AMD EPYC Genoa Memory Scaling

Benchmarks by Michael Larabel for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2212240-NE-AMDEPYCGE62&sro&grs.

AMD EPYC Genoa Memory ScalingProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen Resolution12c10c8c6c2 x AMD EPYC 9654 96-Core @ 2.40GHz (192 Cores / 384 Threads)AMD Titanite_4G (RTI1002E BIOS)AMD Device 14a41520GB800GB INTEL SSDPF21Q800GBASPEEDVGA HDMIBroadcom NetXtreme BCM5720 PCIeUbuntu 22.106.1.0-phx (x86_64)GNOME Shell 43.0X Server 1.21.1.41.3.224GCC 12.2.0 + Clang 15.0.2-1ext41920x10801264GB1008GB768GBOpenBenchmarking.orgKernel Details- Transparent Huge Pages: madviseCompiler Details- --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-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-12-U8K4Qv/gcc-12-12.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-12-U8K4Qv/gcc-12-12.2.0/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 Details- Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110dJava Details- OpenJDK Runtime Environment (build 11.0.17+8-post-Ubuntu-1ubuntu2)Python Details- Python 3.10.7Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected

AMD EPYC Genoa Memory Scalingincompact3d: X3D-benchmarking input.i3dopenfoam: drivaerFastback, Medium Mesh Size - Execution Timerelion: Basic - CPUwrf: conus 2.5kmnpb: MG.Cnpb: SP.Cgraph500: 26deepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamnekrs: TurboPipe Periodicopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUtensorflow: CPU - 256 - ResNet-50gpaw: Carbon Nanotubenpb: CG.Ccompress-7zip: Compression Ratingopenvkl: vklBenchmark ISPConednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUnpb: LU.Coidn: RTLightmap.hdr.4096x4096oidn: RT.hdr_alb_nrm.3840x2160rodinia: OpenMP Streamclusteronednn: Recurrent Neural Network Inference - u8s8f32 - CPUkvazaar: Bosphorus 4K - Very Fastcassandra: Writesgromacs: MPI CPU - water_GMX50_bareonednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUxmrig: Monero - 1Mopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUbuild-gdb: Time To Compilebuild-gem5: Time To Compilecockroach: KV, 50% Reads - 512embree: Pathtracer ISPC - Asian Dragoncockroach: KV, 10% Reads - 512openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUbuild-linux-kernel: defconfigopenvino: Age Gender Recognition Retail 0013 FP16 - CPUrodinia: OpenMP CFD Solverblender: BMW27 - CPU-Onlycockroach: KV, 10% Reads - 1024embree: Pathtracer ISPC - Crownkvazaar: Bosphorus 4K - Ultra Fastospray: particle_volume/scivis/real_timedeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamcockroach: KV, 60% Reads - 512avifenc: 10, Losslessospray: particle_volume/ao/real_timenginx: 500dacapobench: H2cockroach: KV, 50% Reads - 1024avifenc: 6kvazaar: Bosphorus 4K - Mediumcompress-7zip: Decompression Ratingopenvino: Age Gender Recognition Retail 0013 FP16 - CPUdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streambuild-llvm: Ninjaopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUbuild-nodejs: Time To Compileonnx: fcn-resnet101-11 - CPU - Standardospray: gravity_spheres_volume/dim_512/pathtracer/real_timesimdjson: TopTweetdacapobench: Jythonblender: Barbershop - CPU-Onlybuild-linux-kernel: allmodconfigdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamavifenc: 0deepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamcockroach: KV, 60% Reads - 1024build-apache: Time To Compilenwchem: C240 Buckyballcockroach: MoVR - 512build-godot: Time To Compileopenvino: Vehicle Detection FP16-INT8 - CPUopenradioss: Bird Strike on Windshieldopenvino: Vehicle Detection FP16-INT8 - CPUblender: Classroom - CPU-Onlyavifenc: 6, Losslessdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamopenradioss: INIVOL and Fluid Structure Interaction Drop Containeropenvino: Weld Porosity Detection FP16 - CPUxmrig: Wownero - 1Mopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUmt-dgemm: Sustained Floating-Point Rateopenradioss: Bumper Beamopenvino: Weld Porosity Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUastcenc: Exhaustivestargate: 192000 - 1024ospray: particle_volume/pathtracer/real_timesimdjson: LargeRandopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUcockroach: MoVR - 1024simdjson: PartialTweetsospray: gravity_spheres_volume/dim_512/scivis/real_timebuild-mplayer: Time To Compileospray: gravity_spheres_volume/dim_512/ao/real_timeavifenc: 2openvino: Weld Porosity Detection FP16-INT8 - CPUminibude: OpenMP - BM2minibude: OpenMP - BM2build2: Time To Compileastcenc: Thoroughopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUbuild-mesa: Time To Compilenamd: ATPase Simulation - 327,506 Atomssimdjson: DistinctUserIDstargate: 96000 - 1024build-php: Time To Compileliquid-dsp: 256 - 256 - 57liquid-dsp: 384 - 256 - 57simdjson: Kostyacockroach: KV, 95% Reads - 1024cockroach: KV, 95% Reads - 512onednn: Recurrent Neural Network Training - u8s8f32 - CPUonednn: IP Shapes 3D - bf16bf16bf16 - CPUsvt-av1: Preset 12 - Bosphorus 4Kluxcorerender: Orange Juice - CPUluxcorerender: Danish Mood - CPUnpb: IS.Dhpcg: 12c10c8c6c125.526248109.53721128.1014070.19209846.76260471.50565152000111.8909856.0186125.7196761.485382146200000049.98959.16109.1323.15180225.0192317613252275.86489164.651.653.526.0012344.2973.4425179318.7060.44693042.951110.68104604.642.981109.4541.709139.23847621.9213.750735970.0119606.2125.501147769.266.0508.5836846.9182.449877.8342.797084.247084.350652330.14.24143.7061201032.06480247465.52.45962.5611814350.551964.273048.767375.6556.487394.65101.46525453.77486.59338081.03147.1471133.282363.2471133.477452573.320.4611537.1948.534.03211018.37216.884.3520.925.287615.4474155.47970.971195.910280.079081.579867.41126465.6101.74470.9870.40773379.864.859038.4711.72502.829061229.2691.255.3019171.51953.85.6543.12627.77743.977534.8489.958640.310345.61249.917106.5663250.34191.4320.1170.127836.864.34589044.51910347000000103470000004.1164661.864467.61968.703.95471251.76928.829.698491.0186.8143146.289830117.94003151.3984563.183177097.42239496.01574018000113.4079844.4268128.9249742.795678625800000051.29934.71105.9123.37381179.0089343313172325.71489995.201.633.446.2852438.0075.3524360318.6770.46345443.181104.59102599.642.941110.4442.412134.37349102.7214.309335993.1122938.2325.407147717.326.0748.4235776.8184.734677.3042.999984.265784.482251748.84.33743.0316198858.66483248449.02.41162.2311716270.551965.560648.743175.4406.457425.10101.94125554.40836.49332980.37145.4101133.182163.2461135.184551959.520.4801531949.633.61611066.16218.224.3320.765.286611.2926156.53740.981201.139179.713981.159900.47127226.6102.01469.4370.61377579.704.839063.8411.76372.806190230.2821.255.2819254.08949.55.6743.32877.75543.996934.9099.918666.980346.67949.800106.8542249.12192.3020.2050.127596.844.35455644.60810340000000103526666674.1162029.860769.72030.724.00938241.36928.199.627124.9248.2945270.091271166.14971221.3366551.876153458.78208535.23531854000123.8576773.0686135.6212705.711674024700000054.80875.39105.0124.59879784.1587943013252371.78466769.541.643.476.0182375.4573.0424085418.6780.46579642.221129.01101953.542.591119.7942.409136.79347596.6217.406034832.9123571.6825.528152292.395.9708.3436685.7185.490776.8443.844284.154684.211552515.24.25243.9700197081.98473147498.12.42061.8111599010.551954.122748.998275.7256.497389.00101.14925754.50876.57336980.18147.3771136.854462.9611137.511952559.020.5891519.6960.333.90511108.16219.454.3120.685.270614.6105155.81910.981201.983979.686581.099931.49127081.2101.26472.8471.01032379.204.829113.1111.80902.811555228.5811.255.2619278.93946.95.6643.43107.80844.230234.6879.908615.967344.63949.871107.1108249.26192.2520.1070.127686.864.35140244.58310337666667103496666674.1158195.564111.91982.153.99305227.89829.049.566675.7145.0005348.880025227.89595258.5007432.655117733.57167474.70392496000150.9167635.0246166.4322575.751865955433333358.67817.2795.6726.30871662.2882492612122471.57454360.621.543.296.4092479.6271.4124688217.9400.46505941.441150.54100446.241.331153.7043.245134.69547428.0221.289835742.3121027.2524.747151213.176.1528.3336329.6187.610775.8643.239682.261382.486951275.14.25043.3575196805.30483047593.92.43561.4011774840.541930.327749.627876.7476.567306.47102.77625354.60546.55334579.93145.7661148.496463.8031148.327852626.420.7201517.9954.733.67111150.32219.104.3020.715.330608.5336157.21640.971190.528680.439980.819959.38126057.7101.08473.6970.89831279.624.819081.7311.82072.824814230.4401.245.2819314.04952.75.6943.28997.77344.271634.8749.898651.924346.07750.084106.5095250.49191.2920.1570.128206.834.36476744.69810340333333103490000004.1160137.362666.52072.573.96488221.16128.909.495690.0136.5411OpenBenchmarking.org

Xcompact3d Incompact3d

Input: X3D-benchmarking input.i3d

OpenBenchmarking.orgSeconds, Fewer Is BetterXcompact3d Incompact3d 2021-03-11Input: X3D-benchmarking input.i3d10c12c6c8c80160240320400SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 4.79, N = 9SE +/- 2.69, N = 9146.29125.53348.88270.091. (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

OpenFOAM

Input: drivaerFastback, Medium Mesh Size - Execution Time

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution Time10c12c6c8c50100150200250117.94109.54227.90166.151. (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

RELION

Test: Basic - Device: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterRELION 3.1.1Test: Basic - Device: CPU10c12c6c8c60120180240300SE +/- 1.86, N = 4SE +/- 1.38, N = 5SE +/- 2.59, N = 6SE +/- 2.88, N = 3151.40128.10258.50221.341. (CXX) g++ options: -fopenmp -std=c++0x -O3 -rdynamic -ldl -ltiff -lfftw3f -lfftw3 -lpng -lmpi_cxx -lmpi

WRF

Input: conus 2.5km

OpenBenchmarking.orgSeconds, Fewer Is BetterWRF 4.2.2Input: conus 2.5km10c12c6c8c160032004800640080004563.184070.197432.666551.881. (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

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C10c12c6c8c40K80K120K160K200KSE +/- 2631.10, N = 15SE +/- 2393.90, N = 3SE +/- 1626.80, N = 15SE +/- 2089.98, N = 15177097.42209846.76117733.57153458.781. (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 4.1.4

NAS Parallel Benchmarks

Test / Class: SP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.C10c12c6c8c60K120K180K240K300KSE +/- 726.36, N = 3SE +/- 1589.72, N = 3SE +/- 1838.44, N = 3SE +/- 1630.30, N = 3239496.01260471.50167474.70208535.231. (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 4.1.4

Graph500

Scale: 26

OpenBenchmarking.orgsssp median_TEPS, More Is BetterGraph500 3.0Scale: 2610c12c6c8c120M240M360M480M600M5740180005651520003924960005318540001. (CC) gcc options: -fcommon -O3 -lpthread -lm -lmpi

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream10c12c6c8c306090120150SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 1.56, N = 15SE +/- 0.19, N = 3113.41111.89150.92123.86

Neural Magic DeepSparse

Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-Stream10c12c6c8c2004006008001000SE +/- 0.53, N = 3SE +/- 0.57, N = 3SE +/- 6.69, N = 15SE +/- 1.22, N = 3844.43856.02635.02773.07

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream10c12c6c8c4080120160200SE +/- 0.43, N = 3SE +/- 0.11, N = 3SE +/- 1.66, N = 15SE +/- 0.38, N = 3128.92125.72166.43135.62

Neural Magic DeepSparse

Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream10c12c6c8c160320480640800SE +/- 2.41, N = 3SE +/- 0.72, N = 3SE +/- 6.13, N = 15SE +/- 2.11, N = 3742.80761.49575.75705.71

nekRS

Input: TurboPipe Periodic

OpenBenchmarking.orgFLOP/s, More Is BetternekRS 22.0Input: TurboPipe Periodic10c12c6c8c200000M400000M600000M800000M1000000MSE +/- 7825985326.68, N = 3SE +/- 9551971733.63, N = 3SE +/- 1934071468.29, N = 3SE +/- 5892587066.25, N = 37862580000008214620000006595543333337402470000001. (CXX) g++ options: -fopenmp -O2 -march=native -mtune=native -ftree-vectorize -lmpi_cxx -lmpi

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPU10c12c6c8c1326395265SE +/- 0.08, N = 3SE +/- 0.12, N = 3SE +/- 0.37, N = 3SE +/- 0.57, N = 651.2949.9858.6754.80MIN: 40.28 / MAX: 292.83MIN: 38.24 / MAX: 187.97MIN: 43.56 / MAX: 315.05MIN: 40.7 / MAX: 276.861. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Machine Translation EN To DE FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Machine Translation EN To DE FP16 - Device: CPU10c12c6c8c2004006008001000SE +/- 1.48, N = 3SE +/- 2.32, N = 3SE +/- 5.14, N = 3SE +/- 8.79, N = 6934.71959.16817.27875.391. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

TensorFlow

Device: CPU - Batch Size: 256 - Model: ResNet-50

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: ResNet-5010c12c6c8c20406080100SE +/- 0.36, N = 3SE +/- 0.48, N = 3SE +/- 0.26, N = 3SE +/- 0.48, N = 3105.91109.1395.67105.01

GPAW

Input: Carbon Nanotube

OpenBenchmarking.orgSeconds, Fewer Is BetterGPAW 22.1Input: Carbon Nanotube10c12c6c8c612182430SE +/- 0.13, N = 3SE +/- 0.23, N = 5SE +/- 0.20, N = 3SE +/- 0.18, N = 323.3723.1526.3124.601. (CC) gcc options: -shared -fwrapv -O2 -lxc -lblas -lmpi

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.C10c12c6c8c20K40K60K80K100KSE +/- 899.80, N = 15SE +/- 812.04, N = 15SE +/- 554.69, N = 3SE +/- 907.72, N = 1581179.0080225.0171662.2879784.151. (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 4.1.4

7-Zip Compression

Test: Compression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression Rating10c12c6c8c200K400K600K800K1000KSE +/- 2580.44, N = 3SE +/- 6636.11, N = 3SE +/- 7292.38, N = 3SE +/- 3797.71, N = 38934339231768249268794301. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenVKL

Benchmark: vklBenchmark ISPC

OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPC10c12c6c8c30060090012001500SE +/- 11.03, N = 9SE +/- 6.93, N = 3SE +/- 15.59, N = 3SE +/- 8.82, N = 31317132512121325MIN: 327 / MAX: 5660MIN: 329 / MAX: 4553MIN: 328 / MAX: 4115MIN: 330 / MAX: 5664

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU10c12c6c8c5001000150020002500SE +/- 25.04, N = 15SE +/- 24.22, N = 3SE +/- 31.16, N = 3SE +/- 25.14, N = 152325.712275.862471.572371.78MIN: 2171.69MIN: 2213.34MIN: 2410.73MIN: 2234.231. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C10c12c6c8c100K200K300K400K500KSE +/- 2546.14, N = 3SE +/- 5489.08, N = 4SE +/- 4680.97, N = 5SE +/- 5095.33, N = 5489995.20489164.65454360.62466769.541. (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 4.1.4

Intel Open Image Denoise

Run: RTLightmap.hdr.4096x4096

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x409610c12c6c8c0.37130.74261.11391.48521.8565SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 31.631.651.541.64

Intel Open Image Denoise

Run: RT.hdr_alb_nrm.3840x2160

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x216010c12c6c8c0.7921.5842.3763.1683.96SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 33.443.523.293.47

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP Streamcluster10c12c6c8c246810SE +/- 0.079, N = 15SE +/- 0.089, N = 15SE +/- 0.050, N = 3SE +/- 0.078, N = 156.2856.0016.4096.0181. (CXX) g++ options: -O2 -lOpenCL

oneDNN

Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU10c12c6c8c5001000150020002500SE +/- 30.76, N = 3SE +/- 21.01, N = 3SE +/- 25.74, N = 15SE +/- 21.41, N = 32438.002344.292479.622375.45MIN: 2353.97MIN: 2288.85MIN: 2293.49MIN: 2319.451. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Very Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Very Fast10c12c6c8c20406080100SE +/- 0.74, N = 3SE +/- 0.58, N = 10SE +/- 0.77, N = 3SE +/- 1.04, N = 375.3573.4471.4173.041. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 4.0Test: Writes10c12c6c8c50K100K150K200K250KSE +/- 2429.87, N = 3SE +/- 3742.45, N = 12SE +/- 2957.03, N = 3SE +/- 1899.17, N = 3243603251793246882240854

GROMACS

Implementation: MPI CPU - Input: water_GMX50_bare

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_bare10c12c6c8c510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 318.6818.7117.9418.681. (CXX) g++ options: -O3

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU10c12c6c8c0.10480.20960.31440.41920.524SE +/- 0.005241, N = 4SE +/- 0.005042, N = 3SE +/- 0.005815, N = 3SE +/- 0.006374, N = 30.4634540.4469300.4650590.465796MIN: 0.38MIN: 0.38MIN: 0.38MIN: 0.381. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPU10c12c6c8c1020304050SE +/- 0.20, N = 3SE +/- 0.32, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 343.1842.9541.4442.221. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Detection FP32 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP32 - Device: CPU10c12c6c8c2004006008001000SE +/- 5.36, N = 3SE +/- 8.73, N = 3SE +/- 1.87, N = 3SE +/- 0.54, N = 31104.591110.681150.541129.01MIN: 807.38 / MAX: 1818.79MIN: 833.53 / MAX: 1865.19MIN: 870.26 / MAX: 1902.46MIN: 850.94 / MAX: 1870.941. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Xmrig

Variant: Monero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1M10c12c6c8c20K40K60K80K100KSE +/- 152.19, N = 3SE +/- 328.13, N = 3SE +/- 214.10, N = 3SE +/- 383.60, N = 3102599.6104604.6100446.2101953.51. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPU10c12c6c8c1020304050SE +/- 0.12, N = 3SE +/- 0.13, N = 3SE +/- 0.17, N = 3SE +/- 0.15, N = 342.9442.9841.3342.591. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Detection FP16 - Device: CPU10c12c6c8c2004006008001000SE +/- 2.71, N = 3SE +/- 3.30, N = 3SE +/- 4.42, N = 3SE +/- 3.60, N = 31110.441109.451153.701119.79MIN: 769.04 / MAX: 1860.23MIN: 810.74 / MAX: 1835.01MIN: 853.88 / MAX: 1939.06MIN: 808.33 / MAX: 1875.911. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Timed GDB GNU Debugger Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 10.2Time To Compile10c12c6c8c1020304050SE +/- 0.08, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.03, N = 342.4141.7143.2542.41

Timed Gem5 Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Gem5 Compilation 21.2Time To Compile10c12c6c8c306090120150SE +/- 0.36, N = 3SE +/- 0.16, N = 3SE +/- 0.57, N = 3SE +/- 0.77, N = 3134.37139.24134.70136.79

CockroachDB

Workload: KV, 50% Reads - Concurrency: 512

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 51210c12c6c8c11K22K33K44K55KSE +/- 514.54, N = 3SE +/- 464.03, N = 15SE +/- 32.88, N = 3SE +/- 454.84, N = 1549102.747621.947428.047596.6

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon10c12c6c8c50100150200250SE +/- 0.47, N = 3SE +/- 0.13, N = 3SE +/- 0.46, N = 3SE +/- 0.39, N = 3214.31213.75221.29217.41MIN: 209.11 / MAX: 223.97MIN: 209.16 / MAX: 225.43MIN: 215.19 / MAX: 233.21MIN: 211.73 / MAX: 230.1

CockroachDB

Workload: KV, 10% Reads - Concurrency: 512

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 10% Reads - Concurrency: 51210c12c6c8c8K16K24K32K40KSE +/- 270.36, N = 15SE +/- 343.66, N = 15SE +/- 438.30, N = 15SE +/- 351.71, N = 635993.135970.035742.334832.9

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU10c12c6c8c30K60K90K120K150KSE +/- 815.42, N = 3SE +/- 1214.59, N = 3SE +/- 681.80, N = 3SE +/- 1158.58, N = 3122938.23119606.21121027.25123571.681. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Timed Linux Kernel Compilation

Build: defconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: defconfig10c12c6c8c612182430SE +/- 0.21, N = 14SE +/- 0.19, N = 11SE +/- 0.22, N = 7SE +/- 0.21, N = 925.4125.5024.7525.53

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU10c12c6c8c30K60K90K120K150KSE +/- 1134.97, N = 10SE +/- 745.28, N = 3SE +/- 365.43, N = 3SE +/- 994.61, N = 3147717.32147769.26151213.17152292.391. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 3.1Test: OpenMP CFD Solver10c12c6c8c246810SE +/- 0.014, N = 3SE +/- 0.031, N = 3SE +/- 0.024, N = 3SE +/- 0.016, N = 36.0746.0506.1525.9701. (CXX) g++ options: -O2 -lOpenCL

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: BMW27 - Compute: CPU-Only10c12c6c8c246810SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 38.428.588.338.34

CockroachDB

Workload: KV, 10% Reads - Concurrency: 1024

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 10% Reads - Concurrency: 102410c12c6c8c8K16K24K32K40KSE +/- 346.25, N = 3SE +/- 155.07, N = 3SE +/- 206.35, N = 3SE +/- 322.68, N = 335776.836846.936329.636685.7

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Crown10c12c6c8c4080120160200SE +/- 0.47, N = 3SE +/- 1.01, N = 3SE +/- 0.33, N = 3SE +/- 0.36, N = 3184.73182.45187.61185.49MIN: 137.82 / MAX: 210.21MIN: 128.42 / MAX: 209.42MIN: 146.69 / MAX: 208.25MIN: 134.45 / MAX: 211.64

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Ultra Fast

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Ultra Fast10c12c6c8c20406080100SE +/- 1.02, N = 3SE +/- 0.66, N = 3SE +/- 0.63, N = 3SE +/- 0.71, N = 377.3077.8375.8676.841. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

OSPRay

Benchmark: particle_volume/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/scivis/real_time10c12c6c8c1020304050SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 343.0042.8043.2443.84

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream10c12c6c8c20406080100SE +/- 0.03, N = 3SE +/- 0.21, N = 3SE +/- 0.25, N = 3SE +/- 0.16, N = 384.2784.2582.2684.15

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream10c12c6c8c20406080100SE +/- 0.04, N = 3SE +/- 0.18, N = 3SE +/- 0.31, N = 3SE +/- 0.04, N = 384.4884.3582.4984.21

CockroachDB

Workload: KV, 60% Reads - Concurrency: 512

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 51210c12c6c8c11K22K33K44K55KSE +/- 620.92, N = 15SE +/- 268.61, N = 3SE +/- 555.56, N = 15SE +/- 411.73, N = 1351748.852330.151275.152515.2

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 10, Lossless10c12c6c8c0.97581.95162.92743.90324.879SE +/- 0.055, N = 3SE +/- 0.024, N = 3SE +/- 0.043, N = 3SE +/- 0.009, N = 34.3374.2414.2504.2521. (CXX) g++ options: -O3 -fPIC -lm

OSPRay

Benchmark: particle_volume/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/ao/real_time10c12c6c8c1020304050SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 343.0343.7143.3643.97

nginx

Connections: 500

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 50010c12c6c8c40K80K120K160K200KSE +/- 335.64, N = 3SE +/- 291.63, N = 3SE +/- 113.87, N = 3SE +/- 453.48, N = 3198858.66201032.06196805.30197081.981. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H210c12c6c8c10002000300040005000SE +/- 39.79, N = 20SE +/- 53.17, N = 20SE +/- 36.16, N = 20SE +/- 40.50, N = 204832480248304731

CockroachDB

Workload: KV, 50% Reads - Concurrency: 1024

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 50% Reads - Concurrency: 102410c12c6c8c10K20K30K40K50KSE +/- 380.16, N = 3SE +/- 366.75, N = 15SE +/- 391.13, N = 9SE +/- 468.66, N = 1548449.047465.547593.947498.1

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 610c12c6c8c0.55331.10661.65992.21322.7665SE +/- 0.003, N = 3SE +/- 0.016, N = 3SE +/- 0.004, N = 3SE +/- 0.017, N = 32.4112.4592.4352.4201. (CXX) g++ options: -O3 -fPIC -lm

Kvazaar

Video Input: Bosphorus 4K - Video Preset: Medium

OpenBenchmarking.orgFrames Per Second, More Is BetterKvazaar 2.1Video Input: Bosphorus 4K - Video Preset: Medium10c12c6c8c1428425670SE +/- 0.11, N = 3SE +/- 0.68, N = 3SE +/- 0.53, N = 3SE +/- 0.73, N = 362.2362.5661.4061.811. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt

7-Zip Compression

Test: Decompression Rating

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression Rating10c12c6c8c300K600K900K1200K1500KSE +/- 5138.86, N = 3SE +/- 3305.67, N = 3SE +/- 2020.82, N = 3SE +/- 9235.88, N = 311716271181435117748411599011. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU10c12c6c8c0.12380.24760.37140.49520.619SE +/- 0.00, N = 10SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.550.550.540.55MIN: 0.5 / MAX: 41.23MIN: 0.5 / MAX: 34.71MIN: 0.5 / MAX: 34.19MIN: 0.5 / MAX: 30.681. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream10c12c6c8c400800120016002000SE +/- 1.61, N = 3SE +/- 4.95, N = 3SE +/- 8.40, N = 3SE +/- 1.56, N = 31965.561964.271930.331954.12

Neural Magic DeepSparse

Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-Stream10c12c6c8c1122334455SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.04, N = 348.7448.7749.6349.00

Timed LLVM Compilation

Build System: Ninja

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 13.0Build System: Ninja10c12c6c8c20406080100SE +/- 0.21, N = 3SE +/- 0.23, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 375.4475.6676.7575.73

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPU10c12c6c8c246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.456.486.566.49MIN: 4.97 / MAX: 59.86MIN: 5.06 / MAX: 59.88MIN: 4.99 / MAX: 59.46MIN: 4.93 / MAX: 59.511. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Vehicle Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16 - Device: CPU10c12c6c8c16003200480064008000SE +/- 13.32, N = 3SE +/- 2.30, N = 3SE +/- 4.59, N = 3SE +/- 6.27, N = 37425.107394.657306.477389.001. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Timed Node.js Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To Compile10c12c6c8c20406080100SE +/- 0.29, N = 3SE +/- 0.26, N = 3SE +/- 0.06, N = 3SE +/- 0.22, N = 3101.94101.47102.78101.15

ONNX Runtime

Model: fcn-resnet101-11 - Device: CPU - Executor: Standard

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: Standard10c12c6c8c60120180240300SE +/- 3.09, N = 3SE +/- 2.33, N = 7SE +/- 2.17, N = 12SE +/- 2.84, N = 52552542532571. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto=auto -fno-fat-lto-objects -ldl -lrt

OSPRay

Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_time10c12c6c8c1224364860SE +/- 0.12, N = 3SE +/- 0.50, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 354.4153.7754.6154.51

simdjson

Throughput Test: TopTweet

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweet10c12c6c8c246810SE +/- 0.07, N = 6SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.496.596.556.571. (CXX) g++ options: -O3

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython10c12c6c8c7001400210028003500SE +/- 18.49, N = 4SE +/- 29.26, N = 4SE +/- 21.34, N = 4SE +/- 35.24, N = 43329338033453369

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Barbershop - Compute: CPU-Only10c12c6c8c20406080100SE +/- 0.15, N = 3SE +/- 0.21, N = 3SE +/- 0.31, N = 3SE +/- 0.24, N = 380.3781.0379.9380.18

Timed Linux Kernel Compilation

Build: allmodconfig

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 6.1Build: allmodconfig10c12c6c8c306090120150SE +/- 0.72, N = 3SE +/- 0.90, N = 3SE +/- 0.14, N = 3SE +/- 1.03, N = 3145.41147.15145.77147.38

Neural Magic DeepSparse

Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream10c12c6c8c2004006008001000SE +/- 0.20, N = 3SE +/- 0.82, N = 3SE +/- 0.67, N = 3SE +/- 0.88, N = 31133.181133.281148.501136.85

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 010c12c6c8c1428425670SE +/- 0.27, N = 3SE +/- 0.18, N = 3SE +/- 0.47, N = 3SE +/- 0.03, N = 363.2563.2563.8062.961. (CXX) g++ options: -O3 -fPIC -lm

Neural Magic DeepSparse

Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream10c12c6c8c2004006008001000SE +/- 1.00, N = 3SE +/- 1.25, N = 3SE +/- 1.05, N = 3SE +/- 1.67, N = 31135.181133.481148.331137.51

CockroachDB

Workload: KV, 60% Reads - Concurrency: 1024

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 60% Reads - Concurrency: 102410c12c6c8c11K22K33K44K55KSE +/- 400.61, N = 10SE +/- 239.52, N = 3SE +/- 448.33, N = 3SE +/- 447.89, N = 351959.552573.352626.452559.0

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compile10c12c6c8c510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 320.4820.4620.7220.59

NWChem

Input: C240 Buckyball

OpenBenchmarking.orgSeconds, Fewer Is BetterNWChem 7.0.2Input: C240 Buckyball10c12c6c8c300600900120015001531.01537.11517.91519.61. (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

CockroachDB

Workload: MoVR - Concurrency: 512

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: MoVR - Concurrency: 51210c12c6c8c2004006008001000SE +/- 3.66, N = 3SE +/- 3.38, N = 3SE +/- 4.87, N = 3SE +/- 9.03, N = 3949.6948.5954.7960.3

Timed Godot Game Engine Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Godot Game Engine Compilation 3.2.3Time To Compile10c12c6c8c816243240SE +/- 0.04, N = 3SE +/- 0.40, N = 4SE +/- 0.11, N = 3SE +/- 0.19, N = 333.6234.0333.6733.91

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPU10c12c6c8c2K4K6K8K10KSE +/- 3.30, N = 3SE +/- 1.42, N = 3SE +/- 1.79, N = 3SE +/- 1.79, N = 311066.1611018.3711150.3211108.161. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenRadioss

Model: Bird Strike on Windshield

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bird Strike on Windshield10c12c6c8c50100150200250SE +/- 0.54, N = 3SE +/- 0.38, N = 3SE +/- 0.14, N = 3SE +/- 0.19, N = 3218.22216.88219.10219.45

OpenVINO

Model: Vehicle Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Vehicle Detection FP16-INT8 - Device: CPU10c12c6c8c0.97881.95762.93643.91524.894SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.334.354.304.31MIN: 3.51 / MAX: 41.25MIN: 3.52 / MAX: 41.44MIN: 3.52 / MAX: 43.57MIN: 3.51 / MAX: 43.891. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.4Blend File: Classroom - Compute: CPU-Only10c12c6c8c510152025SE +/- 0.09, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 320.7620.9220.7120.68

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6, Lossless10c12c6c8c1.19932.39863.59794.79725.9965SE +/- 0.044, N = 3SE +/- 0.076, N = 3SE +/- 0.055, N = 3SE +/- 0.034, N = 35.2865.2875.3305.2701. (CXX) g++ options: -O3 -fPIC -lm

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream10c12c6c8c130260390520650SE +/- 2.48, N = 3SE +/- 1.72, N = 3SE +/- 2.24, N = 3SE +/- 1.32, N = 3611.29615.45608.53614.61

Neural Magic DeepSparse

Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream10c12c6c8c306090120150SE +/- 0.55, N = 3SE +/- 0.46, N = 3SE +/- 0.58, N = 3SE +/- 0.27, N = 3156.54155.48157.22155.82

OpenVINO

Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU10c12c6c8c0.22050.4410.66150.8821.1025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.980.970.970.98MIN: 0.85 / MAX: 39.82MIN: 0.85 / MAX: 22.9MIN: 0.86 / MAX: 33.82MIN: 0.86 / MAX: 39.581. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream10c12c6c8c30060090012001500SE +/- 0.69, N = 3SE +/- 4.04, N = 3SE +/- 1.21, N = 3SE +/- 3.22, N = 31201.141195.911190.531201.98

Neural Magic DeepSparse

Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-Stream10c12c6c8c20406080100SE +/- 0.03, N = 3SE +/- 0.27, N = 3SE +/- 0.07, N = 3SE +/- 0.20, N = 379.7180.0880.4479.69

OpenRadioss

Model: INIVOL and Fluid Structure Interaction Drop Container

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: INIVOL and Fluid Structure Interaction Drop Container10c12c6c8c20406080100SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.08, N = 3SE +/- 0.12, N = 381.1581.5780.8181.09

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPU10c12c6c8c2K4K6K8K10KSE +/- 2.08, N = 3SE +/- 2.57, N = 3SE +/- 3.42, N = 3SE +/- 7.50, N = 39900.479867.419959.389931.491. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Xmrig

Variant: Wownero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Wownero - Hash Count: 1M10c12c6c8c30K60K90K120K150KSE +/- 70.55, N = 3SE +/- 849.90, N = 3SE +/- 349.73, N = 3SE +/- 122.05, N = 3127226.6126465.6126057.7127081.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPU10c12c6c8c20406080100SE +/- 0.03, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3102.01101.74101.08101.261. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Face Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16 - Device: CPU10c12c6c8c100200300400500SE +/- 0.10, N = 3SE +/- 0.21, N = 3SE +/- 0.14, N = 3SE +/- 0.27, N = 3469.43470.98473.69472.84MIN: 432.92 / MAX: 555.25MIN: 451.07 / MAX: 556.04MIN: 423.34 / MAX: 579.41MIN: 394.37 / MAX: 553.151. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rate10c12c6c8c1632486480SE +/- 0.02, N = 3SE +/- 0.33, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 370.6170.4170.9071.011. (CC) gcc options: -O3 -march=native -fopenmp

OpenRadioss

Model: Bumper Beam

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bumper Beam10c12c6c8c20406080100SE +/- 0.75, N = 3SE +/- 0.79, N = 3SE +/- 0.71, N = 3SE +/- 0.70, N = 379.7079.8679.6279.20

OpenVINO

Model: Weld Porosity Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16 - Device: CPU10c12c6c8c1.09132.18263.27394.36525.4565SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 34.834.854.814.82MIN: 4.08 / MAX: 28.68MIN: 4.06 / MAX: 28.62MIN: 4.14 / MAX: 27.29MIN: 3.98 / MAX: 28.831. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPU10c12c6c8c2K4K6K8K10KSE +/- 5.19, N = 3SE +/- 9.96, N = 3SE +/- 7.67, N = 3SE +/- 2.85, N = 39063.849038.479081.739113.111. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

ASTC Encoder

Preset: Exhaustive

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: Exhaustive10c12c6c8c3691215SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 311.7611.7311.8211.811. (CXX) g++ options: -O3 -flto -pthread

Stargate Digital Audio Workstation

Sample Rate: 192000 - Buffer Size: 1024

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 192000 - Buffer Size: 102410c12c6c8c0.63651.2731.90952.5463.1825SE +/- 0.017291, N = 3SE +/- 0.001919, N = 3SE +/- 0.004057, N = 3SE +/- 0.019484, N = 32.8061902.8290612.8248142.8115551. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

OSPRay

Benchmark: particle_volume/pathtracer/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: particle_volume/pathtracer/real_time10c12c6c8c50100150200250SE +/- 1.94, N = 3SE +/- 1.54, N = 3SE +/- 0.59, N = 3SE +/- 1.74, N = 3230.28229.27230.44228.58

simdjson

Throughput Test: LargeRandom

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandom10c12c6c8c0.28130.56260.84391.12521.4065SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.251.251.241.251. (CXX) g++ options: -O3

OpenVINO

Model: Person Vehicle Bike Detection FP16 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Person Vehicle Bike Detection FP16 - Device: CPU10c12c6c8c1.19252.3853.57754.775.9625SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 35.285.305.285.26MIN: 4.37 / MAX: 41.23MIN: 4.42 / MAX: 40.66MIN: 4.34 / MAX: 38.93MIN: 4.42 / MAX: 42.931. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPU10c12c6c8c4K8K12K16K20KSE +/- 30.88, N = 3SE +/- 12.43, N = 3SE +/- 33.95, N = 3SE +/- 31.30, N = 319254.0819171.5119314.0419278.931. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

CockroachDB

Workload: MoVR - Concurrency: 1024

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: MoVR - Concurrency: 102410c12c6c8c2004006008001000SE +/- 0.58, N = 3SE +/- 1.42, N = 3SE +/- 1.56, N = 3SE +/- 3.18, N = 3949.5953.8952.7946.9

simdjson

Throughput Test: PartialTweets

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweets10c12c6c8c1.28032.56063.84095.12126.4015SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.675.655.695.661. (CXX) g++ options: -O3

OSPRay

Benchmark: gravity_spheres_volume/dim_512/scivis/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/scivis/real_time10c12c6c8c1020304050SE +/- 0.12, N = 3SE +/- 0.15, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 343.3343.1343.2943.43

Timed MPlayer Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.5Time To Compile10c12c6c8c246810SE +/- 0.034, N = 3SE +/- 0.033, N = 3SE +/- 0.010, N = 3SE +/- 0.023, N = 37.7557.7777.7737.808

OSPRay

Benchmark: gravity_spheres_volume/dim_512/ao/real_time

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_time10c12c6c8c1020304050SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 344.0043.9844.2744.23

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 210c12c6c8c816243240SE +/- 0.08, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.10, N = 334.9134.8534.8734.691. (CXX) g++ options: -O3 -fPIC -lm

OpenVINO

Model: Weld Porosity Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Weld Porosity Detection FP16-INT8 - Device: CPU10c12c6c8c3691215SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 39.919.959.899.90MIN: 8.4 / MAX: 50.42MIN: 8.42 / MAX: 52.38MIN: 8.35 / MAX: 32.16MIN: 8.39 / MAX: 56.991. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

miniBUDE

Implementation: OpenMP - Input Deck: BM2

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM210c12c6c8c2K4K6K8K10KSE +/- 31.49, N = 3SE +/- 27.15, N = 3SE +/- 96.81, N = 3SE +/- 63.13, N = 38666.988640.318651.928615.971. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

miniBUDE

Implementation: OpenMP - Input Deck: BM2

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM210c12c6c8c80160240320400SE +/- 1.26, N = 3SE +/- 1.09, N = 3SE +/- 3.87, N = 3SE +/- 2.53, N = 3346.68345.61346.08344.641. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.13Time To Compile10c12c6c8c1122334455SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.28, N = 3SE +/- 0.20, N = 349.8049.9250.0849.87

ASTC Encoder

Preset: Thorough

OpenBenchmarking.orgMT/s, More Is BetterASTC Encoder 4.0Preset: Thorough10c12c6c8c20406080100SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3106.85106.57106.51107.111. (CXX) g++ options: -O3 -flto -pthread

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPU10c12c6c8c50100150200250SE +/- 0.03, N = 3SE +/- 0.32, N = 3SE +/- 0.13, N = 3SE +/- 0.69, N = 3249.12250.34250.49249.26MIN: 209.28 / MAX: 311.3MIN: 222.95 / MAX: 301.42MIN: 213.3 / MAX: 307.84MIN: 207.76 / MAX: 340.531. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

OpenVINO

Model: Face Detection FP16-INT8 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.3Model: Face Detection FP16-INT8 - Device: CPU10c12c6c8c4080120160200SE +/- 0.03, N = 3SE +/- 0.21, N = 3SE +/- 0.09, N = 3SE +/- 0.48, N = 3192.30191.43191.29192.251. (CXX) g++ options: -isystem -fsigned-char -ffunction-sections -fdata-sections -msse4.1 -msse4.2 -O3 -fno-strict-overflow -fwrapv -fPIC -fvisibility=hidden -Os -std=c++11 -MD -MT -MF

Timed Mesa Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Mesa Compilation 21.0Time To Compile10c12c6c8c510152025SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 320.2120.1220.1620.11

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.14ATPase Simulation - 327,506 Atoms10c12c6c8c0.02880.05760.08640.11520.144SE +/- 0.00007, N = 3SE +/- 0.00009, N = 3SE +/- 0.00009, N = 3SE +/- 0.00046, N = 30.127590.127830.128200.12768

simdjson

Throughput Test: DistinctUserID

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserID10c12c6c8c246810SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 36.846.866.836.861. (CXX) g++ options: -O3

Stargate Digital Audio Workstation

Sample Rate: 96000 - Buffer Size: 1024

OpenBenchmarking.orgRender Ratio, More Is BetterStargate Digital Audio Workstation 22.11.5Sample Rate: 96000 - Buffer Size: 102410c12c6c8c0.98211.96422.94633.92844.9105SE +/- 0.010431, N = 3SE +/- 0.023689, N = 3SE +/- 0.002133, N = 3SE +/- 0.008144, N = 34.3545564.3458904.3647674.3514021. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.1.9Time To Compile10c12c6c8c1020304050SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 344.6144.5244.7044.58

Liquid-DSP

Threads: 256 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 256 - Buffer Length: 256 - Filter Length: 5710c12c6c8c2000M4000M6000M8000M10000MSE +/- 5196152.42, N = 3SE +/- 4618802.15, N = 3SE +/- 3844187.53, N = 3SE +/- 4333333.33, N = 3103400000001034700000010340333333103376666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 384 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 384 - Buffer Length: 256 - Filter Length: 5710c12c6c8c2000M4000M6000M8000M10000MSE +/- 4409585.52, N = 3SE +/- 4582575.69, N = 3SE +/- 3214550.25, N = 3SE +/- 5783117.19, N = 3103526666671034700000010349000000103496666671. (CC) gcc options: -O3 -pthread -lm -lc -lliquid

simdjson

Throughput Test: Kostya

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: Kostya10c12c6c8c0.92481.84962.77443.69924.624SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 34.114.114.114.111. (CXX) g++ options: -O3

CockroachDB

Workload: KV, 95% Reads - Concurrency: 1024

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 102410c12c6c8c14K28K42K56K70KSE +/- 1142.40, N = 15SE +/- 575.30, N = 3SE +/- 1310.27, N = 15SE +/- 1317.65, N = 1562029.864661.860137.358195.5

CockroachDB

Workload: KV, 95% Reads - Concurrency: 512

OpenBenchmarking.orgops/s, More Is BetterCockroachDB 22.2Workload: KV, 95% Reads - Concurrency: 51210c12c6c8c14K28K42K56K70KSE +/- 1044.13, N = 15SE +/- 702.29, N = 3SE +/- 813.26, N = 15SE +/- 890.57, N = 360769.764467.662666.564111.9

oneDNN

Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU10c12c6c8c400800120016002000SE +/- 14.89, N = 3SE +/- 31.84, N = 15SE +/- 16.27, N = 10SE +/- 28.30, N = 32030.721968.702072.571982.15MIN: 1981.15MIN: 1632.62MIN: 1942.14MIN: 1911.331. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

oneDNN

Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 3.0Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU10c12c6c8c0.90211.80422.70633.60844.5105SE +/- 0.05885, N = 12SE +/- 0.02537, N = 3SE +/- 0.01788, N = 3SE +/- 0.08932, N = 124.009383.954713.964883.99305MIN: 2.96MIN: 3.05MIN: 2.99MIN: 2.671. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

SVT-AV1

Encoder Mode: Preset 12 - Input: Bosphorus 4K

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4K10c12c6c8c60120180240300SE +/- 7.16, N = 15SE +/- 7.35, N = 15SE +/- 9.18, N = 13SE +/- 7.53, N = 15241.37251.77221.16227.90

LuxCoreRender

Scene: Orange Juice - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Orange Juice - Acceleration: CPU10c12c6c8c714212835SE +/- 0.29, N = 3SE +/- 0.63, N = 15SE +/- 0.71, N = 15SE +/- 0.72, N = 1528.1928.8228.9029.04MIN: 23.3 / MAX: 45.65MIN: 23.01 / MAX: 45.86MIN: 22.4 / MAX: 44.91MIN: 22.62 / MAX: 45.48

LuxCoreRender

Scene: Danish Mood - Acceleration: CPU

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.6Scene: Danish Mood - Acceleration: CPU10c12c6c8c3691215SE +/- 0.17, N = 12SE +/- 0.09, N = 15SE +/- 0.14, N = 12SE +/- 0.11, N = 159.629.699.499.56MIN: 3.97 / MAX: 12.9MIN: 4 / MAX: 12.39MIN: 3.85 / MAX: 12.15MIN: 3.94 / MAX: 12.41

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.D10c12c6c8c2K4K6K8K10KSE +/- 206.91, N = 12SE +/- 84.88, N = 3SE +/- 158.57, N = 12SE +/- 134.50, N = 157124.928491.015690.016675.711. (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 4.1.4

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.110c12c6c8c20406080100SE +/- 3.31, N = 9SE +/- 1.12, N = 12SE +/- 0.99, N = 9SE +/- 0.49, N = 948.2986.8136.5445.001. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -lmpi_cxx -lmpi


Phoronix Test Suite v10.8.5