 4762 / Avg: 4896.67 / Max: 5223Min: 4629 / Avg: 4777.83 / Max: 4946Min: 4775 / Avg: 4843.25 / Max: 4878

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch13002600390052006500SE +/- 52.34, N = 20SE +/- 50.83, N = 20SE +/- 66.39, N = 20SE +/- 53.96, N = 204671595455915600
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch10002000300040005000Min: 4214 / Avg: 4670.95 / Max: 5110Min: 5457 / Avg: 5954.45 / Max: 6300Min: 5113 / Avg: 5590.8 / Max: 6277Min: 5197 / Avg: 5600.15 / Max: 6101

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch11002200330044005500SE +/- 42.72, N = 5SE +/- 44.82, N = 4SE +/- 61.21, N = 4SE +/- 47.07, N = 44621517051485167
OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch9001800270036004500Min: 4484 / Avg: 4621.4 / Max: 4730Min: 5044 / Avg: 5170 / Max: 5238Min: 4978 / Avg: 5147.75 / Max: 5264Min: 5075 / Avg: 5166.75 / Max: 5259

OSPray

Intel OSPray is a portable ray-tracing engine for high-performance, high-fidenlity scientific visualizations. OSPray builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch70140210280350SE +/- 0.00, N = 11333.33250.00250.00250.00MIN: 100 / MAX: 500MIN: 90.91 / MAX: 500MIN: 90.91 / MAX: 333.33MIN: 111.11 / MAX: 333.33
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch60120180240300Min: 333.33 / Avg: 333.33 / Max: 333.33

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch1224364860SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.58, N = 5SE +/- 0.58, N = 555.5652.6354.9754.97MIN: 33.33 / MAX: 58.82MIN: 27.03 / MAX: 58.82MIN: 31.25 / MAX: 58.82MIN: 25.64 / MAX: 58.82
OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch1122334455Min: 55.56 / Avg: 55.56 / Max: 55.56Min: 52.63 / Avg: 52.63 / Max: 52.63Min: 52.63 / Avg: 54.97 / Max: 55.56Min: 52.63 / Avg: 54.97 / Max: 55.56

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch1122334455SE +/- 0.55, N = 3SE +/- 0.60, N = 3SE +/- 0.47, N = 3SE +/- 0.98, N = 1547.443.947.846.91. (CC) gcc options: -fopenmp -O3 -lm
OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 1.2Static OMP SpeedupCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch1020304050Min: 46.4 / Avg: 47.37 / Max: 48.3Min: 43.2 / Avg: 43.9 / Max: 45.1Min: 47.2 / Avg: 47.77 / Max: 48.7Min: 43.1 / Avg: 46.95 / Max: 59.91. (CC) gcc options: -fopenmp -O3 -lm

InfluxDB

This is a benchmark of the InfluxDB open-source time-series database optimized for fast, high-availability storage for IoT and other use-cases. The InfluxDB test profile makes use of InfluxDB Inch for facilitating the benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch200K400K600K800K1000KSE +/- 2401.68, N = 3SE +/- 2183.04, N = 3SE +/- 1525.09, N = 3SE +/- 757.15, N = 3956189.4807463.1812193.6812464.3
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch170K340K510K680K850KMin: 952399.9 / Avg: 956189.37 / Max: 960640.3Min: 804402.8 / Avg: 807463.13 / Max: 811690.1Min: 810252.3 / Avg: 812193.6 / Max: 815201.7Min: 811144.8 / Avg: 812464.33 / Max: 813767.5

OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch300K600K900K1200K1500KSE +/- 9433.94, N = 3SE +/- 6204.63, N = 3SE +/- 2545.78, N = 3SE +/- 5312.25, N = 31360163.01231991.21256112.11264917.7
OpenBenchmarking.orgval/sec, More Is BetterInfluxDB 1.8.2Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch200K400K600K800K1000KMin: 1341751.8 / Avg: 1360163.03 / Max: 1372941.8Min: 1221574.2 / Avg: 1231991.2 / Max: 1243039.8Min: 1251965 / Avg: 1256112.13 / Max: 1260743.8Min: 1254567.2 / Avg: 1264917.73 / Max: 1272169

LeelaChessZero

LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch9001800270036004500SE +/- 17.79, N = 3SE +/- 50.84, N = 3SE +/- 49.90, N = 9SE +/- 36.49, N = 541474106406135221. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: BLASCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch7001400210028003500Min: 4119 / Avg: 4147 / Max: 4180Min: 4010 / Avg: 4106 / Max: 4183Min: 3811 / Avg: 4060.89 / Max: 4359Min: 3402 / Avg: 3522 / Max: 36001. (CXX) g++ options: -flto -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: EigenCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch10002000300040005000SE +/- 26.71, N = 3SE +/- 49.20, N = 4SE +/- 36.23, N = 3SE +/- 54.19, N = 944504284443337491. (CXX) g++ options: -flto -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.26Backend: EigenCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch8001600240032004000Min: 4409 / Avg: 4449.67 / Max: 4500Min: 4171 / Avg: 4283.5 / Max: 4398Min: 4385 / Avg: 4433 / Max: 4504Min: 3536 / Avg: 3749.44 / Max: 40021. (CXX) g++ options: -flto -pthread

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch0.20570.41140.61710.82281.0285SE +/- 0.001697, N = 7SE +/- 0.006064, N = 7SE +/- 0.001510, N = 7SE +/- 0.007039, N = 30.8675450.9141980.8637820.870351MIN: 0.78MIN: 0.78MIN: 0.79MIN: 0.81. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch246810Min: 0.86 / Avg: 0.87 / Max: 0.88Min: 0.9 / Avg: 0.91 / Max: 0.95Min: 0.86 / Avg: 0.86 / Max: 0.87Min: 0.86 / Avg: 0.87 / Max: 0.881. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch0.54121.08241.62362.16482.706SE +/- 0.02560, N = 15SE +/- 0.03372, N = 3SE +/- 0.01587, N = 3SE +/- 0.02377, N = 152.304672.405492.332902.31171MIN: 1.88MIN: 1.92MIN: 2MIN: 1.891. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch246810Min: 2.11 / Avg: 2.3 / Max: 2.43Min: 2.35 / Avg: 2.41 / Max: 2.46Min: 2.31 / Avg: 2.33 / Max: 2.36Min: 2.13 / Avg: 2.31 / Max: 2.461. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch0.19830.39660.59490.79320.9915SE +/- 0.005456, N = 5SE +/- 0.005127, N = 5SE +/- 0.004000, N = 5SE +/- 0.006790, N = 150.8136280.8813480.8492480.823825MIN: 0.69MIN: 0.71MIN: 0.73MIN: 0.681. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch246810Min: 0.8 / Avg: 0.81 / Max: 0.83Min: 0.87 / Avg: 0.88 / Max: 0.9Min: 0.84 / Avg: 0.85 / Max: 0.86Min: 0.79 / Avg: 0.82 / Max: 0.881. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch0.12320.24640.36960.49280.616SE +/- 0.005906, N = 4SE +/- 0.005010, N = 4SE +/- 0.004601, N = 4SE +/- 0.003992, N = 100.5146040.5476740.5219680.511809MIN: 0.43MIN: 0.43MIN: 0.43MIN: 0.431. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch246810Min: 0.51 / Avg: 0.51 / Max: 0.53Min: 0.54 / Avg: 0.55 / Max: 0.56Min: 0.51 / Avg: 0.52 / Max: 0.54Min: 0.48 / Avg: 0.51 / Max: 0.521. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread

TTSIOD 3D Renderer

A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch140280420560700SE +/- 5.92, N = 15SE +/- 9.04, N = 15SE +/- 3.22, N = 3SE +/- 24.62, N = 12665.45627.21655.23642.251. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch120240360480600Min: 632.51 / Avg: 665.45 / Max: 717.26Min: 572.05 / Avg: 627.21 / Max: 682.22Min: 651.25 / Avg: 655.23 / Max: 661.59Min: 398.03 / Avg: 642.25 / Max: 720.411. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes select OpenCL, NVIDIA CUDA and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch3691215SE +/- 0.053, N = 5SE +/- 0.148, N = 15SE +/- 0.141, N = 15SE +/- 0.168, N = 158.5109.2558.8828.9521. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD SolverCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch3691215Min: 8.4 / Avg: 8.51 / Max: 8.65Min: 8.64 / Avg: 9.25 / Max: 10.56Min: 8.4 / Avg: 8.88 / Max: 10.28Min: 8.37 / Avg: 8.95 / Max: 10.281. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch3691215SE +/- 0.04, N = 5SE +/- 0.22, N = 15SE +/- 0.03, N = 5SE +/- 0.13, N = 410.4311.2110.3410.571. (CXX) g++ options: -O2 -lOpenCL
OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP StreamclusterCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch3691215Min: 10.33 / Avg: 10.43 / Max: 10.53Min: 10.56 / Avg: 11.21 / Max: 13.73Min: 10.27 / Avg: 10.34 / Max: 10.45Min: 10.31 / Avg: 10.57 / Max: 10.941. (CXX) g++ options: -O2 -lOpenCL

TensorFlow Lite

This is a benchmark of the TensorFlow Lite implementation. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch10K20K30K40K50KSE +/- 473.02, N = 3SE +/- 1144.94, N = 15SE +/- 395.37, N = 3SE +/- 126.68, N = 339981.946659.239523.540060.0
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet FloatCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch8K16K24K32K40KMin: 39408.4 / Avg: 39981.87 / Max: 40920.2Min: 40779.7 / Avg: 46659.17 / Max: 54552Min: 38800.9 / Avg: 39523.47 / Max: 40162.9Min: 39929.8 / Avg: 40059.97 / Max: 40313.3

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch10K20K30K40K50KSE +/- 211.03, N = 3SE +/- 759.19, N = 15SE +/- 400.94, N = 6SE +/- 60.30, N = 341180.145083.941034.040544.1
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Mobilenet QuantCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch8K16K24K32K40KMin: 40933.4 / Avg: 41180.07 / Max: 41600Min: 42204.7 / Avg: 45083.93 / Max: 52593.3Min: 40070.1 / Avg: 41033.95 / Max: 42901.4Min: 40464 / Avg: 40544.07 / Max: 40662.2

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch40K80K120K160K200KSE +/- 2146.20, N = 15SE +/- 7366.43, N = 15SE +/- 2393.85, N = 15SE +/- 1630.66, N = 3132844189771134044135467
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: NASNet MobileCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch30K60K90K120K150KMin: 119861 / Avg: 132844.47 / Max: 152016Min: 138046 / Avg: 189770.67 / Max: 231817Min: 106838 / Avg: 134043.8 / Max: 146394Min: 133346 / Avg: 135467 / Max: 138673

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch14K28K42K56K70KSE +/- 715.70, N = 4SE +/- 690.93, N = 3SE +/- 412.91, N = 15SE +/- 479.59, N = 1561347.265193.062195.462054.2
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: SqueezeNetCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch11K22K33K44K55KMin: 60282.3 / Avg: 61347.15 / Max: 63426.1Min: 63856.6 / Avg: 65192.97 / Max: 66165.7Min: 59468.9 / Avg: 62195.4 / Max: 65210.3Min: 59445.3 / Avg: 62054.17 / Max: 65116.1

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch160K320K480K640K800KSE +/- 2132.19, N = 3SE +/- 4257.59, N = 3SE +/- 5824.36, N = 9SE +/- 1613.84, N = 3737993765726736285724454
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception ResNet V2CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch130K260K390K520K650KMin: 733830 / Avg: 737993 / Max: 740875Min: 757283 / Avg: 765726.33 / Max: 770904Min: 718390 / Avg: 736285 / Max: 779525Min: 721638 / Avg: 724454.33 / Max: 727228

OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch200K400K600K800K1000KSE +/- 4685.69, N = 3SE +/- 2435.29, N = 3SE +/- 1163.43, N = 3SE +/- 2213.60, N = 3818887894640810750815478
OpenBenchmarking.orgMicroseconds, Fewer Is BetterTensorFlow Lite 2020-08-23Model: Inception V4CPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch160K320K480K640K800KMin: 809516 / Avg: 818887.33 / Max: 823600Min: 889793 / Avg: 894640 / Max: 897478Min: 808813 / Avg: 810749.67 / Max: 812835Min: 812612 / Avg: 815477.67 / Max: 819833

x265

This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch1428425670SE +/- 0.73, N = 15SE +/- 0.42, N = 7SE +/- 0.52, N = 4SE +/- 0.14, N = 362.2947.6649.4550.431. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 1080pCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch1224364860Min: 58.9 / Avg: 62.29 / Max: 69.02Min: 45.27 / Avg: 47.66 / Max: 48.53Min: 48.01 / Avg: 49.45 / Max: 50.31Min: 50.22 / Avg: 50.43 / Max: 50.71. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch510152025SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.07, N = 320.7518.6319.7419.931. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.4Video Input: Bosphorus 4KCPUFreq PerformanceLinux 5.11 GitLinux 5.11 Giovanni PatchLinux 5.11 Rafael Patch510152025Min: 20.59 / Avg: 20.75 / Max: 20.9Min: 18.46 / Avg: 18.63 / Max: 18.82Min: 19.52 / Avg: 19.74 / Max: 19.99Min: 19.81 / Avg: 19.93 / Max: 20.061. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma