AMD EPYC 9755 1P - SMT On/Off Comparison

AMD EPYC 9755 with SMT on/off comparison for a future article by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2410160-NE-TURINSMTO45
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
No Box Plots
On Line Graphs With Missing Data, Connect The Line Gaps

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Toggle/Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
SMT On - Default
September 16
  14 Hours, 1 Minute
SMT Off
September 18
  12 Hours, 29 Minutes
Invert Behavior (Only Show Selected Data)
  13 Hours, 15 Minutes
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

SMT On - Default

Processor: AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

SMT Off

Changed Processor to AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores).

Security Change: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC 9755 1P - SMT On/Off ComparisonOpenBenchmarking.orgPhoronix Test SuiteAMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads)AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores)AMD VOLCANO (RVOT1000D BIOS)AMD Device 153a12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC2 x 1920GB KIOXIA KCD8XPUG1T92ASPEEDBroadcom NetXtreme BCM5720 PCIeUbuntu 24.046.10.0-phx (x86_64)GCC 13.2.0ext41920x1200ProcessorsMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionAMD EPYC 9755 1P - SMT On/Off Comparison BenchmarksSystem Logs- Transparent Huge Pages: madvise- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110 - OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)- Python 3.12.2- SMT On - Default: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected - SMT Off: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

SMT On - Default vs. SMT Off ComparisonPhoronix Test SuiteBaseline+52.6%+52.6%+105.2%+105.2%+157.8%+157.8%165.3%129.3%110%108.7%107.3%105.9%83.7%83%80.6%76.7%71.1%69.5%69.1%69.1%48.9%40.7%38.6%32.5%30.2%27.7%26.5%25.9%21.1%19.7%17.9%17.5%15%13.9%13.9%11.4%11.1%11%10.2%10%8.8%7.9%7.3%7.2%7.2%7.1%7.1%7%6.9%6.8%6.5%5%5%4.5%4.4%4.3%4.1%4%3.9%3.8%3.7%3.7%2.9%2.9%2.6%2.5%2.4%2.4%2.1%2.1%V.P.M210.2%CaffeNet 12-int8 - CPU - Parallel173.8%P.D.F - CPUR.v.1.i - CPU - Parallel144.8%P.P.B.T.TR.S.A.F.I - CPUA.G.R.R.0.F.I - CPUF.D.F.I - CPUW.P.D.F.I - CPUArcFace ResNet-100 - CPU - Parallel104.3%bertsquad-12 - CPU - Parallel97.4%yolov4 - CPU - Parallel91.6%Read While Writing85.6%V.D.F.I - CPUF.D.R.F.I - CPUCPU - 1 - GoogLeNetM.T.E.T.D.F - CPUP.V.B.D.F - CPUCPU - 1 - ResNet-50H.E.R.F.I - CPUP.R.I.R.F - CPURead While Writing65.1%D.R56.3%256 - 256 - 3254.9%P.P.B.T.T51.1%1:10050.9%fcn-resnet101-11 - CPU - Parallel50.8%Pathtracer ISPC - Crown50.2%Pathtracer ISPC - Asian Dragon48.5%Pathtracer ISPC - Asian Dragon Obj48.3%S.F.P.R48.2%WPA PSK44.9%3 - 4K - 32 - Path Tracer - CPU43.9%Time To Solve42.4%leblancbigN.S.P.L.F - CPUBlowfish36.8%bcrypt36.7%ChaCha20-Poly130535%ChaCha2034.2%Chess Benchmark32.6%P.D.F - CPUN.S.P.L.F - CPU32.4%Bosphorus 4K - Slow32%CoreMark Size 666 - I.P.S31.4%Orange Juice - CPU31%Bosphorus 4K - Medium30.3%allmodconfigSHA25630.1%LuxCore Benchmark - CPU29.6%3 - 4K - 1 - Path Tracer - CPU29%3 - 4K - 16 - Path Tracer - CPU28.8%Bosphorus 4K - Slow28.4%1 - 4K - 1 - Path Tracer - CPU27.9%d.M.M.S - Mesh Time1 - 4K - 32 - Path Tracer - CPU27.4%1 - 4K - 16 - Path Tracer - CPU27.4%Bosphorus 4K - Medium27.2%v.I26.9%Rhodopsin ProteinA.w.3.5.Agravity_spheres_volume/dim_512/pathtracer/real_time25.5%Pabellon Barcelona - CPU-Only24.7%Barbershop - CPU-Only23.9%P.R.I.R.F - CPU23.8%Fishy Cat - CPU-Only22.9%Junkshop - CPU-Only22.5%Classroom - CPU-Only22.4%DLSC - CPU22%256 - 256 - 5721.5%F.1.0.R.a.m.i.C21.1%1BEnhanced21%100 - 1000 - Read Only20.6%100 - 1000 - Read Only - Average Latency20.5%Noise-Gaussian20.4%BMW27 - CPU-Only19.8%CPU - 64 - GoogLeNetGhostRider - 1M19.3%P.V.B.D.F - CPU19%H.E.R.F.I - CPU18%d.S.M.S - Mesh Time500MCompression Rating16.9%F.D.R.F.I - CPU16%LU.CV.D.F.I - CPU14.9%RSA409614.5%256 - 256 - 51214.4%Disney MaterialM.T.E.T.D.F - CPU13.3%1.R.H.D.T.Rparticle_volume/scivis/real_time11.3%particle_volume/ao/real_time11.2%CPU - 64 - ResNet-501.R.H.D.F.R.C.C1.R.H.D.S.RMulti-Threaded10.1%defconfigD.B.s - CPUA.G.R.R.0.F.I - CPU8.5%Exhaustive8.3%Very Thorough7.9%Bosphorus 4K - FasterF.R.C.R.5.F.i - CPU - Parallel7.9%Thorough7.6%MG.Cd.S.M.S - Execution TimesedovbigPreset 8 - Bosphorus 4KBosphorus 4K - FastCPU - 64 - AlexNetPreset 13 - Bosphorus 4KCPU - 1 - AlexNetSwirl6.6%Preset 12 - Bosphorus 4Kclover_bm64_shortCPU - 256 - GoogLeNetclover_bm16C.P.D.TRand ReadTime To CompileSHA5124%R.S.A.F.I - CPURand ReadAES-256-GCM3.9%Time To CompileF.D.F.I - CPUTime To CompileBosphorus 4K - Very Fast3.5%tConvolve MT - Gridding3.1%S.w.1.0.6.ACPU - 256 - ResNet-50Carbon NanotubeSP.CCPU - 512 - GoogLeNetd.M.M.S - Execution TimeNinja2.4%tConvolve MPI - Degridding2.2%Time To Compile2.2%CPU - 1 - ResNet-152Preset 4 - Bosphorus 4KF.R.C.R.5.F.i - CPU - Parallel7.9%CaffeNet 12-int8 - CPU - Parallel174%R.v.1.i - CPU - Parallel144.8%ArcFace ResNet-100 - CPU - Parallel104.3%bertsquad-12 - CPU - Parallel97.4%fcn-resnet101-11 - CPU - Parallel50.7%yolov4 - CPU - Parallel91.6%BRL-CADONNX RuntimeOpenVINOONNX RuntimesrsRAN ProjectOpenVINOOpenVINOOpenVINOOpenVINOONNX RuntimeONNX RuntimeONNX RuntimeSpeedbOpenVINOOpenVINOTensorFlowOpenVINOOpenVINOTensorFlowOpenVINOOpenVINORocksDB7-Zip CompressionLiquid-DSPsrsRAN ProjectMemcachedONNX RuntimeEmbreeAircrack-ngEmbreeEmbreeACES DGEMMJohn The RipperOSPRay Studiom-queensPennantOpenVINOJohn The RipperJohn The RipperOpenSSLOpenSSLStockfishOpenVINOOpenVINOuvg266CoremarkLuxCoreRenderuvg266Timed Linux Kernel CompilationOpenSSLLuxCoreRenderOSPRay StudioOSPRay StudioKvazaarOSPRay StudioOpenFOAMOSPRay StudioOSPRay StudioKvazaarOpenVKLLAMMPS Molecular Dynamics SimulatorNAMDOSPRayBlenderBlenderOpenVINOBlenderBlenderBlenderLuxCoreRenderLiquid-DSPParallel BZIP2 CompressionY-CruncherGraphicsMagickPostgreSQLPostgreSQLGraphicsMagickBlenderTensorFlowXmrigOpenVINOOpenVINOOpenFOAMY-Cruncher7-Zip CompressionOpenVINONAS Parallel BenchmarksOpenVINOOpenSSLLiquid-DSPAppleseedLULESHOpenVINOClickHouseOSPRayOSPRayTensorFlowClickHouseClickHouseQuantLibTimed Linux Kernel CompilationoneDNNOpenVINOASTC EncoderASTC EncoderVVenCONNX RuntimeASTC EncoderNAS Parallel BenchmarksOpenFOAMPennantSVT-AV1VVenCTensorFlowSVT-AV1TensorFlowGraphicsMagickSVT-AV1CloverLeafTensorFlowCloverLeafOpenRadiossRocksDBTimed Mesa CompilationOpenSSLOpenVINOSpeedbOpenSSLTimed Gem5 CompilationOpenVINOTimed Godot Game Engine CompilationKvazaarASKAPNAMDTensorFlowGPAWNAS Parallel BenchmarksTensorFlowOpenFOAMTimed LLVM CompilationASKAPTimed Node.js CompilationPyTorchSVT-AV1ONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeONNX RuntimeSMT On - DefaultSMT Off

AMD EPYC 9755 1P - SMT On/Off Comparisonbrl-cad: VGR Performance Metriconnx: CaffeNet 12-int8 - CPU - Parallelopenvino: Person Detection FP16 - CPUonnx: ResNet50 v1-12-int8 - CPU - Parallelopenvino: Road Segmentation ADAS FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUonnx: ArcFace ResNet-100 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: yolov4 - CPU - Parallelopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Face Detection Retail FP16-INT8 - CPUtensorflow: CPU - 1 - GoogLeNetopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUtensorflow: CPU - 1 - ResNet-50openvino: Handwritten English Recognition FP16-INT8 - CPUopenvino: Person Re-Identification Retail FP16 - CPUrocksdb: Read While Writingcompress-7zip: Decompression Ratingliquid-dsp: 256 - 256 - 32srsran: PUSCH Processor Benchmark, Throughput Totalmemcached: 1:100onnx: fcn-resnet101-11 - CPU - Parallelembree: Pathtracer ISPC - Crownaircrack-ng: embree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Asian Dragon Objmt-dgemm: Sustained Floating-Point Ratejohn-the-ripper: WPA PSKospray-studio: 3 - 4K - 32 - Path Tracer - CPUm-queens: Time To Solveopenvino: Noise Suppression Poconet-Like FP16 - CPUjohn-the-ripper: Blowfishjohn-the-ripper: bcryptopenssl: ChaCha20-Poly1305openssl: ChaCha20openvino: Person Detection FP16 - CPUopenvino: Noise Suppression Poconet-Like FP16 - CPUuvg266: Bosphorus 4K - Slowcoremark: CoreMark Size 666 - Iterations Per Seconduvg266: Bosphorus 4K - Mediumbuild-linux-kernel: allmodconfigopenssl: SHA256luxcorerender: LuxCore Benchmark - CPUospray-studio: 3 - 4K - 1 - Path Tracer - CPUospray-studio: 3 - 4K - 16 - Path Tracer - CPUkvazaar: Bosphorus 4K - Slowospray-studio: 1 - 4K - 1 - Path Tracer - CPUopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeospray-studio: 1 - 4K - 32 - Path Tracer - CPUospray-studio: 1 - 4K - 16 - Path Tracer - CPUkvazaar: Bosphorus 4K - Mediumopenvkl: vklBenchmarkCPU ISPClammps: Rhodopsin Proteinnamd: ATPase with 327,506 Atomsospray: gravity_spheres_volume/dim_512/pathtracer/real_timeblender: Pabellon Barcelona - CPU-Onlyblender: Barbershop - CPU-Onlyopenvino: Person Re-Identification Retail FP16 - CPUblender: Fishy Cat - CPU-Onlyblender: Junkshop - CPU-Onlyblender: Classroom - CPU-Onlyliquid-dsp: 256 - 256 - 57compress-pbzip2: FreeBSD-13.0-RELEASE-amd64-memstick.img Compressiony-cruncher: 1Bgraphics-magick: Enhancedpgbench: 100 - 1000 - Read Onlypgbench: 100 - 1000 - Read Only - Average Latencygraphics-magick: Noise-Gaussianblender: BMW27 - CPU-Onlytensorflow: CPU - 64 - GoogLeNetopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Handwritten English Recognition FP16-INT8 - CPUopenfoam: drivaerFastback, Small Mesh Size - Mesh Timey-cruncher: 500Mcompress-7zip: Compression Ratingopenvino: Face Detection Retail FP16-INT8 - CPUnpb: LU.Copenvino: Vehicle Detection FP16-INT8 - CPUopenssl: RSA4096liquid-dsp: 256 - 256 - 512appleseed: Disney Materiallulesh: openvino: Machine Translation EN To DE FP16 - CPUclickhouse: 100M Rows Hits Dataset, Third Runospray: particle_volume/scivis/real_timeospray: particle_volume/ao/real_timetensorflow: CPU - 64 - ResNet-50clickhouse: 100M Rows Hits Dataset, First Run / Cold Cacheclickhouse: 100M Rows Hits Dataset, Second Runquantlib: Multi-Threadedbuild-linux-kernel: defconfigonednn: Deconvolution Batch shapes_3d - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUastcenc: Exhaustiveastcenc: Very Thoroughvvenc: Bosphorus 4K - Fasteronnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelastcenc: Thoroughnpb: MG.Copenfoam: drivaerFastback, Small Mesh Size - Execution Timesvt-av1: Preset 8 - Bosphorus 4Kvvenc: Bosphorus 4K - Fasttensorflow: CPU - 64 - AlexNettensorflow: CPU - 1 - AlexNetgraphics-magick: Swirlsvt-av1: Preset 12 - Bosphorus 4Kcloverleaf: clover_bm64_shorttensorflow: CPU - 256 - GoogLeNetcloverleaf: clover_bm16openradioss: Cell Phone Drop Testrocksdb: Rand Readbuild-mesa: Time To Compileopenssl: SHA512openvino: Road Segmentation ADAS FP16-INT8 - CPUspeedb: Rand Readopenssl: AES-256-GCMbuild-gem5: Time To Compileopenvino: Face Detection FP16-INT8 - CPUbuild-godot: Time To Compilekvazaar: Bosphorus 4K - Very Fastaskap: tConvolve MT - Griddingnamd: STMV with 1,066,628 Atomstensorflow: CPU - 256 - ResNet-50gpaw: Carbon Nanotubenpb: SP.Ctensorflow: CPU - 512 - GoogLeNetopenfoam: drivaerFastback, Medium Mesh Size - Execution Timebuild-llvm: Ninjaaskap: tConvolve MPI - Degriddingbuild-nodejs: Time To Compilepytorch: CPU - 1 - ResNet-152svt-av1: Preset 4 - Bosphorus 4Kpytorch: CPU - 512 - ResNet-50tensorflow: CPU - 512 - ResNet-50pytorch: CPU - 1 - ResNet-50tensorflow: CPU - 256 - AlexNetastcenc: Mediumlammps: 20k Atomsaskap: tConvolve MPI - Griddingpytorch: CPU - 64 - ResNet-50openradioss: Chrysler Neon 1Mnpb: IS.Damg: pytorch: CPU - 256 - ResNet-152incompact3d: X3D-benchmarking input.i3doidn: RTLightmap.hdr.4096x4096 - CPU-Onlypytorch: CPU - 512 - ResNet-152nwchem: C240 Buckyballopenssl: AES-128-GCMgromacs: MPI CPU - water_GMX50_barebuild-imagemagick: Time To Compiletensorflow: CPU - 512 - AlexNetoidn: RT.ldr_alb_nrm.3840x2160 - CPU-Onlyopenradioss: INIVOL and Fluid Structure Interaction Drop Containerpytorch: CPU - 64 - ResNet-152oidn: RT.hdr_alb_nrm.3840x2160 - CPU-Onlyhpcg: 144 144 144 - 60wrf: conus 2.5kmpytorch: CPU - 256 - ResNet-50openvino: Weld Porosity Detection FP16-INT8 - CPUstockfish: Chess Benchmarkxmrig: GhostRider - 1Monnx: Faster R-CNN R-50-FPN-int8 - CPU - Parallelonnx: CaffeNet 12-int8 - CPU - Parallelonnx: ResNet50 v1-12-int8 - CPU - Parallelonnx: ArcFace ResNet-100 - CPU - Parallelonnx: bertsquad-12 - CPU - Parallelonnx: fcn-resnet101-11 - CPU - Parallelonnx: yolov4 - CPU - Parallelsrsran: PDSCH Processor Benchmark, Throughput Totalsvt-av1: Preset 13 - Bosphorus 4Kluxcorerender: Orange Juice - CPUluxcorerender: DLSC - CPUpennant: sedovbigpennant: leblancbigspeedb: Read While WritingSMT On - DefaultSMT Off5899055969.28187.14223.47519.360.48329.536.6141.205224.539114.55115.623.8822.6957.577.227.1126.674.481706302184673684947333337954.213316660.103.22956179.4494133016.391223.2053191.783956.4088901361333239815.49210.733230103230008070098414271186359294450733.8010557.1639.146042366.34304743.85201.75518666039331313.967531198253.42639120.3457203791015453.95365455.79114.2449355.176229.7586.6213949.8912.5012.7124.0081519000000.9348968.17345554186720.1853139.46361.388730.884774.3321.441464.87790815931655.57385558.5311232.262755042.3285546666730.69244137645.9731109.75724.6454.395854.3927137.62698.12729.56465436.823.3440.513417190777.839.657615.719523.74344.9646110.0383167026.9320.597089118.1639.8101086.4825.93851281.58922.09659.11178.9317.8778689658013.669723597672403287.438221028281837765850747128.132193.8083.29396.8116464.14.62277203.3323.822194853.91819.05160.3737888.89370762.8109.56120.2411.27543.83246.2451.202271.95701.731567.77674093.343.6877.268647.62317708200017.42199.8445892.8517.491326.2200736535147022.7299.8682665.925.8573.6717.465.8463.67085574.36343.6118679.3630734392319873.022.23771.029984.4739224.268340.7506309.75768.719619454.1271.92432.0220.944.3936062.761260186878971901425354.04832.8491.30089.220.23158.973.2120.170712.43227.593763.062.1240.9832.584.2212.0515.772.651033799354163554825000005264.28825111.212.14216119.5087198070.058150.3383129.310138.059183939777345197.8237.74236094236198597729532223884300273620972.457974.9629.664598401.13564033.66155.00914342058920310.779711543741.6081794.263759259661293442.41288070.57517.9351443.973537.11107.3411265.5315.3615.5729.3767110666671.1320146.75037644919840.22326011.33432.497335.764044.5618.1854834.14977665827294.20443291.719772.422407045.5249703333326.94235842873.218979.20806.9948.884148.9329152.83774.87804.06422695.221.2220.471717175803.478.919214.566625.61841.6782102.2741179200.0819.215842126.60610.5031162.5027.70798299.97421.03691.93171.2217.1282035783613.130695460463903419.618541807011769373865300123.382201.0180.33093.5415967.94.75581209.1623.210199661.62839.05156.5799190.98969207.5112.00320.6711.51243.01250.8252.142234.75691.992168.69574970.243.1976.428556.57314554433317.28201.2708032.8317.591319.6199918456604322.8219.9042675.125.8373.4417.415.8363.77615583.47643.6818690.3223169900416656.323.99212.8222910.951849.590980.4394466.909131.69544608.9290.63924.4417.164.1003391.96198910067442OpenBenchmarking.org

BRL-CAD

BRL-CAD is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.38.2VGR Performance MetricSMT OffSMT On - Default1.3M2.6M3.9M5.2M6.5M190142558990551. (CXX) g++ options: -std=c++17 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -ltcl8.6 -lnetpbm -lregex_brl -lz_brl -lassimp -ldl -lm -ltk8.6
OpenBenchmarking.orgVGR Performance Metric Per Watt, More Is BetterBRL-CAD 7.38.2VGR Performance MetricSMT OffSMT On - Default11K22K33K44K55K4541.7650873.19
MinAvgMaxSMT Off44.7418.7497.0SMT On - Default44.6116.0244.3OpenBenchmarking.orgWatts, Fewer Is BetterBRL-CAD 7.38.2CPU Power Consumption Monitor130260390520650

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelSMT OffSMT On - Default2004006008001000SE +/- 1.56, N = 3SE +/- 1.72, N = 3354.05969.281. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: CaffeNet 12-int8 - Device: CPU - Executor: ParallelSMT OffSMT On - Default0.6351.271.9052.543.175SE +/- 0.01243, N = 3SE +/- 0.00186, N = 32.822291.029981. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxSMT Off44.4314.1340.6SMT On - Default45.1353.6377.0OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor100200300400500

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 2024.0Model: Person Detection FP16 - Device: CPUSMT OffSMT On - Default20406080100SE +/- 0.20, N = 3SE +/- 0.54, N = 1532.8487.14MIN: 26.14 / MAX: 69.48MIN: 35.35 / MAX: 200.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.4414.2458.7SMT On - Default44.8386.6442.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor120240360480600

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelSMT OffSMT On - Default50100150200250SE +/- 0.18, N = 3SE +/- 1.63, N = 391.30223.481. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ResNet50 v1-12-int8 - Device: CPU - Executor: ParallelSMT OffSMT On - Default3691215SE +/- 0.02184, N = 3SE +/- 0.03295, N = 310.951804.473921. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxSMT Off44.6314.7341.5SMT On - Default44.8345.8372.3OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor100200300400500

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 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUSMT OffSMT On - Default510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 39.2219.36MIN: 7.78 / MAX: 20.73MIN: 9.99 / MAX: 44.411. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.6367.2402.0SMT On - Default44.8372.2403.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor110220330440550

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUSMT OffSMT On - Default0.1080.2160.3240.4320.54SE +/- 0.00, N = 3SE +/- 0.01, N = 30.230.48MIN: 0.13 / MAX: 19.9MIN: 0.13 / MAX: 26.241. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.9325.1358.1SMT On - Default45.0337.4363.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor100200300400500

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection FP16-INT8 - Device: CPUSMT OffSMT On - Default70140210280350SE +/- 0.05, N = 3SE +/- 0.54, N = 3158.97329.53MIN: 147.03 / MAX: 169.16MIN: 165.13 / MAX: 354.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.4352.0388.7SMT On - Default45.1364.9401.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor110220330440550

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUSMT OffSMT On - Default246810SE +/- 0.00, N = 3SE +/- 0.01, N = 33.216.61MIN: 2.13 / MAX: 11.62MIN: 2.25 / MAX: 28.151. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.7345.7374.9SMT On - Default44.8363.2388.4OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor100200300400500

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelSMT OffSMT On - Default918273645SE +/- 0.26, N = 3SE +/- 0.20, N = 320.1741.211. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: ArcFace ResNet-100 - Device: CPU - Executor: ParallelSMT OffSMT On - Default1122334455SE +/- 0.62, N = 3SE +/- 0.12, N = 349.5924.271. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxSMT Off44.5333.6363.0SMT On - Default45.2370.7396.5OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor110220330440550

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelSMT OffSMT On - Default612182430SE +/- 0.08, N = 3SE +/- 0.13, N = 312.4324.541. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: bertsquad-12 - Device: CPU - Executor: ParallelSMT OffSMT On - Default20406080100SE +/- 0.50, N = 3SE +/- 0.21, N = 380.4440.751. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxSMT Off44.4334.3363.9SMT On - Default44.8374.7402.7OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor110220330440550

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelSMT OffSMT On - Default48121620SE +/- 0.05138, N = 3SE +/- 0.02257, N = 37.5937614.551101. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: yolov4 - Device: CPU - Executor: ParallelSMT OffSMT On - Default306090120150SE +/- 0.89, N = 3SE +/- 0.11, N = 3131.7068.721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxSMT Off44.4332.3360.5SMT On - Default45.2367.6394.2OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor110220330440550

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 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUSMT OffSMT On - Default1.26452.5293.79355.0586.3225SE +/- 0.00, N = 3SE +/- 0.00, N = 33.065.62MIN: 1.95 / MAX: 14.46MIN: 2.01 / MAX: 29.211. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.7343.1373.1SMT On - Default44.8395.5423.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor110220330440550

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUSMT OffSMT On - Default0.8731.7462.6193.4924.365SE +/- 0.00, N = 3SE +/- 0.00, N = 32.123.88MIN: 1.56 / MAX: 9.64MIN: 1.55 / MAX: 24.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.5351.5382.3SMT On - Default45.1382.7411.5OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor110220330440550

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 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNetSMT OffSMT On - Default918273645SE +/- 0.16, N = 7SE +/- 0.16, N = 1540.9822.69
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: GoogLeNetSMT OffSMT On - Default0.07070.14140.21210.28280.35350.3140.141
MinAvgMaxSMT Off44.2130.7283.8SMT On - Default44.7161.1285.5OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor70140210280350

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 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUSMT OffSMT On - Default1326395265SE +/- 0.08, N = 3SE +/- 0.16, N = 332.5857.57MIN: 22.75 / MAX: 50.14MIN: 34.99 / MAX: 106.021. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.8399.7448.0SMT On - Default44.8437.1487.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUSMT OffSMT On - Default246810SE +/- 0.01, N = 3SE +/- 0.01, N = 34.227.22MIN: 3.09 / MAX: 10.37MIN: 4.48 / MAX: 26.341. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.4312.3342.0SMT On - Default45.2355.7388.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor100200300400500

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 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50SMT OffSMT On - Default3691215SE +/- 0.01, N = 4SE +/- 0.01, N = 312.057.11
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: ResNet-50SMT OffSMT On - Default0.01510.03020.04530.06040.07550.0670.035
MinAvgMaxSMT Off44.1179.0267.4SMT On - Default44.6202.2266.1OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor70140210280350

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 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUSMT OffSMT On - Default612182430SE +/- 0.04, N = 3SE +/- 0.03, N = 315.7726.67MIN: 14.16 / MAX: 30.7MIN: 15.22 / MAX: 47.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.4396.4440.1SMT On - Default44.8434.0466.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUSMT OffSMT On - Default1.0082.0163.0244.0325.04SE +/- 0.00, N = 3SE +/- 0.00, N = 32.654.48MIN: 1.8 / MAX: 9.28MIN: 1.99 / MAX: 22.311. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off45.2369.6402.2SMT On - Default45.1412.9447.7OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor120240360480600

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Read While WritingSMT OffSMT On - Default4M8M12M16M20MSE +/- 37116.95, N = 3SE +/- 241581.30, N = 1510337993170630211. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Read While WritingSMT OffSMT On - Default8K16K24K32K40K24323.0139264.11
MinAvgMaxSMT Off44.8425.0468.0SMT On - Default44.8434.6500.1OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor130260390520650

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 RatingSMT OffSMT On - Default200K400K600K800K1000KSE +/- 100.03, N = 3SE +/- 276.36, N = 35416358467361. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
OpenBenchmarking.orgMIPS Per Watt, More Is Better7-Zip Compression 22.01Test: Decompression RatingSMT OffSMT On - Default50010001500200025001521.542269.16
MinAvgMaxSMT Off45.0356.0473.9SMT On - Default44.7373.2482.8OpenBenchmarking.orgWatts, Fewer Is Better7-Zip Compression 22.01CPU Power Consumption Monitor120240360480600

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: 256 - Buffer Length: 256 - Filter Length: 32SMT OffSMT On - Default2000M4000M6000M8000M10000MSE +/- 4427565.17, N = 3SE +/- 14339494.80, N = 3548250000084947333331. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 32SMT OffSMT On - Default4M8M12M16M20M12821155.6920115931.63
MinAvgMaxSMT Off44.6427.6491.9SMT On - Default45.2422.3487.6OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor130260390520650

srsRAN Project

srsRAN Project is a complete ORAN-native 5G RAN solution created by Software Radio Systems (SRS). The srsRAN Project radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalSMT OffSMT On - Default2K4K6K8K10KSE +/- 0.03, N = 3SE +/- 0.32, N = 35264.27954.2MIN: 3398.1MIN: 5432.6 / MAX: 7954.61. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PUSCH Processor Benchmark, Throughput TotalSMT OffSMT On - Default61218243019.4725.99
MinAvgMaxSMT Off44.5270.3353.9SMT On - Default44.8306.1405.8OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption Monitor110220330440550

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: 1:100SMT OffSMT On - Default3M6M9M12M15MSE +/- 110048.07, N = 4SE +/- 136953.60, N = 38825111.2113316660.101. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
OpenBenchmarking.orgOps/sec Per Watt, More Is BetterMemcached 1.6.19Set To Get Ratio: 1:100SMT OffSMT On - Default8K16K24K32K40K29665.3037790.62
MinAvgMaxSMT Off44.5297.5348.5SMT On - Default44.5352.4409.0OpenBenchmarking.orgWatts, Fewer Is BetterMemcached 1.6.19CPU Power Consumption Monitor110220330440550

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelSMT OffSMT On - Default0.72671.45342.18012.90683.6335SE +/- 0.02146, N = 3SE +/- 0.04511, N = 32.142163.229561. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: fcn-resnet101-11 - Device: CPU - Executor: ParallelSMT OffSMT On - Default100200300400500SE +/- 4.66, N = 3SE +/- 4.35, N = 3466.91309.761. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxSMT Off44.3326.8358.6SMT On - Default44.7342.4367.7OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor100200300400500

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: CrownSMT OffSMT On - Default4080120160200SE +/- 0.04, N = 6SE +/- 0.11, N = 8119.51179.45MIN: 117.52 / MAX: 122.07MIN: 175.01 / MAX: 186.64
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: CrownSMT OffSMT On - Default0.15750.3150.47250.630.78750.3980.700
MinAvgMaxSMT Off44.5299.9485.8SMT On - Default44.5256.2473.6OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor130260390520650

Aircrack-ng

Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.7SMT OffSMT On - Default40K80K120K160K200KSE +/- 1876.30, N = 3SE +/- 329.61, N = 3198070.06133016.391. (CXX) g++ options: -std=gnu++17 -O3 -fvisibility=hidden -fcommon -rdynamic -lnl-3 -lnl-genl-3 -lpcre -lsqlite3 -lpthread -lz -lssl -lcrypto -lhwloc -ldl -lm -pthread
OpenBenchmarking.orgk/s Per Watt, More Is BetterAircrack-ng 1.7SMT OffSMT On - Default110220330440550531.27407.19
MinAvgMaxSMT Off44.4372.8437.8SMT On - Default44.6326.7379.8OpenBenchmarking.orgWatts, Fewer Is BetterAircrack-ng 1.7CPU Power Consumption Monitor110220330440550

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 DragonSMT OffSMT On - Default50100150200250SE +/- 0.05, N = 7SE +/- 0.06, N = 8150.34223.21MIN: 148.74 / MAX: 152.35MIN: 219.93 / MAX: 227.73
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian DragonSMT OffSMT On - Default0.21710.43420.65130.86841.08550.5470.965
MinAvgMaxSMT Off44.7274.9474.7SMT On - Default44.7231.4467.8OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjSMT OffSMT On - Default4080120160200SE +/- 0.06, N = 4SE +/- 0.14, N = 5129.31191.78MIN: 127.88 / MAX: 131.29MIN: 188.36 / MAX: 196.2
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterEmbree 4.3Binary: Pathtracer ISPC - Model: Asian Dragon ObjSMT OffSMT On - Default0.24410.48820.73230.97641.22050.6091.085
MinAvgMaxSMT Off45.0212.2472.4SMT On - Default44.6176.7465.2OpenBenchmarking.orgWatts, Fewer Is BetterEmbree 4.3CPU Power Consumption Monitor120240360480600

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 RateSMT OffSMT On - Default1326395265SE +/- 0.02, N = 7SE +/- 0.18, N = 838.0656.411. (CC) gcc options: -O3 -march=native -fopenmp
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateSMT OffSMT On - Default0.05540.11080.16620.22160.2770.1420.246
MinAvgMaxSMT Off44.6268.6428.0SMT On - Default44.6229.3419.5OpenBenchmarking.orgWatts, Fewer Is BetterACES DGEMM 1.0CPU Power Consumption Monitor110220330440550

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 PSKSMT OffSMT On - Default300K600K900K1200K1500KSE +/- 341.06, N = 3SE +/- 1201.85, N = 393977713613331. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: WPA PSKSMT OffSMT On - Default70014002100280035002132.193396.83
MinAvgMaxSMT Off22.9440.8504.4SMT On - Default44.9400.8455.8OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor130260390520650

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 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUSMT OffSMT On - Default7K14K21K28K35KSE +/- 23.25, N = 3SE +/- 32.92, N = 33451923981
MinAvgMaxSMT Off45.0344.5478.2SMT On - Default44.7395.1468.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor120240360480600

m-queens

A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveSMT OffSMT On - Default246810SE +/- 0.025, N = 6SE +/- 0.025, N = 77.8235.4921. (CXX) g++ options: -fopenmp -O2 -march=native
MinAvgMaxSMT Off44.9307.7461.7SMT On - Default44.7265.1441.7OpenBenchmarking.orgWatts, Fewer Is Betterm-queens 1.2CPU Power Consumption Monitor120240360480600

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 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUSMT OffSMT On - Default3691215SE +/- 0.03, N = 3SE +/- 0.05, N = 37.7410.73MIN: 5.2 / MAX: 16.54MIN: 6.4 / MAX: 32.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
MinAvgMaxSMT Off44.8330.7367.7SMT On - Default44.9397.2438.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenVINO 2024.0CPU Power Consumption Monitor120240360480600

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: BlowfishSMT OffSMT On - Default70K140K210K280K350KSE +/- 92.96, N = 3SE +/- 53.35, N = 32360943230101. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: BlowfishSMT OffSMT On - Default2004006008001000536.62778.22
MinAvgMaxSMT Off44.4440.0499.5SMT On - Default44.6415.1468.2EPYC 975544.7412.9469.2OpenBenchmarking.orgWatts, Fewer Is BetterJohn The Ripper 2023.03.14CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 2023.03.14Test: bcryptSMT OffSMT On - Default70K140K210K280K350KSE +/- 96.62, N = 3SE +/- 45.32, N = 32361983230001. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
OpenBenchmarking.orgReal C/S Per Watt, More Is BetterJohn The Ripper 2023.03.14Test: bcryptSMT OffSMT On - Default2004006008001000541.58782.32

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 3.3Algorithm: ChaCha20-Poly1305SMT OffSMT On - Default200000M400000M600000M800000M1000000MSE +/- 501642086.81, N = 3SE +/- 89801965.81, N = 35977295322238070098414271. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: ChaCha20-Poly1305SMT OffSMT On - Default400M800M1200M1600M2000M1266724084.661746071268.12
MinAvgMaxSMT Off44.5471.9506.0SMT On - Default44.7462.2499.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.3Algorithm: ChaCha20SMT OffSMT On - Default300000M600000M900000M1200000M1500000MSE +/- 277988469.18, N = 3SE +/- 507390352.95, N = 388430027362011863592944501. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: ChaCha20SMT OffSMT On - Default500M1000M1500M2000M2500M1930320322.622532659749.39
MinAvgMaxSMT Off44.4458.1504.5SMT On - Default45.0468.4501.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor130260390520650

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 2024.0Model: Person Detection FP16 - Device: CPUSMT OffSMT On - Default2004006008001000SE +/- 5.91, N = 3SE +/- 4.77, N = 15972.45733.801. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Noise Suppression Poconet-Like FP16 - Device: CPUSMT OffSMT On - Default2K4K6K8K10KSE +/- 33.26, N = 3SE +/- 33.49, N = 37974.9610557.161. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -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: SlowSMT OffSMT On - Default918273645SE +/- 0.02, N = 3SE +/- 0.09, N = 429.6639.14
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: SlowSMT OffSMT On - Default0.02770.05540.08310.11080.13850.1000.123
MinAvgMaxSMT Off44.5296.9372.9SMT On - Default45.3318.4408.0OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor110220330440550

Coremark

This is a test of EEMBC CoreMark processor benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondSMT OffSMT On - Default1.3M2.6M3.9M5.2M6.5MSE +/- 8927.75, N = 3SE +/- 10789.95, N = 34598401.146042366.341. (CC) gcc options: -O2 -lrt" -lrt
OpenBenchmarking.orgIterations/Sec Per Watt, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondSMT OffSMT On - Default3K6K9K12K15K10891.6614585.74
MinAvgMaxSMT Off44.3422.2478.4SMT On - Default44.7414.3479.8OpenBenchmarking.orgWatts, Fewer Is BetterCoremark 1.0CPU Power Consumption Monitor120240360480600

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: MediumSMT OffSMT On - Default1020304050SE +/- 0.03, N = 3SE +/- 0.04, N = 433.6643.85
OpenBenchmarking.orgFrames Per Second Per Watt, More Is Betteruvg266 0.4.1Video Input: Bosphorus 4K - Video Preset: MediumSMT OffSMT On - Default0.03150.0630.09450.1260.15750.1140.140
MinAvgMaxSMT Off44.6294.7372.8SMT On - Default44.6313.9407.2OpenBenchmarking.orgWatts, Fewer Is Betteruvg266 0.4.1CPU Power Consumption Monitor110220330440550

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 6.8Build: allmodconfigSMT OffSMT On - Default4080120160200SE +/- 0.37, N = 3SE +/- 0.88, N = 3155.01201.76
MinAvgMaxSMT Off44.1386.0483.2SMT On - Default44.4383.8473.4OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8CPU Power Consumption Monitor120240360480600

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 3.3Algorithm: SHA256SMT OffSMT On - Default40000M80000M120000M160000M200000MSE +/- 126118866.35, N = 3SE +/- 76407988.26, N = 31434205892031866603933131. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: SHA256SMT OffSMT On - Default90M180M270M360M450M319679118.20401864487.87
MinAvgMaxSMT Off44.3448.6489.1SMT On - Default44.8464.5492.1OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor130260390520650

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: CPUSMT OffSMT On - Default48121620SE +/- 0.14, N = 3SE +/- 0.14, N = 1510.7713.96MIN: 4.91 / MAX: 12.41MIN: 6.55 / MAX: 16.95
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: LuxCore Benchmark - Acceleration: CPUSMT OffSMT On - Default0.00860.01720.02580.03440.0430.0270.038
MinAvgMaxSMT Off44.8402.9455.4SMT On - Default44.9369.8444.6OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor120240360480600

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 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUSMT OffSMT On - Default2004006008001000SE +/- 0.00, N = 3SE +/- 0.58, N = 3971753
MinAvgMaxSMT Off45.0382.4474.6SMT On - Default44.8373.6459.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUSMT OffSMT On - Default3K6K9K12K15KSE +/- 23.35, N = 3SE +/- 14.19, N = 31543711982
MinAvgMaxSMT Off44.6377.9479.6SMT On - Default44.7371.8469.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor120240360480600

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowSMT OffSMT On - Default1224364860SE +/- 0.04, N = 4SE +/- 0.06, N = 541.6053.421. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: SlowSMT OffSMT On - Default0.04390.08780.13170.17560.21950.1620.195
MinAvgMaxSMT Off44.7256.9340.1SMT On - Default44.7273.8377.9OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor100200300400500

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 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path Tracer - Acceleration: CPUSMT OffSMT On - Default2004006008001000SE +/- 0.33, N = 3SE +/- 0.33, N = 3817639
MinAvgMaxSMT Off45.1382.2476.4SMT On - Default44.8371.8463.5OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor120240360480600

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 TimeSMT OffSMT On - Default30609012015094.26120.351. (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

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 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path Tracer - Acceleration: CPUSMT OffSMT On - Default6K12K18K24K30KSE +/- 34.28, N = 3SE +/- 39.68, N = 32596620379
MinAvgMaxSMT Off44.6410.5476.7SMT On - Default44.9385.4463.9OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 1.0Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path Tracer - Acceleration: CPUSMT OffSMT On - Default3K6K9K12K15KSE +/- 4.36, N = 3SE +/- 3.71, N = 31293410154
MinAvgMaxSMT Off44.7384.5476.0SMT On - Default44.7358.2462.2OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay Studio 1.0CPU Power Consumption Monitor120240360480600

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumSMT OffSMT On - Default1224364860SE +/- 0.02, N = 4SE +/- 0.01, N = 542.4153.951. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: MediumSMT OffSMT On - Default0.04430.08860.13290.17720.22150.1630.197
MinAvgMaxSMT Off44.7260.4340.9SMT On - Default44.6273.6378.0OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor100200300400500

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 ISPCSMT OffSMT On - Default8001600240032004000SE +/- 1.45, N = 3SE +/- 0.88, N = 328803654MIN: 230 / MAX: 36075MIN: 293 / MAX: 42376
OpenBenchmarking.orgItems / Sec Per Watt, More Is BetterOpenVKL 2.0.0Benchmark: vklBenchmarkCPU ISPCSMT OffSMT On - Default36912157.3559.156
OpenBenchmarking.orgWatts, Fewer Is BetterOpenVKL 2.0.0CPU Power Consumption MonitorSMT OffSMT On - Default90180270360450Min: 44.85 / Avg: 391.57 / Max: 483.84Min: 44.92 / Avg: 399.08 / Max: 477.59

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinSMT OffSMT On - Default1632486480SE +/- 0.15, N = 10SE +/- 0.31, N = 1070.5855.791. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: Rhodopsin ProteinSMT OffSMT On - Default0.11810.23620.35430.47240.59050.5250.446
MinAvgMaxSMT Off44.6134.5464.0SMT On - Default44.5125.0352.9OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption Monitor120240360480600

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.orgns/day, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsSMT OffSMT On - Default48121620SE +/- 0.01, N = 8SE +/- 0.03, N = 717.9414.24
OpenBenchmarking.orgns/day Per Watt, More Is BetterNAMD 3.0b6Input: ATPase with 327,506 AtomsSMT OffSMT On - Default0.01890.03780.05670.07560.09450.0840.066
MinAvgMaxSMT Off44.6214.4478.1SMT On - Default44.8214.8414.4OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6CPU Power Consumption Monitor120240360480600

OSPRay

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

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeSMT OffSMT On - Default1224364860SE +/- 0.02, N = 3SE +/- 0.01, N = 343.9755.18
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeSMT OffSMT On - Default0.02930.05860.08790.11720.14650.1040.130
MinAvgMaxSMT Off44.7422.2472.3SMT On - Default44.7425.8477.0OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor120240360480600

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 4.1Blend File: Pabellon Barcelona - Compute: CPU-OnlySMT OffSMT On - Default918273645SE +/- 0.08, N = 3SE +/- 0.06, N = 337.1129.75
MinAvgMaxSMT Off44.6426.7491.3SMT On - Default44.7395.0458.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Barbershop - Compute: CPU-OnlySMT OffSMT On - Default20406080100SE +/- 0.04, N = 3SE +/- 0.12, N = 3107.3486.62
MinAvgMaxSMT Off44.6461.1495.0SMT On - Default45.1446.0487.0OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor130260390520650

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 2024.0Model: Person Re-Identification Retail FP16 - Device: CPUSMT OffSMT On - Default3K6K9K12K15KSE +/- 6.68, N = 3SE +/- 14.83, N = 311265.5313949.891. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -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 4.1Blend File: Fishy Cat - Compute: CPU-OnlySMT OffSMT On - Default48121620SE +/- 0.07, N = 4SE +/- 0.01, N = 415.3612.50
MinAvgMaxSMT Off45.0371.3493.6SMT On - Default44.9338.6471.9OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Junkshop - Compute: CPU-OnlySMT OffSMT On - Default48121620SE +/- 0.04, N = 4SE +/- 0.03, N = 415.5712.71
MinAvgMaxSMT Off45.0371.0493.5SMT On - Default45.0350.7492.1OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 4.1Blend File: Classroom - Compute: CPU-OnlySMT OffSMT On - Default714212835SE +/- 0.06, N = 3SE +/- 0.05, N = 329.3724.00
MinAvgMaxSMT Off44.8432.2496.6SMT On - Default44.8395.6467.1OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor130260390520650

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: 256 - Buffer Length: 256 - Filter Length: 57SMT OffSMT On - Default2000M4000M6000M8000M10000MSE +/- 15159192.30, N = 3SE +/- 6331139.97, N = 3671106666781519000001. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 57SMT OffSMT On - Default4M8M12M16M20M15697848.9819710155.44
MinAvgMaxSMT Off44.6427.5498.3SMT On - Default44.8413.6472.3OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor130260390520650

Parallel BZIP2 Compression

This test measures the time needed to compress a file (FreeBSD-13.0-RELEASE-amd64-memstick.img) using Parallel BZIP2 compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.13FreeBSD-13.0-RELEASE-amd64-memstick.img CompressionSMT OffSMT On - Default0.25470.50940.76411.01881.2735SE +/- 0.015554, N = 15SE +/- 0.010948, N = 151.1320140.9348961. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
MinAvgMaxSMT Off44.5101.0330.5SMT On - Default44.597.5319.0OpenBenchmarking.orgWatts, Fewer Is BetterParallel BZIP2 Compression 1.1.13CPU Power Consumption Monitor80160240320400

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 1BSMT OffSMT On - Default246810SE +/- 0.007, N = 5SE +/- 0.015, N = 56.7508.173
MinAvgMaxSMT Off44.8222.4409.2SMT On - Default45.1243.3425.0OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor110220330440550

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedSMT OffSMT On - Default100200300400500SE +/- 0.67, N = 3SE +/- 0.33, N = 33764551. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: EnhancedSMT OffSMT On - Default0.31610.63220.94831.26441.58050.9981.405
MinAvgMaxSMT Off44.4376.7408.7SMT On - Default44.7323.9350.4OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor110220330440550

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 OnlySMT OffSMT On - Default1.2M2.4M3.6M4.8M6MSE +/- 52234.47, N = 3SE +/- 39392.13, N = 3449198454186721. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm

OpenBenchmarking.orgms, Fewer Is BetterPostgreSQL 16Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average LatencySMT OffSMT On - Default0.05020.10040.15060.20080.251SE +/- 0.002, N = 3SE +/- 0.001, N = 30.2230.1851. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lm
MinAvgMaxSMT Off44.4360.6416.6SMT On - Default44.6394.9457.8OpenBenchmarking.orgWatts, Fewer Is BetterPostgreSQL 16CPU Power Consumption Monitor120240360480600

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianSMT OffSMT On - Default70140210280350SE +/- 1.00, N = 3SE +/- 0.58, N = 32603131. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: Noise-GaussianSMT OffSMT On - Default0.33860.67721.01581.35441.6931.1711.505
MinAvgMaxSMT Off44.4221.2253.7SMT On - Default44.7208.0234.1OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor70140210280350

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 4.1Blend File: BMW27 - Compute: CPU-OnlySMT OffSMT On - Default3691215SE +/- 0.02, N = 4SE +/- 0.01, N = 511.339.46
MinAvgMaxSMT Off44.6348.5493.3SMT On - Default44.7317.6461.2OpenBenchmarking.orgWatts, Fewer Is BetterBlender 4.1CPU Power Consumption Monitor130260390520650

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 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNetSMT OffSMT On - Default90180270360450SE +/- 0.71, N = 3SE +/- 2.87, N = 3432.49361.38
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: GoogLeNetSMT OffSMT On - Default0.40140.80281.20421.60562.0071.7841.361
MinAvgMaxSMT Off44.6242.5320.4SMT On - Default44.9265.5336.6OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor80160240320400

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 2024.0Model: Person Vehicle Bike Detection FP16 - Device: CPUSMT OffSMT On - Default2K4K6K8K10KSE +/- 19.63, N = 3SE +/- 8.58, N = 37335.768730.881. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2024.0Model: Handwritten English Recognition FP16-INT8 - Device: CPUSMT OffSMT On - Default10002000300040005000SE +/- 9.68, N = 3SE +/- 5.09, N = 34044.564774.331. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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, Small Mesh Size - Mesh TimeSMT OffSMT On - Default51015202518.1921.441. (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

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark capable of computing Pi to trillions of digits. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.8.3Pi Digits To Calculate: 500MSMT OffSMT On - Default1.09732.19463.29194.38925.4865SE +/- 0.004, N = 7SE +/- 0.005, N = 64.1494.877
MinAvgMaxSMT Off44.5186.3369.5SMT On - Default44.9202.1376.5OpenBenchmarking.orgWatts, Fewer Is BetterY-Cruncher 0.8.3CPU Power Consumption Monitor100200300400500

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 RatingSMT OffSMT On - Default200K400K600K800K1000KSE +/- 379.38, N = 3SE +/- 3530.77, N = 37766589081591. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

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 2024.0Model: Face Detection Retail FP16-INT8 - Device: CPUSMT OffSMT On - Default7K14K21K28K35KSE +/- 28.47, N = 3SE +/- 0.83, N = 327294.2031655.571. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.CSMT OffSMT On - Default90K180K270K360K450KSE +/- 3233.97, N = 7SE +/- 5529.34, N = 15443291.71385558.531. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CSMT OffSMT On - Default4008001200160020001708.911391.90
MinAvgMaxSMT Off44.7259.4475.5SMT On - Default44.8277.0487.2OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor130260390520650

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 2024.0Model: Vehicle Detection FP16-INT8 - Device: CPUSMT OffSMT On - Default2K4K6K8K10KSE +/- 10.17, N = 3SE +/- 2.97, N = 39772.4211232.261. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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.orgverify/s, More Is BetterOpenSSL 3.3Algorithm: RSA4096SMT OffSMT On - Default600K1200K1800K2400K3000KSE +/- 145.15, N = 3SE +/- 331.00, N = 32407045.52755042.31. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgverify/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: RSA4096SMT OffSMT On - Default130026003900520065005541.826287.44
MinAvgMaxSMT Off44.1434.0469.3SMT On - Default44.9438.2478.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor120240360480600

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: 256 - Buffer Length: 256 - Filter Length: 512SMT OffSMT On - Default600M1200M1800M2400M3000MSE +/- 2305307.88, N = 3SE +/- 3925274.23, N = 3249703333328554666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.orgsamples/s Per Watt, More Is BetterLiquid-DSP 1.6Threads: 256 - Buffer Length: 256 - Filter Length: 512SMT OffSMT On - Default1.6M3.2M4.8M6.4M8M5933020.847237709.10
MinAvgMaxSMT Off44.6420.9484.9SMT On - Default45.4394.5450.7OpenBenchmarking.orgWatts, Fewer Is BetterLiquid-DSP 1.6CPU Power Consumption Monitor120240360480600

Appleseed

Appleseed is an open-source production renderer focused on physically-based global illumination rendering engine primarily designed for animation and visual effects. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialSMT OffSMT On - Default71421283526.9430.69
MinAvgMaxSMT Off45.1342.4382.1SMT On - Default45.4336.9380.2OpenBenchmarking.orgWatts, Fewer Is BetterAppleseed 2.0 BetaCPU Power Consumption Monitor100200300400500

LULESH

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

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.3SMT OffSMT On - Default9K18K27K36K45KSE +/- 169.28, N = 3SE +/- 450.61, N = 1542873.2237645.971. (CXX) g++ options: -O3 -fopenmp -lm -lmpi_cxx -lmpi
OpenBenchmarking.orgz/s Per Watt, More Is BetterLULESH 2.0.3SMT OffSMT On - Default306090120150150.87129.24
MinAvgMaxSMT Off44.5284.2449.0SMT On - Default44.5291.3459.2OpenBenchmarking.orgWatts, Fewer Is BetterLULESH 2.0.3CPU Power Consumption Monitor120240360480600

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 2024.0Model: Machine Translation EN To DE FP16 - Device: CPUSMT OffSMT On - Default2004006008001000SE +/- 2.32, N = 3SE +/- 2.99, N = 3979.201109.751. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

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 RunSMT OffSMT On - Default2004006008001000SE +/- 4.24, N = 3SE +/- 4.70, N = 3806.99724.64MIN: 82.19 / MAX: 7500MIN: 85.11 / MAX: 6666.67
OpenBenchmarking.orgQueries Per Minute, Geo Mean Per Watt, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Third RunSMT OffSMT On - Default1.11942.23883.35824.47765.5974.9754.431
MinAvgMaxSMT Off44.4162.2412.8SMT On - Default44.4163.5407.0OpenBenchmarking.orgWatts, Fewer Is BetterClickHouse 22.12.3.5CPU Power Consumption Monitor110220330440550

OSPRay

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

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeSMT OffSMT On - Default1224364860SE +/- 0.02, N = 3SE +/- 0.01, N = 348.8854.40
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: particle_volume/scivis/real_timeSMT OffSMT On - Default0.03240.06480.09720.12960.1620.1320.144
MinAvgMaxSMT Off45.1370.6453.1SMT On - Default44.8376.8448.6OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeSMT OffSMT On - Default1224364860SE +/- 0.02, N = 3SE +/- 0.02, N = 348.9354.39
OpenBenchmarking.orgItems Per Second Per Watt, More Is BetterOSPRay 3.1Benchmark: particle_volume/ao/real_timeSMT OffSMT On - Default0.02860.05720.08580.11440.1430.1130.127
MinAvgMaxSMT Off44.8431.3453.2SMT On - Default45.0429.8449.3OpenBenchmarking.orgWatts, Fewer Is BetterOSPRay 3.1CPU Power Consumption Monitor120240360480600

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 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50SMT OffSMT On - Default306090120150SE +/- 0.80, N = 3SE +/- 0.26, N = 3152.83137.62
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: ResNet-50SMT OffSMT On - Default0.12310.24620.36930.49240.61550.5470.487
MinAvgMaxSMT Off44.5279.5321.3SMT On - Default44.8282.4318.6OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor80160240320400

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, First Run / Cold CacheSMT OffSMT On - Default2004006008001000SE +/- 3.29, N = 3SE +/- 6.12, N = 3774.87698.12MIN: 80.97 / MAX: 6666.67MIN: 80.86 / MAX: 6666.67

OpenBenchmarking.orgQueries Per Minute, Geo Mean, More Is BetterClickHouse 22.12.3.5100M Rows Hits Dataset, Second RunSMT OffSMT On - Default2004006008001000SE +/- 5.07, N = 3SE +/- 5.27, N = 3804.06729.56MIN: 82.99 / MAX: 7500MIN: 81.63 / MAX: 7500

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-ThreadedSMT OffSMT On - Default100K200K300K400K500KSE +/- 94.33, N = 3SE +/- 401.79, N = 3422695.2465436.81. (CXX) g++ options: -O3 -march=native -fPIE -pie
OpenBenchmarking.orgMFLOPS Per Watt, More Is BetterQuantLib 1.32Configuration: Multi-ThreadedSMT OffSMT On - Default20040060080010001102.521146.37
MinAvgMaxSMT Off45.0383.4482.0SMT On - Default44.4406.0483.0OpenBenchmarking.orgWatts, Fewer Is BetterQuantLib 1.32CPU Power Consumption Monitor120240360480600

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 6.8Build: defconfigSMT OffSMT On - Default612182430SE +/- 0.20, N = 6SE +/- 0.13, N = 321.2223.34
MinAvgMaxSMT Off44.1201.5475.6SMT On - Default44.2204.9467.5OpenBenchmarking.orgWatts, Fewer Is BetterTimed Linux Kernel Compilation 6.8CPU Power Consumption Monitor120240360480600

oneDNN

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

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.4Harness: Deconvolution Batch shapes_3d - Engine: CPUSMT OffSMT On - Default0.11550.2310.34650.4620.5775SE +/- 0.000896, N = 9SE +/- 0.004859, N = 150.4717170.513417MIN: 0.45MIN: 0.481. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
MinAvgMaxSMT Off44.4157.4316.9SMT On - Default44.9156.5315.2OpenBenchmarking.orgWatts, Fewer Is BetteroneDNN 3.4CPU Power Consumption Monitor80160240320400

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 2024.0Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUSMT OffSMT On - Default40K80K120K160K200KSE +/- 585.07, N = 3SE +/- 1255.01, N = 3175803.47190777.831. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ExhaustiveSMT OffSMT On - Default3691215SE +/- 0.0052, N = 3SE +/- 0.0004, N = 38.91929.65761. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ExhaustiveSMT OffSMT On - Default0.00680.01360.02040.02720.0340.0280.030
MinAvgMaxSMT Off44.4320.9449.8SMT On - Default44.7318.6450.4OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: Very ThoroughSMT OffSMT On - Default48121620SE +/- 0.00, N = 3SE +/- 0.00, N = 314.5715.721. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: Very ThoroughSMT OffSMT On - Default0.01130.02260.03390.04520.05650.0460.050
MinAvgMaxSMT Off44.3319.5454.3SMT On - Default44.5317.5448.4OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor120240360480600

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 1.11Video Input: Bosphorus 4K - Video Preset: FasterSMT OffSMT On - Default612182430SE +/- 0.01, N = 3SE +/- 0.02, N = 325.6223.741. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FasterSMT OffSMT On - Default0.02320.04640.06960.09280.1160.1030.099
MinAvgMaxSMT Off44.6248.9340.3SMT On - Default44.6239.4329.0OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11CPU Power Consumption Monitor80160240320400

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Second, More Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelSMT OffSMT On - Default1020304050SE +/- 0.19, N = 3SE +/- 0.06, N = 341.6844.961. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInference Time Cost (ms), Fewer Is BetterONNX Runtime 1.17Model: Faster R-CNN R-50-FPN-int8 - Device: CPU - Executor: ParallelSMT OffSMT On - Default612182430SE +/- 0.11, N = 3SE +/- 0.03, N = 323.9922.241. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
MinAvgMaxSMT Off44.5291.4322.1SMT On - Default45.0305.1331.0OpenBenchmarking.orgWatts, Fewer Is BetterONNX Runtime 1.17CPU Power Consumption Monitor80160240320400

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: ThoroughSMT OffSMT On - Default20406080100SE +/- 0.01, N = 6SE +/- 0.02, N = 6102.27110.041. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: ThoroughSMT OffSMT On - Default0.12170.24340.36510.48680.60850.4930.541
MinAvgMaxSMT Off44.2207.4436.7SMT On - Default44.5203.3437.2OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor110220330440550

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.CSMT OffSMT On - Default40K80K120K160K200KSE +/- 90.58, N = 9SE +/- 1302.88, N = 15179200.08167026.931. (F9X) gfortran options: -O3 -march=native -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz 2. Open MPI 4.1.6
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CSMT OffSMT On - Default300600900120015001148.781197.56
MinAvgMaxSMT Off44.7156.0433.5SMT On - Default44.4139.5414.0OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor110220330440550

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, Small Mesh Size - Execution TimeSMT OffSMT On - Default51015202519.2220.601. (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
MinAvgMaxSMT Off44.9391.4496.6SMT On - Default44.4396.4492.6OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor130260390520650

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KSMT OffSMT On - Default306090120150SE +/- 0.24, N = 7SE +/- 1.10, N = 7126.61118.161. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 8 - Input: Bosphorus 4KSMT OffSMT On - Default0.18990.37980.56970.75960.94950.8440.778
MinAvgMaxSMT Off44.3150.1286.8SMT On - Default44.5151.9282.0OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor70140210280350

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 1.11Video Input: Bosphorus 4K - Video Preset: FastSMT OffSMT On - Default3691215SE +/- 0.065, N = 3SE +/- 0.028, N = 310.5039.8101. (CXX) g++ options: -O3 -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterVVenC 1.11Video Input: Bosphorus 4K - Video Preset: FastSMT OffSMT On - Default0.01080.02160.03240.04320.0540.0480.046
MinAvgMaxSMT Off44.3217.3348.4SMT On - Default44.5212.7338.9OpenBenchmarking.orgWatts, Fewer Is BetterVVenC 1.11CPU Power Consumption Monitor100200300400500

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 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNetSMT OffSMT On - Default30060090012001500SE +/- 8.98, N = 6SE +/- 3.83, N = 61162.501086.48
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 64 - Model: AlexNetSMT OffSMT On - Default2468106.7746.430
MinAvgMaxSMT Off44.6171.6273.2SMT On - Default44.8169.0264.5OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor70140210280350

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNetSMT OffSMT On - Default714212835SE +/- 0.10, N = 7SE +/- 0.16, N = 727.7025.93
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 1 - Model: AlexNetSMT OffSMT On - Default0.03870.07740.11610.15480.19350.1720.154
MinAvgMaxSMT Off44.5161.4303.4SMT On - Default44.7168.5306.4OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor80160240320400

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample high resolution (currently 15400 x 6940) JPEG image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.43Operation: SwirlSMT OffSMT On - Default2004006008001000SE +/- 0.33, N = 3SE +/- 0.33, N = 37988511. (CC) gcc options: -fopenmp -O2 -ltiff -ljbig -lsharpyuv -lwebp -lwebpmux -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lxml2 -lzstd -llzma -lbz2 -lz -lm -lpthread -lgomp
OpenBenchmarking.orgIterations Per Minute Per Watt, More Is BetterGraphicsMagick 1.3.43Operation: SwirlSMT OffSMT On - Default0.64131.28261.92392.56523.20652.5312.850
MinAvgMaxSMT Off44.7315.2341.7SMT On - Default44.7298.6325.9OpenBenchmarking.orgWatts, Fewer Is BetterGraphicsMagick 1.3.43CPU Power Consumption Monitor80160240320400

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KSMT OffSMT On - Default70140210280350SE +/- 0.48, N = 9SE +/- 2.17, N = 9299.97281.591. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 12 - Input: Bosphorus 4KSMT OffSMT On - Default0.58461.16921.75382.33842.9232.5982.421
MinAvgMaxSMT Off22.7115.5298.0SMT On - Default44.5116.3294.8OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor70140210280350

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_shortSMT OffSMT On - Default510152025SE +/- 0.03, N = 3SE +/- 0.07, N = 321.0322.091. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
MinAvgMaxSMT Off44.6325.4394.2SMT On - Default44.6333.7398.9OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption Monitor110220330440550

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 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNetSMT OffSMT On - Default150300450600750SE +/- 2.03, N = 3SE +/- 7.40, N = 3691.93659.11
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: GoogLeNetSMT OffSMT On - Default0.54231.08461.62692.16922.71152.4102.243
MinAvgMaxSMT Off44.5287.1332.6SMT On - Default45.0293.8338.6OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor80160240320400

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_bm16SMT OffSMT On - Default4080120160200SE +/- 0.10, N = 3SE +/- 0.24, N = 3171.22178.931. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
MinAvgMaxSMT Off44.9381.3399.5SMT On - Default45.0388.4407.2OpenBenchmarking.orgWatts, Fewer Is BetterCloverLeaf 1.3CPU Power Consumption Monitor110220330440550

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: Cell Phone Drop TestSMT OffSMT On - Default48121620SE +/- 0.20, N = 3SE +/- 0.16, N = 317.1217.87
MinAvgMaxSMT Off44.7289.4467.8SMT On - Default44.9295.0469.0OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor120240360480600

RocksDB

This is a benchmark of Meta/Facebook's RocksDB as an embeddable persistent key-value store for fast storage based on Google's LevelDB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterRocksDB 9.0Test: Random ReadSMT OffSMT On - Default200M400M600M800M1000MSE +/- 9096243.38, N = 5SE +/- 5260460.78, N = 38203578367868965801. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterRocksDB 9.0Test: Random ReadSMT OffSMT On - Default400K800K1200K1600K2000K1958108.131894471.54
MinAvgMaxSMT Off44.9419.0450.9SMT On - Default44.5415.4446.2OpenBenchmarking.orgWatts, Fewer Is BetterRocksDB 9.0CPU Power Consumption Monitor120240360480600

Timed Mesa Compilation

This test profile times how long it takes to compile Mesa with Meson/Ninja. For minimizing build dependencies and avoid versioning conflicts, test this is just the core Mesa build without LLVM or the extra Gallium3D/Mesa drivers enabled. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 24.0Time To CompileSMT OffSMT On - Default48121620SE +/- 0.02, N = 4SE +/- 0.07, N = 413.1313.67
MinAvgMaxSMT Off44.2142.8478.6SMT On - Default44.4145.0477.1OpenBenchmarking.orgWatts, Fewer Is BetterTimed Mesa Compilation 24.0CPU Power Consumption Monitor120240360480600

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 3.3Algorithm: SHA512SMT OffSMT On - Default15000M30000M45000M60000M75000MSE +/- 155480309.48, N = 3SE +/- 163780192.60, N = 369546046390723597672401. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: SHA512SMT OffSMT On - Default30M60M90M120M150M145258130.79161764658.87
MinAvgMaxSMT Off44.3478.8504.9SMT On - Default45.0447.3471.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor130260390520650

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 2024.0Model: Road Segmentation ADAS FP16-INT8 - Device: CPUSMT OffSMT On - Default7001400210028003500SE +/- 7.32, N = 3SE +/- 2.87, N = 33419.613287.431. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Speedb

Speedb is a next-generation key value storage engine that is RocksDB compatible and aiming for stability, efficiency, and performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Random ReadSMT OffSMT On - Default200M400M600M800M1000MSE +/- 36730.51, N = 3SE +/- 707549.54, N = 38541807018221028281. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Random ReadSMT OffSMT On - Default400K800K1200K1600K2000K2040959.051969975.35
MinAvgMaxSMT Off44.8418.5451.7SMT On - Default45.3417.3445.7OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor120240360480600

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 3.3Algorithm: AES-256-GCMSMT OffSMT On - Default400000M800000M1200000M1600000M2000000MSE +/- 1218174976.10, N = 3SE +/- 2482404044.78, N = 3176937386530018377658507471. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: AES-256-GCMSMT OffSMT On - Default900M1800M2700M3600M4500M3946701676.574339501704.86
MinAvgMaxSMT Off44.4448.3479.4SMT On - Default44.7423.5443.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor120240360480600

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 CompileSMT OffSMT On - Default306090120150SE +/- 1.07, N = 3SE +/- 1.52, N = 3123.38128.13
MinAvgMaxSMT Off44.2200.0475.5SMT On - Default44.4195.4485.4OpenBenchmarking.orgWatts, Fewer Is BetterTimed Gem5 Compilation 23.0.1CPU Power Consumption Monitor130260390520650

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 2024.0Model: Face Detection FP16-INT8 - Device: CPUSMT OffSMT On - Default4080120160200SE +/- 0.09, N = 3SE +/- 0.32, N = 3201.01193.801. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

Timed Godot Game Engine Compilation

This test times how long it takes to compile the Godot Game Engine. Godot is a popular, open-source, cross-platform 2D/3D game engine and is built using the SCons build system and targeting the X11 platform. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 4.0Time To CompileSMT OffSMT On - Default20406080100SE +/- 0.06, N = 3SE +/- 0.10, N = 380.3383.29
MinAvgMaxSMT Off44.3227.1481.1SMT On - Default44.5220.4490.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed Godot Game Engine Compilation 4.0CPU Power Consumption Monitor130260390520650

Kvazaar

This is a test of Kvazaar as a CPU-based H.265/HEVC video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastSMT OffSMT On - Default20406080100SE +/- 0.02, N = 6SE +/- 0.49, N = 793.5496.811. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterKvazaar 2.2Video Input: Bosphorus 4K - Video Preset: Very FastSMT OffSMT On - Default0.09630.19260.28890.38520.48150.4110.428
MinAvgMaxSMT Off44.7227.7358.1SMT On - Default44.7226.3360.3OpenBenchmarking.orgWatts, Fewer Is BetterKvazaar 2.2CPU Power Consumption Monitor100200300400500

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 - GriddingSMT OffSMT On - Default4K8K12K16K20KSE +/- 13.89, N = 3SE +/- 0.00, N = 315967.916464.11. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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.orgns/day, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsSMT OffSMT On - Default1.07012.14023.21034.28045.3505SE +/- 0.00841, N = 4SE +/- 0.00697, N = 34.755814.62277
OpenBenchmarking.orgns/day Per Watt, More Is BetterNAMD 3.0b6Input: STMV with 1,066,628 AtomsSMT OffSMT On - Default0.00360.00720.01080.01440.0180.0160.016
MinAvgMaxSMT Off44.4299.3477.8SMT On - Default44.5284.4425.6OpenBenchmarking.orgWatts, Fewer Is BetterNAMD 3.0b6CPU Power Consumption Monitor120240360480600

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 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50SMT OffSMT On - Default50100150200250SE +/- 0.40, N = 3SE +/- 0.65, N = 3209.16203.33
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: ResNet-50SMT OffSMT On - Default0.15190.30380.45570.60760.75950.6750.659
MinAvgMaxSMT Off44.3309.7333.2SMT On - Default44.8308.7332.3OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor80160240320400

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 NanotubeSMT OffSMT On - Default612182430SE +/- 0.08, N = 3SE +/- 0.10, N = 323.2123.821. (CC) gcc options: -shared -lxc -lblas -lmpi
MinAvgMaxSMT Off44.8399.0492.6SMT On - Default44.6396.6491.5OpenBenchmarking.orgWatts, Fewer Is BetterGPAW 23.6CPU Power Consumption Monitor130260390520650

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.CSMT OffSMT On - Default40K80K120K160K200KSE +/- 247.78, N = 5SE +/- 878.07, N = 5199661.62194853.911. (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 4.1.6
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.CSMT OffSMT On - Default150300450600750677.42644.42
MinAvgMaxSMT Off44.9294.7465.1SMT On - Default44.8302.4488.2OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor130260390520650

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 2.16.1Device: CPU - Batch Size: 512 - Model: GoogLeNetSMT OffSMT On - Default2004006008001000SE +/- 1.83, N = 3SE +/- 3.19, N = 3839.05819.05
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: GoogLeNetSMT OffSMT On - Default0.59061.18121.77182.36242.9532.6252.516
MinAvgMaxSMT Off44.5319.6355.3SMT On - Default44.8325.5361.1OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor100200300400500

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 TimeSMT OffSMT On - Default4080120160200156.58160.371. (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
MinAvgMaxSMT Off44.6455.7493.4SMT On - Default44.6450.2489.9OpenBenchmarking.orgWatts, Fewer Is BetterOpenFOAM 10CPU Power Consumption Monitor130260390520650

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: NinjaSMT OffSMT On - Default20406080100SE +/- 0.05, N = 3SE +/- 0.32, N = 390.9988.89
MinAvgMaxSMT Off22.2312.1478.4SMT On - Default44.4300.1488.2OpenBenchmarking.orgWatts, Fewer Is BetterTimed LLVM Compilation 16.0CPU Power Consumption Monitor130260390520650

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 - DegriddingSMT OffSMT On - Default15K30K45K60K75KSE +/- 382.37, N = 3SE +/- 395.30, N = 369207.570762.81. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp

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 21.7.2Time To CompileSMT OffSMT On - Default306090120150SE +/- 0.10, N = 3SE +/- 0.21, N = 3112.00109.56
MinAvgMaxSMT Off44.1306.8475.5SMT On - Default44.5304.2485.2OpenBenchmarking.orgWatts, Fewer Is BetterTimed Node.js Compilation 21.7.2CPU Power Consumption Monitor120240360480600

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-152SMT OffSMT On - Default510152025SE +/- 0.17, N = 3SE +/- 0.07, N = 320.6720.24MIN: 17.64 / MAX: 21.34MIN: 19.69 / MAX: 20.76
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-152SMT OffSMT On - Default0.01690.03380.05070.06760.08450.0750.072
MinAvgMaxSMT Off44.6274.7306.6SMT On - Default44.8279.6308.3OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

SVT-AV1

This is a benchmark of the SVT-AV1 open-source video encoder/decoder. SVT-AV1 was originally developed by Intel as part of their Open Visual Cloud / Scalable Video Technology (SVT). Development of SVT-AV1 has since moved to the Alliance for Open Media as part of upstream AV1 development. SVT-AV1 is a CPU-based multi-threaded video encoder for the AV1 video format with a sample YUV video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KSMT OffSMT On - Default3691215SE +/- 0.01, N = 4SE +/- 0.04, N = 411.5111.281. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 4 - Input: Bosphorus 4KSMT OffSMT On - Default0.01580.03160.04740.06320.0790.0700.069
MinAvgMaxSMT Off44.4163.7323.2SMT On - Default44.4164.5329.5OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor80160240320400

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-50SMT OffSMT On - Default1020304050SE +/- 0.12, N = 3SE +/- 0.13, N = 343.0143.83MIN: 40.3 / MAX: 44.35MIN: 41.6 / MAX: 45.11
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-50SMT OffSMT On - Default0.03510.07020.10530.14040.17550.1560.156
MinAvgMaxSMT Off44.4276.3317.2SMT On - Default45.0281.8321.0OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

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 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50SMT OffSMT On - Default50100150200250SE +/- 0.10, N = 3SE +/- 0.52, N = 3250.82246.24
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: ResNet-50SMT OffSMT On - Default0.16610.33220.49830.66440.83050.7380.730
MinAvgMaxSMT Off44.4339.7363.0SMT On - Default45.1337.2361.7OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor100200300400500

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50SMT OffSMT On - Default1224364860SE +/- 0.39, N = 3SE +/- 0.42, N = 352.1451.20MIN: 47.46 / MAX: 54.1MIN: 48.71 / MAX: 53.18
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 1 - Model: ResNet-50SMT OffSMT On - Default0.04840.09680.14520.19360.2420.2150.209
MinAvgMaxSMT Off44.5242.1302.2SMT On - Default45.0244.9304.0OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

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 2.16.1Device: CPU - Batch Size: 256 - Model: AlexNetSMT OffSMT On - Default5001000150020002500SE +/- 10.16, N = 4SE +/- 2.78, N = 42234.752271.95
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 256 - Model: AlexNetSMT OffSMT On - Default36912159.8609.558
MinAvgMaxSMT Off44.9226.6308.9SMT On - Default44.8237.7322.8OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor80160240320400

ASTC Encoder

ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.7Preset: MediumSMT OffSMT On - Default150300450600750SE +/- 2.71, N = 8SE +/- 3.94, N = 8691.99701.731. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.orgMT/s Per Watt, More Is BetterASTC Encoder 4.7Preset: MediumSMT OffSMT On - Default1.18282.36563.54844.73125.9145.2465.257
MinAvgMaxSMT Off44.2131.9430.5SMT On - Default44.4133.5427.6OpenBenchmarking.orgWatts, Fewer Is BetterASTC Encoder 4.7CPU Power Consumption Monitor110220330440550

LAMMPS Molecular Dynamics Simulator

LAMMPS is a classical molecular dynamics code, and an acronym for Large-scale Atomic/Molecular Massively Parallel Simulator. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsSMT OffSMT On - Default1530456075SE +/- 0.72, N = 3SE +/- 0.06, N = 368.7067.781. (CXX) g++ options: -O3 -lm -ldl
OpenBenchmarking.orgns/day Per Watt, More Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022Model: 20k AtomsSMT OffSMT On - Default0.03310.06620.09930.13240.16550.1460.147
MinAvgMaxSMT Off44.5470.2495.6SMT On - Default44.3461.9488.1OpenBenchmarking.orgWatts, Fewer Is BetterLAMMPS Molecular Dynamics Simulator 23Jun2022CPU Power Consumption Monitor130260390520650

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 - GriddingSMT OffSMT On - Default16K32K48K64K80KSE +/- 0.00, N = 3SE +/- 438.43, N = 374970.274093.31. (CXX) g++ options: -O3 -fstrict-aliasing -fopenmp
OpenBenchmarking.orgMpix/sec Per Watt, More Is BetterASKAP 1.0Test: tConvolve MPI - GriddingSMT OffSMT On - Default50100150200250212.04207.54
MinAvgMaxSMT Off44.6353.6487.5SMT On - Default45.0357.0474.4OpenBenchmarking.orgWatts, Fewer Is BetterASKAP 1.0CPU Power Consumption Monitor130260390520650

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50SMT OffSMT On - Default1020304050SE +/- 0.06, N = 3SE +/- 0.27, N = 343.1943.68MIN: 39.77 / MAX: 44.9MIN: 41.7 / MAX: 44.98
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-50SMT OffSMT On - Default0.03510.07020.10530.14040.17550.1560.156
MinAvgMaxSMT Off44.5276.2317.1SMT On - Default44.6279.7319.7OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

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 1MSMT OffSMT On - Default20406080100SE +/- 0.05, N = 3SE +/- 0.11, N = 376.4277.26
MinAvgMaxSMT Off44.7364.4489.1SMT On - Default44.9364.1489.3OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor130260390520650

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.DSMT OffSMT On - Default2K4K6K8K10KSE +/- 21.61, N = 6SE +/- 55.66, N = 68556.578647.621. (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 4.1.6
OpenBenchmarking.orgTotal Mop/s Per Watt, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.DSMT OffSMT On - Default91827364538.6340.04
MinAvgMaxSMT Off44.5221.5423.4SMT On - Default44.5216.0421.2OpenBenchmarking.orgWatts, Fewer Is BetterNAS Parallel Benchmarks 3.4CPU Power Consumption Monitor110220330440550

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 1.2SMT OffSMT On - Default700M1400M2100M2800M3500MSE +/- 4101761.26, N = 3SE +/- 6342005.91, N = 3314554433331770820001. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -lmpi
OpenBenchmarking.orgFigure Of Merit Per Watt, More Is BetterAlgebraic Multi-Grid Benchmark 1.2SMT OffSMT On - Default2M4M6M8M10M9715238.289501967.55
MinAvgMaxSMT Off44.3323.8428.4SMT On - Default44.4334.4438.6OpenBenchmarking.orgWatts, Fewer Is BetterAlgebraic Multi-Grid Benchmark 1.2CPU Power Consumption Monitor120240360480600

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-152SMT OffSMT On - Default48121620SE +/- 0.09, N = 3SE +/- 0.19, N = 417.2817.42MIN: 15.38 / MAX: 17.87MIN: 16.53 / MAX: 18.16
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-152SMT OffSMT On - Default0.01310.02620.03930.05240.06550.0580.058
MinAvgMaxSMT Off44.5297.5321.9SMT On - Default44.8301.1326.0OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

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: X3D-benchmarking input.i3dSMT OffSMT On - Default4080120160200SE +/- 0.21, N = 3SE +/- 0.78, N = 3201.27199.841. (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
MinAvgMaxSMT Off44.5400.3425.4SMT On - Default44.9401.7443.9OpenBenchmarking.orgWatts, Fewer Is BetterXcompact3d Incompact3d 2021-03-11CPU Power Consumption Monitor120240360480600

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlySMT OffSMT On - Default0.64131.28261.92392.56523.2065SE +/- 0.00, N = 5SE +/- 0.00, N = 52.832.85
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.2Run: RTLightmap.hdr.4096x4096 - Device: CPU-OnlySMT OffSMT On - Default0.00230.00460.00690.00920.01150.0090.010
MinAvgMaxSMT Off44.8298.3408.0SMT On - Default44.8299.1406.1OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2CPU Power Consumption Monitor110220330440550

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-152SMT OffSMT On - Default48121620SE +/- 0.15, N = 3SE +/- 0.05, N = 317.5917.49MIN: 3.09 / MAX: 18.18MIN: 16.94 / MAX: 18.01
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 512 - Model: ResNet-152SMT OffSMT On - Default0.01330.02660.03990.05320.06650.0590.058
MinAvgMaxSMT Off44.6297.7322.4SMT On - Default45.0302.2325.1OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

NWChem

NWChem is an open-source high performance computational chemistry package. Per NWChem's documentation, "NWChem aims to provide its users with computational chemistry tools that are scalable both in their ability to treat large scientific computational chemistry problems efficiently, and in their use of available parallel computing resources from high-performance parallel supercomputers to conventional workstation clusters." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 BuckyballSMT OffSMT On - Default300600900120015001319.61326.21. (F9X) gfortran options: -lnwctask -lccsd -lmcscf -lselci -lmp2 -lmoints -lstepper -ldriver -loptim -lnwdft -lgradients -lcphf -lesp -lddscf -ldangchang -lguess -lhessian -lvib -lnwcutil -lrimp2 -lproperty -lsolvation -lnwints -lprepar -lnwmd -lnwpw -lofpw -lpaw -lpspw -lband -lnwpwlib -lcafe -lspace -lanalyze -lqhop -lpfft -ldplot -ldrdy -lvscf -lqmmm -lqmd -letrans -ltce -lbq -lmm -lcons -lperfm -ldntmc -lccca -ldimqm -lga -larmci -lpeigs -l64to32 -lopenblas -lpthread -lrt -llapack -lnwcblas -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz -lcomex -m64 -ffast-math -std=legacy -fdefault-integer-8 -finline-functions -O2
OpenBenchmarking.orgWatts, Fewer Is BetterNWChem 7.0.2CPU Power Consumption MonitorSMT OffSMT On - Default90180270360450Min: 44.59 / Avg: 478.93 / Max: 504.52Min: 44.44 / Avg: 477.37 / Max: 499.23

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 3.3Algorithm: AES-128-GCMSMT OffSMT On - Default400000M800000M1200000M1600000M2000000MSE +/- 3907203464.57, N = 3SE +/- 679943093.73, N = 3199918456604320073653514701. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
OpenBenchmarking.orgbyte/s Per Watt, More Is BetterOpenSSL 3.3Algorithm: AES-128-GCMSMT OffSMT On - Default1000M2000M3000M4000M5000M4449627450.394699217928.95
MinAvgMaxSMT Off44.6449.3475.8SMT On - Default44.7427.2447.2OpenBenchmarking.orgWatts, Fewer Is BetterOpenSSL 3.3CPU Power Consumption Monitor120240360480600

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 2024Implementation: MPI CPU - Input: water_GMX50_bareSMT OffSMT On - Default510152025SE +/- 0.05, N = 3SE +/- 0.04, N = 322.8222.731. (CXX) g++ options: -O3 -lm
OpenBenchmarking.orgNs Per Day Per Watt, More Is BetterGROMACS 2024Implementation: MPI CPU - Input: water_GMX50_bareSMT OffSMT On - Default0.01490.02980.04470.05960.07450.0660.065
MinAvgMaxSMT Off44.8341.9488.5SMT On - Default44.6349.2487.2OpenBenchmarking.orgWatts, Fewer Is BetterGROMACS 2024CPU Power Consumption Monitor130260390520650

Timed ImageMagick Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileSMT OffSMT On - Default3691215SE +/- 0.078, N = 5SE +/- 0.013, N = 59.9049.868
MinAvgMaxSMT Off44.1132.3459.6SMT On - Default44.5132.6448.6OpenBenchmarking.orgWatts, Fewer Is BetterTimed ImageMagick Compilation 6.9.0CPU Power Consumption Monitor120240360480600

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 2.16.1Device: CPU - Batch Size: 512 - Model: AlexNetSMT OffSMT On - Default6001200180024003000SE +/- 3.14, N = 3SE +/- 2.64, N = 32675.122665.92
OpenBenchmarking.orgimages/sec Per Watt, More Is BetterTensorFlow 2.16.1Device: CPU - Batch Size: 512 - Model: AlexNetSMT OffSMT On - Default369121510.2299.597
MinAvgMaxSMT Off44.5261.5328.0SMT On - Default44.7277.8340.8OpenBenchmarking.orgWatts, Fewer Is BetterTensorFlow 2.16.1CPU Power Consumption Monitor80160240320400

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlySMT OffSMT On - Default1.31632.63263.94895.26526.5815SE +/- 0.01, N = 7SE +/- 0.00, N = 75.835.85
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.2Run: RT.ldr_alb_nrm.3840x2160 - Device: CPU-OnlySMT OffSMT On - Default0.00560.01120.01680.02240.0280.0240.025
MinAvgMaxSMT Off44.8240.1410.1SMT On - Default44.6237.3409.6OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2CPU Power Consumption Monitor110220330440550

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: INIVOL and Fluid Structure Interaction Drop ContainerSMT OffSMT On - Default1632486480SE +/- 0.14, N = 3SE +/- 0.07, N = 373.4473.67
MinAvgMaxSMT Off44.7424.6489.8SMT On - Default44.9423.7488.8OpenBenchmarking.orgWatts, Fewer Is BetterOpenRadioss 2023.09.15CPU Power Consumption Monitor130260390520650

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-152SMT OffSMT On - Default48121620SE +/- 0.09, N = 3SE +/- 0.12, N = 317.4117.46MIN: 15.31 / MAX: 17.97MIN: 16.79 / MAX: 17.99
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 64 - Model: ResNet-152SMT OffSMT On - Default0.01310.02620.03930.05240.06550.0580.058
MinAvgMaxSMT Off44.6298.3323.0SMT On - Default44.8301.3324.8OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

Intel Open Image Denoise

Open Image Denoise is a denoising library for ray-tracing and part of the Intel oneAPI rendering toolkit. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 2.2Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlySMT OffSMT On - Default1.3142.6283.9425.2566.57SE +/- 0.01, N = 7SE +/- 0.01, N = 75.835.84
OpenBenchmarking.orgImages / Sec Per Watt, More Is BetterIntel Open Image Denoise 2.2Run: RT.hdr_alb_nrm.3840x2160 - Device: CPU-OnlySMT OffSMT On - Default0.00560.01120.01680.02240.0280.0250.024
MinAvgMaxSMT Off44.6235.6409.3SMT On - Default44.6239.9408.8OpenBenchmarking.orgWatts, Fewer Is BetterIntel Open Image Denoise 2.2CPU Power Consumption Monitor110220330440550

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60SMT OffSMT On - Default1428425670SE +/- 0.02, N = 3SE +/- 0.01, N = 363.7863.671. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi
OpenBenchmarking.orgGFLOP/s Per Watt, More Is BetterHigh Performance Conjugate Gradient 3.1X Y Z: 144 144 144 - RT: 60SMT OffSMT On - Default0.03530.07060.10590.14120.17650.1560.157
MinAvgMaxSMT Off44.8408.3463.1SMT On - Default44.6406.0468.4OpenBenchmarking.orgWatts, Fewer Is BetterHigh Performance Conjugate Gradient 3.1CPU Power Consumption Monitor120240360480600

WRF

WRF, the Weather Research and Forecasting Model, is a "next-generation mesoscale numerical weather prediction system designed for both atmospheric research and operational forecasting applications. It features two dynamical cores, a data assimilation system, and a software architecture supporting parallel computation and system extensibility." Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5kmSMT OffSMT On - Default120024003600480060005583.485574.361. (F9X) gfortran options: -O2 -ftree-vectorize -funroll-loops -ffree-form -fconvert=big-endian -frecord-marker=4 -fallow-invalid-boz -lesmf_time -lwrfio_nf -lnetcdff -lnetcdf -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -levent_core -levent_pthreads -lm -lz
OpenBenchmarking.orgWatts, Fewer Is BetterWRF 4.2.2CPU Power Consumption MonitorSMT OffSMT On - Default90180270360450Min: 44.48 / Avg: 440.76 / Max: 479.79Min: 44.4 / Avg: 440.28 / Max: 480.05

PyTorch

This is a benchmark of PyTorch making use of pytorch-benchmark [https://github.com/LukasHedegaard/pytorch-benchmark]. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgbatches/sec, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-50SMT OffSMT On - Default1020304050SE +/- 0.29, N = 3SE +/- 0.29, N = 343.6843.61MIN: 40.37 / MAX: 44.97MIN: 41.9 / MAX: 45.08
OpenBenchmarking.orgbatches/sec Per Watt, More Is BetterPyTorch 2.2.1Device: CPU - Batch Size: 256 - Model: ResNet-50SMT OffSMT On - Default0.03560.07120.10680.14240.1780.1580.155
MinAvgMaxSMT Off44.4276.1318.4SMT On - Default45.1281.3320.6OpenBenchmarking.orgWatts, Fewer Is BetterPyTorch 2.2.1CPU Power Consumption Monitor80160240320400

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 2024.0Model: Weld Porosity Detection FP16-INT8 - Device: CPUSMT OffSMT On - Default4K8K12K16K20KSE +/- 14.17, N = 3SE +/- 13.14, N = 318690.3218679.361. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringSMT OffSMT On - Default90180270360450Min: 22.2 / Avg: 326.39 / Max: 505.98Min: 44.19 / Avg: 324.1 / Max: 500.98

Stockfish

MinAvgMaxSMT Off44.5428.0472.1SMT On - Default44.8440.6487.2OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 16.1Chess BenchmarkSMT OffSMT On - Default150K300K450K600K750K541348.84697627.07

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 16.1Chess BenchmarkSMT OffSMT On - Default70M140M210M280M350MSE +/- 4076501.74, N = 15SE +/- 4338134.07, N = 152316990043073439231. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fno-peel-loops -fno-tracer -pedantic -O3 -funroll-loops -msse -msse3 -mpopcnt -mavx2 -mbmi -mavx512f -mavx512bw -mavx512vnni -mavx512dq -mavx512vl -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto-partition=one -flto=jobserver
OpenBenchmarking.orgNodes Per Second Per Watt, More Is BetterStockfish 16.1Chess BenchmarkSMT OffSMT On - Default150K300K450K600K750K541348.84697627.07
MinAvgMaxSMT Off44.5428.0472.1SMT On - Default44.8440.6487.2OpenBenchmarking.orgWatts, Fewer Is BetterStockfish 16.1CPU Power Consumption Monitor130260390520650

Xmrig

MinAvgMaxSMT Off44.5367.1404.5SMT On - Default44.9425.0482.5OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MSMT OffSMT On - Default112233445545.3746.77

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MSMT OffSMT On - Default4K8K12K16K20KSE +/- 6.58, N = 3SE +/- 912.79, N = 1516656.319873.01. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.orgH/s Per Watt, More Is BetterXmrig 6.21Variant: GhostRider - Hash Count: 1MSMT OffSMT On - Default112233445545.3746.77
MinAvgMaxSMT Off44.5367.1404.5SMT On - Default44.9425.0482.5OpenBenchmarking.orgWatts, Fewer Is BetterXmrig 6.21CPU Power Consumption Monitor120240360480600

srsRAN Project

MinAvgMaxSMT Off44.3270.1456.6SMT On - Default44.5371.7421.8OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalSMT OffSMT On - Default4080120160200165.1452.33

OpenBenchmarking.orgMbps, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalSMT OffSMT On - Default10K20K30K40K50KSE +/- 1047.04, N = 15SE +/- 214.06, N = 344608.919454.11. (CXX) g++ options: -O3 -march=native -mavx2 -mavx -msse4.1 -mfma -mavx512f -mavx512cd -mavx512bw -mavx512dq -fno-trapping-math -fno-math-errno -ldl
OpenBenchmarking.orgMbps Per Watt, More Is BettersrsRAN Project 23.10.1-20240325Test: PDSCH Processor Benchmark, Throughput TotalSMT OffSMT On - Default4080120160200165.1452.33
MinAvgMaxSMT Off44.3270.1456.6SMT On - Default44.5371.7421.8OpenBenchmarking.orgWatts, Fewer Is BettersrsRAN Project 23.10.1-20240325CPU Power Consumption Monitor120240360480600

SVT-AV1

MinAvgMaxSMT Off44.4116.4304.8SMT On - Default44.4115.6288.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor80160240320400

OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KSMT OffSMT On - Default0.56211.12421.68632.24842.81052.4982.353

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KSMT OffSMT On - Default60120180240300SE +/- 8.78, N = 15SE +/- 7.58, N = 15290.64271.921. (CXX) g++ options: -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenBenchmarking.orgFrames Per Second Per Watt, More Is BetterSVT-AV1 2.0Encoder Mode: Preset 13 - Input: Bosphorus 4KSMT OffSMT On - Default0.56211.12421.68632.24842.81052.4982.353
MinAvgMaxSMT Off44.4116.4304.8SMT On - Default44.4115.6288.1OpenBenchmarking.orgWatts, Fewer Is BetterSVT-AV1 2.0CPU Power Consumption Monitor80160240320400

LuxCoreRender

MinAvgMaxSMT Off45.0424.4477.8SMT On - Default45.0431.6490.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUSMT OffSMT On - Default0.01670.03340.05010.06680.08350.0580.074

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUSMT OffSMT On - Default714212835SE +/- 0.24, N = 15SE +/- 0.52, N = 1524.4432.02MIN: 21.11 / MAX: 32.81MIN: 26.48 / MAX: 43.04
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPUSMT OffSMT On - Default0.01670.03340.05010.06680.08350.0580.074
MinAvgMaxSMT Off45.0424.4477.8SMT On - Default45.0431.6490.9OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor130260390520650

MinAvgMaxSMT Off45.1433.4473.4SMT On - Default44.6438.9482.6OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUSMT OffSMT On - Default0.01080.02160.03240.04320.0540.0400.048

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUSMT OffSMT On - Default510152025SE +/- 0.21, N = 15SE +/- 0.33, N = 1517.1620.94MIN: 15.64 / MAX: 21.09MIN: 19.5 / MAX: 27
OpenBenchmarking.orgM samples/sec Per Watt, More Is BetterLuxCoreRender 2.6Scene: DLSC - Acceleration: CPUSMT OffSMT On - Default0.01080.02160.03240.04320.0540.0400.048
MinAvgMaxSMT Off45.1433.4473.4SMT On - Default44.6438.9482.6OpenBenchmarking.orgWatts, Fewer Is BetterLuxCoreRender 2.6CPU Power Consumption Monitor120240360480600

Pennant

MinAvgMaxSMT Off44.5247.5476.3SMT On - Default44.5248.9471.5OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigSMT OffSMT On - Default0.98861.97722.96583.95444.943SE +/- 0.033508, N = 9SE +/- 0.073388, N = 154.1003394.3936061. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxSMT Off44.5247.5476.3SMT On - Default44.5248.9471.5OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

MinAvgMaxSMT Off44.7190.2471.9SMT On - Default44.6210.5475.6OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigSMT OffSMT On - Default0.62131.24261.86392.48523.1065SE +/- 0.039628, N = 15SE +/- 0.045208, N = 151.9619892.7612601. (CXX) g++ options: -fopenmp -lmpi_cxx -lmpi
MinAvgMaxSMT Off44.7190.2471.9SMT On - Default44.6210.5475.6OpenBenchmarking.orgWatts, Fewer Is BetterPennant 1.0.1CPU Power Consumption Monitor120240360480600

Speedb

MinAvgMaxSMT Off44.5373.9440.0SMT On - Default44.6398.2497.6OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor130260390520650

OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read While WritingSMT OffSMT On - Default10K20K30K40K50K26924.5446936.44

OpenBenchmarking.orgOp/s, More Is BetterSpeedb 2.7Test: Read While WritingSMT OffSMT On - Default4M8M12M16M20MSE +/- 205985.46, N = 15SE +/- 433421.14, N = 1210067442186878971. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread
OpenBenchmarking.orgOp/s Per Watt, More Is BetterSpeedb 2.7Test: Read While WritingSMT OffSMT On - Default10K20K30K40K50K26924.5446936.44
MinAvgMaxSMT Off44.5373.9440.0SMT On - Default44.6398.2497.6OpenBenchmarking.orgWatts, Fewer Is BetterSpeedb 2.7CPU Power Consumption Monitor130260390520650

189 Results Shown

BRL-CAD
ONNX Runtime
OpenVINO
ONNX Runtime
OpenVINO:
  Road Segmentation ADAS FP16-INT8 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
  Face Detection FP16-INT8 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
ONNX Runtime:
  ArcFace ResNet-100 - CPU - Parallel
  bertsquad-12 - CPU - Parallel
  yolov4 - CPU - Parallel
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU
  Face Detection Retail FP16-INT8 - CPU
TensorFlow
OpenVINO:
  Machine Translation EN To DE FP16 - CPU
  Person Vehicle Bike Detection FP16 - CPU
TensorFlow
OpenVINO:
  Handwritten English Recognition FP16-INT8 - CPU
  Person Re-Identification Retail FP16 - CPU
RocksDB
7-Zip Compression
Liquid-DSP
srsRAN Project
Memcached
ONNX Runtime
Embree
Aircrack-ng
Embree:
  Pathtracer ISPC - Asian Dragon
  Pathtracer ISPC - Asian Dragon Obj
ACES DGEMM
John The Ripper
OSPRay Studio
m-queens
OpenVINO
John The Ripper:
  Blowfish
  bcrypt
OpenSSL:
  ChaCha20-Poly1305
  ChaCha20
OpenVINO:
  Person Detection FP16 - CPU
  Noise Suppression Poconet-Like FP16 - CPU
uvg266
Coremark
uvg266
Timed Linux Kernel Compilation
OpenSSL
LuxCoreRender
OSPRay Studio:
  3 - 4K - 1 - Path Tracer - CPU
  3 - 4K - 16 - Path Tracer - CPU
Kvazaar
OSPRay Studio
OpenFOAM
OSPRay Studio:
  1 - 4K - 32 - Path Tracer - CPU
  1 - 4K - 16 - Path Tracer - CPU
Kvazaar
OpenVKL
LAMMPS Molecular Dynamics Simulator
NAMD
OSPRay
Blender:
  Pabellon Barcelona - CPU-Only
  Barbershop - CPU-Only
OpenVINO
Blender:
  Fishy Cat - CPU-Only
  Junkshop - CPU-Only
  Classroom - CPU-Only
Liquid-DSP
Parallel BZIP2 Compression
Y-Cruncher
GraphicsMagick
PostgreSQL:
  100 - 1000 - Read Only
  100 - 1000 - Read Only - Average Latency
GraphicsMagick
Blender
TensorFlow
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU
  Handwritten English Recognition FP16-INT8 - CPU
OpenFOAM
Y-Cruncher
7-Zip Compression
OpenVINO
NAS Parallel Benchmarks
OpenVINO
OpenSSL
Liquid-DSP
Appleseed
LULESH
OpenVINO
ClickHouse
OSPRay:
  particle_volume/scivis/real_time
  particle_volume/ao/real_time
TensorFlow
ClickHouse:
  100M Rows Hits Dataset, First Run / Cold Cache
  100M Rows Hits Dataset, Second Run
QuantLib
Timed Linux Kernel Compilation
oneDNN
OpenVINO
ASTC Encoder:
  Exhaustive
  Very Thorough
VVenC
ONNX Runtime
ASTC Encoder
NAS Parallel Benchmarks
OpenFOAM
SVT-AV1
VVenC
TensorFlow:
  CPU - 64 - AlexNet
  CPU - 1 - AlexNet
GraphicsMagick
SVT-AV1
CloverLeaf
TensorFlow
CloverLeaf
OpenRadioss
RocksDB
Timed Mesa Compilation
OpenSSL
OpenVINO
Speedb
OpenSSL
Timed Gem5 Compilation
OpenVINO
Timed Godot Game Engine Compilation
Kvazaar
ASKAP
NAMD
TensorFlow
GPAW
NAS Parallel Benchmarks
TensorFlow
OpenFOAM
Timed LLVM Compilation
ASKAP
Timed Node.js Compilation
PyTorch
SVT-AV1
PyTorch
TensorFlow
PyTorch
TensorFlow
ASTC Encoder
LAMMPS Molecular Dynamics Simulator
ASKAP
PyTorch
OpenRadioss
NAS Parallel Benchmarks
Algebraic Multi-Grid Benchmark
PyTorch
Xcompact3d Incompact3d
Intel Open Image Denoise
PyTorch
NWChem
OpenSSL
GROMACS
Timed ImageMagick Compilation
TensorFlow
Intel Open Image Denoise
OpenRadioss
PyTorch
Intel Open Image Denoise
High Performance Conjugate Gradient
WRF
PyTorch
OpenVINO
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring
  CPU Power Consumption Monitor
  Chess Benchmark
Stockfish
Xmrig:
  CPU Power Consumption Monitor
  GhostRider - 1M
Xmrig
srsRAN Project:
  CPU Power Consumption Monitor
  PDSCH Processor Benchmark, Throughput Total
srsRAN Project
SVT-AV1:
  CPU Power Consumption Monitor
  Preset 13 - Bosphorus 4K
SVT-AV1
LuxCoreRender:
  CPU Power Consumption Monitor
  Orange Juice - CPU
LuxCoreRender
LuxCoreRender:
  CPU Power Consumption Monitor
  DLSC - CPU
LuxCoreRender
Pennant
Pennant
Pennant
Pennant
Speedb:
  CPU Power Consumption Monitor
  Read While Writing
Speedb

SMT On - Default

Processor: AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores / 256 Threads), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 16 September 2024 15:49 by user phoronix.

SMT Off

Processor: AMD EPYC 9755 128-Core @ 2.70GHz (128 Cores), Motherboard: AMD VOLCANO (RVOT1000D BIOS), Chipset: AMD Device 153a, Memory: 12 x 64GB DDR5-6000MT/s Samsung M321R8GA0PB1-CCPKC, Disk: 2 x 1920GB KIOXIA KCD8XPUG1T92, Graphics: ASPEED, Network: Broadcom NetXtreme BCM5720 PCIe

OS: Ubuntu 24.04, Kernel: 6.10.0-phx (x86_64), Compiler: GCC 13.2.0, File-System: ext4, Screen Resolution: 1920x1200

Kernel Notes: Transparent Huge Pages: madvise
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-OiuXZC/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v
Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xb002110
Java Notes: OpenJDK Runtime Environment (build 21.0.3-ea+7-Ubuntu-1build1)
Python Notes: Python 3.12.2
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 + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: disabled; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Testing initiated at 18 September 2024 01:09 by user phoronix.