AMD Threadripper 7995WX NPS / SNC2 SNC4 Benchmarks

AMD Ryzen Threadripper PRO 7995WX 96-Cores testing of NPS/SNC settings with default (disabled), SNC2, and SNC4 modes. Benchmarks by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2311288-NE-TR7995WXN68
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
Show Result Confidence Charts
Allow Limiting Results To Certain Suite(s)

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
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

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
Default - Disabled
November 26 2023
  18 Hours, 13 Minutes
SNC2
November 26 2023
  21 Hours, 15 Minutes
SNC4
November 27 2023
  1 Day, 3 Hours, 55 Minutes
Invert Behavior (Only Show Selected Data)
  22 Hours, 28 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):

Default - Disabled

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

SNC2

SNC4

Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads), Motherboard: HP 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1, Graphics: NVIDIA RTX A4000 16GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

AMD Threadripper 7995WX NPS / SNC2 SNC4 BenchmarksOpenBenchmarking.orgPhoronix Test SuiteAMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads)HP 8B24 (U65 Ver. 01.01.04 BIOS)AMD Device 14a4128GB2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1NVIDIA RTX A4000 16GBNVIDIA GA104 HD AudioASUS VP28URealtek RTL8111/8168/8411Ubuntu 23.106.5.0-13-generic (x86_64)GNOME Shell 45.0X Server 1.21.1.7NVIDIA 535.129.034.6.0OpenCL 3.0 CUDA 12.2.147GCC 13.2.0ext43840x2160ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLOpenCLCompilerFile-SystemScreen ResolutionAMD Threadripper 7995WX NPS / SNC2 SNC4 Benchmarks PerformanceSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105- GPU Compute Cores: 6144- Python 3.11.6- gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Default - DisabledSNC2SNC4Result OverviewPhoronix Test Suite100%119%137%156%ASKAPLULESHTimed Linux Kernel CompilationOpenVINOGraph500easyWaveClickHousePyTorchOpenVKLasmFishTimed Node.js CompilationTimed Gem5 CompilationPostgreSQLTimed LLVM CompilationCloverLeafAlgebraic Multi-Grid BenchmarkOpenFOAMQuantum ESPRESSOTensorFlowJohn The RipperXcompact3d Incompact3dVVenCEmbreeStockfishRadiance BenchmarkSPECFEM3Duvg266RodiniaGROMACSNAS Parallel BenchmarksGPAWQMCPACKPETSc7-Zip CompressionQuantLibMemcachedNumpy BenchmarkTimed CPython CompilationNAMDOpenRadiossBlenderLuxCoreRenderACES DGEMMOpenSSLlibxsmmLiquid-DSPOSPRay Studio

AMD Threadripper 7995WX NPS / SNC2 SNC4 Benchmarksaskap: Hogbom Clean OpenMPaskap: tConvolve OpenMP - Griddingopenvino: Vehicle Detection FP16 - CPUaskap: tConvolve OpenMP - Degriddingopenvino: Road Segmentation ADAS FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Face Detection FP16 - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Face Detection Retail FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUlulesh: build-linux-kernel: allmodconfigopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUgraph500: 26graph500: 26openvino: Vehicle Detection FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUbuild-linux-kernel: defconfigopenvino: Road Segmentation ADAS FP16 - CPUcloverleaf: clover_bm16openvino: Person Vehicle Bike Detection FP16 - CPUbuild-llvm: Ninjaaskap: tConvolve MT - Griddinggraph500: 26openvkl: vklBenchmarkCPU ISPCaskap: tConvolve MT - Degriddingopenvino: Handwritten English Recognition FP16 - CPUopenvino: Handwritten English Recognition FP16 - CPUasmfish: 1024 Hash Memory, 26 Depthbuild-nodejs: Time To Compileopenvino: Face Detection Retail FP16 - CPUbuild-gem5: Time To Compileopenfoam: drivaerFastback, Medium Mesh Size - Execution Timegraph500: 26npb: CG.Cuvg266: Bosphorus 4K - Ultra Fastjohn-the-ripper: MD5vvenc: Bosphorus 4K - Fasteropenvino: Person Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUuvg266: Bosphorus 4K - Super Fastincompact3d: input.i3d 129 Cells Per Directionuvg266: Bosphorus 4K - Very Fastopenvino: Person Detection FP32 - CPUcloverleaf: clover_bmembree: Pathtracer ISPC - Asian Dragon Objtensorflow: CPU - 64 - ResNet-50john-the-ripper: Blowfishcloverleaf: clover_bm64_shortjohn-the-ripper: bcryptamg: vvenc: Bosphorus 4K - Fasttensorflow: CPU - 32 - ResNet-50specfem3d: Tomographic Modelqe: AUSURF112npb: FT.Ctensorflow: CPU - 512 - ResNet-50tensorflow: CPU - 256 - ResNet-50rodinia: OpenMP Leukocytepytorch: CPU - 1 - Efficientnet_v2_lluxcorerender: Orange Juice - CPUembree: Pathtracer ISPC - Asian Dragonpytorch: CPU - 32 - ResNet-152pytorch: CPU - 64 - ResNet-152tensorflow: CPU - 16 - ResNet-50pytorch: CPU - 16 - ResNet-152rodinia: OpenMP Streamclusternpb: SP.Bradiance: SMP Parallelluxcorerender: LuxCore Benchmark - CPUrodinia: OpenMP HotSpot3Dspecfem3d: Layered Halfspaceopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timepytorch: CPU - 16 - ResNet-50vvenc: Bosphorus 1080p - Fastopenvino: Face Detection FP16 - CPUnpb: MG.Cmemcached: 1:100pytorch: CPU - 64 - ResNet-50pytorch: CPU - 32 - ResNet-50npb: IS.Djohn-the-ripper: WPA PSKluxcorerender: Danish Mood - CPUpytorch: CPU - 1 - ResNet-152john-the-ripper: HMAC-SHA512vvenc: Bosphorus 1080p - Fasterincompact3d: input.i3d 193 Cells Per Directionbuild-llvm: Unix Makefilesspecfem3d: Homogeneous Halfspacespecfem3d: Mount St. Helensopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUgpaw: Carbon Nanotubeopenvino: Face Detection Retail FP16-INT8 - CPUuvg266: Bosphorus 1080p - Super Fastuvg266: Bosphorus 1080p - Very Fastspecfem3d: Water-layered Halfspacepytorch: CPU - 1 - ResNet-50compress-7zip: Decompression Ratingpetsc: Streamsuvg266: Bosphorus 1080p - Ultra Fastqmcpack: Li2_STO_aeuvg266: Bosphorus 4K - Slowcompress-7zip: Compression Ratingquantlib: Multi-Threadednpb: SP.Clibxsmm: 128npb: LU.Cpgbench: 1000 - 1000 - Read Onlypgbench: 1000 - 1000 - Read Only - Average Latencyembree: Pathtracer ISPC - Crownnumpy: memcached: 1:10build-python: Released Build, PGO + LTO Optimizedluxcorerender: DLSC - CPUblender: Fishy Cat - CPU-Onlyuvg266: Bosphorus 4K - Mediumliquid-dsp: 192 - 256 - 512openvino: Weld Porosity Detection FP16 - CPUlibxsmm: 256liquid-dsp: 32 - 256 - 57ospray-studio: 2 - 4K - 32 - Path Tracer - CPUopenvino: Weld Porosity Detection FP16 - CPUpgbench: 100 - 1000 - Read Onlyospray-studio: 3 - 4K - 32 - Path Tracer - CPUliquid-dsp: 64 - 256 - 512openradioss: Chrysler Neon 1Mnamd: ATPase Simulation - 327,506 Atomslibxsmm: 32uvg266: Bosphorus 1080p - Slowopenvino: Weld Porosity Detection FP16-INT8 - CPUpgbench: 100 - 1000 - Read Only - Average Latencyopenssl: SHA512ospray-studio: 3 - 4K - 1 - Path Tracer - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUliquid-dsp: 128 - 256 - 512ospray-studio: 1 - 4K - 32 - Path Tracer - CPUmemcached: 1:5ospray-studio: 1 - 4K - 1 - Path Tracer - CPUopenvino: Face Detection FP16-INT8 - CPUospray-studio: 3 - 4K - 16 - Path Tracer - CPUopenvino: Road Segmentation ADAS FP16-INT8 - CPUospray-studio: 2 - 4K - 16 - Path Tracer - CPUblender: Classroom - CPU-Onlyuvg266: Bosphorus 1080p - Mediumlibxsmm: 64npb: BT.Copenssl: AES-128-GCMopenssl: RSA4096mt-dgemm: Sustained Floating-Point Rateliquid-dsp: 128 - 256 - 57liquid-dsp: 64 - 256 - 32blender: BMW27 - CPU-Onlyospray-studio: 1 - 4K - 16 - Path Tracer - CPUblender: Pabellon Barcelona - CPU-Onlyliquid-dsp: 192 - 256 - 57liquid-dsp: 32 - 256 - 32openvino: Handwritten English Recognition FP16-INT8 - CPUospray-studio: 2 - 4K - 1 - Path Tracer - CPUliquid-dsp: 128 - 256 - 32openvino: Handwritten English Recognition FP16-INT8 - CPUliquid-dsp: 192 - 256 - 32openssl: ChaCha20-Poly1305rodinia: OpenMP LavaMDopenssl: AES-256-GCMliquid-dsp: 64 - 256 - 57liquid-dsp: 32 - 256 - 512openssl: ChaCha20rodinia: OpenMP CFD Solveropenssl: RSA4096blender: Barbershop - CPU-Onlyopenssl: SHA256pytorch: CPU - 64 - Efficientnet_v2_lpytorch: CPU - 32 - Efficientnet_v2_lpytorch: CPU - 16 - Efficientnet_v2_lpgbench: 1000 - 1000 - Read Write - Average Latencypgbench: 1000 - 1000 - Read Writepgbench: 100 - 1000 - Read Write - Average Latencypgbench: 100 - 1000 - Read Writegromacs: MPI CPU - water_GMX50_bareaskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddingclickhouse: 100M Rows Hits Dataset, Third Runclickhouse: 100M Rows Hits Dataset, Second Runclickhouse: 100M Rows Hits Dataset, First Run / Cold Cachestockfish: Total Timeeasywave: e2Asean Grid + BengkuluSept2007 Source - 2400easywave: e2Asean Grid + BengkuluSept2007 Source - 1200luxcorerender: Rainbow Colors and Prism - CPUnpb: EP.CDefault - DisabledSNC2SNC41127.8519018.317.5520481.236.57141.78141.54965.6725.26493.578.0793.233.810.628.4923294.844264.07786958.12113350.177561650007276620002730.600.8631.4541310.86329.615643.89121.8688655.84462057000215311871.22592.5937.01248215163111.37012547.91150.970331.8558635712700052079.1369.021460066715.245338.09514.2267.472.6173870566.32338.7410.96112.828790.4617314539.3217433516628940008.71570.357.987430452326.06100728.49135.02118.8629.38611.1622.24129.171916.1615.9151.7716.064.703145525.94119.19212.3958.86618.741871937138.6458138.6824.29849.4195501.507743874.0439.0639.214279.9861426310.6518.9929651866741.39710.6618586175.4689.9429897627.7248900325936.375.3838.12817809.43211.36208.3619.26850590547.70655203183161.1076207.97103.9029.92546936310771.189217.912043.5255135.2419868070.504108.0805746.055811757.93188.35115.2319.4733.23151420000019.332564.61730566667382644962.13379269843999938493333157.350.25803555.689.199.720.2644272391165312529866.451314200000378903359726.87106496.95200171898.141719338.0298.331055.4214445.979414427014471533067.143.8794514495533333264610000015.251693946.775407200000143533333345.25107642281333332120.23552673333336185237586026.95381517570539730209000005225600005116942446535.57749897.3136.291316294998936.366.356.3460.6591662355.3961806810.38043532.940198.3504.59490.52457.0628733109758.64623.98632.758869.84564.98412083.76.1814122.514.5167.2267.17468.3512.52245.024.1449.802.090.365.0633106.244174.354134566.00166444.72106956000010153000003875.390.6124.5791652.91355.044737.07104.6018223.25522187000208911209.22435.2839.36272254945102.32211414.89140.813310.6596338923500054560.0365.341388880014.306356.72481.4164.652.4965933262.99357.0311.82111.360185.5416928741.2117173417321493338.27866.137.544143736316.5097435.24130.65115.9030.89410.6522.77128.009915.3616.0349.5115.304.884151244.49114.28411.9459.85918.359442232135.1001440.0923.71451.0697068.017704668.2740.2740.414282.3661166910.8518.4428922140040.22210.4893306170.8289.7428068037.7562337375783.015.5237.80317366.29206.23203.4819.21560723648.83640928185070.8277204.49106.0129.47535713313010.588668.132026.2256378.2219505070.513106.2642758.025818020.66188.07315.1919.7633.12149913333319.082583.61744433333380155023.42374600644300935170000155.500.25612553.388.689.630.2674315161891012599948.301302833333380093359880.55107497.76201441914.891711338.3398.221052.3215684.069433657325801529451.743.7669204493966667263223333315.321699946.975393633333143643333345.22108042335666672121.18551993333336198754768326.90581539335835730161000005236033335113183479575.58149862.1136.201316274639835.385.315.3663.4381576972.1481409610.45043138.940552.4444.12438.54417.3029578079859.24925.48031.829712.81325.3946602.286.207607.3114.5665.3265.40467.3912.54244.804.1350.562.090.365.0738146.304168.153134176.02164363.19110490000010569800003863.880.6124.0871647.09396.534721.81104.6937467.14527864000190510522.52333.4641.08275458088100.61611421.25137.479302.6916439068200056924.5663.231341900014.014367.12474.1162.252.4161430261.26366.5910.95104.803184.5016179042.0016325917737583338.18666.887.519415000307.0694921.27127.24112.0831.12310.5821.60122.587115.6115.2449.2715.394.933151839.30117.4411.8961.23418.044192295133.744739.8023.45251.1998739.507507583.6839.0739.294155.6859618010.9718.6228795550040.20310.3613243170.5409.6687597337.5451761785797.285.5137.16317402.76206.92207.6218.82173464248.36649120187197.6338208.97103.7729.30536820317145.387467.232004.7259883.6219565090.511106.4294753.645728479.09185.50515.0019.7132.75149300000019.062599.91721266667385235026.69375909444535927276667156.210.25502559.888.189.610.2664320664198312669973.181300233333382843327393.35107397.85201991911.681726238.2497.601059.1215764.829469333786201538165.343.6309784518133333264343333315.311701446.885416600000144093333345.08107942436000002127.42553550000036276550002326.97181713138710730231666675229966675123185804175.58549924.9136.281317066984273.684.074.1565.3281531472.6501406710.66235893.734358.5400.96397.01388.4230026714875.17228.73934.7210411.60OpenBenchmarking.org

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Second, More Is BetterASKAP 1.0Test: Hogbom Clean OpenMPSNC4SNC2Default - Disabled2004006008001000SE +/- 1.54, N = 3SE +/- 1.84, N = 3SE +/- 4.25, N = 3325.39564.981127.851. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - GriddingSNC4SNC2Default - Disabled4K8K12K16K20KSE +/- 54.12, N = 3SE +/- 122.89, N = 15SE +/- 0.00, N = 36602.2812083.7019018.301. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUDefault - DisabledSNC4SNC248121620SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 317.556.206.18MIN: 5.74 / MAX: 43.74MIN: 5.02 / MAX: 17.36MIN: 5.27 / MAX: 16.21. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve OpenMP - DegriddingSNC4SNC2Default - Disabled4K8K12K16K20KSE +/- 0.00, N = 3SE +/- 100.74, N = 157607.3114122.5020481.201. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUDefault - DisabledSNC4SNC2816243240SE +/- 0.36, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 336.5714.5614.51MIN: 15.82 / MAX: 76.01MIN: 11.83 / MAX: 32.54MIN: 12.17 / MAX: 35.531. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUDefault - DisabledSNC2SNC4306090120150SE +/- 0.52, N = 3SE +/- 0.29, N = 3SE +/- 0.13, N = 3141.7867.2265.32MIN: 54.39 / MAX: 210.64MIN: 37.86 / MAX: 90.7MIN: 36.8 / MAX: 87.751. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUDefault - DisabledSNC2SNC4306090120150SE +/- 0.37, N = 3SE +/- 0.43, N = 3SE +/- 0.17, N = 3141.5467.1765.40MIN: 50.69 / MAX: 212.29MIN: 38.08 / MAX: 93.26MIN: 44.03 / MAX: 91.211. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUDefault - DisabledSNC2SNC42004006008001000SE +/- 0.53, N = 3SE +/- 0.78, N = 3SE +/- 1.50, N = 3965.67468.35467.39MIN: 767.19 / MAX: 1026.9MIN: 396.69 / MAX: 533.02MIN: 391.77 / MAX: 504.291. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUDefault - DisabledSNC4SNC2612182430SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 325.2612.5412.52MIN: 12.5 / MAX: 49.19MIN: 10.7 / MAX: 28.81MIN: 10.66 / MAX: 27.971. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUDefault - DisabledSNC2SNC4110220330440550SE +/- 0.76, N = 3SE +/- 0.27, N = 3SE +/- 0.34, N = 3493.57245.02244.80MIN: 246.03 / MAX: 522.95MIN: 201.96 / MAX: 285.01MIN: 212 / MAX: 263.671. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUDefault - DisabledSNC2SNC4246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 38.074.144.13MIN: 4.25 / MAX: 26.67MIN: 3.73 / MAX: 12.01MIN: 3.67 / MAX: 12.511. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUDefault - DisabledSNC4SNC220406080100SE +/- 0.07, N = 3SE +/- 0.15, N = 3SE +/- 0.22, N = 393.2350.5649.80MIN: 42.51 / MAX: 145.87MIN: 38.52 / MAX: 103.27MIN: 38.67 / MAX: 117.731. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUDefault - DisabledSNC4SNC20.85731.71462.57193.42924.2865SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 33.812.092.09MIN: 2.1 / MAX: 21.93MIN: 1.87 / MAX: 8.99MIN: 1.85 / MAX: 7.81. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUDefault - DisabledSNC4SNC20.13950.2790.41850.5580.6975SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.620.360.36MIN: 0.21 / MAX: 39.81MIN: 0.27 / MAX: 41.09MIN: 0.27 / MAX: 31.551. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUDefault - DisabledSNC4SNC2246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 38.495.075.06MIN: 5.66 / MAX: 25.99MIN: 4.35 / MAX: 13.85MIN: 4.47 / MAX: 12.751. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

LULESH

LULESH is the Livermore Unstructured Lagrangian Explicit Shock Hydrodynamics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3Default - DisabledSNC2SNC48K16K24K32K40KSE +/- 398.51, N = 12SE +/- 116.87, N = 3SE +/- 142.33, N = 323294.8433106.2438146.301. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfigDefault - DisabledSNC2SNC460120180240300SE +/- 1.24, N = 3SE +/- 0.85, N = 3SE +/- 0.44, N = 3264.08174.35168.15

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUDefault - DisabledSNC4SNC230K60K90K120K150KSE +/- 195.22, N = 3SE +/- 140.85, N = 3SE +/- 365.77, N = 386958.12134176.02134566.001. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUDefault - DisabledSNC4SNC240K80K120K160K200KSE +/- 251.60, N = 3SE +/- 183.36, N = 3SE +/- 805.14, N = 3113350.17164363.19166444.721. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbfs max_TEPS, More Is BetterGraph500 3.0Scale: 26Default - DisabledSNC2SNC4200M400M600M800M1000M756165000106956000011049000001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

OpenBenchmarking.orgbfs median_TEPS, More Is BetterGraph500 3.0Scale: 26Default - DisabledSNC2SNC4200M400M600M800M1000M727662000101530000010569800001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16 - Device: CPUDefault - DisabledSNC4SNC28001600240032004000SE +/- 9.07, N = 3SE +/- 8.94, N = 3SE +/- 8.11, N = 32730.603863.883875.391. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUDefault - DisabledSNC4SNC20.19350.3870.58050.7740.9675SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.860.610.61MIN: 0.28 / MAX: 17.81MIN: 0.46 / MAX: 16.98MIN: 0.44 / MAX: 16.141. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration (defconfig) for the architecture being tested or alternatively an allmodconfig for building all possible kernel modules for the build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfigDefault - DisabledSNC2SNC4714212835SE +/- 0.34, N = 4SE +/- 0.26, N = 5SE +/- 0.29, N = 431.4524.5824.09

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16 - Device: CPUDefault - DisabledSNC4SNC2400800120016002000SE +/- 12.81, N = 3SE +/- 0.95, N = 3SE +/- 4.22, N = 31310.861647.091652.911. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm16SNC4SNC2Default - Disabled90180270360450SE +/- 1.41, N = 3SE +/- 1.55, N = 3SE +/- 0.23, N = 3396.53355.04329.611. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUSNC4SNC2Default - Disabled12002400360048006000SE +/- 10.32, N = 3SE +/- 6.31, N = 3SE +/- 12.20, N = 34721.814737.075643.891. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: NinjaDefault - DisabledSNC4SNC2306090120150SE +/- 0.08, N = 3SE +/- 0.52, N = 3SE +/- 0.30, N = 3121.87104.69104.60

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - GriddingSNC4SNC2Default - Disabled2K4K6K8K10KSE +/- 78.17, N = 3SE +/- 5.09, N = 3SE +/- 13.20, N = 37467.148223.258655.841. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp max_TEPS, More Is BetterGraph500 3.0Scale: 26Default - DisabledSNC2SNC4110M220M330M440M550M4620570005221870005278640001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

OpenVKL

OpenVKL is the Intel Open Volume Kernel Library that offers high-performance volume computation kernels and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCSNC4SNC2Default - Disabled5001000150020002500SE +/- 5.29, N = 3SE +/- 2.73, N = 3SE +/- 0.88, N = 3190520892153MIN: 180 / MAX: 27886MIN: 178 / MAX: 27767MIN: 179 / MAX: 27831

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 1.0Test: tConvolve MT - DegriddingSNC4SNC2Default - Disabled3K6K9K12K15KSE +/- 138.85, N = 3SE +/- 13.79, N = 3SE +/- 75.70, N = 310522.511209.211871.21. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUSNC4SNC2Default - Disabled6001200180024003000SE +/- 9.95, N = 3SE +/- 24.21, N = 3SE +/- 19.25, N = 32333.462435.282592.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16 - Device: CPUSNC4SNC2Default - Disabled918273645SE +/- 0.17, N = 3SE +/- 0.40, N = 3SE +/- 0.27, N = 341.0839.3637.01MIN: 31.72 / MAX: 55.31MIN: 32.78 / MAX: 55.31MIN: 20.68 / MAX: 66.671. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthDefault - DisabledSNC2SNC460M120M180M240M300MSE +/- 1898256.07, N = 3SE +/- 2257424.10, N = 3SE +/- 1785028.61, N = 3248215163272254945275458088

Timed Node.js Compilation

This test profile times how long it takes to build/compile Node.js itself from source. Node.js is a JavaScript run-time built from the Chrome V8 JavaScript engine while itself is written in C/C++. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 19.8.1Time To CompileDefault - DisabledSNC2SNC420406080100SE +/- 1.21, N = 5SE +/- 0.40, N = 3SE +/- 0.39, N = 3111.37102.32100.62

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16 - Device: CPUSNC2SNC4Default - Disabled3K6K9K12K15KSE +/- 56.50, N = 3SE +/- 61.71, N = 3SE +/- 73.24, N = 311414.8911421.2512547.911. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Timed Gem5 Compilation

This test times how long it takes to compile Gem5. Gem5 is a simulator for computer system architecture research. Gem5 is widely used for computer architecture research within the industry, academia, and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 23.0.1Time To CompileDefault - DisabledSNC2SNC4306090120150SE +/- 1.82, N = 3SE +/- 1.48, N = 3SE +/- 1.46, N = 5150.97140.81137.48

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeDefault - DisabledSNC2SNC470140210280350331.86310.66302.691. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

Graph500

This is a benchmark of the reference implementation of Graph500, an HPC benchmark focused on data intensive loads and commonly tested on supercomputers for complex data problems. Graph500 primarily stresses the communication subsystem of the hardware under test. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 26Default - DisabledSNC2SNC480M160M240M320M400M3571270003892350003906820001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

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: CG.CDefault - DisabledSNC2SNC412K24K36K48K60KSE +/- 476.77, N = 3SE +/- 324.22, N = 3SE +/- 191.96, N = 352079.1354560.0356924.561. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Ultra FastSNC4SNC2Default - Disabled1530456075SE +/- 0.25, N = 3SE +/- 0.36, N = 3SE +/- 0.15, N = 363.2365.3469.02

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: MD5SNC4SNC2Default - Disabled3M6M9M12M15MSE +/- 174193.35, N = 15SE +/- 193319.26, N = 15SE +/- 43978.53, N = 31341900013888800146006671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FasterSNC4SNC2Default - Disabled48121620SE +/- 0.09, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 314.0114.3115.251. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP16 - Device: CPUDefault - DisabledSNC2SNC480160240320400SE +/- 1.27, N = 3SE +/- 1.55, N = 3SE +/- 0.76, N = 3338.09356.72367.121. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Machine Translation EN To DE FP16 - Device: CPUSNC4SNC2Default - Disabled110220330440550SE +/- 1.37, N = 3SE +/- 2.07, N = 3SE +/- 0.33, N = 3474.11481.41514.221. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Super FastSNC4SNC2Default - Disabled1530456075SE +/- 0.42, N = 3SE +/- 0.12, N = 3SE +/- 0.24, N = 362.2564.6567.47

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 129 Cells Per DirectionDefault - DisabledSNC2SNC40.58891.17781.76672.35562.9445SE +/- 0.03355279, N = 3SE +/- 0.01815766, N = 3SE +/- 0.00587555, N = 32.617387052.496593322.416143021. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: Very FastSNC4SNC2Default - Disabled1530456075SE +/- 0.22, N = 3SE +/- 0.60, N = 3SE +/- 0.38, N = 361.2662.9966.32

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Person Detection FP32 - Device: CPUDefault - DisabledSNC2SNC480160240320400SE +/- 0.89, N = 3SE +/- 2.29, N = 3SE +/- 0.96, N = 3338.74357.03366.591. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bmSNC2Default - DisabledSNC43691215SE +/- 0.09, N = 15SE +/- 0.07, N = 14SE +/- 0.07, N = 311.8210.9610.951. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjSNC4SNC2Default - Disabled306090120150SE +/- 0.54, N = 3SE +/- 0.58, N = 3SE +/- 0.59, N = 3104.80111.36112.83MIN: 100.15 / MAX: 112.2MIN: 108.45 / MAX: 114.81MIN: 110.06 / MAX: 116.96

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 64 - Model: ResNet-50SNC4SNC2Default - Disabled20406080100SE +/- 0.09, N = 3SE +/- 0.22, N = 3SE +/- 0.05, N = 384.5085.5490.46

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishSNC4SNC2Default - Disabled40K80K120K160K200KSE +/- 1944.34, N = 15SE +/- 1828.86, N = 12SE +/- 66.40, N = 31617901692871731451. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2

CloverLeaf

CloverLeaf is a Lagrangian-Eulerian hydrodynamics benchmark. This test profile currently makes use of CloverLeaf's OpenMP version. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeaf 1.3Input: clover_bm64_shortSNC4SNC2Default - Disabled1020304050SE +/- 0.08, N = 3SE +/- 0.26, N = 3SE +/- 0.01, N = 342.0041.2139.321. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptSNC4SNC2Default - Disabled40K80K120K160K200KSE +/- 1540.98, N = 15SE +/- 2018.22, N = 4SE +/- 1219.45, N = 31632591717341743351. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2

Algebraic Multi-Grid Benchmark

AMG is a parallel algebraic multigrid solver for linear systems arising from problems on unstructured grids. The driver provided with AMG builds linear systems for various 3-dimensional problems. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark 1.2Default - DisabledSNC2SNC4400M800M1200M1600M2000MSE +/- 1222576.38, N = 3SE +/- 5512706.85, N = 3SE +/- 14033805.07, N = 31662894000173214933317737583331. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 4K - Video Preset: FastSNC4SNC2Default - Disabled246810SE +/- 0.118, N = 3SE +/- 0.051, N = 3SE +/- 0.094, N = 38.1868.2788.7151. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 32 - Model: ResNet-50SNC2SNC4Default - Disabled1632486480SE +/- 0.19, N = 3SE +/- 0.74, N = 3SE +/- 0.29, N = 366.1366.8870.35

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Tomographic ModelDefault - DisabledSNC2SNC4246810SE +/- 0.088577121, N = 3SE +/- 0.094423144, N = 3SE +/- 0.068276455, N = 37.9874304527.5441437367.5194150001. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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 7.0Input: AUSURF112Default - DisabledSNC2SNC470140210280350SE +/- 0.35, N = 3SE +/- 0.87, N = 3SE +/- 0.32, N = 3326.06316.50307.061. (F9X) gfortran options: -pthread -fopenmp -ldevXlib -lopenblas -lFoX_dom -lFoX_sax -lFoX_wxml -lFoX_common -lFoX_utils -lFoX_fsys -lfftw3_omp -lfftw3 -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

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.CSNC4SNC2Default - Disabled20K40K60K80K100KSE +/- 107.70, N = 3SE +/- 925.13, N = 3SE +/- 245.52, N = 394921.2797435.24100728.491. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 512 - Model: ResNet-50SNC4SNC2Default - Disabled306090120150SE +/- 0.33, N = 3SE +/- 0.21, N = 3SE +/- 0.04, N = 3127.24130.65135.02

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 256 - Model: ResNet-50SNC4SNC2Default - Disabled306090120150SE +/- 0.12, N = 3SE +/- 0.23, N = 3SE +/- 0.12, N = 3112.08115.90118.86

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 LeukocyteSNC4SNC2Default - Disabled714212835SE +/- 0.05, N = 3SE +/- 0.14, N = 3SE +/- 0.23, N = 331.1230.8929.391. (CXX) g++ options: -O2 -lOpenCL

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_lSNC4SNC2Default - Disabled3691215SE +/- 0.04, N = 3SE +/- 0.10, N = 3SE +/- 0.08, N = 310.5810.6511.16MIN: 5.94 / MAX: 11.15MIN: 6.15 / MAX: 11.04MIN: 10.83 / MAX: 11.47

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUSNC4Default - DisabledSNC2510152025SE +/- 0.06, N = 3SE +/- 0.26, N = 15SE +/- 0.29, N = 1521.6022.2422.77MIN: 18.58 / MAX: 28.17MIN: 18.56 / MAX: 28.74MIN: 18.36 / MAX: 29.05

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonSNC4SNC2Default - Disabled306090120150SE +/- 1.43, N = 4SE +/- 0.56, N = 3SE +/- 0.63, N = 3122.59128.01129.17MIN: 115.06 / MAX: 129.69MIN: 125.3 / MAX: 131.84MIN: 126.31 / MAX: 136

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-152SNC2SNC4Default - Disabled48121620SE +/- 0.19, N = 3SE +/- 0.13, N = 3SE +/- 0.10, N = 315.3615.6116.16MIN: 8.91 / MAX: 15.79MIN: 8.77 / MAX: 16.18MIN: 15.77 / MAX: 16.51

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-152SNC4Default - DisabledSNC248121620SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.10, N = 315.2415.9116.03MIN: 8.23 / MAX: 15.81MIN: 15.34 / MAX: 16.26MIN: 9.32 / MAX: 16.38

TensorFlow

This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.12Device: CPU - Batch Size: 16 - Model: ResNet-50SNC4SNC2Default - Disabled1224364860SE +/- 0.63, N = 3SE +/- 0.59, N = 3SE +/- 0.23, N = 349.2749.5151.77

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-152SNC2SNC4Default - Disabled48121620SE +/- 0.14, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 515.3015.3916.06MIN: 8.79 / MAX: 15.89MIN: 8.86 / MAX: 16.02MIN: 15.37 / MAX: 16.74

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 StreamclusterSNC4SNC2Default - Disabled1.10992.21983.32974.43965.5495SE +/- 0.027, N = 3SE +/- 0.019, N = 3SE +/- 0.007, N = 34.9334.8844.7031. (CXX) g++ options: -O2 -lOpenCL

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.BDefault - DisabledSNC2SNC430K60K90K120K150KSE +/- 676.26, N = 3SE +/- 674.53, N = 3SE +/- 1739.78, N = 3145525.94151244.49151839.301. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP ParallelDefault - DisabledSNC4SNC2306090120150119.19117.44114.28

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUSNC4SNC2Default - Disabled3691215SE +/- 0.15, N = 3SE +/- 0.09, N = 3SE +/- 0.11, N = 311.8911.9412.39MIN: 5.42 / MAX: 13.74MIN: 5.67 / MAX: 13.6MIN: 5.87 / MAX: 14.11

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 HotSpot3DSNC4SNC2Default - Disabled1428425670SE +/- 0.53, N = 15SE +/- 0.62, N = 15SE +/- 0.82, N = 361.2359.8658.871. (CXX) g++ options: -O2 -lOpenCL

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Layered HalfspaceDefault - DisabledSNC2SNC4510152025SE +/- 0.16, N = 3SE +/- 0.24, N = 3SE +/- 0.14, N = 318.7418.3618.041. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenFOAM

OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Mesh TimeDefault - DisabledSNC2SNC4306090120150138.65135.10133.741. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lfiniteVolume -lmeshTools -lparallel -llagrangian -lregionModels -lgenericPatchFields -lOpenFOAM -ldl -lm

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: ResNet-50Default - DisabledSNC4SNC2918273645SE +/- 0.12, N = 3SE +/- 0.17, N = 3SE +/- 0.17, N = 338.6839.8040.09MIN: 37.08 / MAX: 39.76MIN: 26.68 / MAX: 41.28MIN: 22.35 / MAX: 41.64

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FastSNC4SNC2Default - Disabled612182430SE +/- 0.24, N = 3SE +/- 0.29, N = 3SE +/- 0.17, N = 323.4523.7124.301. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16 - Device: CPUDefault - DisabledSNC2SNC41224364860SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 349.4151.0651.191. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

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.CDefault - DisabledSNC2SNC420K40K60K80K100KSE +/- 1045.55, N = 4SE +/- 59.39, N = 3SE +/- 517.95, N = 395501.5097068.0198739.501. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100SNC4SNC2Default - Disabled1.7M3.4M5.1M6.8M8.5MSE +/- 35640.28, N = 3SE +/- 52363.50, N = 3SE +/- 23469.53, N = 37507583.687704668.277743874.041. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: ResNet-50Default - DisabledSNC4SNC2918273645SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.20, N = 339.0639.0740.27MIN: 37.1 / MAX: 40.22MIN: 19.69 / MAX: 41.1MIN: 23.49 / MAX: 42.09

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: ResNet-50Default - DisabledSNC4SNC2918273645SE +/- 0.10, N = 3SE +/- 0.45, N = 3SE +/- 0.40, N = 339.2139.2940.41MIN: 36.81 / MAX: 40.31MIN: 25.78 / MAX: 41.34MIN: 34.93 / MAX: 42.02

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: IS.DSNC4Default - DisabledSNC29001800270036004500SE +/- 45.26, N = 4SE +/- 21.28, N = 3SE +/- 8.86, N = 34155.684279.984282.361. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKSNC4SNC2Default - Disabled130K260K390K520K650KSE +/- 4063.87, N = 3SE +/- 4996.06, N = 3SE +/- 2146.03, N = 35961806116696142631. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPUDefault - DisabledSNC2SNC43691215SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 310.6510.8510.97MIN: 4.82 / MAX: 12.11MIN: 5.02 / MAX: 12.4MIN: 5.05 / MAX: 12.72

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-152SNC2SNC4Default - Disabled510152025SE +/- 0.21, N = 3SE +/- 0.20, N = 3SE +/- 0.25, N = 318.4418.6218.99MIN: 9.73 / MAX: 19.35MIN: 10.5 / MAX: 19.64MIN: 17.88 / MAX: 19.86

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: HMAC-SHA512SNC4SNC2Default - Disabled60M120M180M240M300MSE +/- 2535178.67, N = 12SE +/- 1930805.92, N = 15SE +/- 1312178.38, N = 32879555002892214002965186671. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lm -lrt -lz -ldl -lcrypt -lbz2

VVenC

VVenC is the Fraunhofer Versatile Video Encoder as a fast/efficient H.266/VVC encoder. The vvenc encoder makes use of SIMD Everywhere (SIMDe). The vvenc software is published under the Clear BSD License. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVVenC 1.9Video Input: Bosphorus 1080p - Video Preset: FasterSNC4SNC2Default - Disabled918273645SE +/- 0.45, N = 3SE +/- 0.32, N = 3SE +/- 0.17, N = 340.2040.2241.401. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects

Xcompact3d Incompact3d

Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: input.i3d 193 Cells Per DirectionDefault - DisabledSNC2SNC43691215SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 310.6610.4910.361. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

Timed LLVM Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 16.0Build System: Unix MakefilesDefault - DisabledSNC2SNC44080120160200SE +/- 0.35, N = 3SE +/- 0.79, N = 3SE +/- 0.32, N = 3175.47170.83170.54

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Homogeneous HalfspaceDefault - DisabledSNC2SNC43691215SE +/- 0.062415502, N = 15SE +/- 0.112412006, N = 4SE +/- 0.063880399, N = 39.9429897629.7428068039.6687597331. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Mount St. HelensSNC2Default - DisabledSNC4246810SE +/- 0.022697239, N = 3SE +/- 0.077041220, N = 3SE +/- 0.073100963, N = 37.7562337377.7248900327.5451761781. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUSNC2SNC4Default - Disabled13002600390052006500SE +/- 14.13, N = 3SE +/- 15.69, N = 3SE +/- 10.15, N = 35783.015797.285936.371. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUSNC2SNC4Default - Disabled1.2422.4843.7264.9686.21SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 35.525.515.38MIN: 4.91 / MAX: 14.41MIN: 4.84 / MAX: 15.48MIN: 3.31 / MAX: 23.311. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

GPAW

GPAW is a density-functional theory (DFT) Python code based on the projector-augmented wave (PAW) method and the atomic simulation environment (ASE). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 23.6Input: Carbon NanotubeDefault - DisabledSNC2SNC4918273645SE +/- 0.34, N = 3SE +/- 0.23, N = 3SE +/- 0.25, N = 338.1337.8037.161. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection Retail FP16-INT8 - Device: CPUSNC2SNC4Default - Disabled4K8K12K16K20KSE +/- 14.02, N = 3SE +/- 11.11, N = 3SE +/- 14.08, N = 317366.2917402.7617809.431. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Super FastSNC2SNC4Default - Disabled50100150200250SE +/- 1.37, N = 3SE +/- 2.03, N = 3SE +/- 0.37, N = 3206.23206.92211.36

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Very FastSNC2SNC4Default - Disabled50100150200250SE +/- 0.63, N = 3SE +/- 1.28, N = 3SE +/- 1.32, N = 3203.48207.62208.36

SPECFEM3D

simulates acoustic (fluid), elastic (solid), coupled acoustic/elastic, poroelastic or seismic wave propagation in any type of conforming mesh of hexahedra. This test profile currently relies on CPU-based execution for SPECFEM3D and using a variety of their built-in examples/models for benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSPECFEM3D 4.0Model: Water-layered HalfspaceDefault - DisabledSNC2SNC4510152025SE +/- 0.08, N = 3SE +/- 0.19, N = 3SE +/- 0.06, N = 319.2719.2218.821. (F9X) gfortran options: -O2 -fopenmp -std=f2003 -fimplicit-none -fmax-errors=10 -pedantic -pedantic-errors -O3 -finline-functions -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 1 - Model: ResNet-50Default - DisabledSNC4SNC21122334455SE +/- 0.07, N = 3SE +/- 0.25, N = 3SE +/- 0.25, N = 347.7048.3648.83MIN: 44.82 / MAX: 49.01MIN: 25.09 / MAX: 50.72MIN: 28.77 / MAX: 50.91

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingSNC2SNC4Default - Disabled140K280K420K560K700KSE +/- 11076.26, N = 3SE +/- 5454.96, N = 3SE +/- 364.51, N = 36409286491206552031. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

PETSc

PETSc, the Portable, Extensible Toolkit for Scientific Computation, is for the scalable (parallel) solution of scientific applications modeled by partial differential equations. This test profile runs the PETSc "make streams" benchmark and records the throughput rate when all available cores are utilized for the MPI Streams build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterPETSc 3.19Test: StreamsDefault - DisabledSNC2SNC440K80K120K160K200KSE +/- 64.39, N = 3SE +/- 708.72, N = 3SE +/- 451.28, N = 3183161.11185070.83187197.631. (CC) gcc options: -fPIC -O3 -O2 -lpthread -lpciaccess -lm

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: Ultra FastSNC2Default - DisabledSNC450100150200250SE +/- 0.83, N = 3SE +/- 0.58, N = 3SE +/- 2.40, N = 3204.49207.97208.97

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 3.17.1Input: Li2_STO_aeSNC2Default - DisabledSNC420406080100SE +/- 1.13, N = 3SE +/- 0.55, N = 3SE +/- 0.06, N = 3106.01103.90103.771. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowSNC4SNC2Default - Disabled714212835SE +/- 0.13, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 329.3029.4729.92

7-Zip Compression

This is a test of 7-Zip compression/decompression with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingSNC2SNC4Default - Disabled120K240K360K480K600KSE +/- 2142.48, N = 3SE +/- 2055.13, N = 3SE +/- 410.41, N = 35357135368205469361. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

QuantLib

QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedDefault - DisabledSNC2SNC470K140K210K280K350KSE +/- 716.12, N = 3SE +/- 1378.05, N = 3SE +/- 3981.12, N = 3310771.1313010.5317145.31. (CXX) g++ options: -O3 -march=native -fPIE -pie

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.CSNC4SNC2Default - Disabled20K40K60K80K100KSE +/- 287.86, N = 3SE +/- 271.76, N = 3SE +/- 61.36, N = 387467.2388668.1389217.911. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 128SNC4SNC2Default - Disabled400800120016002000SE +/- 11.98, N = 3SE +/- 0.82, N = 3SE +/- 2.22, N = 32004.72026.22043.51. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

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.CDefault - DisabledSNC2SNC460K120K180K240K300KSE +/- 1442.62, N = 3SE +/- 427.36, N = 3SE +/- 1304.12, N = 3255135.24256378.22259883.621. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read OnlySNC2SNC4Default - Disabled400K800K1200K1600K2000KSE +/- 19687.71, N = 6SE +/- 14067.03, N = 3SE +/- 7755.83, N = 31950507195650919868071. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Only - Average LatencySNC2SNC4Default - Disabled0.11540.23080.34620.46160.577SE +/- 0.005, N = 6SE +/- 0.004, N = 3SE +/- 0.002, N = 30.5130.5110.5041. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs (and GPUs via SYCL) and supporting instruction sets such as SSE, AVX, AVX2, and AVX-512. Embree also supports making use of the Intel SPMD Program Compiler (ISPC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownSNC2SNC4Default - Disabled20406080100SE +/- 0.53, N = 3SE +/- 0.40, N = 3SE +/- 0.46, N = 3106.26106.43108.08MIN: 102.99 / MAX: 115.22MIN: 103.16 / MAX: 113.77MIN: 105.13 / MAX: 117.76

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 BenchmarkDefault - DisabledSNC4SNC2160320480640800SE +/- 5.73, N = 3SE +/- 7.89, N = 3SE +/- 1.99, N = 3746.05753.64758.02

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:10SNC4Default - DisabledSNC21.2M2.4M3.6M4.8M6MSE +/- 8577.07, N = 3SE +/- 23305.65, N = 3SE +/- 17431.43, N = 35728479.095811757.935818020.661. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

Timed CPython Compilation

This test times how long it takes to build the reference Python implementation, CPython, with optimizations and LTO enabled for a release build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: Released Build, PGO + LTO OptimizedDefault - DisabledSNC2SNC44080120160200188.35188.07185.51

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUSNC4SNC2Default - Disabled48121620SE +/- 0.02, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 315.0015.1915.23MIN: 14.61 / MAX: 18.76MIN: 14.66 / MAX: 18.88MIN: 14.85 / MAX: 18.76

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Fishy Cat - Compute: CPU-OnlySNC2SNC4Default - Disabled510152025SE +/- 0.20, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 319.7619.7119.47

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumSNC4SNC2Default - Disabled816243240SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 332.7533.1233.23

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 512SNC4SNC2Default - Disabled300M600M900M1200M1500MSE +/- 5108163.40, N = 3SE +/- 5353295.97, N = 3SE +/- 4629254.80, N = 31493000000149913333315142000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUDefault - DisabledSNC2SNC4510152025SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 319.3319.0819.06MIN: 9.33 / MAX: 85.74MIN: 15.77 / MAX: 56.75MIN: 17.12 / MAX: 40.941. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 256Default - DisabledSNC2SNC46001200180024003000SE +/- 18.22, N = 3SE +/- 29.68, N = 3SE +/- 21.00, N = 32564.62583.62599.91. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 57SNC4Default - DisabledSNC2400M800M1200M1600M2000MSE +/- 6406333.67, N = 3SE +/- 3985947.54, N = 3SE +/- 3811532.21, N = 31721266667173056666717444333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUSNC4Default - DisabledSNC28K16K24K32K40KSE +/- 65.34, N = 3SE +/- 105.83, N = 3SE +/- 192.95, N = 3385233826438015

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16 - Device: CPUDefault - DisabledSNC2SNC411002200330044005500SE +/- 6.69, N = 3SE +/- 9.79, N = 3SE +/- 6.67, N = 34962.135023.425026.691. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read OnlySNC2SNC4Default - Disabled800K1600K2400K3200K4000KSE +/- 21467.51, N = 3SE +/- 37681.71, N = 6SE +/- 49179.25, N = 33746006375909437926981. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUSNC4SNC2Default - Disabled10K20K30K40K50KSE +/- 146.66, N = 3SE +/- 80.70, N = 3SE +/- 70.44, N = 3445354430043999

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 512SNC4SNC2Default - Disabled200M400M600M800M1000MSE +/- 6276308.19, N = 3SE +/- 8992613.64, N = 3SE +/- 8999104.28, N = 39272766679351700009384933331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenRadioss

OpenRadioss is an open-source AGPL-licensed finite element solver for dynamic event analysis OpenRadioss is based on Altair Radioss and open-sourced in 2022. This open-source finite element solver is benchmarked with various example models available from https://www.openradioss.org/models/ and https://github.com/OpenRadioss/ModelExchange/tree/main/Examples. This test is currently using a reference OpenRadioss binary build offered via GitHub. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2023.09.15Model: Chrysler Neon 1MDefault - DisabledSNC4SNC2306090120150SE +/- 0.18, N = 3SE +/- 0.27, N = 3SE +/- 0.28, N = 3157.35156.21155.50

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 2.14ATPase Simulation - 327,506 AtomsDefault - DisabledSNC2SNC40.05810.11620.17430.23240.2905SE +/- 0.00087, N = 3SE +/- 0.00284, N = 3SE +/- 0.00197, N = 30.258030.256120.25502

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 32SNC2Default - DisabledSNC4120240360480600SE +/- 2.72, N = 3SE +/- 0.58, N = 3SE +/- 1.96, N = 3553.3555.6559.81. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: SlowSNC4SNC2Default - Disabled20406080100SE +/- 0.40, N = 3SE +/- 0.19, N = 3SE +/- 0.27, N = 388.1888.6889.19

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUDefault - DisabledSNC2SNC43691215SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 39.729.639.61MIN: 4.95 / MAX: 29.09MIN: 8.28 / MAX: 16.71MIN: 8.18 / MAX: 19.441. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencySNC2SNC4Default - Disabled0.06010.12020.18030.24040.3005SE +/- 0.002, N = 3SE +/- 0.003, N = 6SE +/- 0.003, N = 30.2670.2660.2641. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA512Default - DisabledSNC2SNC49000M18000M27000M36000M45000MSE +/- 32408039.38, N = 3SE +/- 19206282.00, N = 3SE +/- 16399997.56, N = 34272391165343151618910432066419831. (CC) gcc options: -pthread -m64 -O3 -ldl

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUSNC4SNC2Default - Disabled30060090012001500SE +/- 4.33, N = 3SE +/- 2.40, N = 3SE +/- 1.53, N = 3126612591252

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUDefault - DisabledSNC2SNC42K4K6K8K10KSE +/- 30.53, N = 3SE +/- 17.38, N = 3SE +/- 26.50, N = 39866.459948.309973.181. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 512SNC4SNC2Default - Disabled300M600M900M1200M1500MSE +/- 7198688.15, N = 3SE +/- 6948700.92, N = 3SE +/- 6222807.51, N = 31300233333130283333313142000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUSNC4SNC2Default - Disabled8K16K24K32K40KSE +/- 154.47, N = 3SE +/- 106.88, N = 3SE +/- 51.31, N = 3382843800937890

Memcached

Memcached is a high performance, distributed memory object caching system. This Memcached test profiles makes use of memtier_benchmark for excuting this CPU/memory-focused server benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOps/sec, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:5SNC4Default - DisabledSNC2700K1400K2100K2800K3500KSE +/- 44466.09, N = 3SE +/- 15559.68, N = 3SE +/- 33459.28, N = 33327393.353359726.873359880.551. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUSNC2SNC4Default - Disabled2004006008001000SE +/- 2.73, N = 3SE +/- 1.86, N = 3SE +/- 4.18, N = 3107410731064

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Face Detection FP16-INT8 - Device: CPUDefault - DisabledSNC2SNC420406080100SE +/- 0.15, N = 3SE +/- 0.12, N = 3SE +/- 0.15, N = 396.9597.7697.851. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUSNC4SNC2Default - Disabled4K8K12K16K20KSE +/- 57.00, N = 3SE +/- 18.75, N = 3SE +/- 42.71, N = 3201992014420017

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Road Segmentation ADAS FP16-INT8 - Device: CPUDefault - DisabledSNC4SNC2400800120016002000SE +/- 4.08, N = 3SE +/- 7.31, N = 3SE +/- 7.84, N = 31898.141911.681914.891. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUSNC4Default - DisabledSNC24K8K12K16K20KSE +/- 70.54, N = 3SE +/- 94.37, N = 3SE +/- 54.03, N = 3172621719317113

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Classroom - Compute: CPU-OnlySNC2SNC4Default - Disabled918273645SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 338.3338.2438.02

uvg266

uvg266 is an open-source VVC/H.266 (Versatile Video Coding) encoder based on Kvazaar as part of the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betteruvg266 0.4.1Video Input: Bosphorus 1080p - Video Preset: MediumSNC4SNC2Default - Disabled20406080100SE +/- 0.34, N = 3SE +/- 0.18, N = 3SE +/- 0.23, N = 397.6098.2298.33

libxsmm

Libxsmm is an open-source library for specialized dense and sparse matrix operations and deep learning primitives. Libxsmm supports making use of Intel AMX, AVX-512, and other modern CPU instruction set capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOPS/s, More Is Betterlibxsmm 2-1.17-3645M N K: 64SNC2Default - DisabledSNC42004006008001000SE +/- 2.33, N = 3SE +/- 0.53, N = 3SE +/- 1.09, N = 31052.31055.41059.11. (CXX) g++ options: -dynamic -Bstatic -static-libgcc -lgomp -lm -lrt -ldl -lquadmath -lstdc++ -pthread -fPIC -std=c++14 -O2 -fopenmp-simd -funroll-loops -ftree-vectorize -fdata-sections -ffunction-sections -fvisibility=hidden -msse4.2

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.CDefault - DisabledSNC2SNC450K100K150K200K250KSE +/- 280.16, N = 3SE +/- 322.09, N = 3SE +/- 112.43, N = 3214445.97215684.06215764.821. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-128-GCMDefault - DisabledSNC2SNC4200000M400000M600000M800000M1000000MSE +/- 2155035998.71, N = 3SE +/- 1081587572.26, N = 3SE +/- 179395215.71, N = 39414427014479433657325809469333786201. (CC) gcc options: -pthread -m64 -O3 -ldl

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096SNC2Default - DisabledSNC4300K600K900K1200K1500KSE +/- 486.05, N = 3SE +/- 3444.37, N = 3SE +/- 3270.23, N = 31529451.71533067.11538165.31. (CC) gcc options: -pthread -m64 -O3 -ldl

ACES DGEMM

This is a multi-threaded DGEMM benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateSNC4SNC2Default - Disabled1020304050SE +/- 0.42, N = 3SE +/- 0.36, N = 3SE +/- 0.18, N = 343.6343.7743.881. (CC) gcc options: -O3 -march=native -fopenmp

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 57SNC2Default - DisabledSNC41000M2000M3000M4000M5000MSE +/- 10235938.86, N = 3SE +/- 17623122.44, N = 3SE +/- 22778084.01, N = 34493966667449553333345181333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 32SNC2SNC4Default - Disabled600M1200M1800M2400M3000MSE +/- 22995168.57, N = 3SE +/- 26768908.17, N = 3SE +/- 26479677.74, N = 32632233333264343333326461000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: BMW27 - Compute: CPU-OnlySNC2SNC4Default - Disabled48121620SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 315.3215.3115.25

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUSNC4SNC2Default - Disabled4K8K12K16K20KSE +/- 2.67, N = 3SE +/- 20.23, N = 3SE +/- 35.36, N = 3170141699916939

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Pabellon Barcelona - Compute: CPU-OnlySNC2SNC4Default - Disabled1122334455SE +/- 0.23, N = 3SE +/- 0.29, N = 3SE +/- 0.20, N = 346.9746.8846.77

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 57SNC2Default - DisabledSNC41200M2400M3600M4800M6000MSE +/- 15429013.07, N = 3SE +/- 18999298.23, N = 3SE +/- 14304195.19, N = 35393633333540720000054166000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 32Default - DisabledSNC2SNC4300M600M900M1200M1500MSE +/- 1937638.88, N = 3SE +/- 5024716.69, N = 3SE +/- 3769320.60, N = 31435333333143643333314409333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUDefault - DisabledSNC2SNC41020304050SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.16, N = 345.2545.2245.08MIN: 34.3 / MAX: 61.3MIN: 37.77 / MAX: 56.52MIN: 36.6 / MAX: 52.281. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

OSPRay Studio

Intel OSPRay Studio is an open-source, interactive visualization and ray-tracing software package. OSPRay Studio makes use of Intel OSPRay, a portable ray-tracing engine for high-performance, high-fidelity visualizations. OSPRay builds off Intel's Embree and Intel SPMD Program Compiler (ISPC) components as part of the oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.13Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUSNC2SNC4Default - Disabled2004006008001000SE +/- 3.61, N = 3SE +/- 3.71, N = 3SE +/- 3.79, N = 3108010791076

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 128 - Buffer Length: 256 - Filter Length: 32Default - DisabledSNC2SNC4900M1800M2700M3600M4500MSE +/- 18076719.22, N = 3SE +/- 26426018.32, N = 3SE +/- 26314254.69, N = 34228133333423356666742436000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenVINO

This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2023.2.devModel: Handwritten English Recognition FP16-INT8 - Device: CPUDefault - DisabledSNC2SNC45001000150020002500SE +/- 3.37, N = 3SE +/- 5.01, N = 3SE +/- 7.69, N = 32120.232121.182127.421. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 192 - Buffer Length: 256 - Filter Length: 32SNC2Default - DisabledSNC41200M2400M3600M4800M6000MSE +/- 18095333.96, N = 3SE +/- 19784955.00, N = 3SE +/- 29526993.30, N = 35519933333552673333355355000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20-Poly1305Default - DisabledSNC2SNC480000M160000M240000M320000M400000MSE +/- 176665463.84, N = 3SE +/- 140024932.44, N = 3SE +/- 129282934.95, N = 33618523758603619875476833627655000231. (CC) gcc options: -pthread -m64 -O3 -ldl

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 LavaMDSNC4Default - DisabledSNC2612182430SE +/- 0.09, N = 3SE +/- 0.07, N = 3SE +/- 0.09, N = 326.9726.9526.911. (CXX) g++ options: -O2 -lOpenCL

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: AES-256-GCMDefault - DisabledSNC2SNC4200000M400000M600000M800000M1000000MSE +/- 1400557991.78, N = 3SE +/- 991457061.79, N = 3SE +/- 1023563571.48, N = 38151757053978153933583578171313871071. (CC) gcc options: -pthread -m64 -O3 -ldl

Liquid-DSP

LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 64 - Buffer Length: 256 - Filter Length: 57SNC2Default - DisabledSNC4600M1200M1800M2400M3000MSE +/- 14068522.78, N = 3SE +/- 20219380.14, N = 3SE +/- 1844210.16, N = 33016100000302090000030231666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 1.6Threads: 32 - Buffer Length: 256 - Filter Length: 512Default - DisabledSNC4SNC2110M220M330M440M550MSE +/- 2767116.43, N = 3SE +/- 3819181.12, N = 3SE +/- 3417076.40, N = 35225600005229966675236033331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: ChaCha20SNC2Default - DisabledSNC4110000M220000M330000M440000M550000MSE +/- 45048908.57, N = 3SE +/- 157967680.92, N = 3SE +/- 56755200.60, N = 35113183479575116942446535123185804171. (CC) gcc options: -pthread -m64 -O3 -ldl

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 SolverSNC4SNC2Default - Disabled1.25662.51323.76985.02646.283SE +/- 0.013, N = 3SE +/- 0.002, N = 3SE +/- 0.036, N = 35.5855.5815.5771. (CXX) g++ options: -O2 -lOpenCL

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.1Algorithm: RSA4096SNC2Default - DisabledSNC411K22K33K44K55KSE +/- 67.46, N = 3SE +/- 49.04, N = 3SE +/- 90.07, N = 349862.149897.349924.91. (CC) gcc options: -pthread -m64 -O3 -ldl

Blender

Blender is an open-source 3D creation and modeling software project. This test is of Blender's Cycles performance with various sample files. GPU computing via NVIDIA OptiX and NVIDIA CUDA is currently supported as well as HIP for AMD Radeon GPUs and Intel oneAPI for Intel Graphics. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.0Blend File: Barbershop - Compute: CPU-OnlyDefault - DisabledSNC4SNC2306090120150SE +/- 0.18, N = 3SE +/- 0.23, N = 3SE +/- 0.26, N = 3136.29136.28136.20

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.1Algorithm: SHA256SNC2Default - DisabledSNC430000M60000M90000M120000M150000MSE +/- 241913832.01, N = 3SE +/- 311439878.18, N = 3SE +/- 282602364.23, N = 31316274639831316294998931317066984271. (CC) gcc options: -pthread -m64 -O3 -ldl

PyTorch

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_lSNC4SNC2Default - Disabled246810SE +/- 0.13, N = 6SE +/- 0.02, N = 3SE +/- 0.01, N = 33.685.386.36MIN: 1.19 / MAX: 6.36MIN: 3.75 / MAX: 5.87MIN: 5.69 / MAX: 6.62

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_lSNC4SNC2Default - Disabled246810SE +/- 0.29, N = 6SE +/- 0.04, N = 3SE +/- 0.02, N = 34.075.316.35MIN: 1.11 / MAX: 6.41MIN: 3.81 / MAX: 5.85MIN: 5.72 / MAX: 6.64

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.1Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_lSNC4SNC2Default - Disabled246810SE +/- 0.23, N = 9SE +/- 0.06, N = 3SE +/- 0.02, N = 34.155.366.34MIN: 1.09 / MAX: 6.41MIN: 3.75 / MAX: 5.85MIN: 5.68 / MAX: 6.64

PostgreSQL

This is a benchmark of PostgreSQL using the integrated pgbench for facilitating the database benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read Write - Average LatencySNC4SNC2Default - Disabled1530456075SE +/- 0.79, N = 4SE +/- 0.82, N = 3SE +/- 1.61, N = 1265.3363.4460.661. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 1000 - Clients: 1000 - Mode: Read WriteSNC4SNC2Default - Disabled4K8K12K16K20KSE +/- 181.92, N = 4SE +/- 204.24, N = 3SE +/- 472.23, N = 121531415769166231. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Write - Average LatencySNC4SNC2Default - Disabled1632486480SE +/- 3.47, N = 12SE +/- 3.12, N = 12SE +/- 0.50, N = 1272.6572.1555.401. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read WriteSNC4SNC2Default - Disabled4K8K12K16K20KSE +/- 577.54, N = 12SE +/- 496.25, N = 12SE +/- 160.41, N = 121406714096180681. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

GROMACS

The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing with the water_GMX50 data. This test profile allows selecting between CPU and GPU-based GROMACS builds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2023Implementation: MPI CPU - Input: water_GMX50_bareDefault - DisabledSNC2SNC43691215SE +/- 0.38, N = 9SE +/- 0.07, N = 3SE +/- 0.04, N = 310.3810.4510.661. (CXX) g++ options: -O3

ASKAP

ASKAP is a set of benchmarks from the Australian SKA Pathfinder. The principal ASKAP benchmarks are the Hogbom Clean Benchmark (tHogbomClean) and Convolutional Resamping Benchmark (tConvolve) as well as some previous ASKAP benchmarks being included as well for OpenCL and CUDA execution of tConvolve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingSNC4SNC2Default - Disabled9K18K27K36K45KSE +/- 743.57, N = 15SE +/- 341.22, N = 3SE +/- 199.70, N = 335893.743138.943532.91. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

OpenBenchmarking.orgMpix/sec, More Is BetterASKAP 1.0Test: tConvolve MPI - DegriddingSNC4Default - DisabledSNC29K18K27K36K45KSE +/- 691.76, N = 15SE +/- 170.33, N = 3SE +/- 463.37, N = 334358.540198.340552.41. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

ClickHouse

ClickHouse is an open-source, high performance OLAP data management system. This test profile uses ClickHouse's standard benchmark recommendations per https://clickhouse.com/docs/en/operations/performance-test/ / https://github.com/ClickHouse/ClickBench/tree/main/clickhouse with the 100 million rows web analytics dataset. The reported value is the query processing time using the geometric mean of all separate queries performed as an aggregate. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunSNC4SNC2Default - Disabled110220330440550SE +/- 10.68, N = 12SE +/- 8.91, N = 12SE +/- 5.43, N = 3400.96444.12504.59MIN: 41.1 / MAX: 6000MIN: 48.62 / MAX: 7500MIN: 58.03 / MAX: 3750

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunSNC4SNC2Default - Disabled110220330440550SE +/- 10.89, N = 12SE +/- 8.80, N = 12SE +/- 6.17, N = 3397.01438.54490.52MIN: 39.66 / MAX: 6000MIN: 35.21 / MAX: 6666.67MIN: 34.27 / MAX: 4615.38

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, First Run / Cold CacheSNC4SNC2Default - Disabled100200300400500SE +/- 10.37, N = 12SE +/- 8.46, N = 12SE +/- 4.35, N = 3388.42417.30457.06MIN: 30.26 / MAX: 6000MIN: 32.68 / MAX: 6000MIN: 47.36 / MAX: 4285.71

Stockfish

This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 15Total TimeDefault - DisabledSNC2SNC460M120M180M240M300MSE +/- 2377868.67, N = 3SE +/- 3381815.04, N = 15SE +/- 6406046.35, N = 152873310972957807983002671481. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver

easyWave

The easyWave software allows simulating tsunami generation and propagation in the context of early warning systems. EasyWave supports making use of OpenMP for CPU multi-threading and there are also GPU ports available but not currently incorporated as part of this test profile. The easyWave tsunami generation software is run with one of the example/reference input files for measuring the CPU execution time. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 2400SNC4SNC2Default - Disabled20406080100SE +/- 3.38, N = 12SE +/- 0.49, N = 3SE +/- 0.47, N = 975.1759.2558.651. (CXX) g++ options: -O3 -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BettereasyWave r34Input: e2Asean Grid + BengkuluSept2007 Source - Time: 1200SNC4SNC2Default - Disabled714212835SE +/- 0.57, N = 12SE +/- 0.46, N = 15SE +/- 0.32, N = 1528.7425.4823.991. (CXX) g++ options: -O3 -fopenmp

LuxCoreRender

LuxCoreRender is an open-source 3D physically based renderer formerly known as LuxRender. LuxCoreRender supports CPU-based rendering as well as GPU acceleration via OpenCL, NVIDIA CUDA, and NVIDIA OptiX interfaces. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Rainbow Colors and Prism - Acceleration: CPUSNC2Default - DisabledSNC4816243240SE +/- 1.17, N = 15SE +/- 1.27, N = 15SE +/- 0.24, N = 331.8232.7534.72MIN: 18.52 / MAX: 35.42MIN: 17.73 / MAX: 35.6MIN: 34.26 / MAX: 35.1

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.CDefault - DisabledSNC2SNC42K4K6K8K10KSE +/- 60.80, N = 3SE +/- 257.16, N = 15SE +/- 304.30, N = 128869.849712.8110411.601. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.5

196 Results Shown

ASKAP:
  Hogbom Clean OpenMP
  tConvolve OpenMP - Gridding
OpenVINO
ASKAP
OpenVINO:
  Road Segmentation ADAS FP16 - CPU
  Person Detection FP16 - CPU
  Person Detection FP32 - CPU
  Face Detection FP16 - CPU
  Road Segmentation ADAS FP16-INT8 - CPU
  Face Detection FP16-INT8 - CPU
  Vehicle Detection FP16-INT8 - CPU
  Machine Translation EN To DE FP16 - CPU
  Face Detection Retail FP16 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
  Person Vehicle Bike Detection FP16 - CPU
LULESH
Timed Linux Kernel Compilation
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
Graph500:
  26:
    bfs max_TEPS
    bfs median_TEPS
OpenVINO:
  Vehicle Detection FP16 - CPU
  Age Gender Recognition Retail 0013 FP16 - CPU
Timed Linux Kernel Compilation
OpenVINO
CloverLeaf
OpenVINO
Timed LLVM Compilation
ASKAP
Graph500
OpenVKL
ASKAP
OpenVINO:
  Handwritten English Recognition FP16 - CPU:
    FPS
    ms
asmFish
Timed Node.js Compilation
OpenVINO
Timed Gem5 Compilation
OpenFOAM
Graph500
NAS Parallel Benchmarks
uvg266
John The Ripper
VVenC
OpenVINO:
  Person Detection FP16 - CPU
  Machine Translation EN To DE FP16 - CPU
uvg266
Xcompact3d Incompact3d
uvg266
OpenVINO
CloverLeaf
Embree
TensorFlow
John The Ripper
CloverLeaf
John The Ripper
Algebraic Multi-Grid Benchmark
VVenC
TensorFlow
SPECFEM3D
Quantum ESPRESSO
NAS Parallel Benchmarks
TensorFlow:
  CPU - 512 - ResNet-50
  CPU - 256 - ResNet-50
Rodinia
PyTorch
LuxCoreRender
Embree
PyTorch:
  CPU - 32 - ResNet-152
  CPU - 64 - ResNet-152
TensorFlow
PyTorch
Rodinia
NAS Parallel Benchmarks
Radiance Benchmark
LuxCoreRender
Rodinia
SPECFEM3D
OpenFOAM
PyTorch
VVenC
OpenVINO
NAS Parallel Benchmarks
Memcached
PyTorch:
  CPU - 64 - ResNet-50
  CPU - 32 - ResNet-50
NAS Parallel Benchmarks
John The Ripper
LuxCoreRender
PyTorch
John The Ripper
VVenC
Xcompact3d Incompact3d
Timed LLVM Compilation
SPECFEM3D:
  Homogeneous Halfspace
  Mount St. Helens
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU
  Face Detection Retail FP16-INT8 - CPU
GPAW
OpenVINO
uvg266:
  Bosphorus 1080p - Super Fast
  Bosphorus 1080p - Very Fast
SPECFEM3D
PyTorch
7-Zip Compression
PETSc
uvg266
QMCPACK
uvg266
7-Zip Compression
QuantLib
NAS Parallel Benchmarks
libxsmm
NAS Parallel Benchmarks
PostgreSQL:
  1000 - 1000 - Read Only
  1000 - 1000 - Read Only - Average Latency
Embree
Numpy Benchmark
Memcached
Timed CPython Compilation
LuxCoreRender
Blender
uvg266
Liquid-DSP
OpenVINO
libxsmm
Liquid-DSP
OSPRay Studio
OpenVINO
PostgreSQL
OSPRay Studio
Liquid-DSP
OpenRadioss
NAMD
libxsmm
uvg266
OpenVINO
PostgreSQL
OpenSSL
OSPRay Studio
OpenVINO
Liquid-DSP
OSPRay Studio
Memcached
OSPRay Studio
OpenVINO
OSPRay Studio
OpenVINO
OSPRay Studio
Blender
uvg266
libxsmm
NAS Parallel Benchmarks
OpenSSL:
  AES-128-GCM
  RSA4096
ACES DGEMM
Liquid-DSP:
  128 - 256 - 57
  64 - 256 - 32
Blender
OSPRay Studio
Blender
Liquid-DSP:
  192 - 256 - 57
  32 - 256 - 32
OpenVINO
OSPRay Studio
Liquid-DSP
OpenVINO
Liquid-DSP
OpenSSL
Rodinia
OpenSSL
Liquid-DSP:
  64 - 256 - 57
  32 - 256 - 512
OpenSSL
Rodinia
OpenSSL
Blender
OpenSSL
PyTorch:
  CPU - 64 - Efficientnet_v2_l
  CPU - 32 - Efficientnet_v2_l
  CPU - 16 - Efficientnet_v2_l
PostgreSQL:
  1000 - 1000 - Read Write - Average Latency
  1000 - 1000 - Read Write
  100 - 1000 - Read Write - Average Latency
  100 - 1000 - Read Write
GROMACS
ASKAP:
  tConvolve MPI - Gridding
  tConvolve MPI - Degridding
ClickHouse:
  100M Rows Hits Dataset, Third Run
  100M Rows Hits Dataset, Second Run
  100M Rows Hits Dataset, First Run / Cold Cache
Stockfish
easyWave:
  e2Asean Grid + BengkuluSept2007 Source - 2400
  e2Asean Grid + BengkuluSept2007 Source - 1200
LuxCoreRender
NAS Parallel Benchmarks

Default - Disabled

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 November 2023 00:02 by user phoronix.

SNC2

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 26 November 2023 16:53 by user phoronix.

SNC4

Processor: AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads), Motherboard: HP 8B24 (U65 Ver. 01.01.04 BIOS), Chipset: AMD Device 14a4, Memory: 128GB, Disk: 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1, Graphics: NVIDIA RTX A4000 16GB, Audio: NVIDIA GA104 HD Audio, Monitor: ASUS VP28U, Network: Realtek RTL8111/8168/8411

OS: Ubuntu 23.10, Kernel: 6.5.0-13-generic (x86_64), Desktop: GNOME Shell 45.0, Display Server: X Server 1.21.1.7, Display Driver: NVIDIA 535.129.03, OpenGL: 4.6.0, OpenCL: OpenCL 3.0 CUDA 12.2.147, Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 3840x2160

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --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: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa108105
OpenCL Notes: GPU Compute Cores: 6144
Python Notes: Python 3.11.6
Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 27 November 2023 11:47 by user phoronix.