eptc-7f32

AMD EPYC 7F32 8-Core testing with a ASRockRack EPYCD8 (P2.40 BIOS) and ASPEED on Debian 11 via the Phoronix Test Suite.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 2211213-NE-EPTC7F32616
Jump To Table - Results

View

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

Limit displaying results to tests within:

AV1 2 Tests
C++ Boost Tests 2 Tests
Timed Code Compilation 4 Tests
C/C++ Compiler Tests 7 Tests
Compression Tests 2 Tests
CPU Massive 12 Tests
Creator Workloads 14 Tests
Cryptocurrency Benchmarks, CPU Mining Tests 2 Tests
Cryptography 3 Tests
Encoding 4 Tests
HPC - High Performance Computing 11 Tests
Imaging 6 Tests
Common Kernel Benchmarks 2 Tests
Machine Learning 7 Tests
Multi-Core 14 Tests
Intel oneAPI 2 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 5 Tests
Python Tests 8 Tests
Renderers 2 Tests
Server 2 Tests
Server CPU Tests 7 Tests
Single-Threaded 2 Tests
Video Encoding 3 Tests
Common Workstation Benchmarks 2 Tests

Statistics

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

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Disable Color Branding
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 7F32
November 20
  6 Hours, 7 Minutes
AMD EPYC 7F32
November 20
  6 Hours, 34 Minutes
7F32
November 21
  8 Hours, 28 Minutes
Invert Hiding All Results Option
  7 Hours, 3 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):


eptc-7f32 OpenBenchmarking.orgPhoronix Test Suite 10.8.4AMD EPYC 7F32 8-Core @ 3.70GHz (8 Cores / 16 Threads)ASRockRack EPYCD8 (P2.40 BIOS)AMD Starship/Matisse28GBSamsung SSD 970 EVO Plus 250GBASPEED2 x Intel I350Debian 115.10.0-10-amd64 (x86_64)GNOME Shell 3.38.6X ServerGCC 10.2.1 20210110ext41024x768ProcessorMotherboardChipsetMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionEptc-7f32 BenchmarksSystem Logs- Transparent Huge Pages: always- --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-Km9U7s/gcc-10-10.2.1/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - NONE / errors=remount-ro,relatime,rw / Block Size: 4096- Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8301034 - Python 3.9.2- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected

EPYC 7F32AMD EPYC 7F327F32Result OverviewPhoronix Test Suite 10.8.4100%106%113%119%OpenFOAMoneDNNC-BloscJPEG XL Decoding libjxlOpenRadiossXmrig7-Zip CompressionJPEG XL libjxlY-CruncherTimed Erlang/OTP Compilationlibavif avifencTimed Node.js CompilationAOM AV1Unpacking The Linux KernelGraphicsMagickFFmpegTimed CPython CompilationminiBUDEWebP2 Image EncodeFLAC Audio EncodingsrsRANCpuminer-OptTimed PHP CompilationSMHasherWebP Image Encode

eptc-7f32 onednn: Convolution Batch Shapes Auto - f32 - CPUonednn: IP Shapes 3D - f32 - CPUopenfoam: drivaerFastback, Small Mesh Size - Execution Timemnn: mobilenet-v1-1.0onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPUonednn: Recurrent Neural Network Training - f32 - CPUnatron: Spaceshipjpegxl-decode: Allblosc: blosclz bitshuffleonednn: Recurrent Neural Network Training - u8s8f32 - CPUmnn: MobileNetV2_224onednn: Convolution Batch Shapes Auto - u8s8f32 - CPUmnn: squeezenetv1.1onednn: Recurrent Neural Network Inference - u8s8f32 - CPUstress-ng: CPU Cachemnn: SqueezeNetV1.0tensorflow: CPU - 16 - GoogLeNetopenradioss: Cell Phone Drop Testonednn: Recurrent Neural Network Inference - f32 - CPUtensorflow: CPU - 32 - AlexNettensorflow: CPU - 16 - ResNet-50onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPUtensorflow: CPU - 32 - ResNet-50onednn: IP Shapes 1D - u8s8f32 - CPUcpuminer-opt: Blake-2 Sopenfoam: drivaerFastback, Small Mesh Size - Mesh Timetensorflow: CPU - 64 - ResNet-50aom-av1: Speed 10 Realtime - Bosphorus 1080pcpuminer-opt: x25xmnn: resnet-v2-50tensorflow: CPU - 32 - GoogLeNetopenvino: Person Detection FP32 - CPUy-cruncher: 500Mtensorflow: CPU - 64 - AlexNettensorflow: CPU - 256 - GoogLeNetdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streamdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Streammnn: mobilenetV3openvino: Person Detection FP32 - CPUopenradioss: INIVOL and Fluid Structure Interaction Drop Containercompress-7zip: Compression Ratingtensorflow: CPU - 256 - AlexNetaom-av1: Speed 6 Two-Pass - Bosphorus 4Ktensorflow: CPU - 16 - AlexNetonednn: Deconvolution Batch shapes_1d - f32 - CPUtensorflow: CPU - 64 - GoogLeNetblosc: blosclz shufflestress-ng: Context Switchingstress-ng: Forkingdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Streamstress-ng: Futexstress-ng: MEMFDopenvino: Machine Translation EN To DE FP16 - CPUopenvino: Machine Translation EN To DE FP16 - CPUtensorflow: CPU - 512 - AlexNetopenvino: Person Vehicle Bike Detection FP16 - CPUopenvino: Person Vehicle Bike Detection FP16 - CPUgraphics-magick: HWB Color Spacedeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamdeepsparse: NLP Text Classification, DistilBERT mnli - Synchronous Single-Streamavifenc: 10, Losslessjpegxl: JPEG - 80jpegxl: PNG - 90stress-ng: Memory Copyingstress-ng: CPU Stressopenvino: Person Detection FP16 - CPUjpegxl: PNG - 80xmrig: Monero - 1Maom-av1: Speed 9 Realtime - Bosphorus 4Kaom-av1: Speed 10 Realtime - Bosphorus 4Kaom-av1: Speed 4 Two-Pass - Bosphorus 4Kaom-av1: Speed 9 Realtime - Bosphorus 1080pcpuminer-opt: Ringcoiny-cruncher: 1Bjpegxl: JPEG - 90onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPUopenvino: Person Detection FP16 - CPUaom-av1: Speed 8 Realtime - Bosphorus 4Ksmhasher: t1ha0_aes_avx2 x86_64rocksdb: Read While Writingaom-av1: Speed 8 Realtime - Bosphorus 1080pcpuminer-opt: Magideepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamdeepsparse: CV Classification, ResNet-50 ImageNet - Synchronous Single-Streamspacy: en_core_web_trfaom-av1: Speed 6 Realtime - Bosphorus 4Kaom-av1: Speed 6 Realtime - Bosphorus 1080pstress-ng: Glibc C String Functionsaom-av1: Speed 6 Two-Pass - Bosphorus 1080popenvino: Vehicle Detection FP16 - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamopenvino: Vehicle Detection FP16 - CPUrocksdb: Rand Readstress-ng: MMAPgraphics-magick: Resizingaom-av1: Speed 4 Two-Pass - Bosphorus 1080pstress-ng: IO_uringxmrig: Wownero - 1Monednn: IP Shapes 3D - u8s8f32 - CPUjpegxl: PNG - 100ffmpeg: libx264 - Liveffmpeg: libx264 - Livedeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: CV Detection,YOLOv5s COCO - Asynchronous Multi-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Streamencodec: 1.5 kbpsavifenc: 6, Losslessbuild-erlang: Time To Compilenginx: 1000openvino: Weld Porosity Detection FP16 - CPUopenvino: Weld Porosity Detection FP16 - CPUgraphics-magick: Rotateonednn: Matrix Multiply Batch Shapes Transformer - f32 - CPUdeepsparse: NLP Document Classification, oBERT base uncased on IMDB - Asynchronous Multi-Streamscikit-learn: TSNE MNIST Datasetencodec: 6 kbpsavifenc: 6cpuminer-opt: Garlicoinstress-ng: Matrix Mathwebp2: Defaultencodec: 3 kbpsstress-ng: Socket Activityjpegxl-decode: 1openradioss: Bird Strike on Windshieldstress-ng: Mutexffmpeg: libx265 - Livenginx: 500stress-ng: Glibc Qsort Data Sortingffmpeg: libx265 - Liveunpack-linux: linux-5.19.tar.xzdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamdeepsparse: CV Detection,YOLOv5s COCO - Synchronous Single-Streamavifenc: 0srsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUspacy: en_core_web_lgtensorflow: CPU - 256 - ResNet-50deepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streamopenradioss: Rubber O-Ring Seal Installationgraphics-magick: Sharpendeepsparse: CV Classification, ResNet-50 ImageNet - Asynchronous Multi-Streambuild-nodejs: Time To Compilebuild-python: Released Build, PGO + LTO Optimizednginx: 20openvino: Face Detection FP16-INT8 - CPUdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamopenvino: Age Gender Recognition Retail 0013 FP16 - CPUopenvino: Weld Porosity Detection FP16-INT8 - CPUwebp: Quality 100, Losslessscikit-learn: Sparse Rand Projections, 100 Iterationsopenvino: Weld Porosity Detection FP16-INT8 - CPUsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMbuild-python: Defaultffmpeg: libx265 - Platformffmpeg: libx265 - Platformdeepsparse: NLP Token Classification, BERT base uncased conll2003 - Asynchronous Multi-Streamstress-ng: Cryptodeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamnginx: 100srsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMcpuminer-opt: LBC, LBRY Creditsdeepsparse: NLP Text Classification, DistilBERT mnli - Asynchronous Multi-Streamonednn: Deconvolution Batch shapes_3d - f32 - CPUavifenc: 2ffmpeg: libx264 - Uploadsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMstress-ng: Mallocopenvino: Vehicle Detection FP16-INT8 - CPUopenvino: Vehicle Detection FP16-INT8 - CPUffmpeg: libx264 - Uploadstress-ng: System V Message Passingminibude: OpenMP - BM1mnn: inception-v3minibude: OpenMP - BM1openvino: Face Detection FP16 - CPUgraphics-magick: Enhancedopenvino: Face Detection FP16-INT8 - CPUblender: BMW27 - CPU-Onlysmhasher: FarmHash32 x86_64 AVXnginx: 200openradioss: Bumper Beamffmpeg: libx265 - Uploadsrsran: OFDM_Testdeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamffmpeg: libx265 - Uploaddeepsparse: NLP Text Classification, BERT base uncased SST2 - Asynchronous Multi-Streamcpuminer-opt: Skeincoinsrsran: 4G PHY_DL_Test 100 PRB MIMO 256-QAMminibude: OpenMP - BM2minibude: OpenMP - BM2compress-7zip: Decompression Ratinggraphics-magick: Noise-Gaussianffmpeg: libx265 - Video On Demandsrsran: 4G PHY_DL_Test 100 PRB SISO 64-QAMffmpeg: libx265 - Video On Demandstress-ng: SENDFILEonednn: IP Shapes 1D - f32 - CPUsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMencode-flac: WAV To FLACwebp: Quality 100, Highest Compressionsmhasher: MeowHash x86_64 AES-NIsrsran: 4G PHY_DL_Test 100 PRB MIMO 64-QAMwebp: Quality 100cpuminer-opt: scryptffmpeg: libx264 - Platformbrl-cad: VGR Performance Metricffmpeg: libx264 - Platformcpuminer-opt: Triple SHA-256, Onecoinbuild-php: Time To Compilegraphics-magick: Swirlstress-ng: Vector Mathopenvino: Face Detection FP16 - CPUwebp: Defaultsrsran: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMscikit-learn: MNIST Datasetopenvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPUonednn: Deconvolution Batch shapes_1d - u8s8f32 - CPUrocksdb: Update Randdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamdeepsparse: NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Streamstress-ng: Semaphoresdeepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streamencodec: 24 kbpsonednn: Deconvolution Batch shapes_3d - u8s8f32 - CPUcpuminer-opt: Deepcoinrocksdb: Read Rand Write Randsrsran: 4G PHY_DL_Test 100 PRB SISO 256-QAMsmhasher: t1ha2_atoncecpuminer-opt: Myriad-Groestlffmpeg: libx264 - Video On Demandstress-ng: Atomicstress-ng: NUMAffmpeg: libx264 - Video On Demandsmhasher: SHA3-256cpuminer-opt: Quad SHA-256, Pyritesmhasher: Spooky32smhasher: FarmHash128smhasher: wyhashsmhasher: fasthash32deepsparse: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Asynchronous Multi-Streammnn: nasnetaom-av1: Speed 0 Two-Pass - Bosphorus 1080paom-av1: Speed 0 Two-Pass - Bosphorus 4Kwebp2: Quality 100, Lossless Compressionwebp2: Quality 100, Compression Effort 5webp2: Quality 95, Compression Effort 7webp2: Quality 75, Compression Effort 7webp: Quality 100, Lossless, Highest Compressionjpegxl: JPEG - 100smhasher: MeowHash x86_64 AES-NIsmhasher: t1ha0_aes_avx2 x86_64smhasher: FarmHash32 x86_64 AVXsmhasher: t1ha2_atoncesmhasher: FarmHash128smhasher: fasthash32smhasher: Spooky32smhasher: SHA3-256smhasher: wyhashEPYC 7F32AMD EPYC 7F327F329.555028.67144212.630095154.615083.34198.765662.85251.8912.28321881.3232.89130.171921.0865.369.981864.9210.222.9373534950042.03454511.08107.35401.9932.5822.89274.834.99638.297307682.489.7453.099.6092132.7515057.983.9811846.4218.158.268.44709041.5642.085.5697.351566.8345.228.031.4222530.2259489.575.1413.820.9743.3428.29102812.267488.20.7903510.5928.53177.0012.434120.6647391.287.8932139.286.2943.36330.9173.7768.467.832169.538144.612.67187.5129550.805337.7681.46152.319.15253.4729.88133.3201406.5088780.966227.67143.311.09270.6710.82720524494.95173.95176.332206611560000014.3268290353.7271.09210.8445866227129.88328.3253.563.4807995.121.3433.1834313.46328.59.90145.8842.05180.1519004813228065.04144415.8053.53.934324.858067494.5353.714595.361264041.93180.64136.176623013214.714311.9721044.046027.750.540.190.013.250.050.120.580.5863.12237.77447.67738.50370.2940.67656.2192843.528.3878.115677.35671184.111554.514813.422.1246.325399.45.5235.7885.339.2122.991891.9834876041.187216102.07387.0529.5251.5321.633186.58115.35933.372583.15627.35749739.899.768215048.7524739922867.225.3725186.12262310980.46371.5424166.4817.77224.93119527.194836.7596.2068.438.541918.9818122.931.558.71730442.8143.345.67100.171612.0446.2118.252554.0230.9759287.09156536076.92423.6350.803819.673361821.4442.431327261.328.4624.636.4357162.339007583141.82104612.514364.737636.10.5928.16179.34108.571836.80176.255713.111633.96512.293118.85950516.4518.79212.747391.26884619.19838.60134.9917.8562123.0435043.736.2236.2025664.9343.72331.325679683.174.1052055.66134.0368.157.81437.045426.9827169.306144.45762.941.241128870.0202188.1913057.0733549.975338.97846605.092.716.35811.3829.951.46185.087267.05152.519.027252.1930.04623.112813693.6680.028351130.85133.42026049.91196.5469780.886228.158210067143.38923251.96219.418.2211.073150570.51269.52238.68910.7812.032061468.22149.1124384.8551950.16174.04175.58116100000158.390214.3825.219868130355.1270.06710.8035870427129.97329.5252.74150426.213.4922995.321.2763.1834206.07327.59.93146.0942.14124747179.7613234065.20144339578.061957.7815.8353.6119.5696432.3935207554.871218.2211194194.9522.598539.8657487.49119690435414583.41264041.96392425.59236.71180.54136.226623013216.4114312.821040.946027.73176.838323.6530.540.190.013.250.050.120.580.5863.07337.77447.67738.50370.2940.68455.9212848.53928.38713.481911.365269.881976.3616967.796477.342.8222.054579.46350.116.60214.67666.7132184.2796.6310.36129.73135.82084.2359.619.122027.829.42.7036932427044.37199110.36108.32410.3831.28530.751.6221.76670.7133.15196.84185.083.2012456.02659.677137778.629.4550.7910.039831.3914437.45036770.923802.415.1633193.66272404426.48385.7324.91160.4980.9817.15232.94122628.154335.50646.2528.358.521983.2418710.291.68.637299.242.4242.495.5199.911575.5946.5018.221.385682490.5130.8260752.57152794876.16422.4749.655820.127463221.3342.891299519.6327.8724.126.3025165.7238208038144.76104912.344451.967618.90.7759610.5828.64176.34110.416536.204277.509512.899633.41912.235119.78851272.3518.53215.667291.26277627.238439.07334.587.8022147.835439.826.2535.8015728.2943.24334.585617446.1673.2952630.51132.5768.907.89637.42926.7067167.977143.35811.671.231119712.5769.4795186.7413057.5139554.104340.30246953.572.736.31191.3729.741.45186.351268.87151.519.147253.81114168829.85626.999713609.3680.519250822.3132.62025049.62076.5414580.504228.969381263142.58973004.75220.6218.1211.033167586.04269.31538.88310.7732.042061461.33148.4224497.1452189.35173.25176.342980832115900000159.060614.3225.116668400354.9270.90710.8365888127229.86328.8253.642923405149917.153.4877195.421.3193.1934310.93327.79.92145.6942.03125073180.21197922413261065.10144439495.751953.9615.8153.6119.786443.593.9408435264854.94918.19541192572.0822.573339.8224.862677488.34119588735414594.361263041.94392155.78236.87180.616513283136.246626013220.3314307.9421041.156027.12176.846323.6530.540.190.013.250.050.120.580.5863.11137.77447.67738.50370.38740.68656.1392840.31628.387OpenBenchmarking.org

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F3236912159.555028.1156713.48190MIN: 9.37MIN: 7.9MIN: 13.341. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F3236912158.671447.3567111.36500MIN: 8.55MIN: 7.17MIN: 11.051. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenFOAM

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Execution TimeEPYC 7F32AMD EPYC 7F327F3260120180240300212.63184.11269.881. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lphysicalProperties -lspecie -lfiniteVolume -lfvModels -lgenericPatchFields -lmeshTools -lsampling -lOpenFOAM -ldl -lm

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenet-v1-1.0AMD EPYC 7F327F322468104.5106.361MIN: 4.36 / MAX: 15.87MIN: 6.23 / MAX: 14.151. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPUEPYC 7F327F32150030004500600075005154.616967.79MIN: 5107.06MIN: 6871.031. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F32140028004200560070005083.344813.426477.34MIN: 5017.29MIN: 4777.89MIN: 6423.471. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Natron

OpenBenchmarking.orgFPS, More Is BetterNatron 2.4.3Input: SpaceshipAMD EPYC 7F327F320.631.261.892.523.152.12.8

JPEG XL Decoding libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: AllEPYC 7F32AMD EPYC 7F327F3250100150200250198.76246.32222.05

C-Blosc

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.3Test: blosclz bitshuffleEPYC 7F32AMD EPYC 7F327F32120024003600480060005662.85399.44579.41. (CC) gcc options: -std=gnu99 -O3 -lrt -pthread -lm

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F32140028004200560070005251.896350.11MIN: 5206.92MIN: 6292.311. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: MobileNetV2_224AMD EPYC 7F327F322468105.5236.602MIN: 5.44 / MAX: 6.16MIN: 6.53 / MAX: 16.281. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F324812162012.2814.68MIN: 10.92MIN: 14.241. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: squeezenetv1.1AMD EPYC 7F327F322468105.7806.713MIN: 5.73 / MAX: 6.04MIN: 6.65 / MAX: 6.911. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F3250010001500200025001881.322184.27MIN: 1870.88MIN: 2160.571. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: CPU CacheAMD EPYC 7F327F322040608010085.3396.631. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: SqueezeNetV1.0AMD EPYC 7F327F3236912159.20010.361MIN: 9.09 / MAX: 17.34MIN: 10 / MAX: 24.431. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: GoogLeNetEPYC 7F327F3281624324032.8929.73

OpenRadioss

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Cell Phone Drop TestEPYC 7F32AMD EPYC 7F327F32306090120150130.17122.99135.80

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F324008001200160020001921.081891.982084.23MIN: 1912.63MIN: 1850.14MIN: 2018.091. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 32 - Model: AlexNetEPYC 7F327F32153045607565.3659.61

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: ResNet-50EPYC 7F327F3236912159.989.12

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPUEPYC 7F327F324008001200160020001864.922027.82MIN: 1850.34MIN: 1958.421. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 32 - Model: ResNet-50EPYC 7F327F32369121510.229.40

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F320.66091.32181.98272.64363.30452.937352.70369MIN: 2.65MIN: 2.651. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: Blake-2 SEPYC 7F32AMD EPYC 7F327F3270K140K210K280K350K3495003487603242701. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

OpenFOAM

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenFOAM 10Input: drivaerFastback, Small Mesh Size - Mesh TimeEPYC 7F32AMD EPYC 7F327F32102030405042.0341.1944.371. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lphysicalProperties -lspecie -lfiniteVolume -lfvModels -lgenericPatchFields -lmeshTools -lsampling -lOpenFOAM -ldl -lm

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 64 - Model: ResNet-50EPYC 7F327F32369121511.0810.36

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 10 Realtime - Input: Bosphorus 1080pEPYC 7F32AMD EPYC 7F327F3220406080100107.35102.07108.321. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: x25xEPYC 7F32AMD EPYC 7F327F3290180270360450401.99387.05410.381. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: resnet-v2-50AMD EPYC 7F327F3271421283529.5331.29MIN: 28.58 / MAX: 56.95MIN: 30.43 / MAX: 70.981. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 32 - Model: GoogLeNetEPYC 7F327F3281624324032.5830.75

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAMD EPYC 7F327F320.36450.7291.09351.4581.82251.531.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.10.9513Pi Digits To Calculate: 500MEPYC 7F32AMD EPYC 7F327F3251015202522.8921.6321.77

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 64 - Model: AlexNetEPYC 7F327F322040608010074.8070.71

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: GoogLeNetEPYC 7F327F3281624324034.9933.15

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAMD EPYC 7F327F324080120160200186.58196.84

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-StreamAMD EPYC 7F327F321.20582.41163.61744.82326.0295.35935.0800

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: mobilenetV3AMD EPYC 7F327F320.75831.51662.27493.03323.79153.3703.201MIN: 3.34 / MAX: 3.63MIN: 3.17 / MAX: 11.241. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP32 - Device: CPUAMD EPYC 7F327F3260012001800240030002583.152456.02MIN: 2498.05 / MAX: 2737.57MIN: 2355.49 / MAX: 2547.631. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

OpenRadioss

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: INIVOL and Fluid Structure Interaction Drop ContainerEPYC 7F32AMD EPYC 7F327F32140280420560700638.29627.35659.67

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Compression RatingEPYC 7F32AMD EPYC 7F327F3216K32K48K64K80K7307674973713771. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: AlexNetEPYC 7F327F322040608010082.4878.62

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4KEPYC 7F32AMD EPYC 7F327F3236912159.749.899.451. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 16 - Model: AlexNetEPYC 7F327F32122436486053.0950.79

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F3236912159.609219.7682010.03980MIN: 5.99MIN: 9.06MIN: 6.191. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 64 - Model: GoogLeNetEPYC 7F327F3281624324032.7531.39

C-Blosc

OpenBenchmarking.orgMB/s, More Is BetterC-Blosc 2.3Test: blosclz shuffleEPYC 7F32AMD EPYC 7F327F323K6K9K12K15K15057.915048.714437.41. (CC) gcc options: -std=gnu99 -O3 -lrt -pthread -lm

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: Context SwitchingAMD EPYC 7F327F321.1M2.2M3.3M4.4M5.5M5247399.05036770.91. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: ForkingAMD EPYC 7F327F325K10K15K20K25K22867.2223802.411. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAMD EPYC 7F327F321.20882.41763.62644.83526.0445.37255.1633

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-StreamAMD EPYC 7F327F324080120160200186.12193.66

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: FutexAMD EPYC 7F327F32500K1000K1500K2000K2500K2310980.462404426.481. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: MEMFDAMD EPYC 7F327F3280160240320400371.54385.731. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAMD EPYC 7F327F3261218243024.0024.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Machine Translation EN To DE FP16 - Device: CPUAMD EPYC 7F327F324080120160200166.48160.49MIN: 141.65 / MAX: 180.81MIN: 128.39 / MAX: 175.741. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 512 - Model: AlexNetEPYC 7F327F322040608010083.9880.98

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAMD EPYC 7F327F324812162017.7717.15MIN: 13.09 / MAX: 24.14MIN: 15.05 / MAX: 24.121. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Vehicle Bike Detection FP16 - Device: CPUAMD EPYC 7F327F3250100150200250224.93232.941. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: HWB Color SpaceEPYC 7F32AMD EPYC 7F327F32300600900120015001184119512261. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAMD EPYC 7F327F3271421283527.1928.15

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Synchronous Single-StreamAMD EPYC 7F327F3281624324036.7635.51

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 10, LosslessEPYC 7F32AMD EPYC 7F327F322468106.4216.2066.2521. (CXX) g++ options: -O3 -fPIC -lm

JPEG XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 80EPYC 7F32AMD EPYC 7F327F322468108.158.438.351. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 90EPYC 7F32AMD EPYC 7F327F322468108.268.548.521. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: Memory CopyingAMD EPYC 7F327F324008001200160020001918.981983.241. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: CPU StressAMD EPYC 7F327F324K8K12K16K20K18122.9318710.291. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAMD EPYC 7F327F320.360.721.081.441.81.551.601. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

JPEG XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 80EPYC 7F32AMD EPYC 7F327F322468108.448.718.631. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

Xmrig

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Monero - Hash Count: 1MEPYC 7F32AMD EPYC 7F327F32160032004800640080007090.07304.07299.21. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4KEPYC 7F32AMD EPYC 7F327F32102030405041.5642.8142.421. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4KEPYC 7F32AMD EPYC 7F327F32102030405042.0843.3442.491. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4KEPYC 7F32AMD EPYC 7F327F321.27582.55163.82745.10326.3795.565.675.511. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080pEPYC 7F32AMD EPYC 7F327F322040608010097.35100.1799.911. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: RingcoinEPYC 7F32AMD EPYC 7F327F32300600900120015001566.831612.041575.591. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Y-Cruncher

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.10.9513Pi Digits To Calculate: 1BEPYC 7F32AMD EPYC 7F327F32112233445545.2246.2146.50

JPEG XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 90EPYC 7F32AMD EPYC 7F327F322468108.038.258.221. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F320.320.640.961.281.61.422251.38568MIN: 1.3MIN: 1.31. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Person Detection FP16 - Device: CPUAMD EPYC 7F327F3250010001500200025002554.022490.51MIN: 2208.48 / MAX: 2698.24MIN: 2401.43 / MAX: 2548.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4KEPYC 7F32AMD EPYC 7F327F3271421283530.2230.9730.821. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

SMHasher

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: t1ha0_aes_avx2 x86_64EPYC 7F32AMD EPYC 7F327F3213K26K39K52K65K59489.5059287.0960752.571. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

Facebook RocksDB

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.5.3Test: Read While WritingAMD EPYC 7F327F32300K600K900K1200K1500K156536015279481. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080pEPYC 7F32AMD EPYC 7F327F322040608010075.1076.9276.161. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: MagiEPYC 7F32AMD EPYC 7F327F3290180270360450413.80423.63422.471. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamAMD EPYC 7F327F32112233445550.8049.66

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Synchronous Single-StreamAMD EPYC 7F327F3251015202519.6720.13

spaCy

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_trfAMD EPYC 7F327F32140280420560700618632

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4KEPYC 7F32AMD EPYC 7F327F3251015202520.9721.4421.331. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080pEPYC 7F32AMD EPYC 7F327F32102030405043.3442.4342.891. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: Glibc C String FunctionsAMD EPYC 7F327F32300K600K900K1200K1500K1327261.301299519.631. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080pEPYC 7F32AMD EPYC 7F327F3271421283528.2928.4627.871. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAMD EPYC 7F327F3261218243024.6324.12MIN: 21.3 / MAX: 35.58MIN: 20.63 / MAX: 35.911. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F322468106.43576.3025

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16 - Device: CPUAMD EPYC 7F327F324080120160200162.30165.721. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

Facebook RocksDB

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.5.3Test: Random ReadAMD EPYC 7F327F328M16M24M32M40M39007583382080381. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: MMAPAMD EPYC 7F327F32306090120150141.82144.761. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: ResizingEPYC 7F32AMD EPYC 7F327F3220040060080010001028104610491. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080pEPYC 7F32AMD EPYC 7F327F32369121512.2612.5112.341. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: IO_uringAMD EPYC 7F327F32100020003000400050004364.734451.961. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

Xmrig

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.18.1Variant: Wownero - Hash Count: 1MEPYC 7F32AMD EPYC 7F327F32160032004800640080007488.27636.17618.91. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F320.17780.35560.53340.71120.8890.7903510.775961MIN: 0.7MIN: 0.71. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

JPEG XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: PNG - Quality: 100EPYC 7F32AMD EPYC 7F327F320.13280.26560.39840.53120.6640.590.590.581. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: LiveEPYC 7F32AMD EPYC 7F327F3271421283528.5328.1628.641. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: LiveEPYC 7F32AMD EPYC 7F327F324080120160200177.00179.34176.341. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F3220406080100108.57110.42

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F3281624324036.8036.20

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAMD EPYC 7F327F322040608010076.2677.51

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-StreamAMD EPYC 7F327F32369121513.1112.90

EnCodec

OpenBenchmarking.orgSeconds, Fewer Is BetterEnCodec 0.1.1Target Bandwidth: 1.5 kbpsAMD EPYC 7F327F3281624324033.9733.42

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6, LosslessEPYC 7F32AMD EPYC 7F327F32369121512.4312.2912.241. (CXX) g++ options: -O3 -fPIC -lm

Timed Erlang/OTP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Erlang/OTP Compilation 25.0Time To CompileEPYC 7F32AMD EPYC 7F327F32306090120150120.66118.86119.79

nginx

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 1000AMD EPYC 7F327F3211K22K33K44K55K50516.4551272.351. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAMD EPYC 7F327F3251015202518.7918.53MIN: 10.41 / MAX: 31.29MIN: 9.98 / MAX: 29.581. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16 - Device: CPUAMD EPYC 7F327F3250100150200250212.74215.661. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: RotateEPYC 7F32AMD EPYC 7F327F321603204806408007397397291. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F320.2880.5760.8641.1521.441.280001.268841.26277MIN: 1.24MIN: 1.23MIN: 1.221. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F32140280420560700619.20627.24

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.1.3Benchmark: TSNE MNIST DatasetAMD EPYC 7F327F3291827364538.6039.07

EnCodec

OpenBenchmarking.orgSeconds, Fewer Is BetterEnCodec 0.1.1Target Bandwidth: 6 kbpsAMD EPYC 7F327F3281624324034.9934.58

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 6EPYC 7F32AMD EPYC 7F327F322468107.8937.8567.8021. (CXX) g++ options: -O3 -fPIC -lm

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: GarlicoinEPYC 7F32AMD EPYC 7F327F3250010001500200025002139.282123.042147.801. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: Matrix MathAMD EPYC 7F327F328K16K24K32K40K35043.7335439.821. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

WebP2 Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: DefaultEPYC 7F32AMD EPYC 7F327F322468106.296.226.251. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

EnCodec

OpenBenchmarking.orgSeconds, Fewer Is BetterEnCodec 0.1.1Target Bandwidth: 3 kbpsAMD EPYC 7F327F3281624324036.2035.80

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: Socket ActivityAMD EPYC 7F327F32120024003600480060005664.935728.291. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

JPEG XL Decoding libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL Decoding libjxl 0.7CPU Threads: 1EPYC 7F32AMD EPYC 7F327F32102030405043.3643.7243.24

OpenRadioss

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bird Strike on WindshieldEPYC 7F32AMD EPYC 7F327F3270140210280350330.91331.32334.58

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: MutexAMD EPYC 7F327F321.2M2.4M3.6M4.8M6M5679683.105617446.161. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

FFmpeg

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: LiveEPYC 7F32AMD EPYC 7F327F32163248648073.7774.1073.291. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

nginx

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 500AMD EPYC 7F327F3211K22K33K44K55K52055.6652630.511. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: Glibc Qsort Data SortingAMD EPYC 7F327F32306090120150134.03132.571. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: LiveEPYC 7F32AMD EPYC 7F327F32153045607568.4668.1568.901. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Unpacking The Linux Kernel

OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking The Linux Kernel 5.19linux-5.19.tar.xzEPYC 7F32AMD EPYC 7F327F322468107.8327.8147.896

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAMD EPYC 7F327F3291827364537.0537.43

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Detection,YOLOv5s COCO - Scenario: Synchronous Single-StreamAMD EPYC 7F327F3261218243026.9826.71

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 0EPYC 7F32AMD EPYC 7F327F324080120160200169.54169.31167.981. (CXX) g++ options: -O3 -fPIC -lm

srsRAN

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMEPYC 7F32AMD EPYC 7F327F32306090120150144.6144.4143.31. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAMD EPYC 7F327F32120024003600480060005762.945811.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAMD EPYC 7F327F320.2790.5580.8371.1161.3951.241.23MIN: 0.81 / MAX: 8.45MIN: 0.78 / MAX: 8.171. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

spaCy

OpenBenchmarking.orgtokens/sec, More Is BetterspaCy 3.4.1Model: en_core_web_lgAMD EPYC 7F327F322K4K6K8K10K1128811197

TensorFlow

OpenBenchmarking.orgimages/sec, More Is BetterTensorFlow 2.10Device: CPU - Batch Size: 256 - Model: ResNet-50EPYC 7F327F32369121512.6712.57

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F32163248648070.0269.48

OpenRadioss

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Rubber O-Ring Seal InstallationEPYC 7F32AMD EPYC 7F327F324080120160200187.50188.19186.74

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SharpenEPYC 7F32AMD EPYC 7F327F323060901201501291301301. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: CV Classification, ResNet-50 ImageNet - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F32132639526557.0757.51

Timed Node.js Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Node.js Compilation 18.8Time To CompileEPYC 7F32AMD EPYC 7F327F32120240360480600550.81549.98554.10

Timed CPython Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: Released Build, PGO + LTO OptimizedEPYC 7F32AMD EPYC 7F327F3270140210280350337.77338.98340.30

nginx

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 20AMD EPYC 7F327F3210K20K30K40K50K46605.0946953.571. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAMD EPYC 7F327F320.61431.22861.84292.45723.07152.712.731. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F322468106.35816.3119

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16 - Device: CPUAMD EPYC 7F327F320.31050.6210.93151.2421.55251.381.37MIN: 1.02 / MAX: 11.08MIN: 0.99 / MAX: 13.321. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAMD EPYC 7F327F3271421283529.9529.74MIN: 17.31 / MAX: 48.54MIN: 21.45 / MAX: 46.671. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, LosslessEPYC 7F32AMD EPYC 7F327F320.32850.6570.98551.3141.64251.461.461.451. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.1.3Benchmark: Sparse Random Projections, 100 IterationsAMD EPYC 7F327F324080120160200185.09186.35

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Weld Porosity Detection FP16-INT8 - Device: CPUAMD EPYC 7F327F3260120180240300267.05268.871. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

srsRAN

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMEPYC 7F32AMD EPYC 7F327F32306090120150152.3152.5151.51. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

Timed CPython Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed CPython Compilation 3.10.6Build Configuration: DefaultEPYC 7F32AMD EPYC 7F327F3251015202519.1519.0319.15

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: PlatformEPYC 7F32AMD EPYC 7F327F3260120180240300253.47252.19253.811. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: PlatformEPYC 7F32AMD EPYC 7F327F3271421283529.8830.0429.851. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F32140280420560700623.11627.00

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: CryptoAMD EPYC 7F327F323K6K9K12K15K13693.6613609.361. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F322040608010080.0380.52

nginx

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 100AMD EPYC 7F327F3211K22K33K44K55K51130.8550822.301. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

srsRAN

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMEPYC 7F32AMD EPYC 7F327F32306090120150133.3133.4132.61. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: LBC, LBRY CreditsEPYC 7F32AMD EPYC 7F327F324K8K12K16K20K2014020260202501. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, DistilBERT mnli - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F32112233445549.9149.62

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F322468106.508876.546976.54145MIN: 6.42MIN: 6.48MIN: 6.491. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

libavif avifenc

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.11Encoder Speed: 2EPYC 7F32AMD EPYC 7F327F322040608010080.9780.8980.501. (CXX) g++ options: -O3 -fPIC -lm

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: UploadEPYC 7F32AMD EPYC 7F327F3250100150200250227.67228.16228.971. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

srsRAN

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMEPYC 7F32AMD EPYC 7F327F32306090120150143.3143.3142.51. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: MallocAMD EPYC 7F327F322M4M6M8M10M8923251.968973004.751. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAMD EPYC 7F327F3250100150200250219.40220.621. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Vehicle Detection FP16-INT8 - Device: CPUAMD EPYC 7F327F324812162018.2218.12MIN: 14.76 / MAX: 32.34MIN: 15.25 / MAX: 30.491. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

FFmpeg

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: UploadEPYC 7F32AMD EPYC 7F327F32369121511.0911.0711.031. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: System V Message PassingAMD EPYC 7F327F32700K1400K2100K2800K3500K3150570.513167586.041. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

miniBUDE

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 7F32AMD EPYC 7F327F3260120180240300270.67269.52269.321. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: inception-v3AMD EPYC 7F327F3291827364538.6938.88MIN: 37.64 / MAX: 67.88MIN: 38.02 / MAX: 64.741. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

miniBUDE

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM1EPYC 7F32AMD EPYC 7F327F32369121510.8310.7810.771. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUAMD EPYC 7F327F320.4590.9181.3771.8362.2952.032.041. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: EnhancedEPYC 7F32AMD EPYC 7F327F32501001502002502052062061. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16-INT8 - Device: CPUAMD EPYC 7F327F32300600900120015001468.221461.33MIN: 1444.65 / MAX: 1522.72MIN: 1387.48 / MAX: 1520.081. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

Blender

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 3.3Blend File: BMW27 - Compute: CPU-OnlyAMD EPYC 7F327F32306090120150149.11148.42

SMHasher

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash32 x86_64 AVXEPYC 7F32AMD EPYC 7F327F325K10K15K20K25K24494.9524384.8524497.141. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

nginx

OpenBenchmarking.orgRequests Per Second, More Is Betternginx 1.23.2Connections: 200AMD EPYC 7F327F3211K22K33K44K55K51950.1652189.351. (CC) gcc options: -lluajit-5.1 -lm -lssl -lcrypto -lpthread -ldl -std=c99 -O2

OpenRadioss

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenRadioss 2022.10.13Model: Bumper BeamEPYC 7F32AMD EPYC 7F327F324080120160200173.95174.04173.25

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: UploadEPYC 7F32AMD EPYC 7F327F324080120160200176.33175.58176.341. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

srsRAN

OpenBenchmarking.orgSamples / Second, More Is BettersrsRAN 22.04.1Test: OFDM_TestEPYC 7F32AMD EPYC 7F327F3220M40M60M80M100M1156000001161000001159000001. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F324080120160200158.39159.06

FFmpeg

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: UploadEPYC 7F32AMD EPYC 7F327F324812162014.3214.3814.321. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F3261218243025.2225.12

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: SkeincoinEPYC 7F32AMD EPYC 7F327F3215K30K45K60K75K6829068130684001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

srsRAN

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAMEPYC 7F32AMD EPYC 7F327F3280160240320400353.7355.1354.91. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

miniBUDE

OpenBenchmarking.orgGFInst/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 7F32AMD EPYC 7F327F3260120180240300271.09270.07270.911. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

OpenBenchmarking.orgBillion Interactions/s, More Is BetterminiBUDE 20210901Implementation: OpenMP - Input Deck: BM2EPYC 7F32AMD EPYC 7F327F32369121510.8410.8010.841. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 22.01Test: Decompression RatingEPYC 7F32AMD EPYC 7F327F3213K26K39K52K65K5866258704588811. (CXX) g++ options: -lpthread -ldl -O2 -fPIC

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: Noise-GaussianEPYC 7F32AMD EPYC 7F327F32601201802403002712712721. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

FFmpeg

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: Video On DemandEPYC 7F32AMD EPYC 7F327F3271421283529.8829.9729.861. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

srsRAN

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 64-QAMEPYC 7F32AMD EPYC 7F327F3270140210280350328.3329.5328.81. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx265 - Scenario: Video On DemandEPYC 7F32AMD EPYC 7F327F3260120180240300253.56252.74253.641. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: SENDFILEAMD EPYC 7F327F3230K60K90K120K150K150426.21149917.151. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: IP Shapes 1D - Data Type: f32 - Engine: CPUEPYC 7F32AMD EPYC 7F327F320.78581.57162.35743.14323.9293.480793.492293.48771MIN: 3.38MIN: 3.36MIN: 3.41. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

srsRAN

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMEPYC 7F32AMD EPYC 7F327F322040608010095.195.395.41. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

FLAC Audio Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.4WAV To FLACEPYC 7F32AMD EPYC 7F327F3251015202521.3421.2821.321. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Highest CompressionEPYC 7F32AMD EPYC 7F327F320.71781.43562.15342.87123.5893.183.183.191. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread

SMHasher

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: MeowHash x86_64 AES-NIEPYC 7F32AMD EPYC 7F327F327K14K21K28K35K34313.4634206.0734310.931. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

srsRAN

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAMEPYC 7F32AMD EPYC 7F327F3270140210280350328.5327.5327.71. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100EPYC 7F32AMD EPYC 7F327F3236912159.909.939.921. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: scryptEPYC 7F32AMD EPYC 7F327F32306090120150145.88146.09145.691. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

FFmpeg

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: PlatformEPYC 7F32AMD EPYC 7F327F32102030405042.0542.1442.031. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

BRL-CAD

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.32.6VGR Performance MetricAMD EPYC 7F327F3230K60K90K120K150K1247471250731. (CXX) g++ options: -std=c++11 -pipe -fvisibility=hidden -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -pthread -ldl -lm

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: PlatformEPYC 7F32AMD EPYC 7F327F324080120160200180.15179.76180.211. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: Triple SHA-256, OnecoinEPYC 7F32AMD EPYC 7F327F3230K60K90K120K150K1322801323401326101. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 8.1.9Time To CompileEPYC 7F32AMD EPYC 7F327F32153045607565.0465.2065.10

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.38Operation: SwirlEPYC 7F32AMD EPYC 7F327F321002003004005004444434441. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: Vector MathAMD EPYC 7F327F328K16K24K32K40K39578.0639495.751. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenVINO

OpenBenchmarking.orgms, Fewer Is BetterOpenVINO 2022.2.devModel: Face Detection FP16 - Device: CPUAMD EPYC 7F327F324008001200160020001957.781953.96MIN: 1879.68 / MAX: 2023.26MIN: 1891.5 / MAX: 2037.231. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: DefaultEPYC 7F32AMD EPYC 7F327F324812162015.8015.8315.811. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread

srsRAN

OpenBenchmarking.orgUE Mb/s, More Is BettersrsRAN 22.04.1Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAMEPYC 7F32AMD EPYC 7F327F32122436486053.553.653.61. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 1.1.3Benchmark: MNIST DatasetAMD EPYC 7F327F32306090120150119.57119.78

OpenVINO

OpenBenchmarking.orgFPS, More Is BetterOpenVINO 2022.2.devModel: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPUAMD EPYC 7F327F32140028004200560070006432.396443.591. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -flto -shared

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F320.88671.77342.66013.54684.43353.934323.94084MIN: 3.83MIN: 3.851. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Facebook RocksDB

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.5.3Test: Update RandomAMD EPYC 7F327F3280K160K240K320K400K3520753526481. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAMD EPYC 7F327F32122436486054.8754.95

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-StreamAMD EPYC 7F327F324812162018.2218.20

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: SemaphoresAMD EPYC 7F327F32300K600K900K1200K1500K1194194.951192572.081. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

Neural Magic DeepSparse

OpenBenchmarking.orgitems/sec, More Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F3251015202522.6022.57

EnCodec

OpenBenchmarking.orgSeconds, Fewer Is BetterEnCodec 0.1.1Target Bandwidth: 24 kbpsAMD EPYC 7F327F3291827364539.8739.82

oneDNN

OpenBenchmarking.orgms, Fewer Is BetteroneDNN 2.7Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPUEPYC 7F327F321.09412.18823.28234.37645.47054.858064.86267MIN: 4.82MIN: 4.831. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: DeepcoinEPYC 7F32AMD EPYC 7F327F32160032004800640080007494.507487.497488.341. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Facebook RocksDB

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 7.5.3Test: Read Random Write RandomAMD EPYC 7F327F32300K600K900K1200K1500K119690411958871. (CXX) g++ options: -O3 -march=native -pthread -fno-builtin-memcmp -fno-rtti -lpthread

srsRAN

OpenBenchmarking.orgeNb Mb/s, More Is BettersrsRAN 22.04.1Test: 4G PHY_DL_Test 100 PRB SISO 256-QAMEPYC 7F32AMD EPYC 7F327F3280160240320400353.7354.0354.01. (CXX) g++ options: -std=c++14 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -lpthread -ldl -lm

SMHasher

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: t1ha2_atonceEPYC 7F32AMD EPYC 7F327F323K6K9K12K15K14595.3614583.4014594.361. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: Myriad-GroestlEPYC 7F32AMD EPYC 7F327F323K6K9K12K15K1264012640126301. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

FFmpeg

OpenBenchmarking.orgFPS, More Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: Video On DemandEPYC 7F32AMD EPYC 7F327F32102030405041.9341.9641.941. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Stress-NG

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: AtomicAMD EPYC 7F327F3280K160K240K320K400K392425.59392155.781. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.14.06Test: NUMAAMD EPYC 7F327F3250100150200250236.71236.871. (CC) gcc options: -O2 -std=gnu99 -lm -fuse-ld=gold -lapparmor -latomic -lc -lcrypt -ldl -lEGL -ljpeg -lrt -lsctp -lz -pthread

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 5.1.2Encoder: libx264 - Scenario: Video On DemandEPYC 7F32AMD EPYC 7F327F324080120160200180.64180.54180.621. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

SMHasher

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: SHA3-256EPYC 7F32AMD EPYC 7F327F32306090120150136.17136.22136.241. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

Cpuminer-Opt

OpenBenchmarking.orgkH/s, More Is BetterCpuminer-Opt 3.20.3Algorithm: Quad SHA-256, PyriteEPYC 7F32AMD EPYC 7F327F3214K28K42K56K70K6623066230662601. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

SMHasher

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: Spooky32EPYC 7F32AMD EPYC 7F327F323K6K9K12K15K13214.7013216.4113220.331. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: FarmHash128EPYC 7F32AMD EPYC 7F327F323K6K9K12K15K14311.9714312.8014307.941. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: wyhashEPYC 7F32AMD EPYC 7F327F325K10K15K20K25K21044.0421040.9421041.151. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

OpenBenchmarking.orgMiB/sec, More Is BetterSMHasher 2022-08-22Hash: fasthash32EPYC 7F32AMD EPYC 7F327F32130026003900520065006027.756027.736027.121. (CXX) g++ options: -march=native -O3 -flto -fno-fat-lto-objects -lpthread

Neural Magic DeepSparse

OpenBenchmarking.orgms/batch, Fewer Is BetterNeural Magic DeepSparse 1.1Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-StreamAMD EPYC 7F327F324080120160200176.84176.85

Mobile Neural Network

OpenBenchmarking.orgms, Fewer Is BetterMobile Neural Network 2.1Model: nasnetAMD EPYC 7F327F3261218243023.6523.65MIN: 21.78 / MAX: 47.46MIN: 23.33 / MAX: 44.971. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl

AOM AV1

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080pEPYC 7F32AMD EPYC 7F327F320.12150.2430.36450.4860.60750.540.540.541. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 3.5Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4KEPYC 7F32AMD EPYC 7F327F320.04280.08560.12840.17120.2140.190.190.191. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

WebP2 Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Lossless CompressionEPYC 7F32AMD EPYC 7F327F320.00230.00460.00690.00920.01150.010.010.011. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 100, Compression Effort 5EPYC 7F32AMD EPYC 7F327F320.73131.46262.19392.92523.65653.253.253.251. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 95, Compression Effort 7EPYC 7F32AMD EPYC 7F327F320.01130.02260.03390.04520.05650.050.050.051. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

OpenBenchmarking.orgMP/s, More Is BetterWebP2 Image Encode 20220823Encode Settings: Quality 75, Compression Effort 7EPYC 7F32AMD EPYC 7F327F320.0270.0540.0810.1080.1350.120.120.121. (CXX) g++ options: -msse4.2 -fno-rtti -O3 -ldl -lpthread

WebP Image Encode

OpenBenchmarking.orgMP/s, More Is BetterWebP Image Encode 1.2.4Encode Settings: Quality 100, Lossless, Highest CompressionEPYC 7F32AMD EPYC 7F327F320.13050.2610.39150.5220.65250.580.580.581. (CC) gcc options: -fvisibility=hidden -O2 -lm -pthread

JPEG XL libjxl

OpenBenchmarking.orgMP/s, More Is BetterJPEG XL libjxl 0.7Input: JPEG - Quality: 100EPYC 7F32AMD EPYC 7F327F320.13050.2610.39150.5220.65250.580.580.581. (CXX) g++ options: -fno-rtti -funwind-tables -O3 -O2 -fPIE -pie -lm -pthread -latomic

nginx

Connections: 4000

AMD EPYC 7F32: The test quit with a non-zero exit status.

7F32: The test quit with a non-zero exit status.

Connections: 1

AMD EPYC 7F32: The test quit with a non-zero exit status.

7F32: The test quit with a non-zero exit status.

oneDNN

Harness: Matrix Multiply Batch Shapes Transformer - Data Type: bf16bf16bf16 - Engine: CPU

EPYC 7F32: The test run did not produce a result.

7F32: The test run did not produce a result.

Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU

EPYC 7F32: The test run did not produce a result.

7F32: The test run did not produce a result.

Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU

EPYC 7F32: The test run did not produce a result.

7F32: The test run did not produce a result.

Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU

EPYC 7F32: The test run did not produce a result.

7F32: The test run did not produce a result.

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

EPYC 7F32: The test run did not produce a result.

7F32: The test run did not produce a result.

Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU

EPYC 7F32: The test run did not produce a result.

7F32: The test run did not produce a result.

nekRS

Input: TurboPipe Periodic

EPYC 7F32: The test quit with a non-zero exit status. E: [debian:398654] 7 more processes have sent help message help-mpi-errors.txt / mpi_errors_are_fatal

AMD EPYC 7F32: The test quit with a non-zero exit status. E: [debian:840433] 7 more processes have sent help message help-mpi-errors.txt / mpi_errors_are_fatal

7F32: The test quit with a non-zero exit status. E: [debian:18759] 7 more processes have sent help message help-mpi-errors.txt / mpi_errors_are_fatal

252 Results Shown

oneDNN:
  Convolution Batch Shapes Auto - f32 - CPU
  IP Shapes 3D - f32 - CPU
OpenFOAM
Mobile Neural Network
oneDNN:
  Recurrent Neural Network Training - bf16bf16bf16 - CPU
  Recurrent Neural Network Training - f32 - CPU
Natron
JPEG XL Decoding libjxl
C-Blosc
oneDNN
Mobile Neural Network
oneDNN
Mobile Neural Network
oneDNN
Stress-NG
Mobile Neural Network
TensorFlow
OpenRadioss
oneDNN
TensorFlow:
  CPU - 32 - AlexNet
  CPU - 16 - ResNet-50
oneDNN
TensorFlow
oneDNN
Cpuminer-Opt
OpenFOAM
TensorFlow
AOM AV1
Cpuminer-Opt
Mobile Neural Network
TensorFlow
OpenVINO
Y-Cruncher
TensorFlow:
  CPU - 64 - AlexNet
  CPU - 256 - GoogLeNet
Neural Magic DeepSparse:
  NLP Token Classification, BERT base uncased conll2003 - Synchronous Single-Stream:
    ms/batch
    items/sec
Mobile Neural Network
OpenVINO
OpenRadioss
7-Zip Compression
TensorFlow
AOM AV1
TensorFlow
oneDNN
TensorFlow
C-Blosc
Stress-NG:
  Context Switching
  Forking
Neural Magic DeepSparse:
  NLP Document Classification, oBERT base uncased on IMDB - Synchronous Single-Stream:
    items/sec
    ms/batch
Stress-NG:
  Futex
  MEMFD
OpenVINO:
  Machine Translation EN To DE FP16 - CPU:
    FPS
    ms
TensorFlow
OpenVINO:
  Person Vehicle Bike Detection FP16 - CPU:
    ms
    FPS
GraphicsMagick
Neural Magic DeepSparse:
  NLP Text Classification, DistilBERT mnli - Synchronous Single-Stream:
    ms/batch
    items/sec
libavif avifenc
JPEG XL libjxl:
  JPEG - 80
  PNG - 90
Stress-NG:
  Memory Copying
  CPU Stress
OpenVINO
JPEG XL libjxl
Xmrig
AOM AV1:
  Speed 9 Realtime - Bosphorus 4K
  Speed 10 Realtime - Bosphorus 4K
  Speed 4 Two-Pass - Bosphorus 4K
  Speed 9 Realtime - Bosphorus 1080p
Cpuminer-Opt
Y-Cruncher
JPEG XL libjxl
oneDNN
OpenVINO
AOM AV1
SMHasher
Facebook RocksDB
AOM AV1
Cpuminer-Opt
Neural Magic DeepSparse:
  CV Classification, ResNet-50 ImageNet - Synchronous Single-Stream:
    items/sec
    ms/batch
spaCy
AOM AV1:
  Speed 6 Realtime - Bosphorus 4K
  Speed 6 Realtime - Bosphorus 1080p
Stress-NG
AOM AV1
OpenVINO
Neural Magic DeepSparse
OpenVINO
Facebook RocksDB
Stress-NG
GraphicsMagick
AOM AV1
Stress-NG
Xmrig
oneDNN
JPEG XL libjxl
FFmpeg:
  libx264 - Live:
    Seconds
    FPS
Neural Magic DeepSparse:
  CV Detection,YOLOv5s COCO - Asynchronous Multi-Stream:
    ms/batch
    items/sec
  NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Synchronous Single-Stream:
    ms/batch
    items/sec
EnCodec
libavif avifenc
Timed Erlang/OTP Compilation
nginx
OpenVINO:
  Weld Porosity Detection FP16 - CPU:
    ms
    FPS
GraphicsMagick
oneDNN
Neural Magic DeepSparse
Scikit-Learn
EnCodec
libavif avifenc
Cpuminer-Opt
Stress-NG
WebP2 Image Encode
EnCodec
Stress-NG
JPEG XL Decoding libjxl
OpenRadioss
Stress-NG
FFmpeg
nginx
Stress-NG
FFmpeg
Unpacking The Linux Kernel
Neural Magic DeepSparse:
  CV Detection,YOLOv5s COCO - Synchronous Single-Stream:
    ms/batch
    items/sec
libavif avifenc
srsRAN
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Age Gender Recognition Retail 0013 FP16-INT8 - CPU
spaCy
TensorFlow
Neural Magic DeepSparse
OpenRadioss
GraphicsMagick
Neural Magic DeepSparse
Timed Node.js Compilation
Timed CPython Compilation
nginx
OpenVINO
Neural Magic DeepSparse
OpenVINO:
  Age Gender Recognition Retail 0013 FP16 - CPU
  Weld Porosity Detection FP16-INT8 - CPU
WebP Image Encode
Scikit-Learn
OpenVINO
srsRAN
Timed CPython Compilation
FFmpeg:
  libx265 - Platform:
    Seconds
    FPS
Neural Magic DeepSparse
Stress-NG
Neural Magic DeepSparse
nginx
srsRAN
Cpuminer-Opt
Neural Magic DeepSparse
oneDNN
libavif avifenc
FFmpeg
srsRAN
Stress-NG
OpenVINO:
  Vehicle Detection FP16-INT8 - CPU:
    FPS
    ms
FFmpeg
Stress-NG
miniBUDE
Mobile Neural Network
miniBUDE
OpenVINO
GraphicsMagick
OpenVINO
Blender
SMHasher
nginx
OpenRadioss
FFmpeg
srsRAN
Neural Magic DeepSparse
FFmpeg
Neural Magic DeepSparse
Cpuminer-Opt
srsRAN
miniBUDE:
  OpenMP - BM2:
    GFInst/s
    Billion Interactions/s
7-Zip Compression
GraphicsMagick
FFmpeg
srsRAN
FFmpeg
Stress-NG
oneDNN
srsRAN
FLAC Audio Encoding
WebP Image Encode
SMHasher
srsRAN
WebP Image Encode
Cpuminer-Opt
FFmpeg
BRL-CAD
FFmpeg
Cpuminer-Opt
Timed PHP Compilation
GraphicsMagick
Stress-NG
OpenVINO
WebP Image Encode
srsRAN
Scikit-Learn
OpenVINO
oneDNN
Facebook RocksDB
Neural Magic DeepSparse:
  NLP Text Classification, BERT base uncased SST2 - Synchronous Single-Stream:
    ms/batch
    items/sec
Stress-NG
Neural Magic DeepSparse
EnCodec
oneDNN
Cpuminer-Opt
Facebook RocksDB
srsRAN
SMHasher
Cpuminer-Opt
FFmpeg
Stress-NG:
  Atomic
  NUMA
FFmpeg
SMHasher
Cpuminer-Opt
SMHasher:
  Spooky32
  FarmHash128
  wyhash
  fasthash32
Neural Magic DeepSparse
Mobile Neural Network
AOM AV1:
  Speed 0 Two-Pass - Bosphorus 1080p
  Speed 0 Two-Pass - Bosphorus 4K
WebP2 Image Encode:
  Quality 100, Lossless Compression
  Quality 100, Compression Effort 5
  Quality 95, Compression Effort 7
  Quality 75, Compression Effort 7
WebP Image Encode
JPEG XL libjxl