AMD EPYC 4th Gen AVX-512 Comparison

AMD EPYC 9654 Genoa AVX-512 benchmark comparison by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2212195-NE-AVXCOMPAR69
Jump To Table - Results

View

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

Limit displaying results to tests within:

C/C++ Compiler Tests 3 Tests
CPU Massive 7 Tests
Creator Workloads 9 Tests
Cryptography 2 Tests
Game Development 2 Tests
HPC - High Performance Computing 16 Tests
Machine Learning 11 Tests
Molecular Dynamics 3 Tests
Multi-Core 10 Tests
NVIDIA GPU Compute 3 Tests
Intel oneAPI 7 Tests
OpenMPI Tests 3 Tests
Python 2 Tests
Raytracing 2 Tests
Renderers 2 Tests
Scientific Computing 3 Tests
Server CPU Tests 6 Tests

Statistics

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

Graph Settings

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

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
AVX-512 On
December 18 2022
  20 Hours, 2 Minutes
AVX-512 Off
December 18 2022
  15 Hours, 29 Minutes
Invert Hiding All Results Option
  17 Hours, 45 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):


AMD EPYC 4th Gen AVX-512 ComparisonOpenBenchmarking.orgPhoronix Test Suite2 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 15.0.2-1ext41920x1080ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerVulkanCompilerFile-SystemScreen ResolutionAMD EPYC 4th Gen AVX-512 Comparison BenchmarksSystem Logs- Transparent Huge Pages: madvise- AVX-512 On: CXXFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512" CFLAGS="-O3 -march=native -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mprefer-vector-width=512" - AVX-512 Off: CXXFLAGS="-O3 -march=native -mno-avx512f" CFLAGS="-O3 -march=native -mno-avx512f" - --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 - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa10110d - Python 3.10.7- 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

AVX-512 On vs. AVX-512 Off ComparisonPhoronix Test SuiteBaseline+46.4%+46.4%+92.8%+92.8%+139.2%+139.2%50.5%37.6%3.6%CPU - 16 - AlexNet185.4%R.N.N.T - bf16bf16bf16 - CPU155.1%D.T.S153.4%R.N.N.T - f32 - CPU152.5%W.P.D.F - CPU143.4%W.P.D.F - CPU143%F.D.F - CPU132.2%F.D.F - CPU131.9%A.G.R.R.0.F - CPU120%LBC, LBRY Credits117%Device AI Score115.1%M.T.E.T.D.F - CPU114.8%M.T.E.T.D.F - CPU114.7%W.P.D.F.I - CPU104.7%W.P.D.F.I - CPU104.5%F.D.F.I - CPU104.2%F.D.F.I - CPU103.9%V.D.F - CPU97.1%V.D.F - CPU97%CPU - 16 - GoogLeNet93.3%D.I.S92.8%V.D.F.I - CPU84.7%V.D.F.I - CPU84.6%D.B.s - f32 - CPU78.2%P.V.B.D.F - CPU76.5%P.V.B.D.F - CPU76.4%CPU - 16 - ResNet-5073.7%gravity_spheres_volume/dim_512/scivis/real_time71.4%Q.S.2.P70.9%P.D.F - CPU70%P.D.F - CPU69.5%P.D.F - CPU68.4%P.D.F - CPU67.7%gravity_spheres_volume/dim_512/ao/real_time67.4%scrypt62.9%A.G.R.R.0.F.I - CPU58.3%resnet-v2-5056.1%N.Q.A.B.b.u.S.1.P - A.M.S55.2%N.Q.A.B.b.u.S.1.P - A.M.S55.2%inception-v3Garlicoin46.5%OpenMP - BM144.1%OpenMP - BM144.1%N.Q.A.B.b.u.S.1.P - S.S.S41.5%N.Q.A.B.b.u.S.1.P - S.S.S41.5%C.C.R.5.I - A.M.S38.5%C.C.R.5.I - A.M.S38.4%R.N.N.I - bf16bf16bf16 - CPUA.G.R.R.0.F - CPU37.4%Skeincoin36.7%OpenMP - BM235.4%OpenMP - BM235.4%gravity_spheres_volume/dim_512/pathtracer/real_time33.8%x25x33.1%DistinctUserID30.7%PartialTweets30.4%C.D.Y.C - A.M.S24.1%C.D.Y.C - A.M.S24%Kostya23.3%2 - 1080p - 32 - Path Tracer23%2 - 4K - 16 - Path Tracer22.8%2 - 1080p - 16 - Path Tracer22.7%1 - 1080p - 32 - Path Tracer22.4%1 - 1080p - 1 - Path Tracer22.3%2 - 4K - 32 - Path Tracer22.2%1 - 4K - 1 - Path Tracer22.2%1 - 4K - 32 - Path Tracer22.1%1 - 4K - 16 - Path Tracer22.1%1 - 1080p - 16 - Path Tracer22%3 - 1080p - 16 - Path Tracer21.7%3 - 1080p - 32 - Path Tracer21.6%TopTweet21.2%3 - 4K - 1 - Path Tracer21.2%LargeRand21.2%N.T.C.B.b.u.S - A.M.S21%3 - 4K - 16 - Path Tracer21%N.T.C.B.b.u.S - A.M.S20.9%3 - 1080p - 1 - Path Tracer20.9%3 - 4K - 32 - Path Tracer20.7%Pathtracer ISPC - Asian Dragon20.4%Pathtracer ISPC - Asian Dragon Obj20.2%C.D.Y.C - S.S.S20.1%C.D.Y.C - S.S.S20.1%Pathtracer ISPC - Crown19.8%2 - 4K - 1 - Path Tracer19.5%2 - 1080p - 1 - Path Tracer19.5%N.T.C.D.m - A.M.S19%d.M.M.S - Execution Time19%N.T.C.D.m - A.M.S19%OpenMP - Points2Image18.7%super-resolution-10 - CPU - Standard17.7%N.T.C.B.b.u.S - S.S.S15.6%N.T.C.B.b.u.S - S.S.S15.6%vklBenchmark ISPC15.3%CPU - vision_transformer15%ArcFace ResNet-100 - CPU - Standard14.5%A.G.R.R.0.F.I - CPU12.8%N.T.C.B.b.u.c - S.S.S12.8%N.T.C.B.b.u.c - S.S.S12.8%N.D.C.o.b.u.o.I - S.S.S12.2%N.D.C.o.b.u.o.I - S.S.S12.2%CPU - blazeface12.1%Eigen11.4%CPU - regnety_400m9.2%F.x.A9.1%CPU - efficientnet-b08.9%fcn-resnet101-11 - CPU - Standard8.4%BLAS7.8%Fayalite-FIST6.7%SqueezeNetV1.06.6%d.M.M.S - Mesh Time6.3%N.T.C.D.m - S.S.S5.4%N.T.C.D.m - S.S.S5.4%Preset 12 - Bosphorus 4K5%4.9%JPEG - 904.6%CPU - googlenet4.6%PNG - 904.5%CPU - mnasnet4.5%B.C4.3%C.B.S.A - f32 - CPU4.2%RTLightmap.hdr.4096x4096bertsquad-12 - CPU - Standard3.4%Windowed Gaussian3.3%CPU - FastestDet3%Preset 13 - Bosphorus 4K2.8%JPEG - 1002.8%OpenMP - NDT Mapping2.7%TensorFlowoneDNNAI Benchmark AlphaoneDNNOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOCpuminer-OptAI Benchmark AlphaOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOOpenVINOTensorFlowAI Benchmark AlphaOpenVINOOpenVINOoneDNNOpenVINOOpenVINOTensorFlowOSPRayCpuminer-OptOpenVINOOpenVINOOpenVINOOpenVINOOSPRayCpuminer-OptOpenVINOMobile Neural NetworkNeural Magic DeepSparseNeural Magic DeepSparseMobile Neural NetworkCpuminer-OptminiBUDEminiBUDENeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseoneDNNOpenVINOCpuminer-OptminiBUDEminiBUDEOSPRayCpuminer-OptsimdjsonsimdjsonNeural Magic DeepSparseNeural Magic DeepSparsesimdjsonOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudioOSPRay StudiosimdjsonOSPRay StudiosimdjsonNeural Magic DeepSparseOSPRay StudioNeural Magic DeepSparseOSPRay StudioOSPRay StudioEmbreeEmbreeNeural Magic DeepSparseNeural Magic DeepSparseEmbreeOSPRay StudioOSPRay StudioNeural Magic DeepSparseOpenFOAMNeural Magic DeepSparseDarmstadt Automotive Parallel Heterogeneous SuiteONNX RuntimeNeural Magic DeepSparseNeural Magic DeepSparseOpenVKLNCNNONNX RuntimeOpenVINONeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNeural Magic DeepSparseNCNNLeelaChessZeroNCNNSMHasherNCNNONNX RuntimeLeelaChessZeroCP2K Molecular DynamicsMobile Neural NetworkOpenFOAMNeural Magic DeepSparseNeural Magic DeepSparseSVT-AV1Numpy BenchmarkJPEG XL libjxlNCNNJPEG XL libjxlNCNNNumenta Anomaly BenchmarkoneDNNIntel Open Image DenoiseONNX RuntimeNumenta Anomaly BenchmarkNCNNSVT-AV1JPEG XL libjxlDarmstadt Automotive Parallel Heterogeneous SuiteAVX-512 OnAVX-512 Off

AMD EPYC 4th Gen AVX-512 Comparisonai-benchmark: Device Inference Scoreai-benchmark: Device Training Scoreai-benchmark: Device AI Scoredeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamtensorflow: CPU - 16 - ResNet-50tensorflow: CPU - 16 - AlexNettensorflow: CPU - 16 - GoogLeNetlczero: BLASlczero: Eigenembree: Pathtracer ISPC - Asian Dragonembree: Pathtracer ISPC - Asian Dragon Objembree: Pathtracer ISPC - Crownopenvkl: vklBenchmark ISPCospray: gravity_spheres_volume/dim_512/ao/real_timeospray: gravity_spheres_volume/dim_512/scivis/real_timeospray: gravity_spheres_volume/dim_512/pathtracer/real_timeospray-studio: 1 - 1080p - 1 - Path Tracerospray-studio: 1 - 1080p - 16 - Path Tracerospray-studio: 1 - 1080p - 32 - Path Tracerospray-studio: 1 - 4K - 1 - Path Tracerospray-studio: 1 - 4K - 16 - Path Tracerospray-studio: 1 - 4K - 32 - Path Tracerospray-studio: 2 - 1080p - 1 - Path Tracerospray-studio: 2 - 1080p - 16 - Path Tracerospray-studio: 2 - 1080p - 32 - Path Tracerospray-studio: 2 - 4K - 1 - Path Tracerospray-studio: 2 - 4K - 16 - Path Tracerospray-studio: 2 - 4K - 32 - Path Tracerospray-studio: 3 - 1080p - 1 - Path Tracerospray-studio: 3 - 1080p - 16 - Path Tracerospray-studio: 3 - 1080p - 32 - Path Tracerospray-studio: 3 - 4K - 1 - Path Tracerospray-studio: 3 - 4K - 16 - Path Tracerospray-studio: 3 - 4K - 32 - Path Traceronednn: Convolution Batch Shapes Auto - f32 - CPUonednn: Deconvolution Batch shapes_1d - f32 - CPUonednn: Deconvolution Batch shapes_3d - f32 - CPUonednn: Recurrent Neural Network Training - f32 - CPUonednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUmnn: resnet-v2-50mnn: SqueezeNetV1.0mnn: inception-v3cpuminer-opt: scryptcpuminer-opt: Quad SHA-256, Pyritecpuminer-opt: x25xcpuminer-opt: Garlicoincpuminer-opt: Skeincoincpuminer-opt: LBC, LBRY Creditsncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU - blazefacencnn: CPU - googlenetncnn: CPU - resnet50ncnn: CPU - regnety_400mncnn: CPU - vision_transformerncnn: CPU - FastestDetopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Face Detection FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP16 - CPUopenvino: Person Detection FP32 - CPUopenvino: Person Detection FP32 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Vehicle Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUgromacs: MPI CPU - water_GMX50_bareonnx: fcn-resnet101-11 - CPU - Standardonnx: super-resolution-10 - CPU - Standardonnx: bertsquad-12 - CPU - Standardonnx: ArcFace ResNet-100 - CPU - Standardnumpy: minibude: OpenMP - BM1minibude: OpenMP - BM1minibude: OpenMP - BM2minibude: OpenMP - BM2svt-av1: Preset 13 - Bosphorus 4Ksvt-av1: Preset 12 - Bosphorus 4Knumenta-nab: Bayesian Changepointnumenta-nab: Windowed Gaussiannumenta-nab: Relative Entropyoidn: RT.hdr_alb_nrm.3840x2160oidn: RT.ldr_alb_nrm.3840x2160oidn: RTLightmap.hdr.4096x4096daphne: OpenMP - NDT Mappingdaphne: OpenMP - Points2Imagesimdjson: PartialTweetssimdjson: LargeRandsimdjson: Kostyasimdjson: DistinctUserIDsimdjson: TopTweetopenfoam: drivaerFastback, Medium Mesh Size - Mesh Timeopenfoam: drivaerFastback, Medium Mesh Size - Execution Timecp2k: Fayalite-FISTsmhasher: FarmHash32 x86_64 AVXsmhasher: FarmHash32 x86_64 AVXjpegxl: JPEG - 90jpegxl: JPEG - 100jpegxl: PNG - 90AVX-512 OnAVX-512 Off35102701621184.998811.7586616.6804155.3462187.08375.34131195.936780.08261953.025549.032834.520628.9609100.54589.9408761.2241125.7860189.56115.2712857.2265111.728234.251829.189222.15157.2960.1790779096212.9364184.4701180.9315133244.156643.071154.218714823534698581927118546154238447646049385188081772804560869411070221840.51616722.58750.9895911962.061955.392361.2715.4418.57945.8124800.6122606807696.06715531951330106695042.3057.7125.8872.8066.34247.3274.9358.95102.04469.29193.93246.98148967.980.55170652.710.3643.341100.2543.341101.0019800.209.639988.444.7911202.624.287452.966.439065.345.29956.8850.1118.76427174015161051575.667299.545291.9828652.005346.081246.572245.55516.6774.7279.8983.513.511.661371.1813677.7644948436.701.264.186.866.52135.77418113.637331122.72539794.4426.3879.550.749.9518211066288773.538013.5907509.4462187.8540177.53875.62821005.161595.33471410.805167.911830.606232.664771.043714.0655490.3658195.1656157.8196.3313690.8722138.586130.526732.750512.7555.1131.1284238162176.8831153.4476151.0558115526.379425.135440.51171812871574971011321226471842924586172211524229852143413682084113398267850.53768222.83541.763364953.984989.131715.7624.0989.14630.4362946.0813229605784.2548827142754349174044.1962.8629.0076.1367.48270.1286.1660.7343.941088.5094.97503.50108449.491.21151239.600.5725.501864.9325.741845.959672.9419.694110.4911.666065.767.903782.0812.675135.569.33445.59107.6218.4672506288499918548.835065.096202.6046391.519255.661239.881233.94417.3894.88210.0353.503.511.721335.6311521.385.141.043.395.255.38144.3478135.216481198.40836483.7026.4129.130.729.52OpenBenchmarking.org

AI Benchmark Alpha

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

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Inference ScoreAVX-512 OffAVX-512 On800160024003200400018213510

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device Training ScoreAVX-512 OffAVX-512 On600120018002400300010662701

OpenBenchmarking.orgScore, More Is BetterAI Benchmark Alpha 0.1.2Device AI ScoreAVX-512 OffAVX-512 On1300260039005200650028876211

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On20406080100SE +/- 0.27, N = 3SE +/- 0.45, N = 373.5485.00
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On1632486480Min: 73.03 / Avg: 73.54 / Max: 73.92Min: 84.41 / Avg: 85 / Max: 85.88

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On3691215SE +/- 0.05, N = 3SE +/- 0.06, N = 313.5911.76
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On48121620Min: 13.52 / Avg: 13.59 / Max: 13.69Min: 11.64 / Avg: 11.76 / Max: 11.84

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On130260390520650SE +/- 0.33, N = 3SE +/- 1.92, N = 3509.45616.68
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On110220330440550Min: 508.96 / Avg: 509.45 / Max: 510.07Min: 613.23 / Avg: 616.68 / Max: 619.87

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On4080120160200SE +/- 0.10, N = 3SE +/- 0.47, N = 3187.85155.35
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On306090120150Min: 187.71 / Avg: 187.85 / Max: 188.05Min: 154.62 / Avg: 155.35 / Max: 156.24

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On4080120160200SE +/- 0.29, N = 3SE +/- 0.11, N = 3177.54187.08
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On306090120150Min: 177.08 / Avg: 177.54 / Max: 178.07Min: 186.88 / Avg: 187.08 / Max: 187.25

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On1.26632.53263.79895.06526.3315SE +/- 0.0091, N = 3SE +/- 0.0031, N = 35.62825.3413
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On246810Min: 5.61 / Avg: 5.63 / Max: 5.64Min: 5.34 / Avg: 5.34 / Max: 5.35

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On30060090012001500SE +/- 0.78, N = 3SE +/- 2.39, N = 31005.161195.94
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On2004006008001000Min: 1003.93 / Avg: 1005.16 / Max: 1006.6Min: 1191.45 / Avg: 1195.94 / Max: 1199.62

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On20406080100SE +/- 0.05, N = 3SE +/- 0.14, N = 395.3380.08
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On20406080100Min: 95.24 / Avg: 95.33 / Max: 95.43Min: 79.89 / Avg: 80.08 / Max: 80.37

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On400800120016002000SE +/- 0.17, N = 3SE +/- 4.32, N = 31410.811953.03
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On30060090012001500Min: 1410.51 / Avg: 1410.81 / Max: 1411.1Min: 1946.33 / Avg: 1953.03 / Max: 1961.1

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On1530456075SE +/- 0.02, N = 3SE +/- 0.11, N = 367.9149.03
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On1326395265Min: 67.88 / Avg: 67.91 / Max: 67.93Min: 48.83 / Avg: 49.03 / Max: 49.19

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On816243240SE +/- 0.03, N = 3SE +/- 0.03, N = 330.6134.52
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On714212835Min: 30.54 / Avg: 30.61 / Max: 30.66Min: 34.45 / Avg: 34.52 / Max: 34.56

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On816243240SE +/- 0.04, N = 3SE +/- 0.03, N = 332.6628.96
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On714212835Min: 32.6 / Avg: 32.66 / Max: 32.73Min: 28.93 / Avg: 28.96 / Max: 29.02

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On20406080100SE +/- 0.17, N = 3SE +/- 0.17, N = 371.04100.55
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On20406080100Min: 70.71 / Avg: 71.04 / Max: 71.24Min: 100.37 / Avg: 100.55 / Max: 100.89

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On48121620SE +/- 0.0334, N = 3SE +/- 0.0172, N = 314.06559.9408
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On48121620Min: 14.03 / Avg: 14.07 / Max: 14.13Min: 9.91 / Avg: 9.94 / Max: 9.96

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On160320480640800SE +/- 0.61, N = 3SE +/- 0.79, N = 3490.37761.22
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On130260390520650Min: 489.16 / Avg: 490.37 / Max: 491.14Min: 760.22 / Avg: 761.22 / Max: 762.79

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On4080120160200SE +/- 0.23, N = 3SE +/- 0.11, N = 3195.17125.79
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On4080120160200Min: 194.9 / Avg: 195.17 / Max: 195.63Min: 125.56 / Avg: 125.79 / Max: 125.91

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On4080120160200SE +/- 0.17, N = 3SE +/- 0.22, N = 3157.82189.56
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On306090120150Min: 157.49 / Avg: 157.82 / Max: 158.08Min: 189.14 / Avg: 189.56 / Max: 189.86

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On246810SE +/- 0.0068, N = 3SE +/- 0.0061, N = 36.33135.2712
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On3691215Min: 6.32 / Avg: 6.33 / Max: 6.34Min: 5.26 / Avg: 5.27 / Max: 5.28

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On2004006008001000SE +/- 1.12, N = 3SE +/- 0.77, N = 3690.87857.23
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On150300450600750Min: 688.64 / Avg: 690.87 / Max: 692.09Min: 855.84 / Avg: 857.23 / Max: 858.52

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On306090120150SE +/- 0.25, N = 3SE +/- 0.12, N = 3138.59111.73
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAVX-512 OffAVX-512 On306090120150Min: 138.32 / Avg: 138.59 / Max: 139.08Min: 111.56 / Avg: 111.73 / Max: 111.95

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On816243240SE +/- 0.10, N = 3SE +/- 0.08, N = 330.5334.25
OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On714212835Min: 30.33 / Avg: 30.53 / Max: 30.67Min: 34.13 / Avg: 34.25 / Max: 34.41

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On816243240SE +/- 0.11, N = 3SE +/- 0.07, N = 332.7529.19
OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAVX-512 OffAVX-512 On714212835Min: 32.59 / Avg: 32.75 / Max: 32.97Min: 29.06 / Avg: 29.19 / Max: 29.29

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 too. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: ResNet-50AVX-512 OffAVX-512 On510152025SE +/- 0.01, N = 3SE +/- 0.11, N = 312.7522.15
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: ResNet-50AVX-512 OffAVX-512 On510152025Min: 12.72 / Avg: 12.75 / Max: 12.77Min: 21.93 / Avg: 22.15 / Max: 22.31

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: AlexNetAVX-512 OffAVX-512 On306090120150SE +/- 0.19, N = 3SE +/- 2.35, N = 1255.11157.29
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: AlexNetAVX-512 OffAVX-512 On306090120150Min: 54.87 / Avg: 55.11 / Max: 55.49Min: 140.38 / Avg: 157.29 / Max: 168.09

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: GoogLeNetAVX-512 OffAVX-512 On1326395265SE +/- 0.25, N = 3SE +/- 1.01, N = 1531.1260.17
OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: GoogLeNetAVX-512 OffAVX-512 On1224364860Min: 30.8 / Avg: 31.12 / Max: 31.61Min: 54.32 / Avg: 60.17 / Max: 63.8

LeelaChessZero

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

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASAVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 21.53, N = 3SE +/- 103.04, N = 484239077-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -flto -O3 -march=native -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: BLASAVX-512 OffAVX-512 On16003200480064008000Min: 8380 / Avg: 8422.67 / Max: 8449Min: 8776 / Avg: 9076.5 / Max: 92441. (CXX) g++ options: -flto -O3 -march=native -pthread

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenAVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 43.59, N = 3SE +/- 45.37, N = 381629096-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -flto -O3 -march=native -pthread
OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenAVX-512 OffAVX-512 On16003200480064008000Min: 8076 / Avg: 8162.33 / Max: 8216Min: 9020 / Avg: 9096.33 / Max: 91771. (CXX) g++ options: -flto -O3 -march=native -pthread

Embree

Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs 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 3.13Binary: Pathtracer ISPC - Model: Asian DragonAVX-512 OffAVX-512 On50100150200250SE +/- 0.21, N = 8SE +/- 0.22, N = 9176.88212.94MIN: 170.19 / MAX: 190MIN: 207.72 / MAX: 227.11
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian DragonAVX-512 OffAVX-512 On4080120160200Min: 176.2 / Avg: 176.88 / Max: 178.02Min: 211.85 / Avg: 212.94 / Max: 214.13

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjAVX-512 OffAVX-512 On4080120160200SE +/- 0.36, N = 4SE +/- 0.62, N = 4153.45184.47MIN: 130.31 / MAX: 166.17MIN: 178.83 / MAX: 196.34
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: Asian Dragon ObjAVX-512 OffAVX-512 On306090120150Min: 152.46 / Avg: 153.45 / Max: 154.16Min: 183.33 / Avg: 184.47 / Max: 185.82

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownAVX-512 OffAVX-512 On4080120160200SE +/- 0.25, N = 7SE +/- 0.62, N = 8151.06180.93MIN: 114.4 / MAX: 176.43MIN: 124.41 / MAX: 209.74
OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.13Binary: Pathtracer ISPC - Model: CrownAVX-512 OffAVX-512 On306090120150Min: 150.19 / Avg: 151.06 / Max: 151.76Min: 178.03 / Avg: 180.93 / Max: 183.42

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 1.3.1Benchmark: vklBenchmark ISPCAVX-512 OffAVX-512 On30060090012001500SE +/- 8.11, N = 3SE +/- 13.58, N = 311551332MIN: 251 / MAX: 5181MIN: 329 / MAX: 4770
OpenBenchmarking.orgItems / Sec, More Is BetterOpenVKL 1.3.1Benchmark: vklBenchmark ISPCAVX-512 OffAVX-512 On2004006008001000Min: 1140 / Avg: 1154.67 / Max: 1168Min: 1308 / Avg: 1332 / Max: 1355

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 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_timeAVX-512 OffAVX-512 On1020304050SE +/- 0.02, N = 3SE +/- 0.21, N = 326.3844.16
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/ao/real_timeAVX-512 OffAVX-512 On918273645Min: 26.34 / Avg: 26.38 / Max: 26.42Min: 43.75 / Avg: 44.16 / Max: 44.43

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeAVX-512 OffAVX-512 On1020304050SE +/- 0.04, N = 3SE +/- 0.10, N = 325.1443.07
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/scivis/real_timeAVX-512 OffAVX-512 On918273645Min: 25.05 / Avg: 25.14 / Max: 25.19Min: 42.93 / Avg: 43.07 / Max: 43.27

OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeAVX-512 OffAVX-512 On1224364860SE +/- 0.03, N = 3SE +/- 0.05, N = 340.5154.22
OpenBenchmarking.orgItems Per Second, More Is BetterOSPRay 2.10Benchmark: gravity_spheres_volume/dim_512/pathtracer/real_timeAVX-512 OffAVX-512 On1122334455Min: 40.45 / Avg: 40.51 / Max: 40.56Min: 54.14 / Avg: 54.22 / Max: 54.3

OSPRay Studio

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

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On4080120160200SE +/- 0.33, N = 3SE +/- 0.33, N = 3181148-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On306090120150Min: 180 / Avg: 180.67 / Max: 181Min: 148 / Avg: 148.33 / Max: 1491. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On6001200180024003000SE +/- 1.20, N = 3SE +/- 2.33, N = 328712353-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On5001000150020002500Min: 2869 / Avg: 2870.67 / Max: 2873Min: 2349 / Avg: 2352.67 / Max: 23571. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On12002400360048006000SE +/- 6.56, N = 3SE +/- 3.71, N = 357494698-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On10002000300040005000Min: 5741 / Avg: 5749 / Max: 5762Min: 4691 / Avg: 4698.33 / Max: 47031. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On150300450600750SE +/- 2.08, N = 3SE +/- 1.00, N = 3710581-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On120240360480600Min: 706 / Avg: 710 / Max: 713Min: 580 / Avg: 581 / Max: 5831. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 24.46, N = 3SE +/- 10.17, N = 3113219271-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On2K4K6K8K10KMin: 11288 / Avg: 11321.33 / Max: 11369Min: 9251 / Avg: 9271.33 / Max: 92821. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On5K10K15K20K25KSE +/- 27.41, N = 3SE +/- 13.75, N = 32264718546-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 1 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On4K8K12K16K20KMin: 22609 / Avg: 22646.67 / Max: 22700Min: 18519 / Avg: 18546 / Max: 185641. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On4080120160200SE +/- 0.33, N = 3SE +/- 0.00, N = 3184154-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On306090120150Min: 184 / Avg: 184.33 / Max: 185Min: 154 / Avg: 154 / Max: 1541. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On6001200180024003000SE +/- 0.88, N = 3SE +/- 9.17, N = 329242384-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On5001000150020002500Min: 2923 / Avg: 2924.33 / Max: 2926Min: 2372 / Avg: 2384 / Max: 24021. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On13002600390052006500SE +/- 8.25, N = 3SE +/- 6.24, N = 358614764-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On10002000300040005000Min: 5849 / Avg: 5861.33 / Max: 5877Min: 4755 / Avg: 4764 / Max: 47761. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On160320480640800SE +/- 0.67, N = 3SE +/- 1.00, N = 3722604-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On130260390520650Min: 721 / Avg: 721.67 / Max: 723Min: 603 / Avg: 604 / Max: 6061. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 15.51, N = 3SE +/- 2.19, N = 3115249385-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On2K4K6K8K10KMin: 11505 / Avg: 11524.33 / Max: 11555Min: 9381 / Avg: 9385.33 / Max: 93881. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On5K10K15K20K25KSE +/- 30.02, N = 3SE +/- 20.34, N = 32298518808-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 2 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On4K8K12K16K20KMin: 22942 / Avg: 22985.33 / Max: 23043Min: 18779 / Avg: 18807.67 / Max: 188471. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On50100150200250SE +/- 0.58, N = 3SE +/- 0.00, N = 3214177-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On4080120160200Min: 213 / Avg: 214 / Max: 215Min: 177 / Avg: 177 / Max: 1771. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On7001400210028003500SE +/- 7.00, N = 3SE +/- 3.06, N = 334132804-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On6001200180024003000Min: 3400 / Avg: 3413 / Max: 3424Min: 2798 / Avg: 2804 / Max: 28081. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On15003000450060007500SE +/- 5.51, N = 3SE +/- 9.54, N = 368205608-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 1080p - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On12002400360048006000Min: 6810 / Avg: 6820 / Max: 6829Min: 5592 / Avg: 5608 / Max: 56251. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On2004006008001000SE +/- 1.15, N = 3SE +/- 1.53, N = 3841694-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 1 - Renderer: Path TracerAVX-512 OffAVX-512 On150300450600750Min: 839 / Avg: 841 / Max: 843Min: 692 / Avg: 694 / Max: 6971. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On3K6K9K12K15KSE +/- 22.81, N = 3SE +/- 27.14, N = 31339811070-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 16 - Renderer: Path TracerAVX-512 OffAVX-512 On2K4K6K8K10KMin: 13355 / Avg: 13397.67 / Max: 13433Min: 11023 / Avg: 11069.67 / Max: 111171. (CXX) g++ options: -O3 -march=native -ldl

OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On6K12K18K24K30KSE +/- 15.62, N = 3SE +/- 21.63, N = 32678522184-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ldl
OpenBenchmarking.orgms, Fewer Is BetterOSPRay Studio 0.11Camera: 3 - Resolution: 4K - Samples Per Pixel: 32 - Renderer: Path TracerAVX-512 OffAVX-512 On5K10K15K20K25KMin: 26763 / Avg: 26784.67 / Max: 26815Min: 22142 / Avg: 22184 / Max: 222141. (CXX) g++ options: -O3 -march=native -ldl

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On0.1210.2420.3630.4840.605SE +/- 0.004200, N = 15SE +/- 0.004067, N = 70.5376820.516167-mno-avx512f - MIN: 0.42-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.421. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On246810Min: 0.52 / Avg: 0.54 / Max: 0.56Min: 0.51 / Avg: 0.52 / Max: 0.531. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On510152025SE +/- 0.06, N = 3SE +/- 0.16, N = 322.8422.59-mno-avx512f - MIN: 20.22-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 19.61. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On510152025Min: 22.74 / Avg: 22.84 / Max: 22.94Min: 22.37 / Avg: 22.59 / Max: 22.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On0.39680.79361.19041.58721.984SE +/- 0.004550, N = 9SE +/- 0.001906, N = 91.7633600.989591-mno-avx512f - MIN: 1.55-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.91. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On246810Min: 1.75 / Avg: 1.76 / Max: 1.79Min: 0.98 / Avg: 0.99 / Max: 11. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On11002200330044005500SE +/- 60.12, N = 4SE +/- 20.13, N = 54953.981962.06-mno-avx512f - MIN: 4690.85-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 1899.341. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUAVX-512 OffAVX-512 On9001800270036004500Min: 4839.02 / Avg: 4953.98 / Max: 5101.72Min: 1925.73 / Avg: 1962.06 / Max: 2038.461. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAVX-512 OffAVX-512 On11002200330044005500SE +/- 41.71, N = 3SE +/- 19.67, N = 154989.131955.39-mno-avx512f - MIN: 4767.22-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 1769.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUAVX-512 OffAVX-512 On9001800270036004500Min: 4907.59 / Avg: 4989.13 / Max: 5045.15Min: 1795.46 / Avg: 1955.39 / Max: 2068.281. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAVX-512 OffAVX-512 On5001000150020002500SE +/- 22.32, N = 3SE +/- 24.41, N = 41715.762361.27-mno-avx512f - MIN: 1607.13-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 2265.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread
OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUAVX-512 OffAVX-512 On400800120016002000Min: 1672.8 / Avg: 1715.76 / Max: 1747.75Min: 2289.94 / Avg: 2361.27 / Max: 2399.911. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -ldl -lpthread

Mobile Neural Network

MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50AVX-512 OffAVX-512 On612182430SE +/- 0.08, N = 8SE +/- 0.08, N = 924.1015.44-mno-avx512f - MIN: 23.44 / MAX: 71.32-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 14.79 / MAX: 54.051. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50AVX-512 OffAVX-512 On612182430Min: 23.78 / Avg: 24.1 / Max: 24.43Min: 15.1 / Avg: 15.44 / Max: 15.771. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0AVX-512 OffAVX-512 On3691215SE +/- 0.091, N = 8SE +/- 0.147, N = 99.1468.579-mno-avx512f - MIN: 7.72 / MAX: 19.03-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 6.67 / MAX: 21.51. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0AVX-512 OffAVX-512 On3691215Min: 8.64 / Avg: 9.15 / Max: 9.36Min: 8.11 / Avg: 8.58 / Max: 9.21. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3AVX-512 OffAVX-512 On1020304050SE +/- 0.13, N = 8SE +/- 0.23, N = 930.4445.81-mno-avx512f - MIN: 28.75 / MAX: 109.22-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 44.13 / MAX: 87.281. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3AVX-512 OffAVX-512 On918273645Min: 30.06 / Avg: 30.44 / Max: 30.97Min: 44.44 / Avg: 45.81 / Max: 46.691. (CXX) g++ options: -O3 -march=native -std=c++11 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

Cpuminer-Opt

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

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: scryptAVX-512 OffAVX-512 On10002000300040005000SE +/- 0.31, N = 3SE +/- 0.45, N = 32946.084800.61-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: scryptAVX-512 OffAVX-512 On8001600240032004000Min: 2945.47 / Avg: 2946.08 / Max: 2946.49Min: 4799.75 / Avg: 4800.61 / Max: 4801.271. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: Quad SHA-256, PyriteAVX-512 OffAVX-512 On500K1000K1500K2000K2500KSE +/- 276.83, N = 3SE +/- 9040.25, N = 313229602260680-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: Quad SHA-256, PyriteAVX-512 OffAVX-512 On400K800K1200K1600K2000KMin: 1322630 / Avg: 1322960 / Max: 1323510Min: 2248170 / Avg: 2260680 / Max: 22782401. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: x25xAVX-512 OffAVX-512 On16003200480064008000SE +/- 14.41, N = 3SE +/- 16.58, N = 35784.257696.06-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: x25xAVX-512 OffAVX-512 On13002600390052006500Min: 5764.56 / Avg: 5784.25 / Max: 5812.33Min: 7667.62 / Avg: 7696.06 / Max: 7725.061. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: GarlicoinAVX-512 OffAVX-512 On15K30K45K60K75KSE +/- 13.33, N = 3SE +/- 89.69, N = 34882771553-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: GarlicoinAVX-512 OffAVX-512 On12K24K36K48K60KMin: 48800 / Avg: 48826.67 / Max: 48840Min: 71380 / Avg: 71553.33 / Max: 716801. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: SkeincoinAVX-512 OffAVX-512 On400K800K1200K1600K2000KSE +/- 3964.01, N = 3SE +/- 13005.55, N = 314275431951330-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: SkeincoinAVX-512 OffAVX-512 On300K600K900K1200K1500KMin: 1421210 / Avg: 1427543.33 / Max: 1434840Min: 1928260 / Avg: 1951330 / Max: 19732701. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: LBC, LBRY CreditsAVX-512 OffAVX-512 On200K400K600K800K1000KSE +/- 667.26, N = 3SE +/- 7645.47, N = 34917401066950-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: LBC, LBRY CreditsAVX-512 OffAVX-512 On200K400K600K800K1000KMin: 490410 / Avg: 491740 / Max: 492500Min: 1058250 / Avg: 1066950 / Max: 10821901. (CXX) g++ options: -O3 -march=native -lcurl -lz -lpthread -lssl -lcrypto -lgmp

NCNN

NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetAVX-512 OffAVX-512 On1020304050SE +/- 0.49, N = 3SE +/- 0.26, N = 844.1942.30-mno-avx512f - MIN: 41.56 / MAX: 148.98-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 39.64 / MAX: 571.781. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: mnasnetAVX-512 OffAVX-512 On918273645Min: 43.25 / Avg: 44.19 / Max: 44.89Min: 41.23 / Avg: 42.3 / Max: 43.321. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0AVX-512 OffAVX-512 On1428425670SE +/- 0.31, N = 3SE +/- 0.35, N = 862.8657.71-mno-avx512f - MIN: 59.46 / MAX: 154.82-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 54.52 / MAX: 522.741. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: efficientnet-b0AVX-512 OffAVX-512 On1224364860Min: 62.41 / Avg: 62.86 / Max: 63.45Min: 56.12 / Avg: 57.71 / Max: 59.271. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceAVX-512 OffAVX-512 On714212835SE +/- 0.54, N = 3SE +/- 0.18, N = 829.0025.88-mno-avx512f - MIN: 26.03 / MAX: 144.12-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 24.45 / MAX: 112.371. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: blazefaceAVX-512 OffAVX-512 On612182430Min: 27.97 / Avg: 29 / Max: 29.79Min: 25.05 / Avg: 25.88 / Max: 26.411. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetAVX-512 OffAVX-512 On20406080100SE +/- 1.35, N = 3SE +/- 0.76, N = 876.1372.80-mno-avx512f - MIN: 70.13 / MAX: 155.61-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 67.13 / MAX: 388.521. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: googlenetAVX-512 OffAVX-512 On1530456075Min: 73.52 / Avg: 76.13 / Max: 78.01Min: 69.82 / Avg: 72.8 / Max: 75.891. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50AVX-512 OffAVX-512 On1530456075SE +/- 0.89, N = 3SE +/- 0.50, N = 867.4866.34-mno-avx512f - MIN: 63.4 / MAX: 170.14-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 62.92 / MAX: 194.741. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: resnet50AVX-512 OffAVX-512 On1326395265Min: 65.93 / Avg: 67.48 / Max: 69.01Min: 64.88 / Avg: 66.34 / Max: 69.421. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mAVX-512 OffAVX-512 On60120180240300SE +/- 3.75, N = 3SE +/- 2.25, N = 8270.12247.32-mno-avx512f - MIN: 245.47 / MAX: 498.8-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 232.61 / MAX: 506.551. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: regnety_400mAVX-512 OffAVX-512 On50100150200250Min: 265.02 / Avg: 270.12 / Max: 277.44Min: 238.55 / Avg: 247.32 / Max: 256.841. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerAVX-512 OffAVX-512 On20406080100SE +/- 5.82, N = 3SE +/- 1.59, N = 886.1674.93-mno-avx512f - MIN: 73.72 / MAX: 1760.74-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 65.04 / MAX: 2154.621. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: vision_transformerAVX-512 OffAVX-512 On1632486480Min: 76.86 / Avg: 86.16 / Max: 96.88Min: 70.5 / Avg: 74.93 / Max: 82.121. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetAVX-512 OffAVX-512 On1428425670SE +/- 2.90, N = 3SE +/- 0.49, N = 860.7358.95-mno-avx512f - MIN: 52.89 / MAX: 236.85-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 55.11 / MAX: 282.721. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread
OpenBenchmarking.orgms, Fewer Is BetterNCNN 20220729Target: CPU - Model: FastestDetAVX-512 OffAVX-512 On1224364860Min: 54.93 / Avg: 60.73 / Max: 63.84Min: 57.5 / Avg: 58.95 / Max: 61.61. (CXX) g++ options: -O3 -march=native -rdynamic -lgomp -lpthread

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 2022.2.devModel: Face Detection FP16 - Device: CPUAVX-512 OffAVX-512 On20406080100SE +/- 0.01, N = 3SE +/- 0.07, N = 343.94102.04-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUAVX-512 OffAVX-512 On20406080100Min: 43.92 / Avg: 43.94 / Max: 43.96Min: 101.9 / Avg: 102.04 / Max: 102.121. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUAVX-512 OffAVX-512 On2004006008001000SE +/- 0.51, N = 3SE +/- 0.24, N = 31088.50469.29-mno-avx512f - MIN: 937.5 / MAX: 1231.55-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 410.93 / MAX: 547.331. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUAVX-512 OffAVX-512 On2004006008001000Min: 1087.68 / Avg: 1088.5 / Max: 1089.42Min: 468.86 / Avg: 469.29 / Max: 469.691. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On4080120160200SE +/- 0.02, N = 3SE +/- 0.05, N = 394.97193.93-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On4080120160200Min: 94.94 / Avg: 94.97 / Max: 95.01Min: 193.85 / Avg: 193.93 / Max: 194.021. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On110220330440550SE +/- 0.07, N = 3SE +/- 0.01, N = 3503.50246.98-mno-avx512f - MIN: 402.47 / MAX: 569.65-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 204.5 / MAX: 299.541. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On90180270360450Min: 503.36 / Avg: 503.5 / Max: 503.59Min: 246.97 / Avg: 246.98 / Max: 2471. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAVX-512 OffAVX-512 On30K60K90K120K150KSE +/- 1130.85, N = 4SE +/- 1328.20, N = 3108449.49148967.98-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAVX-512 OffAVX-512 On30K60K90K120K150KMin: 105463.52 / Avg: 108449.49 / Max: 110959.33Min: 147146.13 / Avg: 148967.98 / Max: 151553.121. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAVX-512 OffAVX-512 On0.27230.54460.81691.08921.3615SE +/- 0.01, N = 4SE +/- 0.00, N = 31.210.55-mno-avx512f - MIN: 0.98 / MAX: 47.37-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.5 / MAX: 29.571. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAVX-512 OffAVX-512 On246810Min: 1.19 / Avg: 1.21 / Max: 1.22Min: 0.55 / Avg: 0.55 / Max: 0.551. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On40K80K120K160K200KSE +/- 1455.37, N = 3SE +/- 127.59, N = 3151239.60170652.71-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On30K60K90K120K150KMin: 149021.41 / Avg: 151239.6 / Max: 153980.87Min: 170446.67 / Avg: 170652.71 / Max: 170886.121. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On0.12830.25660.38490.51320.6415SE +/- 0.00, N = 3SE +/- 0.00, N = 30.570.36-mno-avx512f - MIN: 0.52 / MAX: 47.93-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 0.34 / MAX: 33.71. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On246810Min: 0.57 / Avg: 0.57 / Max: 0.57Min: 0.36 / Avg: 0.36 / Max: 0.361. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAVX-512 OffAVX-512 On1020304050SE +/- 0.22, N = 3SE +/- 0.20, N = 325.5043.34-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAVX-512 OffAVX-512 On918273645Min: 25.1 / Avg: 25.5 / Max: 25.87Min: 42.98 / Avg: 43.34 / Max: 43.691. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAVX-512 OffAVX-512 On400800120016002000SE +/- 15.65, N = 3SE +/- 4.83, N = 31864.931100.25-mno-avx512f - MIN: 1371.29 / MAX: 2532.74-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 783.9 / MAX: 1824.921. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAVX-512 OffAVX-512 On30060090012001500Min: 1839.4 / Avg: 1864.93 / Max: 1893.37Min: 1092.24 / Avg: 1100.25 / Max: 1108.941. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAVX-512 OffAVX-512 On1020304050SE +/- 0.04, N = 3SE +/- 0.18, N = 325.7443.34-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAVX-512 OffAVX-512 On918273645Min: 25.67 / Avg: 25.74 / Max: 25.82Min: 43.05 / Avg: 43.34 / Max: 43.681. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAVX-512 OffAVX-512 On400800120016002000SE +/- 3.32, N = 3SE +/- 4.44, N = 31845.951101.00-mno-avx512f - MIN: 1386.31 / MAX: 2798-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 840.82 / MAX: 1792.511. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAVX-512 OffAVX-512 On30060090012001500Min: 1839.47 / Avg: 1845.95 / Max: 1850.41Min: 1092.78 / Avg: 1101 / Max: 1108.031. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On4K8K12K16K20KSE +/- 1.81, N = 3SE +/- 12.72, N = 39672.9419800.20-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On3K6K9K12K15KMin: 9669.49 / Avg: 9672.94 / Max: 9675.62Min: 19774.94 / Avg: 19800.2 / Max: 19815.451. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On510152025SE +/- 0.01, N = 3SE +/- 0.01, N = 319.699.63-mno-avx512f - MIN: 16.4 / MAX: 74.85-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 8.29 / MAX: 57.531. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On510152025Min: 19.67 / Avg: 19.69 / Max: 19.71Min: 9.62 / Avg: 9.63 / Max: 9.641. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 4.29, N = 3SE +/- 6.96, N = 34110.499988.44-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAVX-512 OffAVX-512 On2K4K6K8K10KMin: 4102.12 / Avg: 4110.49 / Max: 4116.28Min: 9979.24 / Avg: 9988.44 / Max: 10002.081. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAVX-512 OffAVX-512 On3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 311.664.79-mno-avx512f - MIN: 9.72 / MAX: 43.7-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 3.98 / MAX: 28.791. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAVX-512 OffAVX-512 On3691215Min: 11.64 / Avg: 11.66 / Max: 11.68Min: 4.78 / Avg: 4.79 / Max: 4.81. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 1.39, N = 3SE +/- 2.53, N = 36065.7611202.62-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On2K4K6K8K10KMin: 6063.35 / Avg: 6065.76 / Max: 6068.18Min: 11199.3 / Avg: 11202.62 / Max: 11207.61. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On246810SE +/- 0.00, N = 3SE +/- 0.00, N = 37.904.28-mno-avx512f - MIN: 6.37 / MAX: 41.53-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 3.5 / MAX: 42.621. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAVX-512 OffAVX-512 On3691215Min: 7.9 / Avg: 7.9 / Max: 7.91Min: 4.27 / Avg: 4.28 / Max: 4.281. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAVX-512 OffAVX-512 On16003200480064008000SE +/- 10.17, N = 3SE +/- 3.52, N = 33782.087452.96-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAVX-512 OffAVX-512 On13002600390052006500Min: 3761.74 / Avg: 3782.08 / Max: 3792.33Min: 7447.61 / Avg: 7452.96 / Max: 7459.591. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAVX-512 OffAVX-512 On3691215SE +/- 0.03, N = 3SE +/- 0.00, N = 312.676.43-mno-avx512f - MIN: 9.58 / MAX: 77.91-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 5.22 / MAX: 61.261. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAVX-512 OffAVX-512 On48121620Min: 12.64 / Avg: 12.67 / Max: 12.74Min: 6.42 / Avg: 6.43 / Max: 6.431. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 2.17, N = 3SE +/- 4.01, N = 35135.569065.34-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAVX-512 OffAVX-512 On16003200480064008000Min: 5131.78 / Avg: 5135.56 / Max: 5139.3Min: 9058.88 / Avg: 9065.34 / Max: 9072.691. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAVX-512 OffAVX-512 On3691215SE +/- 0.00, N = 3SE +/- 0.00, N = 39.335.29-mno-avx512f - MIN: 7.39 / MAX: 57.57-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 4.36 / MAX: 45.251. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAVX-512 OffAVX-512 On3691215Min: 9.33 / Avg: 9.33 / Max: 9.34Min: 5.28 / Avg: 5.29 / Max: 5.291. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAVX-512 OffAVX-512 On2004006008001000SE +/- 3.04, N = 3SE +/- 4.00, N = 3445.59956.88-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAVX-512 OffAVX-512 On2004006008001000Min: 439.5 / Avg: 445.59 / Max: 448.69Min: 948.96 / Avg: 956.88 / Max: 961.841. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAVX-512 OffAVX-512 On20406080100SE +/- 0.74, N = 3SE +/- 0.21, N = 3107.6250.11-mno-avx512f - MIN: 83.48 / MAX: 216.07-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi - MIN: 38.98 / MAX: 166.691. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared
OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAVX-512 OffAVX-512 On20406080100Min: 106.87 / Avg: 107.62 / Max: 109.1Min: 49.85 / Avg: 50.11 / Max: 50.521. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -fno-strict-overflow -fwrapv -flto -shared

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 2022.1Implementation: MPI CPU - Input: water_GMX50_bareAVX-512 OffAVX-512 On510152025SE +/- 0.10, N = 3SE +/- 0.24, N = 318.4718.76-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2022.1Implementation: MPI CPU - Input: water_GMX50_bareAVX-512 OffAVX-512 On510152025Min: 18.32 / Avg: 18.47 / Max: 18.66Min: 18.29 / Avg: 18.76 / Max: 191. (CXX) g++ options: -O3 -march=native

ONNX Runtime

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

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On60120180240300SE +/- 2.36, N = 12SE +/- 0.44, N = 3250271-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: fcn-resnet101-11 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On50100150200250Min: 236 / Avg: 250.13 / Max: 263.5Min: 270.5 / Avg: 271.33 / Max: 2721. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On16003200480064008000SE +/- 260.54, N = 12SE +/- 5.46, N = 362887401-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: super-resolution-10 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On13002600390052006500Min: 5469 / Avg: 6287.88 / Max: 7412Min: 7390.5 / Avg: 7401.33 / Max: 74081. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On110220330440550SE +/- 3.11, N = 3SE +/- 1.86, N = 3499516-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: bertsquad-12 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On90180270360450Min: 495.5 / Avg: 499.33 / Max: 505.5Min: 512.5 / Avg: 516.17 / Max: 518.51. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On2004006008001000SE +/- 20.83, N = 12SE +/- 39.92, N = 129181051-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt
OpenBenchmarking.orgInferences Per Minute, More Is BetterONNX Runtime 1.11Model: ArcFace ResNet-100 - Device: CPU - Executor: StandardAVX-512 OffAVX-512 On2004006008001000Min: 825.5 / Avg: 918.25 / Max: 1020.5Min: 888 / Avg: 1051.21 / Max: 1294.51. (CXX) g++ options: -O3 -march=native -ffunction-sections -fdata-sections -mtune=native -flto=auto -fno-fat-lto-objects -ldl -lrt

Numpy Benchmark

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

OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkAVX-512 OffAVX-512 On120240360480600SE +/- 0.59, N = 3SE +/- 2.18, N = 3548.83575.66
OpenBenchmarking.orgScore, More Is BetterNumpy BenchmarkAVX-512 OffAVX-512 On100200300400500Min: 547.65 / Avg: 548.83 / Max: 549.45Min: 571.31 / Avg: 575.66 / Max: 578.06

miniBUDE

MiniBUDE is a mini application for the the core computation of the Bristol University Docking Engine (BUDE). This test profile currently makes use of the OpenMP implementation of miniBUDE for CPU benchmarking. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1AVX-512 OffAVX-512 On16003200480064008000SE +/- 26.42, N = 8SE +/- 5.79, N = 105065.107299.551. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1AVX-512 OffAVX-512 On13002600390052006500Min: 4941.74 / Avg: 5065.1 / Max: 5152.2Min: 7275.51 / Avg: 7299.54 / Max: 7320.471. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1AVX-512 OffAVX-512 On60120180240300SE +/- 1.06, N = 8SE +/- 0.23, N = 10202.60291.981. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1AVX-512 OffAVX-512 On50100150200250Min: 197.67 / Avg: 202.6 / Max: 206.09Min: 291.02 / Avg: 291.98 / Max: 292.821. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2AVX-512 OffAVX-512 On2K4K6K8K10KSE +/- 31.65, N = 3SE +/- 11.62, N = 46391.528652.011. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2AVX-512 OffAVX-512 On15003000450060007500Min: 6330.61 / Avg: 6391.52 / Max: 6436.88Min: 8634.19 / Avg: 8652.01 / Max: 8686.091. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2AVX-512 OffAVX-512 On80160240320400SE +/- 1.27, N = 3SE +/- 0.46, N = 4255.66346.081. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2AVX-512 OffAVX-512 On60120180240300Min: 253.22 / Avg: 255.66 / Max: 257.48Min: 345.37 / Avg: 346.08 / Max: 347.441. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

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 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4KAVX-512 OffAVX-512 On50100150200250SE +/- 4.01, N = 15SE +/- 4.74, N = 15239.88246.57
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 13 - Input: Bosphorus 4KAVX-512 OffAVX-512 On4080120160200Min: 212.49 / Avg: 239.88 / Max: 272.93Min: 205.7 / Avg: 246.57 / Max: 274.37

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4KAVX-512 OffAVX-512 On50100150200250SE +/- 3.57, N = 15SE +/- 4.78, N = 15233.94245.56
OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 1.4Encoder Mode: Preset 12 - Input: Bosphorus 4KAVX-512 OffAVX-512 On4080120160200Min: 196.34 / Avg: 233.94 / Max: 253.62Min: 209.63 / Avg: 245.56 / Max: 275.28

Numenta Anomaly Benchmark

Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointAVX-512 OffAVX-512 On48121620SE +/- 0.19, N = 5SE +/- 0.21, N = 417.3916.68
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian ChangepointAVX-512 OffAVX-512 On48121620Min: 17.11 / Avg: 17.39 / Max: 18.05Min: 16.36 / Avg: 16.68 / Max: 17.27

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianAVX-512 OffAVX-512 On1.09852.1973.29554.3945.4925SE +/- 0.044, N = 7SE +/- 0.032, N = 154.8824.727
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed GaussianAVX-512 OffAVX-512 On246810Min: 4.78 / Avg: 4.88 / Max: 5.05Min: 4.55 / Avg: 4.73 / Max: 5.01

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyAVX-512 OffAVX-512 On3691215SE +/- 0.082, N = 5SE +/- 0.089, N = 510.0359.898
OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative EntropyAVX-512 OffAVX-512 On3691215Min: 9.82 / Avg: 10.04 / Max: 10.24Min: 9.78 / Avg: 9.9 / Max: 10.25

Intel Open Image Denoise

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

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160AVX-512 OffAVX-512 On0.78981.57962.36943.15923.949SE +/- 0.03, N = 5SE +/- 0.01, N = 53.503.51
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.hdr_alb_nrm.3840x2160AVX-512 OffAVX-512 On246810Min: 3.42 / Avg: 3.5 / Max: 3.55Min: 3.47 / Avg: 3.51 / Max: 3.55

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160AVX-512 OffAVX-512 On0.78981.57962.36943.15923.949SE +/- 0.01, N = 5SE +/- 0.01, N = 53.513.51
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RT.ldr_alb_nrm.3840x2160AVX-512 OffAVX-512 On246810Min: 3.47 / Avg: 3.51 / Max: 3.54Min: 3.49 / Avg: 3.51 / Max: 3.53

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096AVX-512 OffAVX-512 On0.3870.7741.1611.5481.935SE +/- 0.01, N = 3SE +/- 0.01, N = 31.721.66
OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.4.0Run: RTLightmap.hdr.4096x4096AVX-512 OffAVX-512 On246810Min: 1.7 / Avg: 1.72 / Max: 1.73Min: 1.65 / Avg: 1.66 / Max: 1.67

Darmstadt Automotive Parallel Heterogeneous Suite

DAPHNE is the Darmstadt Automotive Parallel HeterogeNEous Benchmark Suite with OpenCL / CUDA / OpenMP test cases for these automotive benchmarks for evaluating programming models in context to vehicle autonomous driving capabilities. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT MappingAVX-512 OffAVX-512 On30060090012001500SE +/- 8.66, N = 3SE +/- 5.94, N = 31335.631371.181. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: NDT MappingAVX-512 OffAVX-512 On2004006008001000Min: 1319.94 / Avg: 1335.63 / Max: 1349.82Min: 1361.03 / Avg: 1371.18 / Max: 1381.611. (CXX) g++ options: -O3 -std=c++11 -fopenmp

OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Points2ImageAVX-512 OffAVX-512 On3K6K9K12K15KSE +/- 269.82, N = 15SE +/- 126.17, N = 1511521.3813677.761. (CXX) g++ options: -O3 -std=c++11 -fopenmp
OpenBenchmarking.orgTest Cases Per Minute, More Is BetterDarmstadt Automotive Parallel Heterogeneous SuiteBackend: OpenMP - Kernel: Points2ImageAVX-512 OffAVX-512 On2K4K6K8K10KMin: 9798.72 / Avg: 11521.38 / Max: 12893.44Min: 12686.22 / Avg: 13677.76 / Max: 14539.711. (CXX) g++ options: -O3 -std=c++11 -fopenmp

simdjson

This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsAVX-512 OffAVX-512 On246810SE +/- 0.01, N = 3SE +/- 0.04, N = 35.146.70-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: PartialTweetsAVX-512 OffAVX-512 On3691215Min: 5.12 / Avg: 5.14 / Max: 5.15Min: 6.63 / Avg: 6.7 / Max: 6.771. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomAVX-512 OffAVX-512 On0.28350.5670.85051.1341.4175SE +/- 0.00, N = 3SE +/- 0.00, N = 31.041.26-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: LargeRandomAVX-512 OffAVX-512 On246810Min: 1.04 / Avg: 1.04 / Max: 1.04Min: 1.26 / Avg: 1.26 / Max: 1.261. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaAVX-512 OffAVX-512 On0.94051.8812.82153.7624.7025SE +/- 0.00, N = 3SE +/- 0.02, N = 33.394.18-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: KostyaAVX-512 OffAVX-512 On246810Min: 3.39 / Avg: 3.39 / Max: 3.39Min: 4.16 / Avg: 4.18 / Max: 4.211. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDAVX-512 OffAVX-512 On246810SE +/- 0.01, N = 3SE +/- 0.02, N = 35.256.86-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: DistinctUserIDAVX-512 OffAVX-512 On3691215Min: 5.24 / Avg: 5.25 / Max: 5.26Min: 6.82 / Avg: 6.86 / Max: 6.891. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetAVX-512 OffAVX-512 On246810SE +/- 0.01, N = 3SE +/- 0.08, N = 45.386.52-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.orgGB/s, More Is Bettersimdjson 2.0Throughput Test: TopTweetAVX-512 OffAVX-512 On3691215Min: 5.36 / Avg: 5.38 / Max: 5.39Min: 6.3 / Avg: 6.52 / Max: 6.671. (CXX) g++ options: -O3 -march=native

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 TimeAVX-512 OffAVX-512 On306090120150144.35135.771. (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

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Medium Mesh Size - Execution TimeAVX-512 OffAVX-512 On306090120150135.22113.641. (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

CP2K Molecular Dynamics

CP2K is an open-source molecular dynamics software package focused on quantum chemistry and solid-state physics. This test profile currently uses the SSMP (OpenMP) version of cp2k. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 8.2Input: Fayalite-FISTAVX-512 OffAVX-512 On300600900120015001198.411122.73

SMHasher

SMHasher is a hash function tester supporting various algorithms and able to make use of AVX and other modern CPU instruction set extensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXAVX-512 OffAVX-512 On9K18K27K36K45KSE +/- 28.78, N = 5SE +/- 0.46, N = 536483.7039794.44-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -flto=auto -fno-fat-lto-objects
OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXAVX-512 OffAVX-512 On7K14K21K28K35KMin: 36395.35 / Avg: 36483.7 / Max: 36557.87Min: 39792.79 / Avg: 39794.44 / Max: 39795.481. (CXX) g++ options: -O3 -march=native -flto=auto -fno-fat-lto-objects

JPEG XL libjxl

The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 90AVX-512 OffAVX-512 On3691215SE +/- 0.03, N = 3SE +/- 0.04, N = 39.139.55-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -fno-rtti -funwind-tables -O2 -fPIE -pie -lm -latomic
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 90AVX-512 OffAVX-512 On3691215Min: 9.07 / Avg: 9.13 / Max: 9.18Min: 9.48 / Avg: 9.55 / Max: 9.591. (CXX) g++ options: -O3 -march=native -fno-rtti -funwind-tables -O2 -fPIE -pie -lm -latomic

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 100AVX-512 OffAVX-512 On0.16650.3330.49950.6660.8325SE +/- 0.01, N = 9SE +/- 0.01, N = 90.720.74-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -fno-rtti -funwind-tables -O2 -fPIE -pie -lm -latomic
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 100AVX-512 OffAVX-512 On246810Min: 0.66 / Avg: 0.72 / Max: 0.77Min: 0.7 / Avg: 0.74 / Max: 0.771. (CXX) g++ options: -O3 -march=native -fno-rtti -funwind-tables -O2 -fPIE -pie -lm -latomic

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 90AVX-512 OffAVX-512 On3691215SE +/- 0.02, N = 3SE +/- 0.02, N = 39.529.95-mno-avx512f-mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi1. (CXX) g++ options: -O3 -march=native -fno-rtti -funwind-tables -O2 -fPIE -pie -lm -latomic
OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 90AVX-512 OffAVX-512 On3691215Min: 9.48 / Avg: 9.52 / Max: 9.56Min: 9.91 / Avg: 9.95 / Max: 9.991. (CXX) g++ options: -O3 -march=native -fno-rtti -funwind-tables -O2 -fPIE -pie -lm -latomic

CPU Power Consumption Monitor

OpenBenchmarking.orgWattsCPU Power Consumption MonitorPhoronix Test Suite System MonitoringAVX-512 OffAVX-512 On130260390520650Min: 106.95 / Avg: 449.58 / Max: 735.32Min: 26.37 / Avg: 434.8 / Max: 766.01

CPU Temperature Monitor

OpenBenchmarking.orgCelsiusCPU Temperature MonitorPhoronix Test Suite System MonitoringAVX-512 OffAVX-512 On1428425670Min: 35.5 / Avg: 51.26 / Max: 73.75Min: 30.13 / Avg: 49.97 / Max: 73.38

136 Results Shown

AI Benchmark Alpha:
  Device Inference Score
  Device Training Score
  Device AI Score
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    items/sec
    ms/batch
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  CV Detection,YOLOv5s COCO - Synchronous Single-Stream:
    items/sec
    ms/batch
  CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream:
    items/sec
    ms/batch
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
TensorFlow:
  CPU - 16 - ResNet-50
  CPU - 16 - AlexNet
  CPU - 16 - GoogLeNet
LeelaChessZero:
  BLAS
  Eigen
Embree:
  Pathtracer ISPC - Asian Dragon
  Pathtracer ISPC - Asian Dragon Obj
  Pathtracer ISPC - Crown
OpenVKL
OSPRay:
  gravity_spheres_volume/dim_512/ao/real_time
  gravity_spheres_volume/dim_512/scivis/real_time
  gravity_spheres_volume/dim_512/pathtracer/real_time
OSPRay Studio:
  1 - 1080p - 1 - Path Tracer
  1 - 1080p - 16 - Path Tracer
  1 - 1080p - 32 - Path Tracer
  1 - 4K - 1 - Path Tracer
  1 - 4K - 16 - Path Tracer
  1 - 4K - 32 - Path Tracer
  2 - 1080p - 1 - Path Tracer
  2 - 1080p - 16 - Path Tracer
  2 - 1080p - 32 - Path Tracer
  2 - 4K - 1 - Path Tracer
  2 - 4K - 16 - Path Tracer
  2 - 4K - 32 - Path Tracer
  3 - 1080p - 1 - Path Tracer
  3 - 1080p - 16 - Path Tracer
  3 - 1080p - 32 - Path Tracer
  3 - 4K - 1 - Path Tracer
  3 - 4K - 16 - Path Tracer
  3 - 4K - 32 - Path Tracer
oneDNN:
  Convolution Batch Shapes Auto - f32 - CPU
  Deconvolution Batch shapes_1d - f32 - CPU
  Deconvolution Batch shapes_3d - f32 - CPU
  Recurrent Neural Network Training - f32 - CPU
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Inference - bf16bf16bf16 - CPU
Mobile Neural Network:
  resnet-v2-50
  SqueezeNetV1.0
  inception-v3
Cpuminer-Opt:
  scrypt
  Quad SHA-256, Pyrite
  x25x
  Garlicoin
  Skeincoin
  LBC, LBRY Credits
NCNN:
  CPU - mnasnet
  CPU - efficientnet-b0
  CPU - blazeface
  CPU - googlenet
  CPU - resnet50
  CPU - regnety_400m
  CPU - vision_transformer
  CPU - FastestDet
OpenVINO:
  Face Detection FP16 - CPU:
    FPS
    ms
  Face Detection FP16-INT8 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16 - CPU:
    FPS
    ms
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU:
    FPS
    ms
  Person Detection FP16 - CPU:
    FPS
    ms
  Person Detection FP32 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16-INT8 - CPU:
    FPS
    ms
  Weld Porosity Detection FP16 - CPU:
    FPS
    ms
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
  Vehicle Detection FP16 - CPU:
    FPS
    ms
  Person Vehicle Bike Detection FP16 - CPU:
    FPS
    ms
  Machine Translation EN To DE FP16 - CPU:
    FPS
    ms
GROMACS
ONNX Runtime:
  fcn-resnet101-11 - CPU - Standard
  super-resolution-10 - CPU - Standard
  bertsquad-12 - CPU - Standard
  ArcFace ResNet-100 - CPU - Standard
Numpy Benchmark
miniBUDE:
  OpenMP - BM1:
    GFInst/s
    Billion Interactions/s
  OpenMP - BM2:
    GFInst/s
    Billion Interactions/s
SVT-AV1:
  Preset 13 - Bosphorus 4K
  Preset 12 - Bosphorus 4K
Numenta Anomaly Benchmark:
  Bayesian Changepoint
  Windowed Gaussian
  Relative Entropy
Intel Open Image Denoise:
  RT.hdr_alb_nrm.3840x2160
  RT.ldr_alb_nrm.3840x2160
  RTLightmap.hdr.4096x4096
Darmstadt Automotive Parallel Heterogeneous Suite:
  OpenMP - NDT Mapping
  OpenMP - Points2Image
simdjson:
  PartialTweets
  LargeRand
  Kostya
  DistinctUserID
  TopTweet
OpenFOAM:
  drivaerFastback, Medium Mesh Size - Mesh Time
  drivaerFastback, Medium Mesh Size - Execution Time
CP2K Molecular Dynamics
SMHasher
JPEG XL libjxl:
  JPEG - 90
  JPEG - 100
  PNG - 90
CPU Power Consumption Monitor:
  Phoronix Test Suite System Monitoring:
    Watts
    Celsius