Big Threadripper

AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (0702 BIOS) and llvmpipe 63GB on Ubuntu 19.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/2003108-PTS-BIGTHREA46&sro&grt.

Big ThreadripperProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionThreadripper 3970X16 CoresAMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads)ASUS ROG ZENITH II EXTREME (0702 BIOS)AMD Starship/Matisse64GB1000GB Force MP600llvmpipe 63GBAMD Navi 10 HDMI AudioAquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200Ubuntu 19.105.3.0-18-generic (x86_64)GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.53.3 Mesa 19.2.8 (LLVM 9.0 128 bits)GCC 9.2.1 20191008 + Clang 9.0.0-2ext43840x2160AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (16 Cores)5.3.0-40-generic (x86_64)OpenBenchmarking.orgCompiler Details- --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,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-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 Disk Details- NONE / errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Java Details- OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1)Python Details- Python 2.7.17 + Python 3.7.5Security Details- Threadripper 3970X: 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 STIBP: conditional RSB filling - 16 Cores: 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 RSB filling + tsx_async_abort: Not affected

Big Threadrippercompress-7zip: Compress Speed Testmt-dgemm: Sustained Floating-Point Rateaircrack-ng: amg: aobench: 2048 x 2048 - Total Timeaom-av1: Speed 8 Realtimeapache: Static Web Page Servingcassandra: Readscassandra: Writeshbase: Rand Write - 16hbase: Rand Write - 16apache-siege: 250appleseed: Emilyappleseed: Disney Materialappleseed: Material Testerarrayfire: BLAS CPUarrayfire: Conjugate Gradient CPUaskap: tConvolve MT - Griddingaskap: tConvolve MT - Degriddingaskap: tConvolve MPI - Griddingaskap: tConvolve MPI - Degriddingaskap: tConvolve OpenMP - Griddingaskap: tConvolve OpenMP - Degriddingasmfish: 1024 Hash Memory, 26 Depthmutex: Shared Mutex Lock Sharedmutex: Semaphore Release And Acquireblake2: blender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyblender: BMW27 - CPU-Onlyblender: Classroom - CPU-Onlyblender: Fishy Cat - CPU-Onlyblender: Barbershop - CPU-Onlyblender: Pabellon Barcelona - CPU-Onlyblogbench: Readblogbench: Writebork: File Encryption Timebotan: KASUMIbotan: AES-256botan: Twofishbotan: Blowfishbotan: CAST-256brl-cad: VGR Performance Metricbuild2: Time To Compilebullet: Raytestsbullet: 3000 Fallbullet: 1000 Stackbullet: 1000 Convexbullet: 136 Ragdollsbullet: Prim Trimeshbullet: Convex Trimeshbyte: Dhrystone 2c-ray: Total Time - 4K, 16 Rays Per Pixelcachebench: Readcachebench: Writecachebench: Read / Modify / Writev-ray: CPUclomp: Static OMP Speedupcloverleaf: Lagrangian-Eulerian Hydrodynamicscompilebench: Initial Createcoremark: CoreMark Size 666 - Iterations Per Secondcp2k: Fayalite-FIST Datacpp-perf-bench: Atolcpp-perf-bench: Ctypecpp-perf-bench: Math Librarycpp-perf-bench: Rand Numberscpp-perf-bench: Stepanov Vectorcpp-perf-bench: Function Objectscpp-perf-bench: Stepanov Abstractioncpuminer-opt: m7mcpuminer-opt: deepcpuminer-opt: lbrycpuminer-opt: skeincpuminer-opt: myr-grcpuminer-opt: sha256tcrafty: Elapsed Timecryptopp: Keyed Algorithmsctx-clock: Context Switch Timecython-bench: dacapobench: H2dacapobench: Jythondacapobench: Tradesoapdacapobench: Tradebeansdarktable: Boat - CPU-onlydarktable: Masskrug - CPU-onlydarktable: Server Rack - CPU-onlydarktable: Server Room - CPU-onlydav1d: Summer Nature 4Kdav1d: Summer Nature 1080pdbench: 12dbench: 12dcraw: RAW To PPM Image Conversiondeepspeech: CPUebizzy: embree: Pathtracer - Crownembree: Pathtracer ISPC - Crownespeak: Text-To-Speech Synthesisethr: HTTP - Bandwidth - 2rocksdb: Rand Fillrocksdb: Rand Readrocksdb: Seq Fillrocksdb: Rand Fill Syncrocksdb: Read While Writingffmpeg: H.264 HD To NTSC DVffte: N=256, 1D Complex FFT Routinefftw: Stock - 2D FFT Size 4096fftw: Float + SSE - 2D FFT Size 4096fhourstones: Complex Connect-4 Solvingencode-flac: WAV To FLACfio: Rand Read - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Write - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Read - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Write - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Read - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Write - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Read - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Write - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Read - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Write - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Read - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Seq Write - POSIX AIO - Yes - No - 4KB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directoryfs-mark: 1000 Files, 1MB Sizefs-mark: 5000 Files, 1MB Size, 4 Threadsfs-mark: 4000 Files, 32 Sub Dirs, 1MB Sizefs-mark: 1000 Files, 1MB Size, No Sync/FSyncgegl: Cropgegl: Scalegegl: Cartoongegl: Reflectgegl: Antialiasgegl: Tile Glassgegl: Wavelet Blurgegl: Color Enhancegegl: Rotate 90 Degreesgimp: resizegimp: rotategimp: auto-levelsgimp: unsharp-maskgit: Time To Complete Common Git Commandsglibc-bench: cosglibc-bench: expglibc-bench: ffsglibc-bench: singlibc-bench: log2glibc-bench: modfglibc-bench: sinhglibc-bench: sqrtglibc-bench: tanhglibc-bench: asinhglibc-bench: atanhglibc-bench: ffsllglibc-bench: sincosglibc-bench: pthread_oncegmpbench: Total Timempcbench: Multi-Precision Benchmarkoctave-benchmark: gnupg: Linux 4.3 Package File Encryptiongnupg: 2GB File Encryptiongo-benchmark: httpgo-benchmark: jsongo-benchmark: buildgo-benchmark: garbagegraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Resizinggraphics-magick: Noise-Gaussiangraphics-magick: HWB Color Spacegromacs: Water Benchmarkcompress-gzip: Linux Source Tree Archiving To .tar.gzhackbench: 32 - Processhint: FLOAThpcg: himeno: Poisson Pressure Solverhpcc: G-HPLhpcc: G-Fftehpcc: EP-DGEMMhpcc: G-Ptranshpcc: EP-STREAM Triadhpcc: G-Rand Accesshpcc: Rand Ring Latencyhpcc: Rand Ring Bandwidthhpcc: Max Ping Pong Bandwidthindigobench: Bedroomindigobench: Supercarinkscape: SVG Files To PNGintel-mpi: IMB-P2P PingPongintel-mpi: IMB-MPI1 Exchangeintel-mpi: IMB-MPI1 Exchangeintel-mpi: IMB-MPI1 PingPongintel-mpi: IMB-MPI1 Sendrecvintel-mpi: IMB-MPI1 Sendrecvoidn: Memorialior: Write Testior: Read Testiozone: 1MB - 512MB - Write Performanceiozone: 4Kb - 512MB - Write Performanceiozone: 64Kb - 512MB - Write Performanceiozone: 4Kb - 512MB - Write Performanceipc-benchmark: TCP Socket - 128ipc-benchmark: Unnamed Pipe - 128ipc-benchmark: FIFO Named Pipe - 128ipc-benchmark: Unnamed Unix Domain Socket - 128iperf: 5201 - 10 Seconds - TCP - 64iperf: 5201 - 10 Seconds - UDP - 64java-scimark2: Compositejava-scimark2: Monte Carlojava-scimark2: Fast Fourier Transformjava-scimark2: Sparse Matrix Multiplyjava-scimark2: Dense LU Matrix Factorizationjava-scimark2: Jacobi Successive Over-Relaxationjohn-the-ripper: Blowfishjohn-the-ripper: MD5keydb: encode-mp3: WAV To MP3lammps: Rhodopsin Proteinlczero: BLASleveldb: Hot Readleveldb: Fill Syncleveldb: Fill Syncleveldb: Overwriteleveldb: Overwriteleveldb: Rand Fillleveldb: Rand Fillleveldb: Rand Readleveldb: Seek Randleveldb: Rand Deleteleveldb: Seq Fillleveldb: Seq Filllibgav1: Summer Nature 1080ptjbench: Decompression Throughputlibreoffice: 20 Documents To PDFrsvg: SVG Files To PNGnetwork-loopback: Time To Transfer 10GB Via Loopbackluajit: Compositeluajit: Monte Carloluajit: Fast Fourier Transformluajit: Sparse Matrix Multiplyluajit: Dense LU Matrix Factorizationluajit: Jacobi Successive Over-Relaxationlulesh: luxcorerender: DLSCluxcorerender: Rainbow Colors and Prismlzbench: XZ 0 - Compressionlzbench: XZ 0 - Decompressionlzbench: Zstd 1 - Compressionlzbench: Zstd 1 - Decompressionlzbench: Zstd 8 - Compressionlzbench: Zstd 8 - Decompressionlzbench: Crush 0 - Compressionlzbench: Crush 0 - Decompressionlzbench: Brotli 0 - Compressionlzbench: Brotli 0 - Decompressionlzbench: Brotli 2 - Compressionlzbench: Brotli 2 - Decompressionlzbench: Libdeflate 1 - Compressionlzbench: Libdeflate 1 - Decompressioncompress-lzma: 256MB File Compressionm-queens: Time To Solvemysqlslap: 64mbw: Memory Copy - 4096 MiBmbw: Memory Copy, Fixed Block Size - 4096 MiBmcperf: Addmcperf: Getmcperf: Setmcperf: Appendmcperf: Deletemcperf: Prependmcperf: Replacemcperf: Add - 64mcperf: Get - 64mcperf: Set - 64memtier-benchmark: Redisminife: Smallminion: Gracefulminion: Solitaireminion: Quasigroupmkl-dnn: IP Batch 1D - f32mkl-dnn: IP Batch All - f32mkl-dnn: Convolution Batch conv_3d - f32mkl-dnn: Convolution Batch conv_all - f32mkl-dnn: Deconvolution Batch deconv_1d - f32mkl-dnn: Deconvolution Batch deconv_3d - f32mkl-dnn: Convolution Batch conv_alexnet - f32mkl-dnn: Deconvolution Batch deconv_all - f32mkl-dnn: Recurrent Neural Network Training - f32mkl-dnn: Convolution Batch conv_googlenet_v3 - f32mlpack: scikit_icamlpack: scikit_qdamlpack: scikit_svmmlpack: scikit_linearridgeregressionmultichase: 1GB Array, 256 Byte Stride, 4 Threadsn-queens: Elapsed Timenamd: ATPase Simulation - 327,506 Atomsnpb: BT.Cnpb: CG.Cnpb: EP.Cnpb: EP.Dnpb: FT.Cnpb: IS.Dnpb: LU.Cnpb: MG.Cnpb: SP.Bneatbench: CPUneat: nginx: Static Web Page Servingnode-express-loadtest: node-octane: numenta-nab: Relative Entropynumenta-nab: Windowed Gaussiannumenta-nab: Earthgecko Skylinenumenta-nab: Bayesian Changepointnumpy: encode-ogg: WAV To Oggopencv-bench: openssl: RSA 4096-bit Performanceoptcarrot: Optimized Benchmarkosbench: Create Filesosbench: Create Threadsosbench: Launch Programsosbench: Create Processesosbench: Memory Allocationsospray: San Miguel - SciVisospray: XFrog Forest - SciVisospray: San Miguel - Path Tracerospray: NASA Streamlines - SciVisospray: XFrog Forest - Path Tracerospray: Magnetic Reconnection - SciVisospray: NASA Streamlines - Path Tracerospray: Magnetic Reconnection - Path Tracerparboil: OpenMP LBMparboil: OpenMP CUTCPparboil: OpenMP Stencilparboil: OpenMP MRI Griddingpennant: sedovbigpennant: leblancbigperl-benchmark: Pod2htmlperl-benchmark: Interpreterphpbench: PHP Benchmark Suiteplaidml: No - Inference - ResNet 50 - CPUpolybench-c: Covariance Computationpolybench-c: Correlation Computationpolybench-c: 3 Matrix Multiplicationspolyhedron: acpgbench: Buffer Test - Normal Load - Read Onlypgbench: Buffer Test - Normal Load - Read Writepostmark: Disk Transaction Performancepovray: Trace Timeprimesieve: 1e12 Prime Number Generationpybench: Total For Average Test Timespyperformance: floatqmcpack: qmlbench: Canvas Text Simplerbenchmark: radiance: Serialradiance: SMP Parallelramspeed: Copy - Integerramspeed: Scale - Integercompress-rar: Linux Source Tree Archiving To RARrawtherapee: Total Benchmark Timerays1bench: Large Sceneredis: GETredis: SETredis: LPOPredis: SADDredis: LPUSHredis: GETredis: SETrenaissance: Scala Dottyrenaissance: Rand Forestrenaissance: Apache Spark ALSrenaissance: Apache Spark Bayesrenaissance: Savina Reactors.IOrenaissance: Apache Spark PageRankrenaissance: In-Memory Database Shootoutrenaissance: Akka Unbalanced Cobwebbed Treerodinia: OpenMP LavaMDrodinia: OpenMP CFD Solverrodinia: OpenMP Streamclusterrust-mandel: Time To Complete Serial/Parallel Mandelbrotrust-prime: Prime Number Test To 200,000,000schbench: 8 - 8scikit-learn: scimark2: Compositescimark2: Monte Carloscimark2: Fast Fourier Transformscimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationscimark2: Jacobi Successive Over-Relaxationsmallpt: Global Illumination Renderer; 128 Samplessockperf: Throughputsockperf: Latency Ping Pongsockperf: Latency Under Loadsqlite: 1sqlite-speedtest: Timed Time - Size 1,000stockfish: Total Timestream: Copystream: Scalestream: Triadstream: Addstress-ng: Cryptostress-ng: Bsearchstress-ng: Forkingstress-ng: Hsearchstress-ng: Lsearchstress-ng: Tsearchstress-ng: CPU Stressstress-ng: Semaphoresstress-ng: Matrix Mathstress-ng: Vector Mathstress-ng: Memory Copyingstress-ng: Socket Activitystress-ng: Context Switchingstress-ng: Glibc C String Functionsstress-ng: Glibc Qsort Data Sortingstress-ng: System V Message Passingsudokut: Total Timesunflow: Global Illumination + Image Synthesissvt-av1: Enc Mode 8 - 1080psvt-hevc: 1080p 8-bit YUV To HEVC Video Encodesvt-vp9: Visual Quality Optimized - Bosphorus 1080pswet: Averagesysbench: Memorysysbench: CPUsystem-libxml2: 1 MBsystemd-boot-total: Totalsystemd-boot-total: Kernelsystemd-boot-total: Loadersystemd-boot-total: Firmwaresystemd-boot-total: Userspacet-test1: 1t-test1: 2tachyon: Total Timetensorflow: Cifar10tesseract-ocr: Time To OCR 7 Imagestiobench: Write - 32MB - 4build-apache: Time To Compilebuild-ffmpeg: Time To Compilebuild-gcc: Time To Compilebuild-gdb: Time To Compilehmmer: Pfam Database Searchbuild-imagemagick: Time To Compilebuild-linux-kernel: Time To Compilebuild-llvm: Time To Compilebuild-mplayer: Time To Compilemrbayes: Primate Phylogeny Analysisbuild-php: Time To Compiletinymembench: Standard Memcpytinymembench: Standard Memsettscp: AI Chess Performancettsiod-renderer: Phong Rendering With Soft-Shadow Mappingtungsten: Hairtungsten: Water Caustictungsten: Non-Exponentialtungsten: Volumetric Causticunpack-linux: linux-4.15.tar.xzvpxenc: Speed 5x264: H.264 Video Encodingx265: H.265 1080p Video Encodingxsbench: compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Threadripper 3970X16 Cores19618610.868534112289.30024786.2831.70840.8836286.78203602930034180337255626.42138.48495770.304869131.522285802.01125.182651.593738.112682.403795.214771.163764.479591619719118.3540.40109.3967.04159.93146.0247.57119.4771.28194.17153.881260198498748.121100.1025902.141391.425475.104154.14750734549.5762.1064753.3942504.0948883.7872012.1735800.7967870.95204244416335.216.3773035.0331832.50418349261162.938268635458410.711.05716.221331439.752235494.65358.05732.166273.2321110.91177.19414.86828.6221624.302932389853102703139232236238892788696.16277514840.85838864023330144966.0103.0880.1201.991324.66726.09595.261665.37139.65556.68455254237237.657235.545727.3531844.58108322518062644411479752916762040767.3319483.926875.52161014702.37.7611440026366745933330700056.2103017941200115129433370618063313463445331052269200576.3485.9560.72724.88.0035.66190.94929.98339.00331.03362.39556.06938.1658.47012.43716.98920.1654.91442.25144.993171.7587042.03665.882182.234427.796962.2202710.68418.4183510.09141.7589712.26221.761335794.6905013.06712.38411.42778251564168200676771015897121590693468669224363114993.28833.91431.389386120425.4211710.67074607.31279073.1964316.1230729.803077.441191.903480.171380.469622.2081421719.6474.9069.31726.27117789641.3768126258.07149.285106.634955.0082.6121.96182.761047.581554.841594.311677.551529.5735787603558893338832424162135484067.13009.121686.792043.322683.186674.411957.92432552520750119630.187.18817.2742105.1144.2863.61938.16726.8263.93827.3259.84044.35368.592256.43627.6256.32876.46218.8990176.66323.87010.4041659.51526.75287.971352.773996.692133.379.39089872.512.0741131543150310716561215005476332167392661245221.24617.94520721587.37712649.30845047.077680.245117.549940.574147.446495.947267.148669.678526.048126.02351667.589322.7541.33611560.649045107.5296213.4165517.32976.82846968.7172.786884.91239137.7851713.90299.85856.580049.2053.0211.501.4774.5613.4960.6235774815.9910815.592831.862907.5834599.491464.4565854.9730218.9133710.7037.612.81836707.66109085012512.4176.11169.66324.895432.115.22566.3559307.4103.9811.44675611.32965149.30257827.96371870.318381508.993.6766.674.6932.6213.58444.4452.9692360.9933425.28214160.1751878885.0378623.6510.114102460.001366236417567.402.1412.1202.1395.91792360.45605911196.802982781213.2356.1239581032581.7358.80.2858564.243173.31741870.342704.7468.08940.810225.762229021.421674234.132175519.081851271.351417209.042005988.501687462.135168.0663840.4594708.5392677.51313551.88016363.8445898.13712746.6148.3379.78420.40132.09310.27235877.973718.03157.71356.71793.80983.931298.022.8945342402.93113.23414.40858.5889572878752075.851667.157321.856819.29207.8520222.0397017.28253747.42434.811111.0412151.313379188.34234235.7688021.728324.5722217.7621267958.313406391.46489.8126168429.6912.9040.51769.741174.75368.418114425489119242.226668765.37784243705557109976200023134525.6008.74325.035342.0224.08410.55018.58421.969589.10983.1154.84213.43024.542122.76611.58175.41332.03712225.420042.41336877667.3398.1821718.68352.642893.563824.98424.48205.3164.90607955418.652170.7758.544784884.66695954172.19726671.3431.73362.3741019.20316677444756738154186.82289.305987146.682849176.691013481.36823.522306.503463.502368.483544.173330.883482.693741550919118.5497.69283.82163.13430.81382.22119.58314.82178.46501.07414.421283483117008.55699.8495858.029385.677471.104154.99221006671.8832.1272263.4281564.1321333.8227672.1952780.8049270.96155242231623.534.1573024.6831631.79198134961009.394690540204333.041.26548.75508354.399417423.75158.98732.378275.7291115.81678.89014.97828.867654.626879.91410634907315369.091069508869846693.03436018539.93926063921321924525.0603.7460.0972.057205.50556.991466.071382.0939.42849.10472128437813.228412.826127.9083314.79260697672774397702809910623813605.0416841.82153415067.47.7761160027700036433332033345.210821424125111600273333369000319333123431573313093350001553397600961245750611.7602.3633.22012.97.4914.94088.67729.41136.36128.68760.11455.42937.6916.92311.18812.77215.1165.01842.81414.951891.7875442.27885.897992.254157.829572.2397910.71658.5371110.20101.7780012.40531.775945767.1901310.57712.46511.4704059352358517244462905897936784732252357184735114172.04834.07174.353381206340.365159.972764880.01510689.9925311.1667349.580702.126293.476140.113620.407883.9768622271.5421.8524.10625.2629362495.73913057217.49104.955828.126263.7363.4914.97622.531117.521335.371283.8743489581361.611280.5537052043701949335394625554314721667.13005.071679.212040.932716.606637.131951.48261111626000167550.107.18212.7473630.248.97411677.70740.343.84640.343.8749.31314.88839.89741.842.299105.76218.3427056.54118.67610.8061624.14515.37278.181319.003910.402097.7410.9021152.302.4041130543149310916501204985396282157362671244220.22655.084108021862.42612748.60872837.789370.875424.085868.988516.688961.484273.871799.088109.772538.52272891.4210962.741.67204461.094678108.5163353.5504211.56879.503721369.923.224353.69166178.6661182.61142.35076.354136.0534.1611.431.4273.27011.3211.2390154825.1310888.191486.441480.1031324.201521.3454335.4628788.0624225.6430.713.98136762.59118585158211.5907.01375.99224.671430.365.25361.5354550.9102.7513.87894346.120485228.57586554.98329867.15599718.523.321.37251.7513.164.9725036.3548372.1222037.78201537.0924184341.3434088.4140.122566290.000911866413807.692.1202.1142.1355.89272392.97447612881.179621635732.24612.53895599.71039.4386.40.1361564.78171.48943057.6936372.4459.83742.41495.942108260.531723424.592097030.001874999.401492623.122184449.111696335.085197.5973826.8034278.4053157.25515896.11816238.5274006.5998732.84116.53412.07711.26640.17319.958463157.875697.80155.44328.58782.85946.171275.977.4075320892.21010.77513.91558.1733693274249216.849498.854847.954720.54392.367239.7510970.25106584.80138.27383.185019.093998333.2276991.0435109.173963.8110510.352258922.931252570.26181.5516301159.7312.2320.95435.89082.13172.138155974668262426.982933077.16624243904861703542201533287816.0595.44958.319845.4423.82310.40927.54238.017979.61682.1933.67822.30249.357232.3325.09069.52048.21412317.720120.61319372617.84619.255824.12608.922158.564204.96428.62131.8873.21384040423.634163.05213.565OpenBenchmarking.org

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test16 CoresThreadripper 3970X40K80K120K160K200KSE +/- 152.64, N = 3SE +/- 801.81, N = 3784881961861. (CXX) g++ options: -pipe -lpthread

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point Rate16 CoresThreadripper 3970X3691215SE +/- 0.029585, N = 3SE +/- 0.169806, N = 34.66695910.8685341. (CC) gcc options: -O3 -march=native -fopenmp

Aircrack-ng

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.5.216 CoresThreadripper 3970X20K40K60K80K100KSE +/- 141.94, N = 3SE +/- 266.32, N = 354172.20112289.301. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread

Algebraic Multi-Grid Benchmark

OpenBenchmarking.orgFigure Of Merit, More Is BetterAlgebraic Multi-Grid Benchmark16 CoresThreadripper 3970X6K12K18K24K30KSE +/- 24.90, N = 3SE +/- 14.75, N = 326671.3424786.281. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi

AOBench

Size: 2048 x 2048 - Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total Time16 CoresThreadripper 3970X714212835SE +/- 0.05, N = 3SE +/- 0.27, N = 1431.7331.711. (CC) gcc options: -lm -O3

AOM AV1

Encoder Mode: Speed 8 Realtime

OpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2020-01-10Encoder Mode: Speed 8 Realtime16 CoresThreadripper 3970X1428425670SE +/- 0.03, N = 3SE +/- 0.21, N = 362.3740.881. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

Apache Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page Serving16 CoresThreadripper 3970X9K18K27K36K45KSE +/- 50.68, N = 3SE +/- 25.01, N = 341019.2036286.781. (CC) gcc options: -shared -fPIC -O2 -pthread

Apache Cassandra

Test: Reads

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Reads16 CoresThreadripper 3970X4K8K12K16K20KSE +/- 37.22, N = 3SE +/- 7579.05, N = 9316620360

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Writes16 CoresThreadripper 3970X60K120K180K240K300KSE +/- 21.67, N = 3SE +/- 3852.60, N = 57744293003

Apache HBase

Test: Random Write - Clients: 16

OpenBenchmarking.orgRows Per Second, More Is BetterApache HBase 2.2.3Test: Random Write - Clients: 1616 CoresThreadripper 3970X100K200K300K400K500KSE +/- 57800.53, N = 15SE +/- 64718.62, N = 15475673418033

Apache HBase

Test: Random Write - Clients: 16

OpenBenchmarking.orgMicroseconds - Average Latency, Fewer Is BetterApache HBase 2.2.3Test: Random Write - Clients: 1616 CoresThreadripper 3970X20406080100SE +/- 29.55, N = 15SE +/- 20.61, N = 158172

Apache Siege

Concurrent Users: 250

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 25016 CoresThreadripper 3970X12K24K36K48K60KSE +/- 579.13, N = 12SE +/- 1582.21, N = 1554186.8255626.421. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

Appleseed

Scene: Emily

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Emily16 CoresThreadripper 3970X60120180240300289.31138.48

Appleseed

Scene: Disney Material

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney Material16 CoresThreadripper 3970X306090120150146.6870.30

Appleseed

Scene: Material Tester

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material Tester16 CoresThreadripper 3970X4080120160200176.69131.52

ArrayFire

Test: BLAS CPU

OpenBenchmarking.orgGFLOPS, More Is BetterArrayFire 3.7Test: BLAS CPU16 CoresThreadripper 3970X2004006008001000SE +/- 1.49, N = 3SE +/- 7.27, N = 3481.37802.011. (CXX) g++ options: -rdynamic

ArrayFire

Test: Conjugate Gradient CPU

OpenBenchmarking.orgms, Fewer Is BetterArrayFire 3.7Test: Conjugate Gradient CPU16 CoresThreadripper 3970X612182430SE +/- 0.23, N = 3SE +/- 0.25, N = 323.5225.181. (CXX) g++ options: -rdynamic

ASKAP

Test: tConvolve MT - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - Gridding16 CoresThreadripper 3970X6001200180024003000SE +/- 1.91, N = 3SE +/- 10.28, N = 32306.502651.591. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve MT - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - Degridding16 CoresThreadripper 3970X8001600240032004000SE +/- 2.81, N = 3SE +/- 12.65, N = 33463.503738.111. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - Gridding16 CoresThreadripper 3970X6001200180024003000SE +/- 1.16, N = 3SE +/- 2.78, N = 32368.482682.401. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - Degridding16 CoresThreadripper 3970X8001600240032004000SE +/- 0.00, N = 3SE +/- 6.40, N = 33544.173795.211. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve OpenMP - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - Gridding16 CoresThreadripper 3970X10002000300040005000SE +/- 29.54, N = 11SE +/- 42.14, N = 153330.884771.161. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve OpenMP - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - Degridding16 CoresThreadripper 3970X8001600240032004000SE +/- 7.16, N = 11SE +/- 8.15, N = 153482.693764.471. (CXX) g++ options: -lpthread

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 Depth16 CoresThreadripper 3970X20M40M60M80M100MSE +/- 159073.11, N = 3SE +/- 334321.64, N = 33741550995916197

BenchmarkMutex

Benchmark: Shared Mutex Lock Shared

OpenBenchmarking.orgns, Fewer Is BetterBenchmarkMutexBenchmark: Shared Mutex Lock Shared16 CoresThreadripper 3970X51015202519191. (CXX) g++ options: -std=c++17 -lbenchmark -pthread

BenchmarkMutex

Benchmark: Semaphore Release And Acquire

OpenBenchmarking.orgns, Fewer Is BetterBenchmarkMutexBenchmark: Semaphore Release And Acquire16 CoresThreadripper 3970X369121511111. (CXX) g++ options: -std=c++17 -lbenchmark -pthread

BLAKE2

OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 2017030716 CoresThreadripper 3970X246810SE +/- 0.03, N = 3SE +/- 0.12, N = 38.548.351. (CC) gcc options: -O3 -march=native -lcrypto -lz

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: BMW27 - Compute: CPU-Only16 CoresThreadripper 3970X20406080100SE +/- 0.11, N = 3SE +/- 0.05, N = 397.6940.40

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Classroom - Compute: CPU-Only16 CoresThreadripper 3970X60120180240300SE +/- 0.30, N = 3SE +/- 0.18, N = 3283.82109.39

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Fishy Cat - Compute: CPU-Only16 CoresThreadripper 3970X4080120160200SE +/- 0.04, N = 3SE +/- 0.05, N = 3163.1367.04

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Barbershop - Compute: CPU-Only16 CoresThreadripper 3970X90180270360450SE +/- 0.65, N = 3SE +/- 0.33, N = 3430.81159.93

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.80Blend File: Pabellon Barcelona - Compute: CPU-Only16 CoresThreadripper 3970X80160240320400SE +/- 0.17, N = 3SE +/- 0.24, N = 3382.22146.02

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: BMW27 - Compute: CPU-Only16 CoresThreadripper 3970X306090120150SE +/- 0.17, N = 3SE +/- 0.09, N = 3119.5847.57

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Classroom - Compute: CPU-Only16 CoresThreadripper 3970X70140210280350SE +/- 0.36, N = 3SE +/- 0.31, N = 3314.82119.47

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Fishy Cat - Compute: CPU-Only16 CoresThreadripper 3970X4080120160200SE +/- 0.09, N = 3SE +/- 0.08, N = 3178.4671.28

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Barbershop - Compute: CPU-Only16 CoresThreadripper 3970X110220330440550SE +/- 0.54, N = 3SE +/- 0.21, N = 3501.07194.17

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.82Blend File: Pabellon Barcelona - Compute: CPU-Only16 CoresThreadripper 3970X90180270360450SE +/- 0.44, N = 3SE +/- 0.59, N = 3414.42153.88

BlogBench

Test: Read

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: Read16 CoresThreadripper 3970X300K600K900K1200K1500KSE +/- 3455.51, N = 3SE +/- 12676.46, N = 8128348312601981. (CC) gcc options: -O2 -pthread

BlogBench

Test: Write

OpenBenchmarking.orgFinal Score, More Is BetterBlogBench 1.1Test: Write16 CoresThreadripper 3970X11K22K33K44K55KSE +/- 102.18, N = 3SE +/- 1160.31, N = 311700498741. (CC) gcc options: -O2 -pthread

Bork File Encrypter

File Encryption Time

OpenBenchmarking.orgSeconds, Fewer Is BetterBork File Encrypter 1.4File Encryption Time16 CoresThreadripper 3970X246810SE +/- 0.011, N = 3SE +/- 0.005, N = 38.5568.121

Botan

Test: KASUMI

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: KASUMI16 CoresThreadripper 3970X20406080100SE +/- 0.13, N = 3SE +/- 0.09, N = 399.85100.101. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: AES-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: AES-25616 CoresThreadripper 3970X13002600390052006500SE +/- 14.95, N = 3SE +/- 7.95, N = 35858.035902.141. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Twofish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: Twofish16 CoresThreadripper 3970X80160240320400SE +/- 0.02, N = 3SE +/- 3.16, N = 3385.68391.431. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: Blowfish

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: Blowfish16 CoresThreadripper 3970X100200300400500SE +/- 0.01, N = 3SE +/- 0.50, N = 3471.10475.101. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Botan

Test: CAST-256

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.13.0Test: CAST-25616 CoresThreadripper 3970X306090120150SE +/- 0.27, N = 3SE +/- 1.54, N = 3154.99154.151. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.28.0VGR Performance Metric16 CoresThreadripper 3970X110K220K330K440K550K2100665073451. (CXX) g++ options: -std=c++98 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To Compile16 CoresThreadripper 3970X1632486480SE +/- 0.80, N = 3SE +/- 0.08, N = 371.8849.58

Bullet Physics Engine

Test: Raytests

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Raytests16 CoresThreadripper 3970X0.47860.95721.43581.91442.393SE +/- 0.001575, N = 3SE +/- 0.001065, N = 32.1272262.1064751. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 3000 Fall

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 Fall16 CoresThreadripper 3970X0.77131.54262.31393.08523.8565SE +/- 0.003898, N = 3SE +/- 0.002468, N = 33.4281563.3942501. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Stack

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Stack16 CoresThreadripper 3970X0.92971.85942.78913.71884.6485SE +/- 0.002167, N = 3SE +/- 0.005908, N = 34.1321334.0948881. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Convex

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Convex16 CoresThreadripper 3970X0.86011.72022.58033.44044.3005SE +/- 0.003706, N = 3SE +/- 0.000553, N = 33.8227673.7872011. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 136 Ragdolls

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 Ragdolls16 CoresThreadripper 3970X0.49390.98781.48171.97562.4695SE +/- 0.001501, N = 3SE +/- 0.001302, N = 32.1952782.1735801. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Prim Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim Trimesh16 CoresThreadripper 3970X0.18110.36220.54330.72440.9055SE +/- 0.000909, N = 3SE +/- 0.000329, N = 30.8049270.7967871. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Convex Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex Trimesh16 CoresThreadripper 3970X0.21630.43260.64890.86521.0815SE +/- 0.000327, N = 3SE +/- 0.000443, N = 30.9615520.9520421. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

BYTE Unix Benchmark

Computational Test: Dhrystone 2

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 216 CoresThreadripper 3970X10M20M30M40M50MSE +/- 411120.29, N = 3SE +/- 385242.29, N = 342231623.544416335.2

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel16 CoresThreadripper 3970X816243240SE +/- 0.03, N = 3SE +/- 0.04, N = 334.1616.381. (CC) gcc options: -lm -lpthread -O3

CacheBench

Test: Read

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read16 CoresThreadripper 3970X7001400210028003500SE +/- 0.65, N = 3SE +/- 4.12, N = 33024.683035.03MIN: 3022.65 / MAX: 3028.8MIN: 3020.86 / MAX: 3044.341. (CC) gcc options: -lrt

CacheBench

Test: Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Write16 CoresThreadripper 3970X7K14K21K28K35KSE +/- 29.01, N = 3SE +/- 14.14, N = 331631.7931832.50MIN: 27804.64 / MAX: 32902.03MIN: 27271.39 / MAX: 33182.751. (CC) gcc options: -lrt

CacheBench

Test: Read / Modify / Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / Write16 CoresThreadripper 3970X13K26K39K52K65KSE +/- 147.71, N = 3SE +/- 167.50, N = 361009.3961162.94MIN: 55206.66 / MAX: 65416.9MIN: 53743.85 / MAX: 65830.071. (CC) gcc options: -lrt

Chaos Group V-RAY

Mode: CPU

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.07Mode: CPU16 CoresThreadripper 3970X10K20K30K40K50KSE +/- 86.26, N = 3SE +/- 663.97, N = 32043345841

CLOMP

Static OMP Speedup

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP Speedup16 CoresThreadripper 3970X0.6841.3682.0522.7363.42SE +/- 0.05, N = 25SE +/- 0.01, N = 253.040.711. (CC) gcc options: --openmp -O3 -lm

CloverLeaf

Lagrangian-Eulerian Hydrodynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian Hydrodynamics16 CoresThreadripper 3970X0.28350.5670.85051.1341.4175SE +/- 0.00, N = 3SE +/- 0.06, N = 121.261.051. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

Compile Bench

Test: Initial Create

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Initial Create16 CoresThreadripper 3970X150300450600750SE +/- 3.20, N = 3SE +/- 1.98, N = 3548.75716.22

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per Second16 CoresThreadripper 3970X300K600K900K1200K1500KSE +/- 1593.11, N = 3SE +/- 6863.17, N = 3508354.401331439.751. (CC) gcc options: -O2 -lrt" -lrt

CP2K Molecular Dynamics

Fayalite-FIST Data

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST Data16 CoresThreadripper 3970X110220330440550423.75494.65

CppPerformanceBenchmarks

Test: Atol

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Atol16 CoresThreadripper 3970X1326395265SE +/- 0.17, N = 3SE +/- 0.26, N = 358.9958.061. (CXX) g++ options: -std=c++11 -O3

CppPerformanceBenchmarks

Test: Ctype

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Ctype16 CoresThreadripper 3970X816243240SE +/- 0.06, N = 3SE +/- 0.03, N = 332.3832.171. (CXX) g++ options: -std=c++11 -O3

CppPerformanceBenchmarks

Test: Math Library

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Math Library16 CoresThreadripper 3970X60120180240300SE +/- 0.39, N = 3SE +/- 1.09, N = 3275.73273.231. (CXX) g++ options: -std=c++11 -O3

CppPerformanceBenchmarks

Test: Random Numbers

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Random Numbers16 CoresThreadripper 3970X2004006008001000SE +/- 0.28, N = 3SE +/- 0.90, N = 31115.821110.911. (CXX) g++ options: -std=c++11 -O3

CppPerformanceBenchmarks

Test: Stepanov Vector

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov Vector16 CoresThreadripper 3970X20406080100SE +/- 0.37, N = 3SE +/- 0.36, N = 378.8977.191. (CXX) g++ options: -std=c++11 -O3

CppPerformanceBenchmarks

Test: Function Objects

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Function Objects16 CoresThreadripper 3970X48121620SE +/- 0.07, N = 3SE +/- 0.02, N = 314.9814.871. (CXX) g++ options: -std=c++11 -O3

CppPerformanceBenchmarks

Test: Stepanov Abstraction

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov Abstraction16 CoresThreadripper 3970X714212835SE +/- 0.16, N = 3SE +/- 0.01, N = 328.8728.621. (CXX) g++ options: -std=c++11 -O3

Cpuminer-Opt

Algorithm: m7m

OpenBenchmarking.orgkH/s - Hash Speed, More Is BetterCpuminer-Opt 3.8.8.1Algorithm: m7m16 CoresThreadripper 3970X30060090012001500SE +/- 2.16, N = 3SE +/- 3.06, N = 3654.621624.301. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: deep

OpenBenchmarking.orgkH/s - Hash Speed, More Is BetterCpuminer-Opt 3.8.8.1Algorithm: deep16 CoresThreadripper 3970X6K12K18K24K30KSE +/- 1488.63, N = 15SE +/- 31.80, N = 36879.9129323.001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: lbry

OpenBenchmarking.orgkH/s - Hash Speed, More Is BetterCpuminer-Opt 3.8.8.1Algorithm: lbry16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 330.05, N = 15SE +/- 464.63, N = 341063898531. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: skein

OpenBenchmarking.orgkH/s - Hash Speed, More Is BetterCpuminer-Opt 3.8.8.1Algorithm: skein16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 200.78, N = 3SE +/- 194.28, N = 3490731027031. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: myr-gr

OpenBenchmarking.orgkH/s - Hash Speed, More Is BetterCpuminer-Opt 3.8.8.1Algorithm: myr-gr16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 1707.65, N = 15SE +/- 71.26, N = 315369.0913923.001. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Cpuminer-Opt

Algorithm: sha256t

OpenBenchmarking.orgkH/s - Hash Speed, More Is BetterCpuminer-Opt 3.8.8.1Algorithm: sha256t16 CoresThreadripper 3970X50K100K150K200K250KSE +/- 826.56, N = 3SE +/- 26.03, N = 31069502236231. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp

Crafty

Elapsed Time

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time16 CoresThreadripper 3970X2M4M6M8M10MSE +/- 20746.21, N = 3SE +/- 13510.52, N = 3886984688927881. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

Crypto++

Test: Keyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed Algorithms16 CoresThreadripper 3970X150300450600750SE +/- 0.14, N = 3SE +/- 1.50, N = 3693.03696.161. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe

ctx_clock

Context Switch Time

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch Time16 CoresThreadripper 3970X4080120160200185148

Cython benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterCython benchmark 0.2716 CoresThreadripper 3970X918273645SE +/- 0.18, N = 3SE +/- 0.04, N = 339.9440.86

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H216 CoresThreadripper 3970X8001600240032004000SE +/- 32.67, N = 5SE +/- 34.65, N = 426063886

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython16 CoresThreadripper 3970X9001800270036004500SE +/- 2.74, N = 4SE +/- 14.99, N = 439214023

DaCapo Benchmark

Java Test: Tradesoap

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradesoap16 CoresThreadripper 3970X7001400210028003500SE +/- 23.31, N = 20SE +/- 29.24, N = 1132193301

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Tradebeans16 CoresThreadripper 3970X10002000300040005000SE +/- 14.45, N = 4SE +/- 10.90, N = 424524496

Darktable

Test: Boat - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Boat - Acceleration: CPU-only16 CoresThreadripper 3970X246810SE +/- 0.007, N = 3SE +/- 0.097, N = 155.0606.010

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Masskrug - Acceleration: CPU-only16 CoresThreadripper 3970X0.84291.68582.52873.37164.2145SE +/- 0.009, N = 3SE +/- 0.017, N = 33.7463.088

Darktable

Test: Server Rack - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Rack - Acceleration: CPU-only16 CoresThreadripper 3970X0.0270.0540.0810.1080.135SE +/- 0.000, N = 3SE +/- 0.004, N = 120.0970.120

Darktable

Test: Server Room - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Room - Acceleration: CPU-only16 CoresThreadripper 3970X0.46280.92561.38841.85122.314SE +/- 0.010, N = 3SE +/- 0.009, N = 32.0571.991

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 4K16 CoresThreadripper 3970X70140210280350SE +/- 0.51, N = 3SE +/- 0.26, N = 3205.50324.66MIN: 190.74 / MAX: 228.56MIN: 214.04 / MAX: 344.181. (CC) gcc options: -pthread

dav1d

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 1080p16 CoresThreadripper 3970X160320480640800SE +/- 1.76, N = 3SE +/- 3.50, N = 3556.99726.09MIN: 471.9 / MAX: 604.99MIN: 460.2 / MAX: 805.891. (CC) gcc options: -pthread

Dbench

Client Count: 12

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 1216 CoresThreadripper 3970X30060090012001500SE +/- 14.76, N = 8SE +/- 13.11, N = 91466.07595.261. (CC) gcc options: -lpopt -O2

Dbench

Client Count: 12

OpenBenchmarking.orgMB/s, More Is BetterDbench 4.0Client Count: 1216 CoresThreadripper 3970X30060090012001500SE +/- 46.78, N = 9SE +/- 26.66, N = 91382.09665.37

dcraw

RAW To PPM Image Conversion

OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image Conversion16 CoresThreadripper 3970X918273645SE +/- 0.24, N = 3SE +/- 0.09, N = 339.4339.661. (CC) gcc options: -lm

DeepSpeech

Acceleration: CPU

OpenBenchmarking.orgSeconds, Fewer Is BetterDeepSpeech 0.6Acceleration: CPU16 CoresThreadripper 3970X1326395265SE +/- 0.09, N = 3SE +/- 0.10, N = 349.1056.68

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.316 CoresThreadripper 3970X500K1000K1500K2000K2500KSE +/- 11166.46, N = 11SE +/- 32997.66, N = 5128437825423721. (CC) gcc options: -pthread -lpthread -O3 -march=native

Embree

Binary: Pathtracer - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Crown16 CoresThreadripper 3970X918273645SE +/- 0.01, N = 3SE +/- 0.20, N = 313.2337.66MIN: 13.15 / MAX: 13.46MIN: 34.74 / MAX: 39.17

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Crown16 CoresThreadripper 3970X816243240SE +/- 0.02, N = 3SE +/- 0.09, N = 312.8335.55MIN: 12.72 / MAX: 13.03MIN: 32.78 / MAX: 37.31

eSpeak Speech Engine

Text-To-Speech Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak Speech Engine 1.48.04Text-To-Speech Synthesis16 CoresThreadripper 3970X714212835SE +/- 0.05, N = 3SE +/- 0.14, N = 327.9127.351. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions

Ethr

Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 2

OpenBenchmarking.orgMbits/sec, More Is BetterEthr 2019-01-02Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 216 CoresThreadripper 3970X7001400210028003500SE +/- 6.36, N = 3SE +/- 3.00, N = 33314.791844.58MIN: 3240 / MAX: 3400MIN: 1810 / MAX: 1910

Facebook RocksDB

Test: Random Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill16 CoresThreadripper 3970X200K400K600K800K1000KSE +/- 6931.83, N = 3SE +/- 8852.93, N = 360697610832251. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Read16 CoresThreadripper 3970X40M80M120M160M200MSE +/- 155873.46, N = 3SE +/- 1599226.86, N = 3727743971806264441. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential Fill16 CoresThreadripper 3970X200K400K600K800K1000KSE +/- 8372.80, N = 15SE +/- 3258.34, N = 370280911479751. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Random Fill Sync

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random Fill Sync16 CoresThreadripper 3970X6K12K18K24K30KSE +/- 17.38, N = 3SE +/- 999.84, N = 159106291671. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

Facebook RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While Writing16 CoresThreadripper 3970X1.3M2.6M3.9M5.2M6.5MSE +/- 32658.12, N = 4SE +/- 71829.99, N = 6238136062040761. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

FFmpeg

H.264 HD To NTSC DV

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 4.0.2H.264 HD To NTSC DV16 CoresThreadripper 3970X246810SE +/- 0.039, N = 3SE +/- 0.056, N = 35.0417.3311. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lxcb-shm -lxcb-shape -lxcb-xfixes -lasound -lSDL2 -lsndio -pthread -lbz2 -llzma -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT

FFTE

Test: N=256, 1D Complex FFT Routine

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 6.0Test: N=256, 1D Complex FFT RoutineThreadripper 3970X2K4K6K8K10KSE +/- 15.75, N = 39483.921. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

FFTW

Build: Stock - Size: 2D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 409616 CoresThreadripper 3970X15003000450060007500SE +/- 16.83, N = 3SE +/- 2.20, N = 36841.86875.51. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Float + SSE - Size: 2D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 409616 CoresThreadripper 3970X5K10K15K20K25KSE +/- 48.64, N = 3SE +/- 102.34, N = 321534216101. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Fhourstones

Complex Connect-4 Solving

OpenBenchmarking.orgKpos / sec, More Is BetterFhourstones 3.1Complex Connect-4 Solving16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 53.43, N = 3SE +/- 35.91, N = 315067.414702.31. (CC) gcc options: -O3

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLAC16 CoresThreadripper 3970X246810SE +/- 0.007, N = 5SE +/- 0.024, N = 57.7767.7611. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

Flexible IO Tester

Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO TesterType: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 57.74, N = 3SE +/- 57.74, N = 31160014400

Flexible IO Tester

Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO TesterType: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X60K120K180K240K300KSE +/- 5033.22, N = 3SE +/- 13593.30, N = 12277000263667

Flexible IO Tester

Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO TesterType: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X100K200K300K400K500KSE +/- 3844.19, N = 3SE +/- 1855.92, N = 3364333459333

Flexible IO Tester

Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO TesterType: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X70K140K210K280K350KSE +/- 2185.81, N = 3SE +/- 4041.45, N = 3320333307000

Flexible IO Tester

Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.12Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X1326395265SE +/- 0.15, N = 3SE +/- 0.20, N = 345.256.2

Flexible IO Tester

Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.12Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X2004006008001000SE +/- 8.11, N = 3SE +/- 53.12, N = 1210681030

Flexible IO Tester

Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.12Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X400800120016002000SE +/- 14.74, N = 3SE +/- 7.64, N = 314241794

Flexible IO Tester

Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.12Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X30060090012001500SE +/- 2.73, N = 3SE +/- 16.50, N = 312461200

Flexible IO Tester

Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.12Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 Cores2K4K6K8K10K11600

Flexible IO Tester

Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.12Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 Cores60K120K180K240K300KSE +/- 2333.33, N = 3273333

Flexible IO Tester

Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.12Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 Cores80K160K240K320K400KSE +/- 1527.53, N = 3369000

Flexible IO Tester

Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.12Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory16 Cores70K140K210K280K350KSE +/- 666.67, N = 3319333

Flexible IO Tester

Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X30060090012001500SE +/- 10.95, N = 15SE +/- 2.91, N = 3123411511. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X70K140K210K280K350KSE +/- 2820.78, N = 15SE +/- 881.92, N = 33157332943331. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X30060090012001500SE +/- 102.96, N = 1213097061. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X70K140K210K280K350KSE +/- 26330.47, N = 123350001806331. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X30060090012001500SE +/- 27.78, N = 15SE +/- 15.41, N = 15155313461. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X90K180K270K360K450KSE +/- 7133.29, N = 15SE +/- 3928.97, N = 153976003445331. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgMB/s, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X2004006008001000SE +/- 12.94, N = 496110521. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

Flexible IO Tester

Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory

OpenBenchmarking.orgIOPS, More Is BetterFlexible IO Tester 3.18Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory16 CoresThreadripper 3970X60K120K180K240K300KSE +/- 3424.79, N = 4SE +/- 10149.45, N = 152457502692001. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl

FS-Mark

Test: 1000 Files, 1MB Size

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size16 CoresThreadripper 3970X130260390520650SE +/- 7.97, N = 3SE +/- 9.01, N = 3611.7576.31. (CC) gcc options: -static

FS-Mark

Test: 5000 Files, 1MB Size, 4 Threads

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 5000 Files, 1MB Size, 4 Threads16 CoresThreadripper 3970X130260390520650SE +/- 81.95, N = 12SE +/- 28.74, N = 12602.3485.91. (CC) gcc options: -static

FS-Mark

Test: 4000 Files, 32 Sub Dirs, 1MB Size

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 4000 Files, 32 Sub Dirs, 1MB Size16 CoresThreadripper 3970X140280420560700SE +/- 4.34, N = 3SE +/- 3.35, N = 3633.2560.71. (CC) gcc options: -static

FS-Mark

Test: 1000 Files, 1MB Size, No Sync/FSync

OpenBenchmarking.orgFiles/s, More Is BetterFS-Mark 3.3Test: 1000 Files, 1MB Size, No Sync/FSync16 CoresThreadripper 3970X6001200180024003000SE +/- 6.33, N = 3SE +/- 6.09, N = 32012.92724.81. (CC) gcc options: -static

GEGL

Operation: Crop

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Crop16 CoresThreadripper 3970X246810SE +/- 0.043, N = 3SE +/- 0.062, N = 37.4918.003

GEGL

Operation: Scale

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Scale16 CoresThreadripper 3970X1.27372.54743.82115.09486.3685SE +/- 0.031, N = 3SE +/- 0.040, N = 34.9405.661

GEGL

Operation: Cartoon

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Cartoon16 CoresThreadripper 3970X20406080100SE +/- 0.08, N = 3SE +/- 0.05, N = 388.6890.95

GEGL

Operation: Reflect

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Reflect16 CoresThreadripper 3970X714212835SE +/- 0.02, N = 3SE +/- 0.02, N = 329.4129.98

GEGL

Operation: Antialias

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Antialias16 CoresThreadripper 3970X918273645SE +/- 0.01, N = 3SE +/- 0.07, N = 336.3639.00

GEGL

Operation: Tile Glass

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Tile Glass16 CoresThreadripper 3970X714212835SE +/- 0.07, N = 3SE +/- 0.02, N = 328.6931.03

GEGL

Operation: Wavelet Blur

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Wavelet Blur16 CoresThreadripper 3970X1428425670SE +/- 0.06, N = 3SE +/- 0.18, N = 360.1162.40

GEGL

Operation: Color Enhance

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Color Enhance16 CoresThreadripper 3970X1326395265SE +/- 0.01, N = 3SE +/- 0.03, N = 355.4356.07

GEGL

Operation: Rotate 90 Degrees

OpenBenchmarking.orgSeconds, Fewer Is BetterGEGLOperation: Rotate 90 Degrees16 CoresThreadripper 3970X918273645SE +/- 0.03, N = 3SE +/- 0.02, N = 337.6938.17

GIMP

Test: resize

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: resize16 CoresThreadripper 3970X246810SE +/- 0.041, N = 3SE +/- 0.137, N = 36.9238.470

GIMP

Test: rotate

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: rotate16 CoresThreadripper 3970X3691215SE +/- 0.02, N = 3SE +/- 0.02, N = 311.1912.44

GIMP

Test: auto-levels

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: auto-levels16 CoresThreadripper 3970X48121620SE +/- 0.01, N = 3SE +/- 0.07, N = 312.7716.99

GIMP

Test: unsharp-mask

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: unsharp-mask16 CoresThreadripper 3970X510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 315.1220.17

Git

Time To Complete Common Git Commands

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git Commands16 CoresThreadripper 3970X1.12912.25823.38734.51645.6455SE +/- 0.006, N = 3SE +/- 0.014, N = 35.0184.9141. git version 2.20.1

glibc bench

Benchmark: cos

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cos16 CoresThreadripper 3970X1020304050SE +/- 0.02, N = 3SE +/- 0.27, N = 342.8142.25

glibc bench

Benchmark: exp

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: exp16 CoresThreadripper 3970X1.12352.2473.37054.4945.6175SE +/- 0.00851, N = 3SE +/- 0.01485, N = 34.951894.99317

glibc bench

Benchmark: ffs

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffs16 CoresThreadripper 3970X0.40220.80441.20661.60882.011SE +/- 0.00045, N = 3SE +/- 0.01753, N = 31.787541.75870

glibc bench

Benchmark: sin

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sin16 CoresThreadripper 3970X1020304050SE +/- 0.02, N = 3SE +/- 0.05, N = 342.2842.04

glibc bench

Benchmark: log2

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: log216 CoresThreadripper 3970X1.3272.6543.9815.3086.635SE +/- 0.01183, N = 3SE +/- 0.00811, N = 35.897995.88218

glibc bench

Benchmark: modf

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: modf16 CoresThreadripper 3970X0.50721.01441.52162.02882.536SE +/- 0.00154, N = 3SE +/- 0.00267, N = 32.254152.23442

glibc bench

Benchmark: sinh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinh16 CoresThreadripper 3970X246810SE +/- 0.01214, N = 3SE +/- 0.05215, N = 37.829577.79696

glibc bench

Benchmark: sqrt

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrt16 CoresThreadripper 3970X0.5041.0081.5122.0162.52SE +/- 0.00107, N = 3SE +/- 0.00274, N = 32.239792.22027

glibc bench

Benchmark: tanh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanh16 CoresThreadripper 3970X3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 310.7210.68

glibc bench

Benchmark: asinh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: asinh16 CoresThreadripper 3970X246810SE +/- 0.00260, N = 3SE +/- 0.07346, N = 38.537118.41835

glibc bench

Benchmark: atanh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: atanh16 CoresThreadripper 3970X3691215SE +/- 0.00, N = 3SE +/- 0.01, N = 310.2010.09

glibc bench

Benchmark: ffsll

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsll16 CoresThreadripper 3970X0.40010.80021.20031.60042.0005SE +/- 0.00227, N = 3SE +/- 0.01102, N = 31.778001.75897

glibc bench

Benchmark: sincos

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sincos16 CoresThreadripper 3970X3691215SE +/- 0.10, N = 13SE +/- 0.02, N = 312.4112.26

glibc bench

Benchmark: pthread_once

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_once16 CoresThreadripper 3970X0.39960.79921.19881.59841.998SE +/- 0.00019, N = 3SE +/- 0.00270, N = 31.775941.76133

GNU GMP GMPbench

Total Time

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.1.2Total Time16 CoresThreadripper 3970X120024003600480060005767.15794.61. (CC) gcc options: -O3 -fomit-frame-pointer -lm

GNU MPC

Multi-Precision Benchmark

OpenBenchmarking.orgGlobal Score, More Is BetterGNU MPC 1.1.0Multi-Precision Benchmark16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 17.64, N = 3SE +/- 10.00, N = 3901390501. (CC) gcc options: -lm -O2 -pedantic -fomit-frame-pointer -m64 -mtune=k8 -march=k8 -MT -MD -MP -MF

GNU Octave Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 4.4.116 CoresThreadripper 3970X3691215SE +/- 0.01, N = 3SE +/- 0.19, N = 310.5813.07

GnuPG

Linux 4.3 Package File Encryption

OpenBenchmarking.orgSeconds, Fewer Is BetterGnuPGLinux 4.3 Package File Encryption16 CoresThreadripper 3970X3691215SE +/- 0.17, N = 4SE +/- 0.16, N = 512.4712.38

GnuPG

2GB File Encryption

OpenBenchmarking.orgSeconds, Fewer Is BetterGnuPG 1.4.222GB File Encryption16 CoresThreadripper 3970X3691215SE +/- 0.02, N = 3SE +/- 0.04, N = 311.4711.431. (CC) gcc options: -O2 -MT -MD -MP -MF

Go Benchmarks

Test: http

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: http16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 6.17, N = 3SE +/- 46.62, N = 340597825

Go Benchmarks

Test: json

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: json16 CoresThreadripper 3970X800K1600K2400K3200K4000KSE +/- 16615.41, N = 3SE +/- 7331.16, N = 335235851564168

Go Benchmarks

Test: build

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: build16 CoresThreadripper 3970X4000M8000M12000M16000M20000MSE +/- 162720428.03, N = 3SE +/- 170009930.60, N = 31724446290520067677101

Go Benchmarks

Test: garbage

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: garbage16 CoresThreadripper 3970X200K400K600K800K1000KSE +/- 2753.72, N = 3SE +/- 1243.04, N = 3897936589712

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Swirl16 CoresThreadripper 3970X30060090012001500SE +/- 1.86, N = 378415901. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Rotate16 CoresThreadripper 3970X160320480640800SE +/- 1.53, N = 3SE +/- 3.46, N = 37326931. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Sharpen16 CoresThreadripper 3970X100200300400500SE +/- 0.33, N = 3SE +/- 3.38, N = 32524681. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Enhanced16 CoresThreadripper 3970X140280420560700SE +/- 2.91, N = 33576691. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Resizing16 CoresThreadripper 3970X5001000150020002500SE +/- 1.73, N = 3SE +/- 8.01, N = 3184722431. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-Gaussian16 CoresThreadripper 3970X140280420560700SE +/- 2.00, N = 33516311. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: HWB Color Space16 CoresThreadripper 3970X30060090012001500SE +/- 1.33, N = 3SE +/- 1.53, N = 3141714991. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2020Water Benchmark16 CoresThreadripper 3970X0.73981.47962.21942.95923.699SE +/- 0.002, N = 3SE +/- 0.004, N = 32.0483.2881. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm

Gzip Compression

Linux Source Tree Archiving To .tar.gz

OpenBenchmarking.orgSeconds, Fewer Is BetterGzip CompressionLinux Source Tree Archiving To .tar.gz16 CoresThreadripper 3970X816243240SE +/- 0.05, N = 3SE +/- 0.05, N = 334.0733.91

Hackbench

Count: 32 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: Process16 CoresThreadripper 3970X20406080100SE +/- 0.31, N = 3SE +/- 0.40, N = 374.3531.391. (CC) gcc options: -lpthread

Hierarchical INTegration

Test: FLOAT

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOAT16 CoresThreadripper 3970X80M160M240M320M400MSE +/- 450887.49, N = 3SE +/- 452031.90, N = 3381206340.37386120425.421. (CC) gcc options: -O3 -march=native -lm

High Performance Conjugate Gradient

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.116 CoresThreadripper 3970X3691215SE +/- 0.00185, N = 3SE +/- 0.00239, N = 39.9727610.670701. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver16 CoresThreadripper 3970X10002000300040005000SE +/- 41.21, N = 3SE +/- 17.46, N = 34880.024607.311. (CC) gcc options: -O3 -mavx2

HPC Challenge

Test / Class: G-HPL

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-HPL16 CoresThreadripper 3970X20406080100SE +/- 0.19, N = 3SE +/- 0.17, N = 389.9973.201. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: G-Ffte

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ffte16 CoresThreadripper 3970X48121620SE +/- 0.02, N = 3SE +/- 0.05, N = 311.1716.121. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: EP-DGEMM

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: EP-DGEMM16 CoresThreadripper 3970X1122334455SE +/- 0.43, N = 3SE +/- 0.44, N = 349.5829.801. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: G-Ptrans

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Ptrans16 CoresThreadripper 3970X246810SE +/- 0.00225, N = 3SE +/- 0.01053, N = 32.126297.441191. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: EP-STREAM Triad

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: EP-STREAM Triad16 CoresThreadripper 3970X0.78211.56422.34633.12843.9105SE +/- 0.00112, N = 3SE +/- 0.00672, N = 33.476141.903481. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: G-Random Access

OpenBenchmarking.orgGUP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-Random Access16 CoresThreadripper 3970X0.03860.07720.11580.15440.193SE +/- 0.00040, N = 3SE +/- 0.00021, N = 30.113620.171381. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: Random Ring Latency

OpenBenchmarking.orgusecs, Fewer Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Latency16 CoresThreadripper 3970X0.10570.21140.31710.42280.5285SE +/- 0.00064, N = 3SE +/- 0.00770, N = 30.407880.469621. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: Random Ring Bandwidth

OpenBenchmarking.orgGB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Random Ring Bandwidth16 CoresThreadripper 3970X0.89481.78962.68443.57924.474SE +/- 0.00338, N = 3SE +/- 0.02486, N = 33.976862.208141. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

HPC Challenge

Test / Class: Max Ping Pong Bandwidth

OpenBenchmarking.orgMB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Max Ping Pong Bandwidth16 CoresThreadripper 3970X5K10K15K20K25KSE +/- 607.12, N = 3SE +/- 271.12, N = 322271.5421719.651. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

IndigoBench

Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Bedroom16 CoresThreadripper 3970X1.10392.20783.31174.41565.5195SE +/- 0.002, N = 3SE +/- 0.006, N = 31.8524.906

IndigoBench

Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Supercar16 CoresThreadripper 3970X3691215SE +/- 0.005, N = 3SE +/- 0.005, N = 34.1069.317

Inkscape

Operation: SVG Files To PNG

OpenBenchmarking.orgSeconds, Fewer Is BetterInkscapeOperation: SVG Files To PNG16 CoresThreadripper 3970X612182430SE +/- 0.05, N = 3SE +/- 0.09, N = 325.2626.271. Inkscape 0.92.4 (5da689c313, 2019-01-14)

Intel MPI Benchmarks

Test: IMB-P2P PingPong

OpenBenchmarking.orgAverage Msg/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-P2P PingPong16 CoresThreadripper 3970X4M8M12M16M20MSE +/- 15568.26, N = 3SE +/- 175648.50, N = 39362495.7417789641.38MIN: 3568 / MAX: 21761153MIN: 4183 / MAX: 425919601. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Intel MPI Benchmarks

Test: IMB-MPI1 Exchange

OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 Exchange16 CoresThreadripper 3970X15003000450060007500SE +/- 11.57, N = 3SE +/- 53.06, N = 37217.496258.07MAX: 27690.75MAX: 25730.71. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Intel MPI Benchmarks

Test: IMB-MPI1 Exchange

OpenBenchmarking.orgAverage usec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 Exchange16 CoresThreadripper 3970X306090120150SE +/- 0.54, N = 3SE +/- 3.02, N = 3104.95149.28MIN: 0.58 / MAX: 3114.62MIN: 0.65 / MAX: 5739.971. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Intel MPI Benchmarks

Test: IMB-MPI1 PingPong

OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 PingPong16 CoresThreadripper 3970X12002400360048006000SE +/- 201.66, N = 15SE +/- 139.42, N = 155828.125106.63MIN: 5.29 / MAX: 21984.97MIN: 5.04 / MAX: 18618.891. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Intel MPI Benchmarks

Test: IMB-MPI1 Sendrecv

OpenBenchmarking.orgAverage Mbytes/sec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 Sendrecv16 CoresThreadripper 3970X13002600390052006500SE +/- 114.95, N = 15SE +/- 64.08, N = 36263.734955.00MAX: 41562.16MAX: 30545.391. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Intel MPI Benchmarks

Test: IMB-MPI1 Sendrecv

OpenBenchmarking.orgAverage usec, More Is BetterIntel MPI Benchmarks 2019.3Test: IMB-MPI1 Sendrecv16 CoresThreadripper 3970X20406080100SE +/- 0.45, N = 15SE +/- 0.48, N = 363.4982.61MIN: 0.19 / MAX: 1638.64MIN: 0.38 / MAX: 2576.081. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi

Intel Open Image Denoise

Scene: Memorial

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.0.0Scene: Memorial16 CoresThreadripper 3970X510152025SE +/- 0.06, N = 3SE +/- 0.12, N = 314.9721.96

IOR

Write Test

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Write Test16 CoresThreadripper 3970X130260390520650SE +/- 10.86, N = 15SE +/- 0.80, N = 3622.53182.76MIN: 13.63 / MAX: 942.3MIN: 58.47 / MAX: 193.161. (CC) gcc options: -O2 -lm -pthread -lmpi

IOR

Read Test

OpenBenchmarking.orgMB/s, More Is BetterIOR 3.2.1Read Test16 CoresThreadripper 3970X2004006008001000SE +/- 10.56, N = 15SE +/- 23.08, N = 31117.521047.58MIN: 229.66 / MAX: 1510.8MIN: 520.5 / MAX: 1149.411. (CC) gcc options: -O2 -lm -pthread -lmpi

IOzone

Record Size: 1MB - File Size: 512MB - Disk Test: Write Performance

OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 1MB - File Size: 512MB - Disk Test: Write Performance16 CoresThreadripper 3970X30060090012001500SE +/- 0.83, N = 3SE +/- 59.80, N = 121335.371554.841. (CC) gcc options: -O3

IOzone

Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance

OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance16 CoresThreadripper 3970X30060090012001500SE +/- 4.10, N = 3SE +/- 20.79, N = 31283.871594.311. (CC) gcc options: -O3

IOzone

Record Size: 64Kb - File Size: 512MB - Disk Test: Write Performance

OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 64Kb - File Size: 512MB - Disk Test: Write Performance16 CoresThreadripper 3970X400800120016002000SE +/- 3.66, N = 3SE +/- 6.54, N = 31361.611677.551. (CC) gcc options: -O3

IOzone

Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance

OpenBenchmarking.orgMB/s, More Is BetterIOzone 3.465Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance16 CoresThreadripper 3970X30060090012001500SE +/- 4.09, N = 3SE +/- 62.42, N = 121280.551529.571. (CC) gcc options: -O3

IPC_benchmark

Type: TCP Socket - Message Bytes: 128

OpenBenchmarking.orgMessages Per Second, More Is BetterIPC_benchmarkType: TCP Socket - Message Bytes: 12816 CoresThreadripper 3970X800K1600K2400K3200K4000KSE +/- 2955.16, N = 3SE +/- 13943.76, N = 337052043578760

IPC_benchmark

Type: Unnamed Pipe - Message Bytes: 128

OpenBenchmarking.orgMessages Per Second, More Is BetterIPC_benchmarkType: Unnamed Pipe - Message Bytes: 12816 CoresThreadripper 3970X800K1600K2400K3200K4000KSE +/- 43879.72, N = 6SE +/- 36545.27, N = 837019493558893

IPC_benchmark

Type: FIFO Named Pipe - Message Bytes: 128

OpenBenchmarking.orgMessages Per Second, More Is BetterIPC_benchmarkType: FIFO Named Pipe - Message Bytes: 12816 CoresThreadripper 3970X700K1400K2100K2800K3500KSE +/- 30085.47, N = 15SE +/- 32378.59, N = 1533539463388324

IPC_benchmark

Type: Unnamed Unix Domain Socket - Message Bytes: 128

OpenBenchmarking.orgMessages Per Second, More Is BetterIPC_benchmarkType: Unnamed Unix Domain Socket - Message Bytes: 12816 CoresThreadripper 3970X500K1000K1500K2000K2500KSE +/- 26516.90, N = 3SE +/- 10877.55, N = 325554312416213

iPerf

Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 6416 CoresThreadripper 3970X12K24K36K48K60KSE +/- 1271.94, N = 12SE +/- 423.19, N = 347216548401. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm

iPerf

Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64

OpenBenchmarking.orgMbits/sec, More Is BetteriPerf 3.7Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 6416 CoresThreadripper 3970X1530456075SE +/- 0.00, N = 3SE +/- 0.00, N = 367.167.11. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm

Java SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Composite16 CoresThreadripper 3970X6001200180024003000SE +/- 7.84, N = 4SE +/- 1.94, N = 43005.073009.12

Java SciMark

Computational Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Monte Carlo16 CoresThreadripper 3970X400800120016002000SE +/- 2.89, N = 4SE +/- 2.62, N = 41679.211686.79

Java SciMark

Computational Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Fast Fourier Transform16 CoresThreadripper 3970X400800120016002000SE +/- 14.00, N = 4SE +/- 9.49, N = 42040.932043.32

Java SciMark

Computational Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Sparse Matrix Multiply16 CoresThreadripper 3970X6001200180024003000SE +/- 8.43, N = 4SE +/- 4.74, N = 42716.602683.18

Java SciMark

Computational Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Dense LU Matrix Factorization16 CoresThreadripper 3970X14002800420056007000SE +/- 22.75, N = 4SE +/- 2.88, N = 46637.136674.41

Java SciMark

Computational Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Jacobi Successive Over-Relaxation16 CoresThreadripper 3970X400800120016002000SE +/- 1.78, N = 4SE +/- 2.45, N = 41951.481957.92

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: Blowfish16 CoresThreadripper 3970X9K18K27K36K45KSE +/- 36.67, N = 3SE +/- 236.95, N = 326111432551. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

John The Ripper

Test: MD5

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.9.0-jumbo-1Test: MD516 CoresThreadripper 3970X500K1000K1500K2000K2500KSE +/- 3055.05, N = 3SE +/- 33415.00, N = 4162600025207501. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

KeyDB

OpenBenchmarking.orgOps/sec, More Is BetterKeyDB 5.3.116 CoresThreadripper 3970X40K80K120K160K200KSE +/- 1098.87, N = 3SE +/- 2224.40, N = 15167550.10119630.181. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP316 CoresThreadripper 3970X246810SE +/- 0.007, N = 3SE +/- 0.020, N = 37.1827.1881. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm

LAMMPS Molecular Dynamics Simulator

Model: Rhodopsin Protein

OpenBenchmarking.orgns/day, More Is BetterLAMMPS Molecular Dynamics Simulator 9Jan2020Model: Rhodopsin Protein16 CoresThreadripper 3970X48121620SE +/- 0.05, N = 3SE +/- 0.22, N = 1512.7517.271. (CXX) g++ options: -O3 -rdynamic -ljpeg -lpng -lz -lfftw3 -lm

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.23.2Backend: BLAS16 CoresThreadripper 3970X8001600240032004000SE +/- 26.84, N = 3SE +/- 19.66, N = 33630.242105.111. (CXX) g++ options: -lpthread

LevelDB

Benchmark: Hot Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Hot Read16 CoresThreadripper 3970X1020304050SE +/- 0.106, N = 15SE +/- 0.383, N = 118.97444.2861. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Fill Sync16 CoresThreadripper 3970X0.811.622.433.244.05SE +/- 0.00, N = 31.03.61. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Fill Sync

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Fill Sync16 CoresThreadripper 3970X400800120016002000SE +/- 4.63, N = 3SE +/- 2.37, N = 31677.711938.171. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Overwrite16 CoresThreadripper 3970X918273645SE +/- 0.10, N = 3SE +/- 0.37, N = 340.326.81. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Overwrite

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Overwrite16 CoresThreadripper 3970X60120180240300SE +/- 0.12, N = 3SE +/- 3.84, N = 343.85263.941. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Random Fill16 CoresThreadripper 3970X918273645SE +/- 0.13, N = 3SE +/- 0.03, N = 340.327.31. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Random Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Fill16 CoresThreadripper 3970X60120180240300SE +/- 0.15, N = 3SE +/- 0.33, N = 343.87259.841. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Random Read

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Read16 CoresThreadripper 3970X1020304050SE +/- 0.093, N = 3SE +/- 0.404, N = 109.31344.3531. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Seek Random

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Seek Random16 CoresThreadripper 3970X1530456075SE +/- 0.02, N = 3SE +/- 0.08, N = 314.8968.591. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Random Delete

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Random Delete16 CoresThreadripper 3970X60120180240300SE +/- 0.14, N = 3SE +/- 0.71, N = 339.90256.441. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMB/s, More Is BetterLevelDB 1.22Benchmark: Sequential Fill16 CoresThreadripper 3970X1020304050SE +/- 0.18, N = 3SE +/- 0.32, N = 341.827.61. (CXX) g++ options: -O3 -lsnappy -lpthread

LevelDB

Benchmark: Sequential Fill

OpenBenchmarking.orgMicroseconds Per Op, Fewer Is BetterLevelDB 1.22Benchmark: Sequential Fill16 CoresThreadripper 3970X60120180240300SE +/- 0.17, N = 3SE +/- 2.86, N = 342.30256.331. (CXX) g++ options: -O3 -lsnappy -lpthread

libgav1

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 1080p16 CoresThreadripper 3970X20406080100SE +/- 0.11, N = 3SE +/- 0.06, N = 3105.7676.461. (CXX) g++ options: -O3 -lpthread

libjpeg-turbo tjbench

Test: Decompression Throughput

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.0.2Test: Decompression Throughput16 CoresThreadripper 3970X50100150200250SE +/- 0.16, N = 3SE +/- 0.42, N = 3218.34218.901. (CC) gcc options: -O3 -rdynamic

LibreOffice

Test: 20 Documents To PDF

OpenBenchmarking.orgSeconds, Fewer Is BetterLibreOfficeTest: 20 Documents To PDF16 CoresThreadripper 3970X246810SE +/- 0.037, N = 22SE +/- 0.052, N = 226.5416.6631. LibreOffice 6.3.4.2 30(Build:2)

librsvg

Operation: SVG Files To PNG

OpenBenchmarking.orgSeconds, Fewer Is BetterlibrsvgOperation: SVG Files To PNG16 CoresThreadripper 3970X612182430SE +/- 0.12, N = 3SE +/- 0.12, N = 318.6823.871. rsvg-convert version 2.44.14

Loopback TCP Network Performance

Time To Transfer 10GB Via Loopback

OpenBenchmarking.orgSeconds, Fewer Is BetterLoopback TCP Network PerformanceTime To Transfer 10GB Via Loopback16 CoresThreadripper 3970X3691215SE +/- 0.15, N = 3SE +/- 0.01, N = 310.8110.40

LuaJIT

Test: Composite

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Composite16 CoresThreadripper 3970X400800120016002000SE +/- 1.55, N = 3SE +/- 12.94, N = 31624.141659.511. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

LuaJIT

Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Monte Carlo16 CoresThreadripper 3970X110220330440550SE +/- 0.46, N = 3SE +/- 4.85, N = 3515.37526.751. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

LuaJIT

Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Fast Fourier Transform16 CoresThreadripper 3970X60120180240300SE +/- 1.67, N = 3SE +/- 2.18, N = 3278.18287.971. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

LuaJIT

Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Sparse Matrix Multiply16 CoresThreadripper 3970X30060090012001500SE +/- 1.25, N = 3SE +/- 11.74, N = 31319.001352.771. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

LuaJIT

Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Dense LU Matrix Factorization16 CoresThreadripper 3970X9001800270036004500SE +/- 7.05, N = 3SE +/- 27.57, N = 33910.403996.691. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

LuaJIT

Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Jacobi Successive Over-Relaxation16 CoresThreadripper 3970X5001000150020002500SE +/- 0.94, N = 3SE +/- 18.57, N = 32097.742133.371. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector

LULESH

OpenBenchmarking.orgz/s, More Is BetterLULESH 2.0.316 CoresThreadripper 3970X3691215SE +/- 0.0215340, N = 3SE +/- 0.0012891, N = 310.90211509.39089871. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi

LuxCoreRender

Scene: DLSC

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: DLSC16 CoresThreadripper 3970X0.56481.12961.69442.25922.824SE +/- 0.02, N = 3SE +/- 0.19, N = 152.302.51MIN: 2.18 / MAX: 2.41MIN: 1.3 / MAX: 3

LuxCoreRender

Scene: Rainbow Colors and Prism

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: Rainbow Colors and Prism16 CoresThreadripper 3970X0.541.081.622.162.7SE +/- 0.02, N = 3SE +/- 0.17, N = 152.402.07MIN: 2.33 / MAX: 2.49MIN: 1.13 / MAX: 3.1

lzbench

Test: XZ 0 - Process: Compression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: XZ 0 - Process: Compression16 CoresThreadripper 3970X91827364541411. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: XZ 0 - Process: Decompression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: XZ 0 - Process: Decompression16 CoresThreadripper 3970X3060901201501301311. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Zstd 1 - Process: Compression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Compression16 CoresThreadripper 3970X120240360480600SE +/- 1.53, N = 3SE +/- 0.67, N = 35435431. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Zstd 1 - Process: Decompression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 1 - Process: Decompression16 CoresThreadripper 3970X30060090012001500SE +/- 4.18, N = 3149315031. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Zstd 8 - Process: Compression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 8 - Process: Compression16 CoresThreadripper 3970X20406080100SE +/- 0.67, N = 31091071. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Zstd 8 - Process: Decompression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Zstd 8 - Process: Decompression16 CoresThreadripper 3970X400800120016002000SE +/- 4.18, N = 3SE +/- 4.06, N = 3165016561. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Crush 0 - Process: Compression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Compression16 CoresThreadripper 3970X306090120150SE +/- 0.58, N = 3SE +/- 0.67, N = 31201211. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Crush 0 - Process: Decompression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Crush 0 - Process: Decompression16 CoresThreadripper 3970X110220330440550SE +/- 1.00, N = 3SE +/- 1.15, N = 34985001. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Brotli 0 - Process: Compression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 0 - Process: Compression16 CoresThreadripper 3970X120240360480600SE +/- 0.33, N = 3SE +/- 3.67, N = 35395471. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Brotli 0 - Process: Decompression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 0 - Process: Decompression16 CoresThreadripper 3970X140280420560700SE +/- 2.33, N = 3SE +/- 4.26, N = 36286331. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Brotli 2 - Process: Compression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 2 - Process: Compression16 CoresThreadripper 3970X50100150200250SE +/- 0.67, N = 32152161. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Brotli 2 - Process: Decompression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Brotli 2 - Process: Decompression16 CoresThreadripper 3970X160320480640800SE +/- 0.88, N = 3SE +/- 1.20, N = 37367391. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Libdeflate 1 - Process: Compression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Libdeflate 1 - Process: Compression16 CoresThreadripper 3970X60120180240300SE +/- 1.45, N = 32672661. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

lzbench

Test: Libdeflate 1 - Process: Decompression

OpenBenchmarking.orgMB/s, More Is Betterlzbench 1.8Test: Libdeflate 1 - Process: Decompression16 CoresThreadripper 3970X30060090012001500SE +/- 0.67, N = 3SE +/- 1.20, N = 3124412451. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

LZMA Compression

256MB File Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterLZMA Compression256MB File Compression16 CoresThreadripper 3970X50100150200250SE +/- 0.09, N = 3SE +/- 0.33, N = 3220.23221.251. (CXX) g++ options: -O2

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve16 CoresThreadripper 3970X1224364860SE +/- 0.02, N = 3SE +/- 0.01, N = 355.0817.951. (CXX) g++ options: -fopenmp -O2 -march=native

MariaDB

Clients: 64

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 6416 CoresThreadripper 3970X2004006008001000SE +/- 1.35, N = 3SE +/- 2.66, N = 310802071. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

MBW

Test: Memory Copy - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiB16 CoresThreadripper 3970X5K10K15K20K25KSE +/- 82.44, N = 3SE +/- 72.04, N = 321862.4321587.381. (CC) gcc options: -O3 -march=native

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 2.58, N = 3SE +/- 6.90, N = 312748.6112649.311. (CC) gcc options: -O3 -march=native

Memcached mcperf

Method: Add

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Add16 CoresThreadripper 3970X16K32K48K64K80KSE +/- 1667.09, N = 12SE +/- 143.36, N = 372837.745047.01. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Get

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Get16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 689.43, N = 15SE +/- 422.66, N = 389370.877680.21. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Set

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Set16 CoresThreadripper 3970X16K32K48K64K80KSE +/- 2447.09, N = 12SE +/- 556.85, N = 575424.045117.51. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Append

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Append16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 4614.05, N = 15SE +/- 1452.18, N = 1285868.949940.51. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Delete

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Delete16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 702.49, N = 15SE +/- 80.10, N = 388516.674147.41. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Prepend

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Prepend16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 5449.52, N = 12SE +/- 36.76, N = 388961.446495.91. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Replace

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Replace16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 5340.89, N = 12SE +/- 677.13, N = 384273.847267.11. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Add - Connections: 64

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.22Method: Add - Connections: 6416 CoresThreadripper 3970X15K30K45K60K75KSE +/- 347.35, N = 3SE +/- 803.43, N = 371799.048669.61. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Get - Connections: 64

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.22Method: Get - Connections: 6416 CoresThreadripper 3970X20K40K60K80K100KSE +/- 238.31, N = 3SE +/- 810.66, N = 388109.778526.01. (CC) gcc options: -O2 -lm -rdynamic

Memcached mcperf

Method: Set - Connections: 64

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.22Method: Set - Connections: 6416 CoresThreadripper 3970X16K32K48K64K80KSE +/- 722.58, N = 3SE +/- 524.58, N = 372538.548126.01. (CC) gcc options: -O2 -lm -rdynamic

Memtier_benchmark

Protocol: Redis

OpenBenchmarking.orgOps/sec, More Is BetterMemtier_benchmark 1.2.17Protocol: Redis16 CoresThreadripper 3970X500K1000K1500K2000K2500KSE +/- 8570.47, N = 3SE +/- 34708.07, N = 42272891.422351667.581. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

miniFE

Problem Size: Small

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: Small16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 6.07, N = 3SE +/- 87.71, N = 310962.709322.751. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi

Minion

Benchmark: Graceful

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Graceful16 CoresThreadripper 3970X1020304050SE +/- 0.09, N = 3SE +/- 0.10, N = 341.6741.341. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Minion

Benchmark: Solitaire

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Solitaire16 CoresThreadripper 3970X1428425670SE +/- 0.21, N = 3SE +/- 0.14, N = 361.0960.651. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Minion

Benchmark: Quasigroup

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Quasigroup16 CoresThreadripper 3970X20406080100SE +/- 0.16, N = 3SE +/- 0.37, N = 3108.52107.531. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

MKL-DNN DNNL

Harness: IP Batch 1D - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: f3216 CoresThreadripper 3970X0.79881.59762.39643.19523.994SE +/- 0.02584, N = 3SE +/- 0.05025, N = 153.550423.41655MIN: 3.4MIN: 2.081. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: IP Batch All - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: f3216 CoresThreadripper 3970X48121620SE +/- 0.04, N = 3SE +/- 0.09, N = 311.5717.33MIN: 11.24MIN: 11.671. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Convolution Batch conv_3d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_3d - Data Type: f3216 CoresThreadripper 3970X3691215SE +/- 0.09666, N = 3SE +/- 0.08221, N = 39.503726.82846MIN: 9.16MIN: 4.631. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Convolution Batch conv_all - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_all - Data Type: f3216 CoresThreadripper 3970X30060090012001500SE +/- 2.68, N = 3SE +/- 4.86, N = 31369.92968.72MIN: 1354.97MIN: 791.361. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Deconvolution Batch deconv_1d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_1d - Data Type: f3216 CoresThreadripper 3970X0.72551.4512.17652.9023.6275SE +/- 0.00642, N = 3SE +/- 0.02372, N = 143.224352.78688MIN: 3.13MIN: 1.781. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Deconvolution Batch deconv_3d - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_3d - Data Type: f3216 CoresThreadripper 3970X1.10532.21063.31594.42125.5265SE +/- 0.02100, N = 3SE +/- 0.26685, N = 123.691664.91239MIN: 3.53MIN: 2.561. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Convolution Batch conv_alexnet - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_alexnet - Data Type: f3216 CoresThreadripper 3970X4080120160200SE +/- 0.48, N = 3SE +/- 1.57, N = 6178.67137.79MIN: 176.74MIN: 97.041. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Deconvolution Batch deconv_all - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Deconvolution Batch deconv_all - Data Type: f3216 CoresThreadripper 3970X400800120016002000SE +/- 0.54, N = 3SE +/- 2.16, N = 31182.611713.90MIN: 1163.99MIN: 1362.261. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Recurrent Neural Network Training - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Recurrent Neural Network Training - Data Type: f3216 CoresThreadripper 3970X70140210280350SE +/- 0.28, N = 3SE +/- 2.80, N = 10142.35299.86MIN: 140.83MIN: 188.071. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

MKL-DNN DNNL

Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: Convolution Batch conv_googlenet_v3 - Data Type: f3216 CoresThreadripper 3970X20406080100SE +/- 0.24, N = 3SE +/- 0.89, N = 376.3556.58MIN: 75.02MIN: 41.141. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Mlpack Benchmark

Benchmark: scikit_ica

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_ica16 CoresThreadripper 3970X1122334455SE +/- 0.04, N = 3SE +/- 0.31, N = 336.0549.20

Mlpack Benchmark

Benchmark: scikit_qda

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_qda16 CoresThreadripper 3970X1224364860SE +/- 0.21, N = 3SE +/- 0.42, N = 334.1653.02

Mlpack Benchmark

Benchmark: scikit_svm

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_svm16 CoresThreadripper 3970X3691215SE +/- 0.02, N = 3SE +/- 0.01, N = 311.4311.50

Mlpack Benchmark

Benchmark: scikit_linearridgeregression

OpenBenchmarking.orgSeconds, Fewer Is BetterMlpack BenchmarkBenchmark: scikit_linearridgeregression16 CoresThreadripper 3970X0.33080.66160.99241.32321.654SE +/- 0.02, N = 12SE +/- 0.02, N = 31.421.47

Multichase Pointer Chaser

Test: 1GB Array, 256 Byte Stride, 4 Threads

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stride, 4 Threads16 CoresThreadripper 3970X20406080100SE +/- 0.03, N = 3SE +/- 0.04, N = 373.2774.561. (CC) gcc options: -O2 -static -pthread -lrt

N-Queens

Elapsed Time

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed Time16 CoresThreadripper 3970X3691215SE +/- 0.012, N = 3SE +/- 0.006, N = 311.3213.4961. (CC) gcc options: -static -fopenmp -O3 -march=native

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13ATPase Simulation - 327,506 Atoms16 CoresThreadripper 3970X0.27880.55760.83641.11521.394SE +/- 0.00167, N = 3SE +/- 0.00773, N = 151.239010.62357

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.C16 CoresThreadripper 3970X16K32K48K64K80KSE +/- 12.23, N = 3SE +/- 105.14, N = 354825.1374815.991. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: CG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: CG.C16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 13.07, N = 3SE +/- 35.93, N = 310888.1910815.591. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.C16 CoresThreadripper 3970X6001200180024003000SE +/- 2.47, N = 3SE +/- 48.12, N = 31486.442831.861. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.D16 CoresThreadripper 3970X6001200180024003000SE +/- 0.41, N = 3SE +/- 2.52, N = 31480.102907.581. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.C16 CoresThreadripper 3970X7K14K21K28K35KSE +/- 46.20, N = 3SE +/- 17.98, N = 331324.2034599.491. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: IS.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: IS.D16 CoresThreadripper 3970X30060090012001500SE +/- 1.71, N = 3SE +/- 17.87, N = 31521.341464.451. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.C16 CoresThreadripper 3970X14K28K42K56K70KSE +/- 21.03, N = 3SE +/- 279.99, N = 354335.4665854.971. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.C16 CoresThreadripper 3970X6K12K18K24K30KSE +/- 43.00, N = 3SE +/- 110.51, N = 328788.0630218.911. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NAS Parallel Benchmarks

Test / Class: SP.B

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.B16 CoresThreadripper 3970X7K14K21K28K35KSE +/- 37.51, N = 3SE +/- 446.30, N = 324225.6433710.701. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

NeatBench

Acceleration: CPU

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPU16 CoresThreadripper 3970X918273645SE +/- 0.12, N = 3SE +/- 0.22, N = 330.737.6

Nebular Empirical Analysis Tool

OpenBenchmarking.orgSeconds, Fewer Is BetterNebular Empirical Analysis Tool 2020-02-2916 CoresThreadripper 3970X48121620SE +/- 0.02, N = 3SE +/- 0.01, N = 313.9812.821. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace

NGINX Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page Serving16 CoresThreadripper 3970X8K16K24K32K40KSE +/- 50.77, N = 3SE +/- 177.49, N = 336762.5936707.661. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

Node.js Express HTTP Load Test

OpenBenchmarking.orgRequests Per Second, More Is BetterNode.js Express HTTP Load Test16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 91.62, N = 3SE +/- 82.23, N = 311858109081. Nodejs v10.15.2

Node.js Octane Benchmark

OpenBenchmarking.orgScore, More Is BetterNode.js Octane Benchmark16 CoresThreadripper 3970X11K22K33K44K55KSE +/- 179.38, N = 3SE +/- 97.00, N = 351582501251. Nodejs v10.15.2

Numenta Anomaly Benchmark

Detector: Relative Entropy

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Relative Entropy16 CoresThreadripper 3970X3691215SE +/- 0.10, N = 3SE +/- 0.18, N = 311.5912.42

Numenta Anomaly Benchmark

Detector: Windowed Gaussian

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Windowed Gaussian16 CoresThreadripper 3970X246810SE +/- 0.067, N = 3SE +/- 0.034, N = 37.0136.111

Numenta Anomaly Benchmark

Detector: Earthgecko Skyline

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Earthgecko Skyline16 CoresThreadripper 3970X20406080100SE +/- 0.59, N = 3SE +/- 0.44, N = 375.9969.66

Numenta Anomaly Benchmark

Detector: Bayesian Changepoint

OpenBenchmarking.orgSeconds, Fewer Is BetterNumenta Anomaly Benchmark 1.1Detector: Bayesian Changepoint16 CoresThreadripper 3970X612182430SE +/- 0.11, N = 3SE +/- 0.22, N = 324.6724.90

Numpy Benchmark

OpenBenchmarking.orgScore, More Is BetterNumpy Benchmark16 CoresThreadripper 3970X90180270360450SE +/- 0.33, N = 3SE +/- 1.07, N = 3430.36432.11

Ogg Encoding

WAV To Ogg

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.3WAV To Ogg16 CoresThreadripper 3970X1.18192.36383.54574.72765.9095SE +/- 0.007, N = 3SE +/- 0.009, N = 35.2535.2251. (CC) gcc options: -O2 -ffast-math -fsigned-char -logg

OpenCV Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenCV Benchmark 3.3.016 CoresThreadripper 3970X1530456075SE +/- 0.10, N = 3SE +/- 0.40, N = 361.5466.361. (CXX) g++ options: -std=c++11 -rdynamic

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 10.52, N = 3SE +/- 32.86, N = 34550.99307.41. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Optcarrot

Optimized Benchmark

OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized Benchmark16 CoresThreadripper 3970X20406080100SE +/- 1.31, N = 4SE +/- 0.29, N = 4102.75103.981. ruby 2.5.5p157 (2019-03-15 revision 67260) [x86_64-linux-gnu]

OSBench

Test: Create Files

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Files16 CoresThreadripper 3970X48121620SE +/- 0.02, N = 3SE +/- 0.05, N = 313.8811.451. (CC) gcc options: -lm

OSBench

Test: Create Threads

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Threads16 CoresThreadripper 3970X1020304050SE +/- 0.22, N = 3SE +/- 0.05, N = 346.1211.331. (CC) gcc options: -lm

OSBench

Test: Launch Programs

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch Programs16 CoresThreadripper 3970X50100150200250SE +/- 0.65, N = 3SE +/- 0.36, N = 3228.5849.301. (CC) gcc options: -lm

OSBench

Test: Create Processes

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Processes16 CoresThreadripper 3970X1224364860SE +/- 0.76, N = 3SE +/- 0.58, N = 1254.9827.961. (CC) gcc options: -lm

OSBench

Test: Memory Allocations

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations16 CoresThreadripper 3970X1632486480SE +/- 0.22, N = 3SE +/- 0.29, N = 367.1670.321. (CC) gcc options: -lm

OSPray

Demo: San Miguel - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVis16 CoresThreadripper 3970X1122334455SE +/- 0.00, N = 1218.5250.00MIN: 17.86 / MAX: 19.61MIN: 43.48 / MAX: 52.63

OSPray

Demo: XFrog Forest - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVis16 CoresThreadripper 3970X3691215SE +/- 0.00, N = 4SE +/- 0.02, N = 53.328.99MIN: 3.27 / MAX: 3.38MIN: 8.77 / MAX: 9.17

OSPray

Demo: San Miguel - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path Tracer16 CoresThreadripper 3970X0.82581.65162.47743.30324.129SE +/- 0.00, N = 3SE +/- 0.00, N = 41.373.67MIN: 1.36 / MAX: 1.38MIN: 3.65 / MAX: 3.72

OSPray

Demo: NASA Streamlines - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVis16 CoresThreadripper 3970X1530456075SE +/- 0.00, N = 1225.0066.67MIN: 23.81 / MAX: 25.64MIN: 52.63 / MAX: 71.43

OSPray

Demo: XFrog Forest - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path Tracer16 CoresThreadripper 3970X1.05532.11063.16594.22125.2765SE +/- 0.00, N = 3SE +/- 0.00, N = 121.754.69MIN: 1.73 / MAX: 1.77MIN: 4.65 / MAX: 4.76

OSPray

Demo: Magnetic Reconnection - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVis16 CoresThreadripper 3970X816243240SE +/- 0.00, N = 12SE +/- 0.36, N = 313.1632.62MIN: 12.5 / MAX: 13.51MIN: 31.25 / MAX: 33.33

OSPray

Demo: NASA Streamlines - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path Tracer16 CoresThreadripper 3970X3691215SE +/- 0.00, N = 5SE +/- 0.06, N = 34.9713.58MIN: 4.9 / MAX: 5.05MIN: 13.33 / MAX: 13.89

OSPray

Demo: Magnetic Reconnection - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path Tracer16 CoresThreadripper 3970X100200300400500SE +/- 21.00, N = 15250.00444.44MIN: 200 / MAX: 333.33MIN: 43.48 / MAX: 500

Parboil

Test: OpenMP LBM

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP LBM16 CoresThreadripper 3970X1224364860SE +/- 0.08, N = 3SE +/- 0.75, N = 436.3552.971. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Parboil

Test: OpenMP CUTCP

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCP16 CoresThreadripper 3970X0.47750.9551.43251.912.3875SE +/- 0.019941, N = 3SE +/- 0.005586, N = 32.1222030.9933421. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Parboil

Test: OpenMP Stencil

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP Stencil16 CoresThreadripper 3970X246810SE +/- 0.124137, N = 3SE +/- 0.009377, N = 37.7820155.2821411. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Parboil

Test: OpenMP MRI Gridding

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI Gridding16 CoresThreadripper 3970X1326395265SE +/- 0.64, N = 3SE +/- 0.26, N = 337.0960.181. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

Pennant

Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbig16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 4.90, N = 3SE +/- 5.38, N = 34341.348885.041. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

Pennant

Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbig16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 1.62, N = 3SE +/- 2.82, N = 34088.418623.651. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

Perl Benchmarks

Test: Pod2html

OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: Pod2html16 CoresThreadripper 3970X0.02760.05520.08280.11040.138SE +/- 0.00047037, N = 3SE +/- 0.00045305, N = 30.122566290.11410246

Perl Benchmarks

Test: Interpreter

OpenBenchmarking.orgSeconds, Fewer Is BetterPerl BenchmarksTest: Interpreter16 CoresThreadripper 3970X0.00030.00060.00090.00120.0015SE +/- 0.00000115, N = 3SE +/- 0.00000312, N = 30.000911860.00136623

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite16 CoresThreadripper 3970X140K280K420K560K700KSE +/- 266.61, N = 3SE +/- 808.97, N = 3641380641756

PlaidML

FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU

OpenBenchmarking.orgFPS, More Is BetterPlaidMLFP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU16 CoresThreadripper 3970X246810SE +/- 0.03, N = 3SE +/- 0.05, N = 37.697.40

PolyBench-C

Test: Covariance Computation

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: Covariance Computation16 CoresThreadripper 3970X0.48170.96341.44511.92682.4085SE +/- 0.009, N = 3SE +/- 0.004, N = 32.1202.1411. (CC) gcc options: -O3 -march=native

PolyBench-C

Test: Correlation Computation

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: Correlation Computation16 CoresThreadripper 3970X0.4770.9541.4311.9082.385SE +/- 0.003, N = 3SE +/- 0.002, N = 32.1142.1201. (CC) gcc options: -O3 -march=native

PolyBench-C

Test: 3 Matrix Multiplications

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: 3 Matrix Multiplications16 CoresThreadripper 3970X0.48130.96261.44391.92522.4065SE +/- 0.023, N = 3SE +/- 0.012, N = 32.1352.1391. (CC) gcc options: -O3 -march=native

Polyhedron Fortran Benchmarks

Benchmark: ac

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyhedron Fortran BenchmarksBenchmark: ac16 CoresThreadripper 3970X1.32982.65963.98945.31926.6495.895.91

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Only16 CoresThreadripper 3970X200K400K600K800K1000KSE +/- 1543.39, N = 3SE +/- 3547.45, N = 3272392.97792360.461. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 12.0Scaling: Buffer Test - Test: Normal Load - Mode: Read Write16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 1319.04, N = 15SE +/- 333.19, N = 1512881.1811196.801. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostMark

Disk Transaction Performance

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction Performance16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 53.33, N = 3635778121. (CC) gcc options: -O3

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time16 CoresThreadripper 3970X714212835SE +/- 0.02, N = 3SE +/- 0.02, N = 332.2513.241. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number Generation16 CoresThreadripper 3970X3691215SE +/- 0.033, N = 3SE +/- 0.021, N = 312.5386.1231. (CXX) g++ options: -O3 -lpthread

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Times16 CoresThreadripper 3970X2004006008001000SE +/- 2.31, N = 3SE +/- 0.88, N = 3955958

PyPerformance

Benchmark: float

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyPerformance 1.0.0Benchmark: float16 CoresThreadripper 3970X20406080100SE +/- 0.09, N = 399.7103.0

QMCPACK

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.816 CoresThreadripper 3970X60012001800240030001039.42581.71. (CXX) g++ options: -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -ffast-math -lm

Qmlbench

Test: Canvas Text Simple

OpenBenchmarking.orgFrames, More Is BetterQmlbench 2Test: Canvas Text Simple16 CoresThreadripper 3970X80160240320400386.4358.81. (CXX) g++ options: -lpthread

R Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterR Benchmark16 CoresThreadripper 3970X0.06430.12860.19290.25720.3215SE +/- 0.0007, N = 3SE +/- 0.0005, N = 30.13610.28581. R scripting front-end version 3.6.1 (2019-07-05)

Radiance Benchmark

Test: Serial

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: Serial16 CoresThreadripper 3970X120240360480600564.78564.24

Radiance Benchmark

Test: SMP Parallel

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP Parallel16 CoresThreadripper 3970X4080120160200171.49173.32

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integer16 CoresThreadripper 3970X9K18K27K36K45K43057.6941870.301. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Scale - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Integer16 CoresThreadripper 3970X9K18K27K36K45K36372.4442704.741. (CC) gcc options: -O3 -march=native

RAR Compression

Linux Source Tree Archiving To RAR

OpenBenchmarking.orgSeconds, Fewer Is BetterRAR Compression 5.6.1Linux Source Tree Archiving To RAR16 CoresThreadripper 3970X1530456075SE +/- 0.10, N = 3SE +/- 0.63, N = 359.8468.09

RawTherapee

Total Benchmark Time

OpenBenchmarking.orgSeconds, Fewer Is BetterRawTherapeeTotal Benchmark Time16 CoresThreadripper 3970X1020304050SE +/- 0.03, N = 3SE +/- 0.13, N = 342.4140.811. RawTherapee, version 5.6, command line.

rays1bench

Large Scene

OpenBenchmarking.orgmrays/s, More Is Betterrays1bench 2020-01-09Large Scene16 CoresThreadripper 3970X50100150200250SE +/- 0.15, N = 3SE +/- 0.30, N = 395.94225.76

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GET16 CoresThreadripper 3970X500K1000K1500K2000K2500KSE +/- 27476.98, N = 15SE +/- 14781.22, N = 32108260.532229021.421. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SET16 CoresThreadripper 3970X400K800K1200K1600K2000KSE +/- 20540.77, N = 15SE +/- 10340.63, N = 31723424.591674234.131. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: LPOP

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPOP16 CoresThreadripper 3970X500K1000K1500K2000K2500KSE +/- 106189.37, N = 12SE +/- 5677.11, N = 32097030.002175519.08

Redis

Test: SADD

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SADD16 CoresThreadripper 3970X400K800K1200K1600K2000KSE +/- 19315.80, N = 15SE +/- 20821.87, N = 61874999.401851271.35

Redis

Test: LPUSH

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: LPUSH16 CoresThreadripper 3970X300K600K900K1200K1500KSE +/- 17705.07, N = 15SE +/- 8830.13, N = 31492623.121417209.04

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GET16 CoresThreadripper 3970X500K1000K1500K2000K2500KSE +/- 45838.11, N = 15SE +/- 25232.39, N = 32184449.112005988.50

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SET16 CoresThreadripper 3970X400K800K1200K1600K2000KSE +/- 19904.56, N = 3SE +/- 12046.69, N = 31696335.081687462.13

Renaissance

Test: Scala Dotty

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Scala Dotty16 CoresThreadripper 3970X11002200330044005500SE +/- 10.46, N = 5SE +/- 45.89, N = 55197.605168.07

Renaissance

Test: Random Forest

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Random Forest16 CoresThreadripper 3970X8001600240032004000SE +/- 37.21, N = 9SE +/- 29.83, N = 253826.803840.46

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark ALS16 CoresThreadripper 3970X10002000300040005000SE +/- 41.81, N = 5SE +/- 46.56, N = 54278.414708.54

Renaissance

Test: Apache Spark Bayes

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark Bayes16 CoresThreadripper 3970X7001400210028003500SE +/- 38.62, N = 25SE +/- 33.74, N = 53157.262677.51

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Savina Reactors.IO16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 57.87, N = 5SE +/- 227.73, N = 2515896.1213551.88

Renaissance

Test: Apache Spark PageRank

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Apache Spark PageRank16 CoresThreadripper 3970X4K8K12K16K20KSE +/- 74.89, N = 5SE +/- 139.90, N = 516238.5316363.84

Renaissance

Test: In-Memory Database Shootout

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: In-Memory Database Shootout16 CoresThreadripper 3970X13002600390052006500SE +/- 10.28, N = 5SE +/- 23.00, N = 54006.605898.14

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.10.0Test: Akka Unbalanced Cobwebbed Tree16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 104.84, N = 6SE +/- 140.29, N = 78732.8412746.61

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMD16 CoresThreadripper 3970X48121620SE +/- 0.025, N = 3SE +/- 0.047, N = 316.5348.3371. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD Solver16 CoresThreadripper 3970X3691215SE +/- 0.011, N = 3SE +/- 0.095, N = 312.0779.7841. (CXX) g++ options: -O2 -lOpenCL

Rodinia

Test: OpenMP Streamcluster

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP Streamcluster16 CoresThreadripper 3970X510152025SE +/- 0.08, N = 3SE +/- 0.29, N = 311.2720.401. (CXX) g++ options: -O2 -lOpenCL

Rust Mandelbrot

Time To Complete Serial/Parallel Mandelbrot

OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel Mandelbrot16 CoresThreadripper 3970X918273645SE +/- 0.04, N = 3SE +/- 0.04, N = 340.1732.091. (CC) gcc options: -m64 -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm

Rust Prime Benchmark

Prime Number Test To 200,000,000

OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,00016 CoresThreadripper 3970X510152025SE +/- 0.01, N = 3SE +/- 0.03, N = 319.9610.271. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil

Schbench

Message Threads: 8 - Workers Per Message Thread: 8

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 816 CoresThreadripper 3970X10K20K30K40K50KSE +/- 740.24, N = 3SE +/- 468.91, N = 124631535871. (CC) gcc options: -O2 -lpthread

Scikit-Learn

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.22.116 CoresThreadripper 3970X246810SE +/- 0.016, N = 3SE +/- 0.021, N = 37.8757.973

SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Composite16 CoresThreadripper 3970X150300450600750SE +/- 3.51, N = 3SE +/- 7.72, N = 3697.80718.031. (CC) gcc options: -lm

SciMark

Computational Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlo16 CoresThreadripper 3970X306090120150SE +/- 0.04, N = 3SE +/- 1.57, N = 3155.44157.711. (CC) gcc options: -lm

SciMark

Computational Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform16 CoresThreadripper 3970X80160240320400SE +/- 0.60, N = 3SE +/- 3.52, N = 3328.58356.711. (CC) gcc options: -lm

SciMark

Computational Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiply16 CoresThreadripper 3970X2004006008001000SE +/- 0.56, N = 3SE +/- 7.44, N = 3782.85793.801. (CC) gcc options: -lm

SciMark

Computational Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorization16 CoresThreadripper 3970X2004006008001000SE +/- 17.46, N = 3SE +/- 13.80, N = 3946.17983.931. (CC) gcc options: -lm

SciMark

Computational Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxation16 CoresThreadripper 3970X30060090012001500SE +/- 0.75, N = 3SE +/- 12.34, N = 31275.971298.021. (CC) gcc options: -lm

Smallpt

Global Illumination Renderer; 128 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 Samples16 CoresThreadripper 3970X246810SE +/- 0.008, N = 3SE +/- 0.010, N = 37.4072.8941. (CXX) g++ options: -fopenmp -O3

Sockperf

Test: Throughput

OpenBenchmarking.orgMessages Per Second, More Is BetterSockperf 3.4Test: Throughput16 CoresThreadripper 3970X110K220K330K440K550KSE +/- 5246.61, N = 5SE +/- 3079.75, N = 55320895342401. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

Sockperf

Test: Latency Ping Pong

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping Pong16 CoresThreadripper 3970X0.65951.3191.97852.6383.2975SE +/- 0.009, N = 5SE +/- 0.026, N = 252.2102.9311. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

Sockperf

Test: Latency Under Load

OpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under Load16 CoresThreadripper 3970X3691215SE +/- 0.41, N = 25SE +/- 0.66, N = 2510.7813.231. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread

SQLite

Threads / Copies: 1

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 116 CoresThreadripper 3970X48121620SE +/- 0.05, N = 3SE +/- 0.02, N = 313.9214.411. (CC) gcc options: -O2 -lreadline -ltermcap -lz -lm -ldl -lpthread

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,00016 CoresThreadripper 3970X1326395265SE +/- 0.09, N = 3SE +/- 0.32, N = 358.1758.591. (CC) gcc options: -O2 -ldl -lz -lpthread

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time16 CoresThreadripper 3970X20M40M60M80M100MSE +/- 303886.69, N = 3SE +/- 914534.22, N = 336932742957287871. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy16 CoresThreadripper 3970X11K22K33K44K55KSE +/- 4.33, N = 5SE +/- 18.90, N = 549216.852075.81. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Scale

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scale16 CoresThreadripper 3970X11K22K33K44K55KSE +/- 11.54, N = 5SE +/- 29.94, N = 549498.851667.11. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triad16 CoresThreadripper 3970X12K24K36K48K60KSE +/- 13.13, N = 5SE +/- 39.30, N = 554847.957321.81. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add16 CoresThreadripper 3970X12K24K36K48K60KSE +/- 11.11, N = 5SE +/- 47.58, N = 554720.556819.21. (CC) gcc options: -O3 -march=native -fopenmp

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Crypto16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 5.17, N = 3SE +/- 23.39, N = 34392.369207.851. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Bsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Bsearch16 CoresThreadripper 3970X4K8K12K16K20KSE +/- 66.23, N = 3SE +/- 115.68, N = 37239.7520222.031. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Forking

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Forking16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 11.00, N = 3SE +/- 1093.43, N = 310970.2597017.281. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Hsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Hsearch16 CoresThreadripper 3970X50K100K150K200K250KSE +/- 141.77, N = 3SE +/- 134.40, N = 3106584.80253747.421. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Lsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Lsearch16 CoresThreadripper 3970X90180270360450SE +/- 2.93, N = 15SE +/- 3.61, N = 3138.27434.811. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Tsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Tsearch16 CoresThreadripper 3970X2004006008001000SE +/- 2.00, N = 3SE +/- 0.72, N = 3383.181111.041. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CPU Stress16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 4.68, N = 3SE +/- 35.07, N = 35019.0912151.311. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Semaphores

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Semaphores16 CoresThreadripper 3970X900K1800K2700K3600K4500KSE +/- 35197.46, N = 15SE +/- 11364.25, N = 33998333.223379188.341. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Matrix Math16 CoresThreadripper 3970X50K100K150K200K250KSE +/- 114.46, N = 3SE +/- 2518.16, N = 776991.04234235.761. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Vector Math16 CoresThreadripper 3970X20K40K60K80K100KSE +/- 10.48, N = 3SE +/- 30.84, N = 335109.1788021.721. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Memory Copying16 CoresThreadripper 3970X2K4K6K8K10KSE +/- 6.58, N = 3SE +/- 46.71, N = 33963.818324.571. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket Activity16 CoresThreadripper 3970X5K10K15K20K25KSE +/- 30.56, N = 3SE +/- 93.30, N = 310510.3522217.761. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context Switching16 CoresThreadripper 3970X5M10M15M20M25MSE +/- 9547.22, N = 3SE +/- 434072.66, N = 152258922.9321267958.311. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Glibc C String Functions

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc C String Functions16 CoresThreadripper 3970X700K1400K2100K2800K3500KSE +/- 21196.38, N = 3SE +/- 19841.27, N = 31252570.263406391.461. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: Glibc Qsort Data Sorting

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc Qsort Data Sorting16 CoresThreadripper 3970X110220330440550SE +/- 2.46, N = 4SE +/- 1.89, N = 3181.55489.811. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stress-NG

Test: System V Message Passing

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message Passing16 CoresThreadripper 3970X6M12M18M24M30MSE +/- 23221.11, N = 3SE +/- 271951.30, N = 1516301159.7326168429.691. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Sudokut

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterSudokut 0.4Total Time16 CoresThreadripper 3970X3691215SE +/- 0.03, N = 3SE +/- 0.02, N = 312.2312.90

Sunflow Rendering System

Global Illumination + Image Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image Synthesis16 CoresThreadripper 3970X0.21470.42940.64410.85881.0735SE +/- 0.023, N = 15SE +/- 0.005, N = 30.9540.517

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.8Encoder Mode: Enc Mode 8 - Input: 1080p16 CoresThreadripper 3970X1632486480SE +/- 0.18, N = 3SE +/- 0.37, N = 335.8969.741. (CXX) g++ options: -fPIE -fPIC -pie

SVT-HEVC

1080p 8-bit YUV To HEVC Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 1.4.11080p 8-bit YUV To HEVC Video Encode16 CoresThreadripper 3970X4080120160200SE +/- 0.38, N = 3SE +/- 0.72, N = 382.13174.751. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080p16 CoresThreadripper 3970X80160240320400SE +/- 2.55, N = 3SE +/- 4.19, N = 13172.13368.411. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

Swet

Average

OpenBenchmarking.orgOperations Per Second, More Is BetterSwet 1.5.16Average16 CoresThreadripper 3970X200M400M600M800M1000MSE +/- 5620679.90, N = 3SE +/- 1647184.49, N = 38155974668114425481. (CC) gcc options: -lm -lpthread -lcurses -lrt

Sysbench

Test: Memory

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: Memory16 CoresThreadripper 3970X2M4M6M8M10MSE +/- 81796.05, N = 3SE +/- 37741.69, N = 38262426.989119242.231. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm

Sysbench

Test: CPU

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPU16 CoresThreadripper 3970X15K30K45K60K75KSE +/- 26.51, N = 3SE +/- 71.18, N = 333077.1768765.381. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm

System Libxml2 Parsing

Filesize: 1 MB

OpenBenchmarking.orgms, Fewer Is BetterSystem Libxml2 ParsingFilesize: 1 MB16 CoresThreadripper 3970X90180270360450SE +/- 5.08, N = 6SE +/- 3.06, N = 3424424

Systemd Total Boot Time

Test: Total

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Total16 CoresThreadripper 3970X8K16K24K32K40K3904837055

Systemd Total Boot Time

Test: Kernel

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Kernel16 CoresThreadripper 3970X1300260039005200650061705710

Systemd Total Boot Time

Test: Loader

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Loader16 CoresThreadripper 3970X2K4K6K8K10K35429976

Systemd Total Boot Time

Test: Firmware

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Firmware16 CoresThreadripper 3970X4K8K12K16K20K2015320002

Systemd Total Boot Time

Test: Userspace

OpenBenchmarking.orgms, Fewer Is BetterSystemd Total Boot TimeTest: Userspace16 CoresThreadripper 3970X7K14K21K28K35K3287831345

t-test1

Threads: 1

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 116 CoresThreadripper 3970X612182430SE +/- 0.04, N = 3SE +/- 0.11, N = 316.0625.601. (CC) gcc options: -pthread

t-test1

Threads: 2

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 216 CoresThreadripper 3970X246810SE +/- 0.008, N = 3SE +/- 0.005, N = 35.4498.7431. (CC) gcc options: -pthread

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.99b6Total Time16 CoresThreadripper 3970X1326395265SE +/- 0.08, N = 3SE +/- 0.41, N = 358.3225.041. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Tensorflow

Build: Cifar10

OpenBenchmarking.orgSeconds, Fewer Is BetterTensorflowBuild: Cifar1016 CoresThreadripper 3970X1020304050SE +/- 0.07, N = 3SE +/- 0.53, N = 545.4442.02

Tesseract OCR

Time To OCR 7 Images

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.0Time To OCR 7 Images16 CoresThreadripper 3970X612182430SE +/- 0.02, N = 3SE +/- 0.03, N = 323.8224.08

Threaded I/O Tester

Test: Write - Size Per Thread: 32MB - Thread Count: 4

OpenBenchmarking.orgMB/s, More Is BetterThreaded I/O Tester 20170503Test: Write - Size Per Thread: 32MB - Thread Count: 416 CoresThreadripper 3970X3691215SE +/- 0.21, N = 15SE +/- 0.31, N = 1510.4110.551. (CC) gcc options: -O2

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.41Time To Compile16 CoresThreadripper 3970X612182430SE +/- 0.02, N = 3SE +/- 0.02, N = 327.5418.58

Timed FFmpeg Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed FFmpeg Compilation 4.2.2Time To Compile16 CoresThreadripper 3970X918273645SE +/- 0.02, N = 3SE +/- 0.08, N = 338.0221.97

Timed GCC Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To Compile16 CoresThreadripper 3970X2004006008001000SE +/- 1.05, N = 3SE +/- 0.83, N = 3979.62589.11

Timed GDB GNU Debugger Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GDB GNU Debugger Compilation 9.1Time To Compile16 CoresThreadripper 3970X20406080100SE +/- 0.03, N = 3SE +/- 0.06, N = 382.1983.12

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database Search16 CoresThreadripper 3970X1.08952.1793.26854.3585.4475SE +/- 0.057, N = 3SE +/- 0.059, N = 33.6784.8421. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm

Timed ImageMagick Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compile16 CoresThreadripper 3970X510152025SE +/- 0.12, N = 3SE +/- 0.06, N = 322.3013.43

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To Compile16 CoresThreadripper 3970X1122334455SE +/- 0.59, N = 3SE +/- 0.31, N = 549.3624.54

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To Compile16 CoresThreadripper 3970X50100150200250232.33122.77

Timed MPlayer Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MPlayer Compilation 1.4Time To Compile16 CoresThreadripper 3970X612182430SE +/- 0.06, N = 3SE +/- 0.04, N = 325.0911.58

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny Analysis16 CoresThreadripper 3970X20406080100SE +/- 0.16, N = 3SE +/- 0.44, N = 369.5275.411. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm -lreadline

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.4.2Time To Compile16 CoresThreadripper 3970X1122334455SE +/- 0.03, N = 3SE +/- 0.03, N = 348.2132.04

Tinymembench

Standard Memcpy

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpy16 CoresThreadripper 3970X3K6K9K12K15KSE +/- 3.80, N = 3SE +/- 13.44, N = 312317.712225.41. (CC) gcc options: -O2 -lm

Tinymembench

Standard Memset

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memset16 CoresThreadripper 3970X4K8K12K16K20KSE +/- 20.00, N = 3SE +/- 54.47, N = 320120.620042.41. (CC) gcc options: -O2 -lm

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performance16 CoresThreadripper 3970X300K600K900K1200K1500KSE +/- 12160.81, N = 5SE +/- 3552.56, N = 5131937213368771. (CC) gcc options: -O3 -march=native

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow Mapping16 CoresThreadripper 3970X140280420560700SE +/- 0.91, N = 3SE +/- 9.67, N = 13617.85667.341. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

Tungsten Renderer

Scene: Hair

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Hair16 CoresThreadripper 3970X510152025SE +/- 0.01435, N = 3SE +/- 0.03105, N = 319.255808.182171. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl

Tungsten Renderer

Scene: Water Caustic

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water Caustic16 CoresThreadripper 3970X612182430SE +/- 0.06, N = 3SE +/- 0.03, N = 324.1318.681. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl

Tungsten Renderer

Scene: Non-Exponential

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-Exponential16 CoresThreadripper 3970X246810SE +/- 0.01806, N = 3SE +/- 0.00612, N = 38.922152.642891. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl

Tungsten Renderer

Scene: Volumetric Caustic

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric Caustic16 CoresThreadripper 3970X246810SE +/- 0.00838, N = 3SE +/- 0.00339, N = 38.564203.563821. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl

Unpacking The Linux Kernel

linux-4.15.tar.xz

OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking The Linux Kernellinux-4.15.tar.xz16 CoresThreadripper 3970X1.12142.24283.36424.48565.607SE +/- 0.009, N = 4SE +/- 0.010, N = 44.9644.984

VP9 libvpx Encoding

Speed: Speed 5

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.2Speed: Speed 516 CoresThreadripper 3970X714212835SE +/- 0.13, N = 3SE +/- 0.24, N = 328.6224.481. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2019-12-17H.264 Video Encoding16 CoresThreadripper 3970X50100150200250SE +/- 2.11, N = 3SE +/- 3.52, N = 12131.88205.311. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

x265

H.265 1080p Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video Encoding16 CoresThreadripper 3970X1632486480SE +/- 0.40, N = 3SE +/- 0.16, N = 373.2164.901. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Xsbench

OpenBenchmarking.orgLookups/s, More Is BetterXsbench 2017-07-0616 CoresThreadripper 3970X1.3M2.6M3.9M5.2M6.5MSE +/- 5142.30, N = 3SE +/- 2938.92, N = 3384040460795541. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm

XZ Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9

OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 916 CoresThreadripper 3970X612182430SE +/- 0.04, N = 3SE +/- 0.08, N = 323.6318.651. (CC) gcc options: -pthread -fvisibility=hidden -O2

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd CompressionCompressing ubuntu-16.04.3-server-i386.img, Compression Level 1916 CoresThreadripper 3970X4080120160200SE +/- 0.45, N = 3SE +/- 1.03, N = 3163.05170.78

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 1916 CoresThreadripper 3970X3691215SE +/- 0.020, N = 3SE +/- 0.054, N = 313.5658.5441. (CC) gcc options: -O3 -pthread -lz -llzma


Phoronix Test Suite v10.8.5