threadripper-3960x-reference

AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and AMD Navi 10 8GB on Ubuntu 19.10 via the Phoronix Test Suite.

HTML result view exported from: https://openbenchmarking.org/result/1911259-HU-THREADRIP53&grr&sro.

threadripper-3960x-reference ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionThreadripper 3960XAMD Ryzen Threadripper 3960X 24-CoreAMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads)MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS)AMD Starship/Matisse32768MB240GB Force MP510AMD Navi 10 8GB (2100/875MHz)AMD Navi 10 HDMI AudioASUS PB278Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723Ubuntu 19.105.3.0-23-generic (x86_64)GNOME Shell 3.34.1X Server 1.20.5modesetting 1.20.54.5 Mesa 19.2.1 (LLVM 9.0.0)GCC 9.2.1 20191008ext42560x1440OpenBenchmarking.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- Threadripper 3960X: NONE / errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025Java Details- OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1)Python Details- Python 2.7.17rc1 + Python 3.7.5rc1Security Details- 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 STIBP: conditional RSB filling + tsx_async_abort: Not affected

threadripper-3960x-reference pennant: sedovbigpennant: leblancbigspec-jbb2015: SPECjbb2015-Composite critical-jOPSspec-jbb2015: SPECjbb2015-Composite max-jOPShpcc: G-HPLcassandra: Mixed 1:3cpp-perf-bench: Rand Numberscassandra: Mixed 1:1qmcpack: mkl-dnn: Convolution Batch conv_all - f32build-gcc: Time To Compilelibgav1: Chimera 1080p 10-bitcassandra: Readsmkl-dnn: Deconvolution Batch deconv_all - f32pgbench: Buffer Test - Normal Load - Read Writefftw: Float + SSE - 2D FFT Size 4096svt-av1: Enc Mode 0 - 1080pcpp-perf-bench: Math Libraryluxcorerender: Rainbow Colors and Prismblender: Barbershop - CPU-Onlybrl-cad: VGR Performance Metriccompress-lzma: 256MB File Compressiontinymembench: Standard Memsettinymembench: Standard Memcpyrenaissance: Savina Reactors.IOblender: Pabellon Barcelona - CPU-Onlyradiance: Serialselenium: Jetstream - Firefoxlibgav1: Chimera 1080pselenium: Jetstream - Google Chromeapache-siege: 250fftw: Stock - 2D FFT Size 4096dav1d: Chimera 1080p 10-bitlibgav1: Summer Nature 4Kselenium: ARES-6 - Firefoxblender: Classroom - CPU-Onlystress-ng: Context Switchingapache-siege: 200cp2k: Fayalite-FIST Dataasmfish: 1024 Hash Memory, 26 Depthmkl-dnn: Convolution Batch conv_googlenet_v3 - f32cachebench: Read / Modify / Writecachebench: Writecachebench: Readbyte: Dhrystone 2ospray: San Miguel - SciVismemtier-benchmark: Redisappleseed: Emilycassandra: Writesminion: Quasigroupselenium: StyleBench - Google Chromeospray: San Miguel - Path Tracerappleseed: Material Testerrenaissance: Apache Spark Bayesospray: NASA Streamlines - Path Tracervpxenc: vpxenc VP9 1080p Video Encodeblender: Fishy Cat - CPU-Onlyselenium: Speedometer - Firefoxpgbench: Buffer Test - Normal Load - Read Onlynpb: SP.Bgromacs: Water Benchmarkcpp-perf-bench: Stepanov Vectoraskap: tConvolve MT - Degriddingaskap: tConvolve MT - Griddingfftw: Float + SSE - 2D FFT Size 2048mrbayes: Primate Phylogeny Analysisv-ray: CPUopencv-bench: selenium: StyleBench - Firefoxselenium: Speedometer - Google Chromenpb: EP.Drocksdb: Seq Fillindigobench: Bedroomluxcorerender: DLSCsqlite: 8indigobench: Supercarminion: Solitaireospray: XFrog Forest - Path Tracerrocksdb: Read While Writinggraphics-magick: Resizingrocksdb: Rand Readgraphics-magick: Noise-Gaussiangraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Rotategraphics-magick: Swirlgraphics-magick: HWB Color Spaceblender: BMW27 - CPU-Onlycpp-perf-bench: Atolsqlite-speedtest: Timed Time - Size 1,000himeno: Poisson Pressure Solverappleseed: Disney Materialradiance: SMP Parallelrenaissance: Apache Spark PageRanknginx: Static Web Page Servingaskap: tConvolve MPI - Degriddingaskap: tConvolve MPI - Griddingnpb: BT.Clibreoffice: 20 Documents To PDFbuild2: Time To Compileoctave-benchmark: redis: SETredis: GETstockfish: Total Timelibgav1: Summer Nature 1080pparboil: OpenMP MRI Griddingnamd: ATPase Simulation - 327,506 Atomsselenium: ARES-6 - Google Chromebuild-llvm: Time To Compilemkl-dnn: IP Batch All - f32selenium: Octane - Firefoxjava-scimark2: Compositehackbench: 32 - Processlczero: BLASospray: XFrog Forest - SciVisrav1e: 1080p To AV1 Video Encodeselenium: Octane - Google Chromeminion: Gracefulnpb: LU.Cbuild-php: Time To Compiledcraw: RAW To PPM Image Conversionmkl-dnn: Convolution Batch conv_3d - f32stream: Copyfftw: Stock - 2D FFT Size 2048build-linux-kernel: Time To Compilecompress-7zip: Compress Speed Testmbw: Memory Copy, Fixed Block Size - 4096 MiBmkl-dnn: Recurrent Neural Network Training - f32renaissance: Akka Unbalanced Cobwebbed Treeminife: Smallrenaissance: In-Memory Database Shootoutembree: Pathtracer ISPC - Asian Dragon Objcompress-gzip: Linux Source Tree Archiving To .tar.gzembree: Pathtracer - Asian Dragon Objrust-mandel: Time To Complete Serial/Parallel Mandelbrotcpp-perf-bench: Ctypettsiod-renderer: Phong Rendering With Soft-Shadow Mappingmkl-dnn: IP Batch 1D - f32glibc-bench: expstress-ng: CPU Stressstress-ng: Tsearchstress-ng: Cryptostress-ng: Vector Mathstress-ng: System V Message Passingstress-ng: Semaphoresstress-ng: Lsearchstress-ng: Bsearchstress-ng: Glibc C String Functionsstress-ng: Memory Copyingstress-ng: Hsearchstress-ng: Forkingstress-ng: Matrix Mathstress-ng: Glibc Qsort Data Sortingstress-ng: Socket Activityapache: Static Web Page Servingcpp-perf-bench: Stepanov Abstractionespeak: Text-To-Speech Synthesismt-dgemm: Sustained Floating-Point Raterenaissance: Apache Spark ALSscimark2: Compositeospray: NASA Streamlines - SciViscoremark: CoreMark Size 666 - Iterations Per Secondtesseract-ocr: Time To OCR 7 Imagesnpb: FT.Cm-queens: Time To Solvehackbench: 16 - Threadtensorflow: Cifar10fftw: Float + SSE - 2D FFT Size 1024hackbench: 16 - Processmbw: Memory Copy - 4096 MiBpybench: Total For Average Test Timesembree: Pathtracer ISPC - Crowncrafty: Elapsed Timec-ray: Total Time - 4K, 16 Rays Per Pixelmkl-dnn: Deconvolution Batch deconv_1d - f32embree: Pathtracer - Crowntungsten: Water Causticgimp: unsharp-maskcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9glibc-bench: cosglibc-bench: sincosglibc-bench: sinebizzy: fftw: Float + SSE - 1D FFT Size 256embree: Pathtracer - Asian Dragonembree: Pathtracer ISPC - Asian Dragongo-benchmark: buildselenium: PSPDFKit WASM - Firefoxdav1d: Chimera 1080ppovray: Trace Timetungsten: Non-Exponentialselenium: PSPDFKit WASM - Google Chromeselenium: Maze Solver - Firefoxparaview: Many Spheres - 2560 x 1440paraview: Many Spheres - 2560 x 1440gimp: auto-levelsramspeed: Triad - Floating Pointmkl-dnn: Convolution Batch conv_alexnet - f32ramspeed: Average - Integersqlite: 1phpbench: PHP Benchmark Suiteramspeed: Copy - Floating Pointrust-prime: Prime Number Test To 200,000,000cpp-perf-bench: Function Objectsbuild-imagemagick: Time To Compileramspeed: Scale - Floating Pointramspeed: Add - Floating Pointramspeed: Average - Floating Pointramspeed: Add - Integerramspeed: Scale - Integerramspeed: Triad - Integerramspeed: Copy - Integerfftw: Float + SSE - 1D FFT Size 64fftw: Stock - 1D FFT Size 64selenium: Maze Solver - Google Chromecompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19encode-flac: WAV To FLAChackbench: 1 - Processxsbench: dav1d: Summer Nature 4Kgimp: rotatedacapobench: Tradebeansgo-benchmark: jsonhackbench: 8 - Threadsvt-av1: Enc Mode 4 - 1080phackbench: 8 - Processaskap: tConvolve OpenMP - Degriddingaskap: tConvolve OpenMP - Griddingdacapobench: Tradesoaplczero: Randencode-opus: WAV, Opus Encode, Opus Decodeglibc-bench: asinhglibc-bench: sinhglibc-bench: log2glibc-bench: ffsllglibc-bench: tanhglibc-bench: atanhglibc-bench: sqrtglibc-bench: modfglibc-bench: ffsglibc-bench: pthread_oncerodinia: OpenMP LavaMDtungsten: Hairfftw: Stock - 2D FFT Size 1024dacapobench: H2go-benchmark: httpmbw: Memory Copy, Fixed Block Size - 1024 MiBospray: Magnetic Reconnection - SciVisx265: H.265 1080p Video Encodingrodinia: OpenMP CFD Solverneatbench: CPUsvt-vp9: VMAF Optimized - Bosphorus 1080pparboil: OpenMP Stencilgimp: resizego-benchmark: garbagebork: File Encryption Timenpb: MG.Csunflow: Global Illumination + Image Synthesisencode-mp3: WAV To MP3dacapobench: Jythondarktable: Boat - CPU-onlyfftw: Float + SSE - 2D FFT Size 512fftw: Float + SSE - 1D FFT Size 4096ospray: Magnetic Reconnection - Path Tracerhackbench: 4 - Threadmbw: Memory Copy - 1024 MiBhackbench: 4 - Processosbench: Create Filesdav1d: Summer Nature 1080poidn: Memorialsvt-av1: Enc Mode 8 - 1080pfftw: Float + SSE - 1D FFT Size 2048osbench: Memory Allocationsosbench: Create Processesosbench: Launch Programsosbench: Create Threadsparaview: Wavelet Contour - 2560 x 1440paraview: Wavelet Contour - 2560 x 1440git: Time To Complete Common Git Commandsmbw: Memory Copy, Fixed Block Size - 512 MiBfftw: Stock - 1D FFT Size 4096fftw: Stock - 2D FFT Size 256fftw: Float + SSE - 2D FFT Size 256n-queens: Elapsed Timenpb: EP.Ctungsten: Volumetric Causticdarktable: Masskrug - CPU-onlyfftw: Float + SSE - 1D FFT Size 1024fftw: Stock - 1D FFT Size 256fftw: Stock - 2D FFT Size 32bullet: Raytestsfftw: Stock - 2D FFT Size 512fftw: Float + SSE - 1D FFT Size 32fftw: Float + SSE - 2D FFT Size 32fftw: Float + SSE - 1D FFT Size 512fftw: Stock - 1D FFT Size 32hackbench: 2 - Threadfftw: Stock - 1D FFT Size 2048smallpt: Global Illumination Renderer; 128 Samplesfftw: Stock - 2D FFT Size 128darktable: Server Rack - CPU-onlyfftw: Stock - 1D FFT Size 128hackbench: 2 - Processdarktable: Server Room - CPU-onlyx264: H.264 Video Encodingoptcarrot: Optimized Benchmarkmkl-dnn: Deconvolution Batch deconv_3d - f32fftw: Float + SSE - 2D FFT Size 128fftw: Stock - 1D FFT Size 1024hackbench: 1 - Threadmbw: Memory Copy - 512 MiBfftw: Stock - 2D FFT Size 64fftw: Stock - 1D FFT Size 512fftw: Float + SSE - 1D FFT Size 128fftw: Float + SSE - 2D FFT Size 64svt-vp9: Visual Quality Optimized - Bosphorus 1080pffte: N=256, 1D Complex FFT Routinetscp: AI Chess Performancesvt-vp9: PSNR/SSIM Optimized - Bosphorus 1080pparaview: Wavelet Volume - 2560 x 1440paraview: Wavelet Volume - 2560 x 1440tachyon: Total Timeparboil: OpenMP CUTCPmbw: Memory Copy, Fixed Block Size - 128 MiBmbw: Memory Copy - 128 MiBcloverleaf: Lagrangian-Eulerian Hydrodynamicsctx-clock: Context Switch Timebullet: Convex Trimeshbullet: Prim Trimeshbullet: 136 Ragdollsbullet: 1000 Convexbullet: 1000 Stackbullet: 3000 Fallhpcc: Max Ping Pong Bandwidthhpcc: Rand Ring Bandwidthhpcc: Rand Ring Latencyhpcc: G-Rand Accesshpcc: EP-STREAM Triadhpcc: G-Ptranshpcc: EP-DGEMMhpcc: G-Fftehpcc: G-Fftestream: Addstream: Triadstream: ScaleThreadripper 3960XAMD Ryzen Threadripper 3960X 24-Core6502.5646305.17060.460731711105.4274971875.81070.54598.91220.46300781772.7813768.050779223140.064270.6902.29237.55393502226.23517756.910538.014138.775191.48558.724217.5749.67217.506784.187.1922.9950.67150.8915705353.86419.6937554026657.283061655.49410027032059.6992957463063.5445423513.138.462912967.74160.60522230619107.18049436.62.88136.8049863355.90710.75201.3684.0097.1662564.29652823242.082.48676.6473410471.1333940464.11879.01332214.2710303683.9262.7961.4108.10460.5100683.72487771422631436882705653795697101351146257.9957.76158.4304748.29360687.464249172.07917245.11936127.8552747.626.78854.08313.3061834121.402649622.707543452874.2949.0677960.7223519.97141.55716.7995367393033.2644.56132.73497.081.3694743341.78130251711.8839.64439.4986.8473533465.17864.328.53815091511493.070226.81912584.8567790.676759.03227.739433.75428.785833.088780.0442.817694.840419167.11964.427072.9367241.3723627101.303239494.25357.0616332.262449871.8312234.52199421.4580851.06151388.05380.7318734.3434193.1528.30427.8118.5438876643.079714.9252.631069837.22863924.13617832.3923.28122.9554089722.73719697.47596828.3694904172921.0592.5961129.767319.335520.51120.35742.020612.137041.41683826032.152032.1513192910137591324587.8116.4103.5642215084.45900.23258.8517.12537623.85142.22736961.6315.73865840835940.8914.67714.53937097.9943043.8440240.9843028.4438106.3843894.2637204.25189009362.24.010.2277.8342.7625029528291.0912.3164643190107811.6668.04311.14633641069086.2728.420527.826345.837171.7530710.519710.01722.162352.219841.759271.7439510.1039.797378097.93694861911380.3222565.719.037382.227.2434408.6097025008.01825120.080.6857.11739636.2794304958875333.336.03219435.3825.46811.538926677.0619.5978.7926111270.59605941.03660648.14624820.8433472578.928247.474.76511306.1848818.88674.1426164.4692208.114.156463.402599378883.8111132.1143488684.6150424612351240112373.7369048.13.6758902.30.1308569.23.5292.242193.76106.882.86390469709356.22.85819400.4329585.49114.02746047733326.419627.341341412392.872811.522175.721.68991.26465710863.42110893.6780.821520.9551880.7987752.1816233.813674.1109413.41694122107.9133.364000.456830.142921.822285.5402231.6369010.7307710.7307736666.436725.133514.626415526591103.853271.78757247.2755723.6376.7673307.001911.4159.3023311.011865.0333.391532.69831.86928.31217.04225419616.36014.99914.6933915.534617.4710666935.319.75OpenBenchmarking.org

Pennant

Test: sedovbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: sedovbigThreadripper 3960X14002800420056007000SE +/- 2.00, N = 36502.561. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

Pennant

Test: leblancbig

OpenBenchmarking.orgHydro Cycle Time - Seconds, Fewer Is BetterPennant 1.0.1Test: leblancbigThreadripper 3960X14002800420056007000SE +/- 12.26, N = 36305.171. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi

SPECjbb 2015

SPECjbb2015-Composite critical-jOPS

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite critical-jOPSAMD Ryzen Threadripper 3960X 24-Core6K12K18K24K30K26415

SPECjbb 2015

SPECjbb2015-Composite max-jOPS

OpenBenchmarking.orgjOPS, More Is BetterSPECjbb 2015SPECjbb2015-Composite max-jOPSAMD Ryzen Threadripper 3960X 24-Core11K22K33K44K55K52659

HPC Challenge

Test / Class: G-HPL

OpenBenchmarking.orgGFLOPS, More Is BetterHPC Challenge 1.5.0Test / Class: G-HPLThreadripper 3960X1428425670SE +/- 0.16, N = 360.461. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

Apache Cassandra

Test: Mixed 1:3

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Mixed 1:3Threadripper 3960X4080120160200SE +/- 5.83, N = 7171

CppPerformanceBenchmarks

Test: Random Numbers

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Random NumbersAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X2004006008001000SE +/- 1.36, N = 3SE +/- 0.65, N = 31103.851105.431. (CXX) g++ options: -std=c++11 -O3

Apache Cassandra

Test: Mixed 1:1

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: Mixed 1:1Threadripper 3960X110220330440550SE +/- 77.62, N = 7497

QMCPACK

OpenBenchmarking.orgTotal Execution Time - Seconds, Fewer Is BetterQMCPACK 3.8Threadripper 3960X4008001200160020001875.81. (CXX) g++ options: -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -ffast-math -lm

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: f32Threadripper 3960X2004006008001000SE +/- 2.64, N = 31070.54MIN: 997.441. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Timed GCC Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To CompileThreadripper 3960X130260390520650SE +/- 1.15, N = 3598.91

libgav1

Video Input: Chimera 1080p 10-bit

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080p 10-bitThreadripper 3960X510152025SE +/- 0.11, N = 320.461. (CXX) g++ options: -O3 -lpthread

Apache Cassandra

Test: Reads

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: ReadsThreadripper 3960X6K12K18K24K30KSE +/- 12892.81, N = 930078

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: f32Threadripper 3960X400800120016002000SE +/- 6.22, N = 31772.78MIN: 16771. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

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 WriteThreadripper 3960X3K6K9K12K15KSE +/- 1254.90, N = 1213768.051. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

FFTW

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

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 4096Threadripper 3960X5K10K15K20K25KSE +/- 60.75, N = 3223141. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

SVT-AV1

Encoder Mode: Enc Mode 0 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.7Encoder Mode: Enc Mode 0 - Input: 1080pThreadripper 3960X0.01440.02880.04320.05760.072SE +/- 0.000, N = 30.0641. (CXX) g++ options: -fPIE -fPIC -pie

CppPerformanceBenchmarks

Test: Math Library

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Math LibraryAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X60120180240300SE +/- 0.18, N = 3SE +/- 2.14, N = 3271.79270.691. (CXX) g++ options: -std=c++11 -O3

LuxCoreRender

Scene: Rainbow Colors and Prism

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: Rainbow Colors and PrismThreadripper 3960X0.51531.03061.54592.06122.5765SE +/- 0.15, N = 122.29MIN: 1.36 / MAX: 2.94

Blender

Blend File: Barbershop - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.81Blend File: Barbershop - Compute: CPU-OnlyThreadripper 3960X50100150200250SE +/- 0.15, N = 3237.55

BRL-CAD

VGR Performance Metric

OpenBenchmarking.orgVGR Performance Metric, More Is BetterBRL-CAD 7.28.0VGR Performance MetricThreadripper 3960X80K160K240K320K400K3935021. (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

LZMA Compression

256MB File Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterLZMA Compression256MB File CompressionThreadripper 3960X50100150200250SE +/- 0.29, N = 3226.241. (CXX) g++ options: -O2

Tinymembench

Standard Memset

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard MemsetThreadripper 3960X4K8K12K16K20KSE +/- 18.62, N = 317756.91. (CC) gcc options: -O2 -lm

Tinymembench

Standard Memcpy

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard MemcpyThreadripper 3960X2K4K6K8K10KSE +/- 165.90, N = 310538.01. (CC) gcc options: -O2 -lm

Renaissance

Test: Savina Reactors.IO

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Savina Reactors.IOThreadripper 3960X3K6K9K12K15KSE +/- 209.59, N = 4014138.78

Blender

Blend File: Pabellon Barcelona - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.81Blend File: Pabellon Barcelona - Compute: CPU-OnlyThreadripper 3960X4080120160200SE +/- 0.19, N = 3191.48

Radiance Benchmark

Test: Serial

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SerialThreadripper 3960X120240360480600558.72

Selenium

Benchmark: Jetstream - Browser: Firefox

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream - Browser: FirefoxThreadripper 3960X50100150200250SE +/- 0.36, N = 3217.571. firefox 70.0.1

libgav1

Video Input: Chimera 1080p

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Chimera 1080pThreadripper 3960X1122334455SE +/- 0.18, N = 349.671. (CXX) g++ options: -O3 -lpthread

Selenium

Benchmark: Jetstream - Browser: Google Chrome

OpenBenchmarking.orgScore, More Is BetterSeleniumBenchmark: Jetstream - Browser: Google ChromeThreadripper 3960X50100150200250SE +/- 0.77, N = 3217.501. chrome 78.0.3904.108

Apache Siege

Concurrent Users: 250

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250AMD Ryzen Threadripper 3960X 24-Core12K24K36K48K60KSE +/- 2486.04, N = 1257247.271. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

FFTW

Build: Stock - Size: 2D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096Threadripper 3960X15003000450060007500SE +/- 8.75, N = 36784.11. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

dav1d

Video Input: Chimera 1080p 10-bit

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Chimera 1080p 10-bitThreadripper 3960X20406080100SE +/- 0.14, N = 387.19MIN: 54.26 / MAX: 180.021. (CC) gcc options: -pthread

libgav1

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 4KThreadripper 3960X612182430SE +/- 0.05, N = 322.991. (CXX) g++ options: -O3 -lpthread

Selenium

Benchmark: ARES-6 - Browser: Firefox

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: FirefoxThreadripper 3960X1122334455SE +/- 0.41, N = 350.671. firefox 70.0.1

Blender

Blend File: Classroom - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.81Blend File: Classroom - Compute: CPU-OnlyThreadripper 3960X306090120150SE +/- 0.20, N = 3150.89

Stress-NG

Test: Context Switching

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context SwitchingThreadripper 3960X3M6M9M12M15MSE +/- 214670.64, N = 1515705353.861. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Apache Siege

Concurrent Users: 200

OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 200AMD Ryzen Threadripper 3960X 24-Core12K24K36K48K60KSE +/- 2566.16, N = 1255723.631. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto

CP2K Molecular Dynamics

Fayalite-FIST Data

OpenBenchmarking.orgSeconds, Fewer Is BetterCP2K Molecular Dynamics 6.1Fayalite-FIST DataThreadripper 3960X90180270360450419.69

asmFish

1024 Hash Memory, 26 Depth

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2018-07-231024 Hash Memory, 26 DepthThreadripper 3960X16M32M48M64M80MSE +/- 575831.34, N = 375540266

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: f32Threadripper 3960X1326395265SE +/- 0.28, N = 357.28MIN: 51.081. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

CacheBench

Test: Read / Modify / Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteThreadripper 3960X13K26K39K52K65KSE +/- 95.04, N = 361655.49MIN: 55797.19 / MAX: 66291.681. (CC) gcc options: -lrt

CacheBench

Test: Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteThreadripper 3960X7K14K21K28K35KSE +/- 55.58, N = 332059.70MIN: 28046.66 / MAX: 33459.41. (CC) gcc options: -lrt

CacheBench

Test: Read

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: ReadThreadripper 3960X7001400210028003500SE +/- 3.47, N = 33063.54MIN: 3047.77 / MAX: 3069.921. (CC) gcc options: -lrt

BYTE Unix Benchmark

Computational Test: Dhrystone 2

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2Threadripper 3960X10M20M30M40M50MSE +/- 405676.33, N = 345423513.1

OSPray

Demo: San Miguel - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: SciVisThreadripper 3960X918273645SE +/- 0.00, N = 1238.46MIN: 35.71 / MAX: 40

Memtier_benchmark

Protocol: Redis

OpenBenchmarking.orgOps/sec, More Is BetterMemtier_benchmark 1.2.17Protocol: RedisThreadripper 3960X600K1200K1800K2400K3000KSE +/- 26919.58, N = 32912967.741. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre

Appleseed

Scene: Emily

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: EmilyThreadripper 3960X4080120160200160.61

Apache Cassandra

Test: Writes

OpenBenchmarking.orgOp/s, More Is BetterApache Cassandra 3.11.4Test: WritesThreadripper 3960X50K100K150K200K250KSE +/- 3283.40, N = 4230619

Minion

Benchmark: Quasigroup

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: QuasigroupThreadripper 3960X20406080100SE +/- 0.62, N = 3107.181. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Selenium

Benchmark: StyleBench - Browser: Google Chrome

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: Google ChromeThreadripper 3960X816243240SE +/- 0.09, N = 336.61. chrome 78.0.3904.108

OSPray

Demo: San Miguel - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: San Miguel - Renderer: Path TracerThreadripper 3960X0.6481.2961.9442.5923.24SE +/- 0.00, N = 32.88MIN: 2.87 / MAX: 2.92

Appleseed

Scene: Material Tester

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Material TesterThreadripper 3960X306090120150136.80

Renaissance

Test: Apache Spark Bayes

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark BayesThreadripper 3960X7001400210028003500SE +/- 30.14, N = 403355.91

OSPray

Demo: NASA Streamlines - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: Path TracerThreadripper 3960X3691215SE +/- 0.00, N = 1210.75MIN: 10.53 / MAX: 10.99

VP9 libvpx Encoding

vpxenc VP9 1080p Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.1vpxenc VP9 1080p Video EncodeThreadripper 3960X4080120160200SE +/- 0.93, N = 3201.361. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

Blender

Blend File: Fishy Cat - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.81Blend File: Fishy Cat - Compute: CPU-OnlyThreadripper 3960X20406080100SE +/- 0.11, N = 384.00

Selenium

Benchmark: Speedometer - Browser: Firefox

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: FirefoxThreadripper 3960X20406080100SE +/- 0.27, N = 397.11. firefox 70.0.1

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 OnlyThreadripper 3960X140K280K420K560K700KSE +/- 1102.78, N = 3662564.301. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

NAS Parallel Benchmarks

Test / Class: SP.B

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: SP.BThreadripper 3960X5K10K15K20K25KSE +/- 269.46, N = 1523242.081. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

GROMACS

Water Benchmark

OpenBenchmarking.orgNs Per Day, More Is BetterGROMACS 2019.4Water BenchmarkThreadripper 3960X0.55941.11881.67822.23762.797SE +/- 0.004, N = 32.4861. (CXX) g++ options: -mavx2 -mfma -std=c++11 -O3 -funroll-all-loops -pthread -lrt -lpthread -lm

CppPerformanceBenchmarks

Test: Stepanov Vector

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov VectorAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X20406080100SE +/- 0.16, N = 3SE +/- 0.17, N = 376.7776.651. (CXX) g++ options: -std=c++11 -O3

ASKAP

Test: tConvolve MT - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - DegriddingAMD Ryzen Threadripper 3960X 24-Core7001400210028003500SE +/- 8.26, N = 33307.001. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve MT - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MT - GriddingAMD Ryzen Threadripper 3960X 24-Core400800120016002000SE +/- 9.48, N = 31911.411. (CXX) g++ options: -lpthread

FFTW

Build: Float + SSE - Size: 2D FFT Size 2048

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2048Threadripper 3960X7K14K21K28K35KSE +/- 375.01, N = 3341041. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Timed MrBayes Analysis

Primate Phylogeny Analysis

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.2.7Primate Phylogeny AnalysisThreadripper 3960X1632486480SE +/- 0.28, N = 371.131. (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

Chaos Group V-RAY

Mode: CPU

OpenBenchmarking.orgKsamples, More Is BetterChaos Group V-RAY 4.10.03Mode: CPUThreadripper 3960X8K16K24K32K40KSE +/- 88.94, N = 339404

OpenCV Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterOpenCV Benchmark 3.3.0Threadripper 3960X1428425670SE +/- 0.13, N = 364.121. (CXX) g++ options: -std=c++11 -rdynamic

Selenium

Benchmark: StyleBench - Browser: Firefox

OpenBenchmarking.orgRuns / Minute, More Is BetterSeleniumBenchmark: StyleBench - Browser: FirefoxThreadripper 3960X20406080100SE +/- 0.32, N = 379.01. firefox 70.0.1

Selenium

Benchmark: Speedometer - Browser: Google Chrome

OpenBenchmarking.orgRuns Per Minute, More Is BetterSeleniumBenchmark: Speedometer - Browser: Google ChromeThreadripper 3960X306090120150SE +/- 0.33, N = 31331. chrome 78.0.3904.108

NAS Parallel Benchmarks

Test / Class: EP.D

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.DThreadripper 3960X5001000150020002500SE +/- 7.75, N = 32214.271. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Facebook RocksDB

Test: Sequential Fill

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Sequential FillThreadripper 3960X200K400K600K800K1000KSE +/- 13038.81, N = 410303681. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

IndigoBench

Scene: Bedroom

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: BedroomThreadripper 3960X0.88341.76682.65023.53364.417SE +/- 0.010, N = 33.926

LuxCoreRender

Scene: DLSC

OpenBenchmarking.orgM samples/sec, More Is BetterLuxCoreRender 2.2Scene: DLSCThreadripper 3960X0.62781.25561.88342.51123.139SE +/- 0.01, N = 32.79MIN: 2.72 / MAX: 2.85

SQLite

Threads / Copies: 8

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 8Threadripper 3960X1428425670SE +/- 0.32, N = 361.411. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

IndigoBench

Scene: Supercar

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: SupercarThreadripper 3960X246810SE +/- 0.003, N = 38.104

Minion

Benchmark: Solitaire

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: SolitaireThreadripper 3960X1428425670SE +/- 0.35, N = 360.511. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

OSPray

Demo: XFrog Forest - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: Path TracerThreadripper 3960X0.8371.6742.5113.3484.185SE +/- 0.01, N = 33.72MIN: 3.66 / MAX: 3.76

Facebook RocksDB

Test: Read While Writing

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Read While WritingThreadripper 3960X1000K2000K3000K4000K5000KSE +/- 40449.58, N = 348777141. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: ResizingThreadripper 3960X5001000150020002500SE +/- 12.39, N = 322631. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

Facebook RocksDB

Test: Random Read

OpenBenchmarking.orgOp/s, More Is BetterFacebook RocksDB 6.3.6Test: Random ReadThreadripper 3960X30M60M90M120M150MSE +/- 1282448.37, N = 31436882701. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: Noise-GaussianThreadripper 3960X120240360480600SE +/- 0.33, N = 35651. (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: SharpenThreadripper 3960X80160240320400SE +/- 2.19, N = 33791. (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: EnhancedThreadripper 3960X120240360480600SE +/- 0.67, N = 35691. (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: RotateThreadripper 3960X150300450600750SE +/- 3.84, N = 37101. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.33Operation: SwirlThreadripper 3960X30060090012001500SE +/- 5.49, N = 313511. (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 SpaceThreadripper 3960X30060090012001500SE +/- 1.86, N = 314621. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread

Blender

Blend File: BMW27 - Compute: CPU-Only

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.81Blend File: BMW27 - Compute: CPU-OnlyThreadripper 3960X1326395265SE +/- 0.06, N = 357.99

CppPerformanceBenchmarks

Test: Atol

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: AtolAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X1326395265SE +/- 0.64, N = 3SE +/- 0.19, N = 359.3057.761. (CXX) g++ options: -std=c++11 -O3

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000Threadripper 3960X1326395265SE +/- 0.15, N = 358.431. (CC) gcc options: -O2 -ldl -lz -lpthread

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverThreadripper 3960X10002000300040005000SE +/- 50.65, N = 34748.291. (CC) gcc options: -O3 -mavx2

Appleseed

Scene: Disney Material

OpenBenchmarking.orgSeconds, Fewer Is BetterAppleseed 2.0 BetaScene: Disney MaterialThreadripper 3960X2040608010087.46

Radiance Benchmark

Test: SMP Parallel

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP ParallelThreadripper 3960X4080120160200172.08

Renaissance

Test: Apache Spark PageRank

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark PageRankThreadripper 3960X4K8K12K16K20KSE +/- 108.55, N = 817245.12

NGINX Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page ServingThreadripper 3960X8K16K24K32K40KSE +/- 62.41, N = 336127.851. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

ASKAP

Test: tConvolve MPI - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - DegriddingAMD Ryzen Threadripper 3960X 24-Core7001400210028003500SE +/- 9.46, N = 33311.011. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve MPI - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve MPI - GriddingAMD Ryzen Threadripper 3960X 24-Core400800120016002000SE +/- 4.29, N = 31865.031. (CXX) g++ options: -lpthread

NAS Parallel Benchmarks

Test / Class: BT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: BT.CThreadripper 3960X11K22K33K44K55KSE +/- 720.74, N = 352747.621. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

LibreOffice

Test: 20 Documents To PDF

OpenBenchmarking.orgSeconds, Fewer Is BetterLibreOfficeTest: 20 Documents To PDFThreadripper 3960X246810SE +/- 0.054, N = 246.7881. LibreOffice 6.3.3.2 30(Build:2)

Build2

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterBuild2 0.12Time To CompileThreadripper 3960X1224364860SE +/- 0.10, N = 354.08

GNU Octave Benchmark

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 4.4.1Threadripper 3960X3691215SE +/- 0.11, N = 1213.31

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: SETThreadripper 3960X400K800K1200K1600K2000KSE +/- 31778.19, N = 151834121.401. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 5.0.5Test: GETThreadripper 3960X600K1200K1800K2400K3000KSE +/- 58191.94, N = 152649622.701. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total TimeThreadripper 3960X16M32M48M64M80MSE +/- 740558.08, N = 3754345281. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

libgav1

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterlibgav1 2019-10-05Video Input: Summer Nature 1080pThreadripper 3960X1632486480SE +/- 0.15, N = 374.291. (CXX) g++ options: -O3 -lpthread

Parboil

Test: OpenMP MRI Gridding

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingThreadripper 3960X1122334455SE +/- 0.16, N = 349.071. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

NAMD

ATPase Simulation - 327,506 Atoms

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 AtomsThreadripper 3960X0.16250.3250.48750.650.8125SE +/- 0.00128, N = 30.72235

Selenium

Benchmark: ARES-6 - Browser: Google Chrome

OpenBenchmarking.orgms, Fewer Is BetterSeleniumBenchmark: ARES-6 - Browser: Google ChromeThreadripper 3960X510152025SE +/- 0.05, N = 319.971. chrome 78.0.3904.108

Timed LLVM Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileThreadripper 3960X306090120150141.56

MKL-DNN DNNL

Harness: IP Batch All - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch All - Data Type: f32Threadripper 3960X48121620SE +/- 0.12, N = 316.80MIN: 15.381. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Selenium

Benchmark: Octane - Browser: Firefox

OpenBenchmarking.orgGeometric Mean, More Is BetterSeleniumBenchmark: Octane - Browser: FirefoxThreadripper 3960X8K16K24K32K40KSE +/- 203.61, N = 3367391. firefox 70.0.1

Java SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: CompositeThreadripper 3960X7001400210028003500SE +/- 3.56, N = 43033.26

Hackbench

Count: 32 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: ProcessThreadripper 3960X1020304050SE +/- 0.08, N = 344.561. (CC) gcc options: -lpthread

LeelaChessZero

Backend: BLAS

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.22.0Backend: BLASAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X816243240SE +/- 2.09, N = 12SE +/- 0.94, N = 1233.3932.731. (CXX) g++ options: -lpthread

OSPray

Demo: XFrog Forest - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: XFrog Forest - Renderer: SciVisThreadripper 3960X246810SE +/- 0.01, N = 47.08MIN: 6.94 / MAX: 7.19

rav1e

1080p To AV1 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is Betterrav1e 0.11080p To AV1 Video EncodeThreadripper 3960X0.3080.6160.9241.2321.54SE +/- 0.002, N = 31.369

Selenium

Benchmark: Octane - Browser: Google Chrome

OpenBenchmarking.orgGeometric Mean, More Is BetterSeleniumBenchmark: Octane - Browser: Google ChromeThreadripper 3960X10K20K30K40K50KSE +/- 57.21, N = 3474331. chrome 78.0.3904.108

Minion

Benchmark: Graceful

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: GracefulThreadripper 3960X1020304050SE +/- 0.26, N = 341.781. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

NAS Parallel Benchmarks

Test / Class: LU.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: LU.CThreadripper 3960X11K22K33K44K55KSE +/- 232.22, N = 351711.881. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To CompileThreadripper 3960X918273645SE +/- 0.04, N = 339.641. (CC) gcc options: -O2 -pedantic -ldl -lz -lm

dcraw

RAW To PPM Image Conversion

OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image ConversionThreadripper 3960X918273645SE +/- 0.06, N = 339.501. (CC) gcc options: -lm

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: f32Threadripper 3960X246810SE +/- 0.08494, N = 36.84735MIN: 5.91. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: CopyThreadripper 3960X7K14K21K28K35KSE +/- 15.88, N = 533465.11. (CC) gcc options: -O3 -march=native -fopenmp

FFTW

Build: Stock - Size: 2D FFT Size 2048

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2048Threadripper 3960X2K4K6K8K10KSE +/- 3.11, N = 37864.31. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 5.4Time To CompileThreadripper 3960X714212835SE +/- 0.39, N = 428.54

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed TestThreadripper 3960X30K60K90K120K150KSE +/- 539.47, N = 31509151. (CXX) g++ options: -pipe -lpthread

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 MiBThreadripper 3960X2K4K6K8K10KSE +/- 4.86, N = 311493.071. (CC) gcc options: -O3 -march=native

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: f32Threadripper 3960X50100150200250SE +/- 1.80, N = 3226.82MIN: 196.671. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Renaissance

Test: Akka Unbalanced Cobwebbed Tree

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Akka Unbalanced Cobwebbed TreeThreadripper 3960X3K6K9K12K15KSE +/- 127.16, N = 812584.86

miniFE

Problem Size: Small

OpenBenchmarking.orgCG Mflops, More Is BetterminiFE 2.2Problem Size: SmallThreadripper 3960X2K4K6K8K10KSE +/- 16.76, N = 37790.671. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi

Renaissance

Test: In-Memory Database Shootout

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: In-Memory Database ShootoutThreadripper 3960X14002800420056007000SE +/- 52.85, N = 86759.03

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian Dragon ObjThreadripper 3960X714212835SE +/- 0.02, N = 327.74MIN: 27.42 / MAX: 28.3

Gzip Compression

Linux Source Tree Archiving To .tar.gz

OpenBenchmarking.orgSeconds, Fewer Is BetterGzip CompressionLinux Source Tree Archiving To .tar.gzThreadripper 3960X816243240SE +/- 0.01, N = 333.75

Embree

Binary: Pathtracer - Model: Asian Dragon Obj

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian Dragon ObjThreadripper 3960X714212835SE +/- 0.01, N = 328.79MIN: 28.45 / MAX: 29.34

Rust Mandelbrot

Time To Complete Serial/Parallel Mandelbrot

OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel MandelbrotAMD Ryzen Threadripper 3960X 24-Core816243240SE +/- 0.11, N = 332.701. (CC) gcc options: -m64 -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm

CppPerformanceBenchmarks

Test: Ctype

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: CtypeAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X816243240SE +/- 0.03, N = 3SE +/- 0.33, N = 331.8733.091. (CXX) g++ options: -std=c++11 -O3

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow MappingThreadripper 3960X2004006008001000SE +/- 9.82, N = 4780.041. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

MKL-DNN DNNL

Harness: IP Batch 1D - Data Type: f32

OpenBenchmarking.orgms, Fewer Is BetterMKL-DNN DNNL 1.1Harness: IP Batch 1D - Data Type: f32Threadripper 3960X0.6341.2681.9022.5363.17SE +/- 0.03365, N = 62.81769MIN: 2.361. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

glibc bench

Benchmark: exp

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: expThreadripper 3960X1.08912.17823.26734.35645.4455SE +/- 0.05687, N = 34.84041

Stress-NG

Test: CPU Stress

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CPU StressThreadripper 3960X2K4K6K8K10KSE +/- 16.14, N = 39167.111. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Tsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: TsearchThreadripper 3960X2004006008001000SE +/- 1.41, N = 3964.421. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CryptoThreadripper 3960X15003000450060007500SE +/- 27.32, N = 37072.931. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Vector MathThreadripper 3960X14K28K42K56K70KSE +/- 2.23, N = 367241.371. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: System V Message Passing

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message PassingThreadripper 3960X5M10M15M20M25MSE +/- 196376.22, N = 323627101.301. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Semaphores

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: SemaphoresThreadripper 3960X700K1400K2100K2800K3500KSE +/- 8385.90, N = 33239494.251. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Lsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: LsearchThreadripper 3960X80160240320400SE +/- 0.48, N = 3357.061. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Bsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: BsearchThreadripper 3960X3K6K9K12K15KSE +/- 134.01, N = 316332.261. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Glibc C String Functions

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc C String FunctionsThreadripper 3960X500K1000K1500K2000K2500KSE +/- 28050.29, N = 32449871.831. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Memory CopyingThreadripper 3960X3K6K9K12K15KSE +/- 31.26, N = 312234.521. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Hsearch

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: HsearchThreadripper 3960X40K80K120K160K200KSE +/- 582.97, N = 3199421.451. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Forking

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: ForkingThreadripper 3960X20K40K60K80K100KSE +/- 775.10, N = 380851.061. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Matrix MathThreadripper 3960X30K60K90K120K150KSE +/- 505.47, N = 3151388.051. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Glibc Qsort Data Sorting

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc Qsort Data SortingThreadripper 3960X80160240320400SE +/- 1.42, N = 3380.731. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket ActivityThreadripper 3960X4K8K12K16K20KSE +/- 48.18, N = 318734.341. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Apache Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingThreadripper 3960X7K14K21K28K35KSE +/- 49.18, N = 334193.151. (CC) gcc options: -shared -fPIC -O2 -pthread

CppPerformanceBenchmarks

Test: Stepanov Abstraction

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov AbstractionAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X714212835SE +/- 0.01, N = 3SE +/- 0.15, N = 328.3128.301. (CXX) g++ options: -std=c++11 -O3

eSpeak Speech Engine

Text-To-Speech Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak Speech Engine 1.48.04Text-To-Speech SynthesisThreadripper 3960X714212835SE +/- 0.48, N = 327.811. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions

ACES DGEMM

Sustained Floating-Point Rate

OpenBenchmarking.orgGFLOP/s, More Is BetterACES DGEMM 1.0Sustained Floating-Point RateThreadripper 3960X246810SE +/- 0.028924, N = 38.5438871. (CC) gcc options: -O3 -march=native -fopenmp

Renaissance

Test: Apache Spark ALS

OpenBenchmarking.orgms, Fewer Is BetterRenaissance 0.9.0Test: Apache Spark ALSThreadripper 3960X14002800420056007000SE +/- 43.26, N = 86643.08

SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeThreadripper 3960X150300450600750SE +/- 1.06, N = 3714.921. (CC) gcc options: -lm

OSPray

Demo: NASA Streamlines - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: NASA Streamlines - Renderer: SciVisThreadripper 3960X1224364860SE +/- 0.00, N = 1252.63MIN: 43.48 / MAX: 55.56

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondThreadripper 3960X200K400K600K800K1000KSE +/- 601.18, N = 31069837.231. (CC) gcc options: -O2 -lrt" -lrt

Tesseract OCR

Time To OCR 7 Images

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.1.0Time To OCR 7 ImagesThreadripper 3960X612182430SE +/- 0.05, N = 324.14

NAS Parallel Benchmarks

Test / Class: FT.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: FT.CThreadripper 3960X4K8K12K16K20KSE +/- 33.84, N = 317832.391. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

m-queens

Time To Solve

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To SolveThreadripper 3960X612182430SE +/- 0.02, N = 323.281. (CXX) g++ options: -fopenmp -O2 -march=native

Hackbench

Count: 16 - Type: Thread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ThreadThreadripper 3960X510152025SE +/- 0.01, N = 322.961. (CC) gcc options: -lpthread

Tensorflow

Build: Cifar10

OpenBenchmarking.orgSeconds, Fewer Is BetterTensorflow 2017-02-03Build: Cifar10AMD Ryzen Threadripper 3960X 24-Core48121620SE +/- 0.04, N = 317.04

FFTW

Build: Float + SSE - Size: 2D FFT Size 1024

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 1024Threadripper 3960X9K18K27K36K45KSE +/- 199.23, N = 3408971. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Hackbench

Count: 16 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ProcessThreadripper 3960X510152025SE +/- 0.07, N = 322.741. (CC) gcc options: -lpthread

MBW

Test: Memory Copy - Array Size: 4096 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiBThreadripper 3960X4K8K12K16K20KSE +/- 33.30, N = 319697.481. (CC) gcc options: -O3 -march=native

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test TimesThreadripper 3960X2004006008001000SE +/- 10.69, N = 3968

Embree

Binary: Pathtracer ISPC - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: CrownThreadripper 3960X714212835SE +/- 0.02, N = 328.37MIN: 27.81 / MAX: 29.1

Crafty

Elapsed Time

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed TimeThreadripper 3960X2M4M6M8M10MSE +/- 53093.30, N = 390417291. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelThreadripper 3960X510152025SE +/- 0.03, N = 321.061. (CC) gcc options: -lm -lpthread -O3

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: f32Threadripper 3960X0.58411.16821.75232.33642.9205SE +/- 0.03171, N = 32.59611MIN: 2.271. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

Embree

Binary: Pathtracer - Model: Crown

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: CrownThreadripper 3960X714212835SE +/- 0.07, N = 329.77MIN: 29.2 / MAX: 30.55

Tungsten Renderer

Scene: Water Caustic

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Water CausticThreadripper 3960X510152025SE +/- 0.03, N = 319.341. (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 -lpthread -ldl

GIMP

Test: unsharp-mask

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: unsharp-maskThreadripper 3960X510152025SE +/- 0.04, N = 320.51

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 9Threadripper 3960X510152025SE +/- 0.04, N = 320.361. (CC) gcc options: -pthread -fvisibility=hidden -O2

glibc bench

Benchmark: cos

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cosThreadripper 3960X1020304050SE +/- 0.04, N = 342.02

glibc bench

Benchmark: sincos

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sincosThreadripper 3960X3691215SE +/- 0.01, N = 312.14

glibc bench

Benchmark: sin

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinThreadripper 3960X918273645SE +/- 0.34, N = 341.42

ebizzy

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3AMD Ryzen Threadripper 3960X 24-Core500K1000K1500K2000K2500KSE +/- 22054.77, N = 322541961. (CC) gcc options: -pthread -lpthread -O3 -march=native

FFTW

Build: Float + SSE - Size: 1D FFT Size 256

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 256Threadripper 3960X8K16K24K32K40KSE +/- 412.34, N = 15382601. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Embree

Binary: Pathtracer - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer - Model: Asian DragonThreadripper 3960X714212835SE +/- 0.01, N = 332.15MIN: 31.73 / MAX: 32.8

Embree

Binary: Pathtracer ISPC - Model: Asian Dragon

OpenBenchmarking.orgFrames Per Second, More Is BetterEmbree 3.6.1Binary: Pathtracer ISPC - Model: Asian DragonThreadripper 3960X714212835SE +/- 0.02, N = 332.15MIN: 31.68 / MAX: 32.72

Go Benchmarks

Test: build

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: buildThreadripper 3960X4000M8000M12000M16000M20000MSE +/- 83434537.14, N = 319291013759

Selenium

Benchmark: PSPDFKit WASM - Browser: Firefox

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: FirefoxThreadripper 3960X30060090012001500SE +/- 5.46, N = 313241. firefox 70.0.1

dav1d

Video Input: Chimera 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Chimera 1080pThreadripper 3960X130260390520650SE +/- 1.35, N = 3587.81MIN: 448.01 / MAX: 721.981. (CC) gcc options: -pthread

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X48121620SE +/- 0.04, N = 3SE +/- 0.06, N = 316.3616.411. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lXpm -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Tungsten Renderer

Scene: Non-Exponential

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Non-ExponentialThreadripper 3960X0.80191.60382.40573.20764.0095SE +/- 0.10003, N = 153.564221. (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 -lpthread -ldl

Selenium

Benchmark: PSPDFKit WASM - Browser: Google Chrome

OpenBenchmarking.orgScore, Fewer Is BetterSeleniumBenchmark: PSPDFKit WASM - Browser: Google ChromeThreadripper 3960X30060090012001500SE +/- 3.28, N = 315081. chrome 78.0.3904.108

Selenium

Benchmark: Maze Solver - Browser: Firefox

OpenBenchmarking.orgSeconds, Fewer Is BetterSeleniumBenchmark: Maze Solver - Browser: FirefoxThreadripper 3960X0.991.982.973.964.95SE +/- 0.07, N = 34.41. firefox 70.0.1

ParaView

Test: Many Spheres - Resolution: 2560 x 1440

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 2560 x 1440Threadripper 3960X13002600390052006500SE +/- 4.91, N = 35900.23

ParaView

Test: Many Spheres - Resolution: 2560 x 1440

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Many Spheres - Resolution: 2560 x 1440Threadripper 3960X1326395265SE +/- 0.05, N = 358.85

GIMP

Test: auto-levels

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: auto-levelsThreadripper 3960X48121620SE +/- 0.05, N = 317.13

RAMspeed SMP

Type: Triad - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating PointThreadripper 3960X8K16K24K32K40K37623.851. (CC) gcc options: -O3 -march=native

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: f32Threadripper 3960X306090120150SE +/- 1.31, N = 3142.23MIN: 123.191. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

RAMspeed SMP

Type: Average - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerThreadripper 3960X8K16K24K32K40K36961.631. (CC) gcc options: -O3 -march=native

SQLite

Threads / Copies: 1

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.30.1Threads / Copies: 1Threadripper 3960X48121620SE +/- 0.10, N = 315.741. (CC) gcc options: -O2 -lz -lm -ldl -lpthread

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteThreadripper 3960X140K280K420K560K700KSE +/- 5664.15, N = 3658408

RAMspeed SMP

Type: Copy - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating PointThreadripper 3960X8K16K24K32K40K35940.891. (CC) gcc options: -O3 -march=native

Rust Prime Benchmark

Prime Number Test To 200,000,000

OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,000AMD Ryzen Threadripper 3960X 24-Core48121620SE +/- 0.02, N = 315.001. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil

CppPerformanceBenchmarks

Test: Function Objects

OpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Function ObjectsAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X48121620SE +/- 0.02, N = 3SE +/- 0.12, N = 314.6914.681. (CXX) g++ options: -std=c++11 -O3

Timed ImageMagick Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileThreadripper 3960X48121620SE +/- 0.12, N = 314.54

RAMspeed SMP

Type: Scale - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating PointThreadripper 3960X8K16K24K32K40K37097.991. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Add - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating PointThreadripper 3960X9K18K27K36K45K43043.841. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Average - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating PointThreadripper 3960X9K18K27K36K45K40240.981. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Add - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerThreadripper 3960X9K18K27K36K45K43028.441. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Scale - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerThreadripper 3960X8K16K24K32K40K38106.381. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Triad - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: IntegerThreadripper 3960X9K18K27K36K45K43894.261. (CC) gcc options: -O3 -march=native

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerThreadripper 3960X8K16K24K32K40K37204.251. (CC) gcc options: -O3 -march=native

FFTW

Build: Float + SSE - Size: 1D FFT Size 64

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 64Threadripper 3960X4K8K12K16K20KSE +/- 715.56, N = 15189001. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 1D FFT Size 64

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 64Threadripper 3960X2K4K6K8K10KSE +/- 231.46, N = 159362.21. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Selenium

Benchmark: Maze Solver - Browser: Google Chrome

OpenBenchmarking.orgSeconds, Fewer Is BetterSeleniumBenchmark: Maze Solver - Browser: Google ChromeThreadripper 3960X0.91.82.73.64.5SE +/- 0.03, N = 34.01. chrome 78.0.3904.108

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 19Threadripper 3960X3691215SE +/- 0.15, N = 410.231. (CC) gcc options: -O3 -pthread -lz -llzma

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACThreadripper 3960X246810SE +/- 0.013, N = 57.8341. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

Hackbench

Count: 1 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: ProcessThreadripper 3960X0.62151.2431.86452.4863.1075SE +/- 0.027, N = 142.7621. (CC) gcc options: -lpthread

Xsbench

OpenBenchmarking.orgLookups/s, More Is BetterXsbench 2017-07-06Threadripper 3960X1.1M2.2M3.3M4.4M5.5MSE +/- 3935.07, N = 350295281. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm

dav1d

Video Input: Summer Nature 4K

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 4KThreadripper 3960X60120180240300SE +/- 0.85, N = 3291.09MIN: 179.18 / MAX: 309.081. (CC) gcc options: -pthread

GIMP

Test: rotate

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: rotateThreadripper 3960X3691215SE +/- 0.02, N = 312.32

DaCapo Benchmark

Java Test: Tradebeans

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradebeansThreadripper 3960X10002000300040005000SE +/- 13.42, N = 44643

Go Benchmarks

Test: json

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: jsonThreadripper 3960X400K800K1200K1600K2000KSE +/- 13151.09, N = 31901078

Hackbench

Count: 8 - Type: Thread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ThreadThreadripper 3960X3691215SE +/- 0.04, N = 311.671. (CC) gcc options: -lpthread

SVT-AV1

Encoder Mode: Enc Mode 4 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.7Encoder Mode: Enc Mode 4 - Input: 1080pThreadripper 3960X246810SE +/- 0.027, N = 38.0431. (CXX) g++ options: -fPIE -fPIC -pie

Hackbench

Count: 8 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ProcessThreadripper 3960X3691215SE +/- 0.07, N = 311.151. (CC) gcc options: -lpthread

ASKAP

Test: tConvolve OpenMP - Degridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - DegriddingAMD Ryzen Threadripper 3960X 24-Core8001600240032004000SE +/- 0.00, N = 33915.531. (CXX) g++ options: -lpthread

ASKAP

Test: tConvolve OpenMP - Gridding

OpenBenchmarking.orgMillion Grid Points Per Second, More Is BetterASKAP 2018-11-10Test: tConvolve OpenMP - GriddingAMD Ryzen Threadripper 3960X 24-Core10002000300040005000SE +/- 26.85, N = 34617.471. (CXX) g++ options: -lpthread

DaCapo Benchmark

Java Test: Tradesoap

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: TradesoapThreadripper 3960X7001400210028003500SE +/- 29.66, N = 43364

LeelaChessZero

Backend: Random

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.22.0Backend: RandomAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X20K40K60K80K100KSE +/- 557.11, N = 3SE +/- 513.36, N = 31066691069081. (CXX) g++ options: -lpthread

Opus Codec Encoding

WAV, Opus Encode, Opus Decode

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.0.1WAV, Opus Encode, Opus DecodeThreadripper 3960X246810SE +/- 0.013, N = 56.2721. (CC) gcc options: -O3 -ffast-math -fPIE -pie -logg -lm -lopus

glibc bench

Benchmark: asinh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: asinhThreadripper 3960X246810SE +/- 0.00200, N = 38.42052

glibc bench

Benchmark: sinh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sinhThreadripper 3960X246810SE +/- 0.07381, N = 37.82634

glibc bench

Benchmark: log2

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: log2Threadripper 3960X1.31342.62683.94025.25366.567SE +/- 0.00530, N = 35.83717

glibc bench

Benchmark: ffsll

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsllThreadripper 3960X0.39440.78881.18321.57761.972SE +/- 0.00365, N = 31.75307

glibc bench

Benchmark: tanh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanhThreadripper 3960X3691215SE +/- 0.11, N = 310.52

glibc bench

Benchmark: atanh

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: atanhThreadripper 3960X3691215SE +/- 0.00, N = 310.02

glibc bench

Benchmark: sqrt

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtThreadripper 3960X0.48650.9731.45951.9462.4325SE +/- 0.01495, N = 32.16235

glibc bench

Benchmark: modf

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: modfThreadripper 3960X0.49950.9991.49851.9982.4975SE +/- 0.00220, N = 32.21984

glibc bench

Benchmark: ffs

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsThreadripper 3960X0.39580.79161.18741.58321.979SE +/- 0.00277, N = 31.75927

glibc bench

Benchmark: pthread_once

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceThreadripper 3960X0.39240.78481.17721.56961.962SE +/- 0.00112, N = 31.74395

Rodinia

Test: OpenMP LavaMD

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMDThreadripper 3960X3691215SE +/- 0.01, N = 310.101. (CXX) g++ options: -O2 -lOpenCL

Tungsten Renderer

Scene: Hair

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: HairThreadripper 3960X3691215SE +/- 0.02317, N = 39.797371. (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 -lpthread -ldl

FFTW

Build: Stock - Size: 2D FFT Size 1024

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1024Threadripper 3960X2K4K6K8K10KSE +/- 4.47, N = 38097.91. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

DaCapo Benchmark

Java Test: H2

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: H2Threadripper 3960X8001600240032004000SE +/- 28.55, N = 43694

Go Benchmarks

Test: http

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: httpThreadripper 3960X2K4K6K8K10KSE +/- 59.54, N = 38619

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiBThreadripper 3960X2K4K6K8K10KSE +/- 13.80, N = 311380.321. (CC) gcc options: -O3 -march=native

OSPray

Demo: Magnetic Reconnection - Renderer: SciVis

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: SciVisThreadripper 3960X61218243025MIN: 24.39 / MAX: 25.64

x265

H.265 1080p Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.1.2H.265 1080p Video EncodingThreadripper 3960X1530456075SE +/- 0.22, N = 365.711. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Rodinia

Test: OpenMP CFD Solver

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverThreadripper 3960X3691215SE +/- 0.025, N = 39.0371. (CXX) g++ options: -O2 -lOpenCL

NeatBench

Acceleration: CPU

OpenBenchmarking.orgFPS, More Is BetterNeatBench 5Acceleration: CPUAMD Ryzen Threadripper 3960X 24-Core816243240SE +/- 0.18, N = 335.3

SVT-VP9

Tuning: VMAF Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: VMAF Optimized - Input: Bosphorus 1080pThreadripper 3960X80160240320400SE +/- 4.06, N = 13382.221. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

Parboil

Test: OpenMP Stencil

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilThreadripper 3960X246810SE +/- 0.018289, N = 37.2434401. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

GIMP

Test: resize

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.8Test: resizeThreadripper 3960X246810SE +/- 0.135, N = 38.609

Go Benchmarks

Test: garbage

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: garbageThreadripper 3960X150K300K450K600K750KSE +/- 2346.17, N = 3702500

Bork File Encrypter

File Encryption Time

OpenBenchmarking.orgSeconds, Fewer Is BetterBork File Encrypter 1.4File Encryption TimeThreadripper 3960X246810SE +/- 0.021, N = 38.018

NAS Parallel Benchmarks

Test / Class: MG.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: MG.CThreadripper 3960X5K10K15K20K25KSE +/- 41.78, N = 325120.081. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Sunflow Rendering System

Global Illumination + Image Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image SynthesisThreadripper 3960X0.15410.30820.46230.61640.7705SE +/- 0.010, N = 30.685

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Threadripper 3960X246810SE +/- 0.003, N = 37.1171. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm

DaCapo Benchmark

Java Test: Jython

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: JythonThreadripper 3960X8001600240032004000SE +/- 10.28, N = 43963

Darktable

Test: Boat - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Boat - Acceleration: CPU-onlyThreadripper 3960X246810SE +/- 0.046, N = 36.279

FFTW

Build: Float + SSE - Size: 2D FFT Size 512

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 512Threadripper 3960X9K18K27K36K45KSE +/- 137.80, N = 3430491. (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: 1D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 4096Threadripper 3960X13K26K39K52K65KSE +/- 410.08, N = 3588751. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OSPray

Demo: Magnetic Reconnection - Renderer: Path Tracer

OpenBenchmarking.orgFPS, More Is BetterOSPray 1.8.5Demo: Magnetic Reconnection - Renderer: Path TracerThreadripper 3960X70140210280350SE +/- 0.00, N = 12333.33MIN: 166.67 / MAX: 500

Hackbench

Count: 4 - Type: Thread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: ThreadThreadripper 3960X246810SE +/- 0.034, N = 36.0321. (CC) gcc options: -lpthread

MBW

Test: Memory Copy - Array Size: 1024 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 1024 MiBThreadripper 3960X4K8K12K16K20KSE +/- 19.92, N = 319435.381. (CC) gcc options: -O3 -march=native

Hackbench

Count: 4 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: ProcessThreadripper 3960X1.23032.46063.69094.92126.1515SE +/- 0.008, N = 35.4681. (CC) gcc options: -lpthread

OSBench

Test: Create Files

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create FilesThreadripper 3960X3691215SE +/- 0.01, N = 311.541. (CC) gcc options: -lm

dav1d

Video Input: Summer Nature 1080p

OpenBenchmarking.orgFPS, More Is Betterdav1d 0.5.0Video Input: Summer Nature 1080pThreadripper 3960X150300450600750SE +/- 1.15, N = 3677.06MIN: 426.02 / MAX: 738.111. (CC) gcc options: -pthread

Intel Open Image Denoise

Scene: Memorial

OpenBenchmarking.orgImages / Sec, More Is BetterIntel Open Image Denoise 1.0.0Scene: MemorialAMD Ryzen Threadripper 3960X 24-CoreThreadripper 3960X510152025SE +/- 0.03, N = 3SE +/- 0.05, N = 319.7519.59

SVT-AV1

Encoder Mode: Enc Mode 8 - Input: 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 0.7Encoder Mode: Enc Mode 8 - Input: 1080pThreadripper 3960X20406080100SE +/- 0.12, N = 378.791. (CXX) g++ options: -fPIE -fPIC -pie

FFTW

Build: Float + SSE - Size: 1D FFT Size 2048

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 2048Threadripper 3960X13K26K39K52K65KSE +/- 623.77, N = 3611121. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OSBench

Test: Memory Allocations

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory AllocationsThreadripper 3960X1632486480SE +/- 0.15, N = 370.601. (CC) gcc options: -lm

OSBench

Test: Create Processes

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ProcessesThreadripper 3960X918273645SE +/- 0.55, N = 341.041. (CC) gcc options: -lm

OSBench

Test: Launch Programs

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Launch ProgramsThreadripper 3960X1122334455SE +/- 0.47, N = 348.151. (CC) gcc options: -lm

OSBench

Test: Create Threads

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create ThreadsThreadripper 3960X510152025SE +/- 0.25, N = 320.841. (CC) gcc options: -lm

ParaView

Test: Wavelet Contour - Resolution: 2560 x 1440

OpenBenchmarking.orgMiPolys / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 2560 x 1440Threadripper 3960X6001200180024003000SE +/- 1.76, N = 32578.93

ParaView

Test: Wavelet Contour - Resolution: 2560 x 1440

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Contour - Resolution: 2560 x 1440Threadripper 3960X50100150200250SE +/- 0.17, N = 3247.47

Git

Time To Complete Common Git Commands

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git CommandsThreadripper 3960X1.07212.14423.21634.28845.3605SE +/- 0.035, N = 34.7651. git version 2.20.1

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 512 MiBThreadripper 3960X2K4K6K8K10KSE +/- 6.27, N = 311306.181. (CC) gcc options: -O3 -march=native

FFTW

Build: Stock - Size: 1D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 4096Threadripper 3960X2K4K6K8K10KSE +/- 31.06, N = 38818.81. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 2D FFT Size 256

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 256Threadripper 3960X2K4K6K8K10KSE +/- 8.89, N = 38674.11. (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 256

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 256Threadripper 3960X9K18K27K36K45KSE +/- 310.57, N = 3426161. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

N-Queens

Elapsed Time

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed TimeThreadripper 3960X1.00552.0113.01654.0225.0275SE +/- 0.012, N = 34.4691. (CC) gcc options: -static -fopenmp -O3 -march=native

NAS Parallel Benchmarks

Test / Class: EP.C

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.4Test / Class: EP.CThreadripper 3960X5001000150020002500SE +/- 5.95, N = 32208.111. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi2. Open MPI 3.1.3

Tungsten Renderer

Scene: Volumetric Caustic

OpenBenchmarking.orgSeconds, Fewer Is BetterTungsten Renderer 0.2.2Scene: Volumetric CausticThreadripper 3960X0.93521.87042.80563.74084.676SE +/- 0.00428, N = 34.156461. (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 -lpthread -ldl

Darktable

Test: Masskrug - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Masskrug - Acceleration: CPU-onlyThreadripper 3960X0.76551.5312.29653.0623.8275SE +/- 0.027, N = 33.402

FFTW

Build: Float + SSE - Size: 1D FFT Size 1024

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 1024Threadripper 3960X13K26K39K52K65KSE +/- 370.51, N = 3599371. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 1D FFT Size 256

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 256Threadripper 3960X2K4K6K8K10KSE +/- 12.22, N = 38883.81. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 2D FFT Size 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 32Threadripper 3960X2K4K6K8K10KSE +/- 17.13, N = 3111131. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Bullet Physics Engine

Test: Raytests

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: RaytestsThreadripper 3960X0.47570.95141.42711.90282.3785SE +/- 0.004788, N = 32.1143481. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

FFTW

Build: Stock - Size: 2D FFT Size 512

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 512Threadripper 3960X2K4K6K8K10KSE +/- 17.50, N = 38684.61. (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: 1D FFT Size 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 32Threadripper 3960X3K6K9K12K15KSE +/- 208.40, N = 4150421. (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 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 32Threadripper 3960X10K20K30K40K50KSE +/- 88.57, N = 3461231. (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: 1D FFT Size 512

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 512Threadripper 3960X11K22K33K44K55KSE +/- 123.47, N = 3512401. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 1D FFT Size 32

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 32Threadripper 3960X2K4K6K8K10KSE +/- 5.51, N = 3112371. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Hackbench

Count: 2 - Type: Thread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: ThreadThreadripper 3960X0.84061.68122.52183.36244.203SE +/- 0.057, N = 33.7361. (CC) gcc options: -lpthread

FFTW

Build: Stock - Size: 1D FFT Size 2048

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2048Threadripper 3960X2K4K6K8K10KSE +/- 21.61, N = 39048.11. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Smallpt

Global Illumination Renderer; 128 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesThreadripper 3960X0.82691.65382.48073.30764.1345SE +/- 0.005, N = 33.6751. (CXX) g++ options: -fopenmp -O3

FFTW

Build: Stock - Size: 2D FFT Size 128

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 128Threadripper 3960X2K4K6K8K10KSE +/- 14.00, N = 38902.31. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Darktable

Test: Server Rack - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Rack - Acceleration: CPU-onlyThreadripper 3960X0.02930.05860.08790.11720.1465SE +/- 0.002, N = 150.130

FFTW

Build: Stock - Size: 1D FFT Size 128

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 128Threadripper 3960X2K4K6K8K10KSE +/- 77.36, N = 38569.21. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Hackbench

Count: 2 - Type: Process

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: ProcessThreadripper 3960X0.7941.5882.3823.1763.97SE +/- 0.014, N = 33.5291. (CC) gcc options: -lpthread

Darktable

Test: Server Room - Acceleration: CPU-only

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.6.0Test: Server Room - Acceleration: CPU-onlyThreadripper 3960X0.50451.0091.51352.0182.5225SE +/- 0.016, N = 32.242

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video EncodingThreadripper 3960X4080120160200SE +/- 1.86, N = 3193.761. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

Optcarrot

Optimized Benchmark

OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized BenchmarkThreadripper 3960X20406080100SE +/- 0.64, N = 4106.881. ruby 2.5.5p157 (2019-03-15 revision 67260) [x86_64-linux-gnu]

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: f32Threadripper 3960X0.64441.28881.93322.57763.222SE +/- 0.01436, N = 32.86390MIN: 2.451. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl

FFTW

Build: Float + SSE - Size: 2D FFT Size 128

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 128Threadripper 3960X10K20K30K40K50KSE +/- 237.97, N = 3469701. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 1D FFT Size 1024

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1024Threadripper 3960X2K4K6K8K10KSE +/- 5.17, N = 39356.21. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

Hackbench

Count: 1 - Type: Thread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: ThreadThreadripper 3960X0.64311.28621.92932.57243.2155SE +/- 0.030, N = 32.8581. (CC) gcc options: -lpthread

MBW

Test: Memory Copy - Array Size: 512 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 512 MiBThreadripper 3960X4K8K12K16K20KSE +/- 62.41, N = 319400.431. (CC) gcc options: -O3 -march=native

FFTW

Build: Stock - Size: 2D FFT Size 64

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 64Threadripper 3960X2K4K6K8K10KSE +/- 21.91, N = 39585.41. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

FFTW

Build: Stock - Size: 1D FFT Size 512

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 512Threadripper 3960X2K4K6K8K10KSE +/- 39.54, N = 39114.01. (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: 1D FFT Size 128

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 128Threadripper 3960X6K12K18K24K30KSE +/- 98.24, N = 3274601. (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 64

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 64Threadripper 3960X10K20K30K40K50KSE +/- 259.03, N = 3477331. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

SVT-VP9

Tuning: Visual Quality Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: Visual Quality Optimized - Input: Bosphorus 1080pThreadripper 3960X70140210280350SE +/- 2.33, N = 3326.411. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

FFTE

Test: N=256, 1D Complex FFT Routine

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 6.0Test: N=256, 1D Complex FFT RoutineThreadripper 3960X2K4K6K8K10KSE +/- 86.87, N = 39627.341. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceThreadripper 3960X300K600K900K1200K1500KSE +/- 2224.51, N = 513414121. (CC) gcc options: -O3 -march=native

SVT-VP9

Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 0.1Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080pThreadripper 3960X90180270360450SE +/- 2.37, N = 3392.871. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm

ParaView

Test: Wavelet Volume - Resolution: 2560 x 1440

OpenBenchmarking.orgMiVoxels / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 2560 x 1440Threadripper 3960X6001200180024003000SE +/- 15.86, N = 32811.52

ParaView

Test: Wavelet Volume - Resolution: 2560 x 1440

OpenBenchmarking.orgFrames / Sec, More Is BetterParaView 5.4.1Test: Wavelet Volume - Resolution: 2560 x 1440Threadripper 3960X4080120160200SE +/- 0.99, N = 3175.72

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total TimeThreadripper 3960X0.38020.76041.14061.52081.901SE +/- 0.0039, N = 31.68991. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

Parboil

Test: OpenMP CUTCP

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPThreadripper 3960X0.28450.5690.85351.1381.4225SE +/- 0.000632, N = 31.2646571. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

MBW

Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 128 MiBThreadripper 3960X2K4K6K8K10KSE +/- 15.80, N = 310863.421. (CC) gcc options: -O3 -march=native

MBW

Test: Memory Copy - Array Size: 128 MiB

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 128 MiBThreadripper 3960X2K4K6K8K10KSE +/- 18.64, N = 310893.681. (CC) gcc options: -O3 -march=native

CloverLeaf

Lagrangian-Eulerian Hydrodynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterCloverLeafLagrangian-Eulerian HydrodynamicsThreadripper 3960X0.18450.3690.55350.7380.9225SE +/- 0.00, N = 30.821. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp

ctx_clock

Context Switch Time

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeThreadripper 3960X306090120150152

Bullet Physics Engine

Test: Convex Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex TrimeshThreadripper 3960X0.21490.42980.64470.85961.0745SE +/- 0.001348, N = 30.9551881. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Prim Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim TrimeshThreadripper 3960X0.17970.35940.53910.71880.8985SE +/- 0.000720, N = 30.7987751. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 136 Ragdolls

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 RagdollsThreadripper 3960X0.49090.98181.47271.96362.4545SE +/- 0.002207, N = 32.1816231. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Convex

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 ConvexThreadripper 3960X0.85811.71622.57433.43244.2905SE +/- 0.01304, N = 33.813671. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Stack

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 StackThreadripper 3960X0.9251.852.7753.74.625SE +/- 0.006196, N = 34.1109411. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 3000 Fall

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 FallThreadripper 3960X0.76881.53762.30643.07523.844SE +/- 0.005941, N = 33.4169411. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

HPC Challenge

Test / Class: Max Ping Pong Bandwidth

OpenBenchmarking.orgMB/s, More Is BetterHPC Challenge 1.5.0Test / Class: Max Ping Pong BandwidthThreadripper 3960X5K10K15K20K25KSE +/- 366.52, N = 322107.911. (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 BandwidthThreadripper 3960X0.75691.51382.27073.02763.7845SE +/- 0.00987, N = 33.364001. (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 LatencyThreadripper 3960X0.10280.20560.30840.41120.514SE +/- 0.00045, N = 30.456831. (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 AccessThreadripper 3960X0.03220.06440.09660.12880.161SE +/- 0.00070, N = 30.142921. (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 TriadThreadripper 3960X0.410.821.231.642.05SE +/- 0.00309, N = 31.822281. (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-PtransThreadripper 3960X1.24652.4933.73954.9866.2325SE +/- 0.01609, N = 35.540221. (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-DGEMMThreadripper 3960X714212835SE +/- 0.45, N = 331.641. (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.orgGFLOP/s, More Is BetterHPC Challenge 1.5.0Test / Class: G-FfteThreadripper 3960X3691215SE +/- 0.19, N = 310.731. (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-FfteThreadripper 3960X3691215SE +/- 0.19, N = 310.731. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops2. ATLAS + Open MPI 3.1.3

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: AddThreadripper 3960X8K16K24K32K40KSE +/- 12.82, N = 536666.41. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: TriadThreadripper 3960X8K16K24K32K40KSE +/- 19.57, N = 536725.11. (CC) gcc options: -O3 -march=native -fopenmp

Stream

Type: Scale

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: ScaleThreadripper 3960X7K14K21K28K35KSE +/- 16.43, N = 533514.61. (CC) gcc options: -O3 -march=native -fopenmp


Phoronix Test Suite v10.8.5