AMD EPYC vs. Intel Xeon vs. POWER9 Linux Benchmarks

AMD EPYC vs. Intel Xeon open-source server benchmarks on Ubuntu Linux. Latest as of November 2018. Tests by Michael Larabel for a future article.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1811168-SK-EPYCPOWER73
Jump To Table - Results

View

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

Limit displaying results to tests within:

Audio Encoding 3 Tests
Bioinformatics 2 Tests
C++ Boost Tests 2 Tests
Chess Test Suite 6 Tests
Timed Code Compilation 6 Tests
C/C++ Compiler Tests 28 Tests
Compression Tests 5 Tests
CPU Massive 65 Tests
Creator Workloads 24 Tests
Cryptography 5 Tests
Database Test Suite 3 Tests
Encoding 7 Tests
Game Development 2 Tests
HPC - High Performance Computing 10 Tests
Imaging 5 Tests
Java 4 Tests
Common Kernel Benchmarks 7 Tests
Machine Learning 2 Tests
Memory Test Suite 5 Tests
Multi-Core 40 Tests
NVIDIA GPU Compute 4 Tests
OpenCL 3 Tests
Productivity 2 Tests
Programmer / Developer System Benchmarks 10 Tests
Python 2 Tests
Raytracing 3 Tests
Renderers 9 Tests
Rust Tests 2 Tests
Scientific Computing 5 Tests
Server 8 Tests
Server CPU Tests 35 Tests
Single-Threaded 32 Tests
Video Encoding 4 Tests
Common Workstation Benchmarks 7 Tests

Statistics

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

Graph Settings

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

Additional Graphs

Show Perf Per Core/Thread Calculation Graphs Where Applicable
Show Perf Per Clock Calculation Graphs Where Applicable

Multi-Way Comparison

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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
EPYC 7251
November 13 2018
  15 Hours, 35 Minutes
EPYC 7351P
November 12 2018
  12 Hours, 2 Minutes
EPYC 7401P
November 11 2018
  11 Hours, 45 Minutes
EPYC 7551
November 08 2018
  12 Hours, 10 Minutes
EPYC 7601
November 10 2018
  11 Hours, 23 Minutes
2 x EPYC 7601
November 09 2018
  12 Hours, 1 Minute
Xeon Silver 4108
November 14 2018
  19 Hours, 32 Minutes
2 x Xeon Gold 6138
November 14 2018
  9 Hours, 44 Minutes
2 x 22-Core POWER9 176 Threads
November 15 2018
  10 Hours, 40 Minutes
Invert Hiding All Results Option
  12 Hours, 46 Minutes

Only show results where is faster than
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):


AMD EPYC vs. Intel Xeon vs. POWER9 Linux BenchmarksProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkAudioOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionEPYC 7251EPYC 7351PEPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601Xeon Silver 41082 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsAMD EPYC 7251 8-Core @ 2.10GHz (8 Cores / 16 Threads)TYAN B8026T70AE24HR (V1.02.B10 BIOS)AMD Family 17h129024MB280GB INTEL SSDPE21D280GAllvmpipe 126GBVE228Broadcom NetXtreme BCM5720 Gigabit PCIeUbuntu 18.104.19.1-041901-generic (x86_64)GNOME Shell 3.30.1X Server 1.20.1modesetting 1.20.13.3 Mesa 18.2.2 (LLVM 7.0 128 bits)GCC 8.2.0ext41920x1080AMD EPYC 7351P 16-Core @ 2.40GHz (16 Cores / 32 Threads)AMD EPYC 7401P 24-Core @ 2.00GHz (24 Cores / 48 Threads)AMD EPYC 7551 32-Core @ 2.00GHz (32 Cores / 64 Threads)AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads)2 x AMD EPYC 7601 32-Core @ 3.07GHz (64 Cores / 128 Threads)Dell 02MJ3T (1.2.5 BIOS)516096MBMatrox Matrox G200eW3Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMAIntel Xeon Silver 4108 @ 3.00GHz (8 Cores / 16 Threads)TYAN S7100AG2NR (V3.03 BIOS)Intel Sky Lake-E DMI3 Registers23552MBSamsung SSD 970 EVO 250GBASPEED ASPEED FamilyRealtek ALC892Intel I350 Gigabit Connection3.3 Mesa 18.2.2 (LLVM 7.0 256 bits)2 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads)TYAN S7106 (V1.01 BIOS)96256MB280GB INTEL SSDPE21D280GAllvmpipe 93GBIntel I210 Gigabit ConnectionPOWER9 altivec supported @ 3.80GHz (44 Cores / 176 Threads)PowerNV T2P9D01 REV 1.0165536MBASPEED ASPEED FamilyBroadcom NetXtreme BCM5719 Gigabit PCIe4.19.1-041901-generic (ppc64le)OpenBenchmarking.orgEnvironment Details- EPYC 7251: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- EPYC 7351P: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- EPYC 7401P: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- EPYC 7551: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- EPYC 7601: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- 2 x EPYC 7601: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- Xeon Silver 4108: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- 2 x Xeon Gold 6138: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- 2 x 22-Core POWER9 176 Threads: CXXFLAGS=-O3-mtune=power9-mcpu=power9 CFLAGS=-O3-mtune=power9-mcpu=power9Compiler Details- EPYC 7251: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - EPYC 7351P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - EPYC 7401P: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - EPYC 7551: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - EPYC 7601: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - 2 x EPYC 7601: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - Xeon Silver 4108: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - 2 x Xeon Gold 6138: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++ --enable-libmpx --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none --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 --with-tune=generic --without-cuda-driver -v - 2 x 22-Core POWER9 176 Threads: --build=powerpc64le-linux-gnu --disable-libphobos --disable-multilib --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc=auto --enable-plugin --enable-secureplt --enable-shared --enable-targets=powerpcle-linux --enable-threads=posix --host=powerpc64le-linux-gnu --program-prefix=powerpc64le-linux-gnu- --target=powerpc64le-linux-gnu --with-cpu=power8 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-long-double-128 -v Disk Details- NONE / errors=remount-ro,relatime,rwProcessor Details- EPYC 7251: Scaling Governor: acpi-cpufreq ondemand- EPYC 7351P: Scaling Governor: acpi-cpufreq ondemand- EPYC 7401P: Scaling Governor: acpi-cpufreq ondemand- EPYC 7551: Scaling Governor: acpi-cpufreq ondemand- EPYC 7601: Scaling Governor: acpi-cpufreq ondemand- Xeon Silver 4108: Scaling Governor: intel_pstate powersave- 2 x Xeon Gold 6138: Scaling Governor: intel_pstate powersave- 2 x 22-Core POWER9 176 Threads: Scaling Governor: powernv-cpufreq ondemandPython Details- Python 2.7.15+ + Python 3.6.7Security Details- EPYC 7251: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- EPYC 7351P: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- EPYC 7401P: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- EPYC 7551: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- EPYC 7601: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- 2 x EPYC 7601: __user pointer sanitization + Full AMD retpoline IBPB + SSB disabled via prctl and seccomp- Xeon Silver 4108: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- 2 x Xeon Gold 6138: KPTI + __user pointer sanitization + Full generic retpoline IBPB IBRS_FW + SSB disabled via prctl and seccomp + PTE Inversion; VMX: conditional cache flushes SMT vulnerable

EPYC 7251EPYC 7351PEPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601Xeon Silver 41082 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsLogarithmic Result OverviewPhoronix Test SuitePOV-RayStress-NGSmallptStockfishVP9 libvpx EncodingBlenderPrimesieveOpenSSL7-Zip CompressionTimed Linux Kernel CompilationTimed LLVM CompilationFLAC Audio EncodingParboilMencoderx264RodiniaBork File EncrypterPostgreSQL pgbenchTimed ImageMagick CompilationZstd CompressionSunflow Rendering SystemMemcached mcperfOptcarrotSciMarkR BenchmarkTinymembenchSwetRust Prime BenchmarkC-RaySudokutPHPBenchDaCapo BenchmarkRust MandelbrotJava SciMarkCryptsetupNode.js Octane BenchmarkAOBenchBullet Physics EngineGIMPRediseSpeak Speech EngineGraphicsMagickLAME MP3 EncodingPyBenchGNU MPClibjpeg-turbo tjbenchdcrawGNU Octave BenchmarkBYTE Unix BenchmarkApache BenchmarkGNU GMP GMPbenchTimed Apache CompilationTesseract OCRTimed MAFFT AlignmentlzbenchGitCacheBenchGzip CompressionGnuPGFhourstonesMinionGo BenchmarksFFTWCompile BenchOSBench

AMD EPYC vs. Intel Xeon vs. POWER9 Linux Benchmarksmysqlslap: 64numpy: blender: Barbershop - CPU-Onlyblender: Classroom - CPU-Onlyvpxenc: vpxencopm-git: Flow MPI Extra - 16blender: Pabellon Barcelona - CPU-Onlyfftw: Float + SSE - 2D FFT Size 4096build-gcc: Time To Compileradiance: Serialblender: Barbershop - CPU-Onlyblender: Fishy Cat - CPU-Onlyopm-git: Flow MPI Extra - 32fftw: Stock - 2D FFT Size 4096tinymembench: Standard Memcpycompress-rar: Linux Source Tree Archiving To RARblender: BMW27 - CPU-Onlyasmfish: 1024 Hash Memory, 26 Depthfhourstones: Complex Connect-4 Solvingblender: Pabellon Barcelona - CPU-Onlyhint: FLOATminion: Quasigrouppgbench: Buffer Test - Single Thread - Read Onlygmpbench: Total Timepgbench: Buffer Test - Normal Load - Read Onlyfftw: Float + SSE - 2D FFT Size 2048cachebench: Writecachebench: Read / Modify / Writecachebench: Readbyte: Dhrystone 2mbw: Memory Copy, Fixed Block Size - 8192 MiBblender: Classroom - CPU-Onlyopm-git: Flow MPI Norne - 32mcperf: Addbuild-llvm: Time To Compilebuild-linux-kernel: Time To Compileradiance: SMP Parallelstockfish: Total Timembw: Memory Copy - 8192 MiBcompress-7zip: Compress Speed Testnamd: ATPase Simulation - 327,506 Atomsminion: Solitairemcperf: Prependblender: Fishy Cat - CPU-Onlymcperf: Setgraphics-magick: Noise-Gaussianbuild-php: Time To Compilerbenchmark: opm-git: Flow MPI Norne - 16indigobench: Supercarstress-ng: Context Switchingmcperf: Replacemcperf: Appendopm-git: Flow MPI Norne - 64aobench: 2048 x 2048 - Total Timeindigobench: Bedroommcperf: Getmbw: Memory Copy, Fixed Block Size - 4096 MiBv-ray: CPUminion: Gracefulfftw: Stock - 2D FFT Size 2048graphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: HWB Color Spacerust-mandel: Time To Complete Serial/Parallel Mandelbrotapache: Static Web Page Servingmbw: Memory Copy - 4096 MiBblender: BMW27 - CPU-Onlym-queens: Time To Solvemcperf: Deletempcbench: Multi-Precision Benchmarknpb: LU.Cstress-ng: Socket Activityc-ray: Total Time - 4K, 16 Rays Per Pixellzbench: XZ 0 - Compressionx265: H.265 Video Encodingcompress-gzip: Linux Source Tree Archiving To .tar.gzjohn-the-ripper: Traditional DESebizzy: rodinia: OpenMP Streamclusterbuild-imagemagick: Time To Compiletesseract-ocr: Time To OCR 7 Imagesespeak: Text-To-Speech Synthesispovray: Trace Timejava-scimark2: Compositesunflow: Global Illumination + Image Synthesiscompilebench: Compilecryptsetup: PBKDF2-sha512octave-benchmark: pybench: Total For Average Test Timeslzbench: Brotli 0 - Compressionlzbench: Libdeflate 1 - Compressioncrafty: Elapsed Timelzbench: Zstd 1 - Compressionnode-octane: fftw: Float + SSE - 2D FFT Size 1024y-cruncher: Calculating 500M Pi Digitscompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19build-apache: Time To Compilestress-ng: CPU Stressaircrack-ng: stress-ng: Matrix Mathstress-ng: Cryptostress-ng: Vector Mathstream: Copyswet: Averagescimark2: Compositemencoder: AVI To LAVCjohn-the-ripper: Blowfishluajit: Compositeencode-flac: WAV To FLACrodinia: OpenMP LavaMDgimp: auto-levelsphpbench: PHP Benchmark Suitego-benchmark: buildredis: SADDramspeed: Copy - Integerramspeed: Add - Integerramspeed: Average - Integerrust-prime: Prime Number Test To 200,000,000ramspeed: Scale - Floating Pointramspeed: Average - Floating Pointgimp: rotateramspeed: Triad - Floating Pointramspeed: Add - Floating Pointramspeed: Copy - Floating Pointprimesieve: 1e12 Prime Number Generationopenssl: RSA 4096-bit Performancegnupg: Linux 4.3 Package File Encryptionredis: SETsudokut: Total Timedcraw: RAW To PPM Image Conversionnpb: EP.Cmbw: Memory Copy, Fixed Block Size - 1024 MiBx264: H.264 Video Encodingredis: LPUSHfftw: Stock - 2D FFT Size 1024gimp: resizeredis: GETbork: File Encryption Timefftw: Float + SSE - 1D FFT Size 4096ffmpeg: H.264 HD To NTSC DVdacapobench: Jythonencode-mp3: WAV To MP3mbw: Memory Copy - 1024 MiBmafft: Multiple Sequence Alignmentn-queens: Elapsed Timefftw: Float + SSE - 1D FFT Size 2048sysbench: CPUhmmer: Pfam Database Searchfftw: Float + SSE - 2D FFT Size 512darktable: Masskrug - CPU-onlymbw: Memory Copy, Fixed Block Size - 512 MiBencode-ogg: WAV To Oggsmallpt: Global Illumination Renderer; 128 Samplesgit: Time To Complete Common Git Commandsfftw: Float + SSE - 1D FFT Size 1024osbench: Memory Allocationsfftw: Float + SSE - 1D FFT Size 32fftw: Stock - 1D FFT Size 4096tjbench: Decompression Throughputpolybench-c: Correlation Computationpolybench-c: Covariance Computationbullet: Raytestsfftw: Float + SSE - 1D FFT Size 256osbench: Create Filesnpb: LU.Ambw: Memory Copy - 512 MiBfftw: Float + SSE - 2D FFT Size 256optcarrot: Optimized Benchmarkfftw: Float + SSE - 1D FFT Size 512fftw: Stock - 2D FFT Size 512fftw: Stock - 1D FFT Size 2048tachyon: Total Timefftw: Float + SSE - 1D FFT Size 64fftw: Float + SSE - 2D FFT Size 32fftw: Stock - 2D FFT Size 256parboil: OpenMP CUTCPpolybench-c: 3 Matrix Multiplicationsfftw: Stock - 1D FFT Size 1024fftw: Stock - 2D FFT Size 32fftw: Float + SSE - 1D FFT Size 128fftw: Stock - 2D FFT Size 64fftw: Float + SSE - 2D FFT Size 128fftw: Float + SSE - 2D FFT Size 64fftw: Stock - 1D FFT Size 64fftw: Stock - 1D FFT Size 512fftw: Stock - 2D FFT Size 128tscp: AI Chess Performancefftw: Stock - 1D FFT Size 128fftw: Stock - 1D FFT Size 256fftw: Stock - 1D FFT Size 32glibc-bench: singlibc-bench: cosmbw: Memory Copy, Fixed Block Size - 128 MiBglibc-bench: tanhglibc-bench: pthread_onceglibc-bench: ffsglibc-bench: ffsllglibc-bench: sqrtmbw: Memory Copy - 128 MiBjava-scimark2: Jacobi Successive Over-Relaxationjava-scimark2: Dense LU Matrix Factorizationjava-scimark2: Sparse Matrix Multiplyjava-scimark2: Fast Fourier Transformjava-scimark2: Monte Carlobullet: Convex Trimeshbullet: Prim Trimeshbullet: 136 Ragdollsbullet: 1000 Convexbullet: 1000 Stackbullet: 3000 Fallscimark2: Jacobi Successive Over-Relaxationscimark2: Dense LU Matrix Factorizationscimark2: Sparse Matrix Multiplyscimark2: Fast Fourier Transformscimark2: Monte Carloluajit: Jacobi Successive Over-Relaxationluajit: Dense LU Matrix Factorizationluajit: Sparse Matrix Multiplyluajit: Fast Fourier Transformluajit: Monte Carlostream: Addstream: Triadstream: Scalecompilebench: Read Compiled TreeEPYC 7251EPYC 7351PEPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601Xeon Silver 41082 x Xeon Gold 61382 x 22-Core POWER9 176 Threads42187861881841106311.0589111704146011281798496.5248117215190347.991759792795259692373891501641151535701230391231519802384952008304846837091706.1622956640116.953471628240211660306273.0852598.1026623466.162344210599.040.29311.613412470252602603849.650.78500396878116.8663.79485011112815517118270.691536411730335.0699.1240913559025279565280.34237.1653.144318000046129526.7349.9146.4044.1571.2318022.30140184928722.7516683061585146918292256861448653.4226.9933.932050110074184616091847783409485004712134724.981010787713.6651.1523.7636286623894546930138456426326306032655457.82237302729721.9427950327232757343.01124218.99112318620.3017.76241684755.91986285541814.48154652513.492455111.24743511.59118284.0719.4224724121019.202075410.2168858.3615.357.932430298.24863571791326.056.043.481862221.0323683118912073054.9922612631572767.69120622328468254.954.32770396481457970492269023052715774587089773139682373899225143144606836.205.095.085.084.9511908121934881901128611141.491.273.806.207.056.20152622932203206504128417138292173439432894020837492136606891694387450311.142734151200710141123853237.6048857373152170.963739901097084442374853311641266135732495781402319858385012008298829787098342.862617634162.803393307541212553600381.5075595.9426435221.452497313581.560.390882.663.556568333267002648749.161.6945533700759.2862.40530113915316917118759.501644411991164.4349.77429335603448151099240.342310.6352.208363666793017815.0933.4745.5244.1736.6917801.32143985065921.1216683061565214390292262281889429.1815.8030.294189219588418532153691086857479366975180524.4419422102613.6426.0623.2136216923606784874147451028253337742731329.07236052867420.4928513332782681120.61248319.45130826320.5917.81481697793.661064769600113.48171653213.442440310.68707511.59126073.439.7324743241528.37211676.9870408.387.927.862433196.68885171511326.006.013.471882720.4943353126672073955.7122565685872103.94121652328769692.823.88770795911463870712260923048715174627053772047677273467211164164616441.415.825.815.815.6512660122034961899117011141.481.263.445.926.425.551530448623022035041289243483822434599688100146867882169555856185069740211.122703341239510901084672193.7549947404152139.2749280378101243512456725571581366837003175361385020532398422077306697707127272.912697528252.903294354157912509776651.2121592.5528955181.962645514977.520.445575.994.648529514298812889347.452.2066800706248.1460.28521515416717917619354.561592312613132.7435.86543995780561071339928.712411.3049.06107115000111463117.2530.8844.9842.7128.9618591.13147187822421.1516153191625371574303273911956123.0415.0629.4857973079210335644945119084408505076073185923.5623048106613.1819.8123.0737274523648119496153169528445340642683922.65234862910120.1828664324652840016.83350318.74131866519.9217.256906994106.131107291624913.23173123213.022507510.70681311.20126893.656.8425430349018.03218806.4270528.165.797.632537296.19946373511375.775.763.351949019.9960871127232147556.7923368705574742.86127072407571442.363.87796699711516672892345223857741177627256800096695075979537132132619533.334.694.684.684.5512729126235791967133311551.441.213.325.706.175.36158246422342208521133425438682293569693697224850762207857381454930811.57398259122721087527155.9049917484149110.1763302402102932762436355821581449937044074531274420578399082081314226116509209.4693.012558424743.983235630869112356851230.9333792.4237074146.342525015877.050.489280.905.6010765409263992619147.332.8155388700139.5060.19512716317218217819753.161572511253105.3628.35613245810367421660823.112311.0848.37137931000117821921.4829.7744.5042.6223.0118631.25144387919322.6616143191635431520305272641794421.5614.6730.26736838667132994566364348506969513186923.5526621107113.1415.4424.0737164523875872285159490417.02217442453120.1227361319742734712.93436218.39131039219.9117.18835714499.501119292580313.48186955112.872551410.83694211.18128673.955.5825605422398.23219256.4971458.074.687.502514994.89941074511385.825.803.341945119.5554846129452157457.3523496712075222.37127172412572141.963.72799999971517572832066323888741177247255803842710776649560132132627833.344.694.684.684.5512985126435951970133011551.431.213.315.696.165.33158646402385210523133625648682313572158607805602752329612.252632481303310381014504149.6026652267483145106.2466907463106082652612106131491480539413968411476121909424972216334744687292201.9390.503078323642.983155700807312634912200.9088587.4250405139.912903016573.190.463875.745.9711160061417782984344.472.9461957715038.9056.76578117018119118720649.991636312647101.9327.22634996140599691739021.972511.7045.51136821857113906818.3128.0242.4040.1422.6119901.02155193902820.9215143391735710603325292422045919.3314.0028.8677004073613744559186869182083528874816194022.1127591113112.3715.3922.9739966022955552367165688627113315612661315.63233882885919.1428314315712801412.70455417.36136785918.7816.158927100106.751197469658712.86183839612.232723310.51674310.51127223.455.2927240447227.92233686.0771437.614.517.152694693.48998278791475.475.483.142064118.8870764127492278160.7425143754579842.37134202566677071.853.6685121062616184778125024254177894823077758531277505809110169136137625835.194.834.824.824.7012807134638572097142312301.341.143.115.355.845.05168847962441219556142226959182383809363293875826722334442803576630915212.2219013412991821101632388.131655367804110860.5411944826110350141262007933147151453940518285133642191542505221633652455782498.7968.354473014926.46310100932062125631302390.4582887.904485583.634118918470.360.472856.375.4417118926455764505258.7244.513.3453996765024.5756.81590318218819418820847.47159551257758.0213.636394461901148772545811.212513.5045.48258237667172679920.6423.2743.9940.1412.8219911.27155993289820.9015183421745689725326295431901815.6113.4525.94158088187129341911952136062158697491869221194222.0471591112412.348.1222.393979292205870568216525772974233834295048.14259493102617.802998335322305806.34922517.23139631218.0716.3317777600131.751215090662312.34190282612.2126877643710.51127573.452.7827128887496.73233397.1375997.572.577.102698292.47980278781465.465.443.142071819.55133328128392292059.8224876750179671.48134582570476881.903.6485071064016160765225097255097790829077768547357548818710163136137687534.504.834.824.824.7012943134638612098141312351.341.143.125.355.815.061686484423982275561423267289924838017409117607615469123791072039132910.79109414107174410251892692.4550709104148439.39151029901011011572971733991491507638391565041446220901342092533306562788086944.2849494736134.05361127172828468280113.8043391.8855171651.914929286102.630.28991.663229231545265468643.180.69813178067138.0766.9852388911014217617682.76186088470408.69177.57816607073178363314121.782820.1149.652778566721114821.1257.2339.6038.46109.4317802.421217114020025.6114053001666006573298297391752456.5023.1435.892208354029801241163795526995827191323.368005108211.4971.7026.0547973023329557382165494925452258572554523.03250522549722.8925636256552555547.66128617.82139167713.8315.94259803135.481381396566016.4919413199.903027018.34527812.3283764.8530.2332149964214.32185538.88797420.497.453867899.491183073161337.117.103.292540917.981917384531931092.9135404644073429.78126113057565787.804.4675681014016347827722949258789507783373779602217879758910179117117798930.964.223.633.639.98852211544245166311027371.451.223.305.705.795.26151147552224411661112526229583323754916949018445602149989545138140723613.91238195167041021832374125.311965688615311884.0681933755128112043666991911201780547105845541880525798422183125378432575125164.6284.255699817233.942596981555947801379140.6511875.0766549117.625673818060.290.430875.507.8021250062674736737635.703.5896790511331.5054.45591918219720820822648.1322360479276.8428.10974518713768681897630.703334.8938.9015478433396982413.2922.8333.5731.3219.0221770.991685140459923.4711303592007403335359367592322012.6610.9725.0413547217318620376477130443614121047244618.724869113569.2813.2823.705920042116006684219689232997730552292654.48234572659220.712678526862307028.88774514.42178417211.1113.0416274923112.631724352757215.3824753797.655598343789.9147923.504.84600796021612.28231605.3849056.724.096.206047196.431492687431635.755.752.673478616.0586125482924425114.6749508776190162.49165933712379731.873.2693211277921540101372850132447118669441900611860009827948912627105106495027.873.803.273.268.98498014155128205513799111.170.992.694.634.694.2318675856300968581613883202118953746211479011153810917225359197040114733311.782441053194.98601013063110.301249417515502326858261111869214514896250384474912317151.598319023015860099.1753344495931580.648310422869527435260559.877524168.58608814815516519818468.85214037470754602858217.992149.4528.5724.6547.7351.4520.3311642.00234381792116.7318153201152812185011.8332.411165648574113069828595173293453929125570.2144.2116.8442.543326592810698772813015223.5429.3116.42737718.58108660519.4419.9849.36888114659617.95162284422.15698515.894.304.108.6765.3873181064.9732.7149.077066735072422.69757188037072682577357276720382517478797234210288967562.021.554.188.827.726.321248344011203051621583OpenBenchmarking.org

MariaDB

OpenBenchmarking.orgQueries Per Second, More Is BetterMariaDB 10.3.8Clients: 642 x Xeon Gold 6138EPYC 7601EPYC 7351PEPYC 7401P2 x EPYC 7601EPYC 7251Xeon Silver 41082 x 22-Core POWER9 176 Threads2004006008001000SE +/- 2.26, N = 3SE +/- 0.21, N = 3SE +/- 1.09, N = 3SE +/- 0.36, N = 3SE +/- 18.74, N = 9SE +/- 0.51, N = 3SE +/- 2.04, N = 9SE +/- 1.04, N = 398960760655544242110791-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl

Numpy Benchmark

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

OpenBenchmarking.orgNanoseconds, Fewer Is BetterNumpy Benchmark2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads2M4M6M8M10M54513818035766805602785618508573814878618889169439704011

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Barbershop - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108400800120016002000SE +/- 0.96, N = 3SE +/- 0.41, N = 3SE +/- 0.35, N = 3SE +/- 0.21, N = 3SE +/- 1.57, N = 3SE +/- 0.37, N = 3SE +/- 0.61, N = 3SE +/- 3.30, N = 3SE +/- 0.27, N = 330940747352354969787418412039

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 16 - Solver Time2 x EPYC 7601EPYC 7601EPYC 755180160240320400SE +/- 0.70, N = 3SE +/- 4.09, N = 3SE +/- 5.26, N = 91842573911. Build Time Thu Nov 8 18:40:03 EST 2018;

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Classroom - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410830060090012001500SE +/- 0.21, N = 3SE +/- 0.28, N = 3SE +/- 0.14, N = 3SE +/- 0.60, N = 3SE +/- 0.41, N = 3SE +/- 1.07, N = 3SE +/- 1.06, N = 3SE +/- 2.59, N = 3SE +/- 0.09, N = 315223629630833140250310631329

VP9 libvpx Encoding

This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.7.0vpxenc2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7351PEPYC 7401PEPYC 7251Xeon Silver 41082 x 22-Core POWER9 176 Threads48121620SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.21, N = 3SE +/- 0.01, N = 313.9112.2512.2211.5711.1411.1211.0510.791.78-m64 -march=native-m64 -march=native-m64 -march=native-m64 -march=native-m64 -march=native-m64 -march=native-m64 -march=native-m64 -march=native1. (CXX) g++ options: -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE

Open Porous Media Git

This is a test of a DUNE (Distributed and Unified Numerics Environment) module called OPM Benchmarks from the Open Porous Media project. Open Porous Media is a set of open-source tools concerning simulation of flow and transport of fluids in porous media. This test profile builds OPM and its dependencies from upstream Git. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 162 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7401PEPYC 7351PEPYC 755190180270360450SE +/- 0.73, N = 3SE +/- 0.40, N = 3SE +/- 4.11, N = 3SE +/- 2.97, N = 3SE +/- 0.81, N = 3SE +/- 5.28, N = 91902382632702733981. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;2. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;3. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;4. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018;5. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018;6. EPYC 7551: Build Time Thu Nov 8 18:40:03 EST 2018;

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Pabellon Barcelona - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082004006008001000SE +/- 0.27, N = 3SE +/- 0.40, N = 3SE +/- 0.36, N = 3SE +/- 0.55, N = 3SE +/- 0.61, N = 3SE +/- 0.76, N = 3SE +/- 0.08, N = 3SE +/- 1.23, N = 3SE +/- 0.59, N = 31341952442482593344158911094

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 40962 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72514K8K12K16K20KSE +/- 238.01, N = 3SE +/- 134.57, N = 3SE +/- 45.21, N = 3SE +/- 25.94, N = 3SE +/- 33.71, N = 3SE +/- 82.85, N = 3SE +/- 17.33, N = 3SE +/- 2.60, N = 316704141071303312991123951227212007117041. (CC) gcc options: -pthread -O3 -march=native -lm

Timed GCC Compilation

This test times how long it takes to build the GNU Compiler Collection (GCC). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed GCC Compilation 8.2Time To Compile2 x EPYC 7601EPYC 7351P2 x Xeon Gold 6138EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7251Xeon Silver 41084008001200160020008211014102110381053109014601744

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: Serial2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 7351PEPYC 725120040060080010008321014101610251084108711231128

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Barbershop - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410840080012001600200032337450452767285317981892

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 16 - Solver Time2 x Xeon Gold 6138EPYC 7401PEPYC 7351P60120180240300SE +/- 0.41, N = 3SE +/- 2.97, N = 3SE +/- 0.84, N = 32322642661. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;2. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018;3. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018;

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: Fishy Cat - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsEPYC 7351PEPYC 7251Xeon Silver 4108150300450600750SE +/- 0.66, N = 3SE +/- 0.20, N = 3SE +/- 0.18, N = 3SE +/- 0.45, N = 3SE +/- 0.35, N = 3SE +/- 0.55, N = 3SE +/- 0.04, N = 3SE +/- 0.32, N = 3SE +/- 0.60, N = 388.13125.31149.60155.90193.75194.98237.60496.52692.45

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 32 - Solver Time2 x EPYC 7601EPYC 760160120180240300SE +/- 1.56, N = 3SE +/- 3.23, N = 31582591. Build Time Thu Nov 8 18:40:03 EST 2018;

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 322 x EPYC 76012 x Xeon Gold 6138EPYC 760160120180240300SE +/- 1.53, N = 3SE +/- 2.26, N = 3SE +/- 3.24, N = 31651962661. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;2. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;3. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Extra - Threads: 32 - Solver Time2 x Xeon Gold 61384080120160200SE +/- 2.02, N = 3188.561. Build Time Wed Nov 14 07:09:02 EST 2018;

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 40962 x 22-Core POWER9 176 Threads2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 7351PEPYC 725113002600390052006500SE +/- 10.97, N = 3SE +/- 62.63, N = 3SE +/- 1.04, N = 3SE +/- 8.17, N = 3SE +/- 12.47, N = 3SE +/- 6.10, N = 3SE +/- 29.24, N = 3SE +/- 16.65, N = 3SE +/- 3.79, N = 36010568853675226507049944991488548111. (CC) gcc options: -pthread -O3 -march=native -lm

Tinymembench

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard MemsetXeon Silver 41082 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x Xeon Gold 61384K8K12K16K20KSE +/- 10.13, N = 3SE +/- 11.26, N = 3SE +/- 7.22, N = 3SE +/- 3.57, N = 3SE +/- 5.65, N = 3SE +/- 10.43, N = 3SE +/- 1.78, N = 3SE +/- 4.33, N = 3SE +/- 34.89, N = 3197971721111162995799199873981196709323-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O2 -O3 -lm

OpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpy2 x 22-Core POWER9 176 ThreadsXeon Silver 41082 x EPYC 7601EPYC 7551EPYC 7601EPYC 7401PEPYC 7351PEPYC 72512 x Xeon Gold 61383K6K9K12K15KSE +/- 19.82, N = 3SE +/- 5.48, N = 3SE +/- 7.00, N = 3SE +/- 4.79, N = 3SE +/- 2.17, N = 3SE +/- 4.14, N = 3SE +/- 22.35, N = 3SE +/- 6.56, N = 3SE +/- 32.99, N = 31306391048041748474837404737372156153-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O2 -O3 -lm

RAR Compression

This test measures the time needed to archive/compress two copies of the Linux 4.13 kernel source tree using RAR/WinRAR compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRAR Compression 5.6.1Linux Source Tree Archiving To RAR2 x EPYC 76012 x Xeon Gold 6138EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7351PEPYC 7401PEPYC 72514080120160200SE +/- 1.84, N = 12SE +/- 0.39, N = 3SE +/- 0.29, N = 3SE +/- 1.04, N = 3SE +/- 2.27, N = 3SE +/- 0.16, N = 3SE +/- 0.24, N = 3SE +/- 0.04, N = 3108118145148149152152190

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing is supported. This system/blender test profile makes use of the system-supplied Blender. Use pts/blender if wishing to stick to a fixed version of Blender. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79Blend File: BMW27 - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108100200300400500SE +/- 0.24, N = 3SE +/- 0.38, N = 3SE +/- 0.14, N = 3SE +/- 0.33, N = 3SE +/- 0.10, N = 3SE +/- 0.16, N = 3SE +/- 0.12, N = 3SE +/- 1.19, N = 3SE +/- 0.73, N = 360.5484.06106.24110.17110.30139.27170.96347.99439.39

asmFish

This is a test of asmFish, an advanced chess benchmark written in Assembly. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes/second, More Is BetterasmFish 2017-09-191024 Hash Memory, 26 Depth2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410830M60M90M120M150MSE +/- 1024911.36, N = 3SE +/- 1344269.02, N = 4SE +/- 351504.20, N = 3SE +/- 689157.25, N = 3SE +/- 543463.40, N = 3SE +/- 309490.22, N = 3SE +/- 41751.52, N = 3SE +/- 107251.48, N = 311944826181933755669074636330240249280378373990101759792715102990

Fhourstones

This integer benchmark solves positions in the game of Connect-4, as played on a vertical 7x6 board. By default, it uses a 64Mb transposition table with the twobig replacement strategy. Positions are represented as 64-bit bitboards, and the hash function is computed using a single 64-bit modulo operation, giving 64-bit machines a slight edge. The alpha-beta searcher sorts moves dynamically based on the history heuristic. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgKpos / sec, More Is BetterFhourstones 3.1Complex Connect-4 Solving2 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsEPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7351PEPYC 72513K6K9K12K15KSE +/- 11.81, N = 3SE +/- 2.98, N = 3SE +/- 19.85, N = 3SE +/- 12.05, N = 3SE +/- 15.44, N = 3SE +/- 21.63, N = 3SE +/- 5.67, N = 3SE +/- 147.31, N = 5SE +/- 19.69, N = 312811124941060810350102931012410110970895251. (CC) gcc options: -O3

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Pabellon Barcelona - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410820040060080010001412042652763514449691157

Hierarchical INTegration

This test runs the U.S. Department of Energy's Ames Laboratory Hierarchical INTegration (HINT) benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOAT2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 725180M160M240M320M400MSE +/- 767909.83, N = 3SE +/- 871757.89, N = 3SE +/- 126220.51, N = 3SE +/- 652352.80, N = 3SE +/- 40280.23, N = 3SE +/- 2471240.27, N = 3SE +/- 114111.35, N = 3SE +/- 73811.70, N = 33666991912971733992620079332612106132456725572436355822374853312373891501. (CC) gcc options: -O3 -march=native -lm

Minion

Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Quasigroup2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads4080120160200SE +/- 0.28, N = 3SE +/- 0.95, N = 3SE +/- 0.63, N = 3SE +/- 0.28, N = 3SE +/- 0.10, N = 3SE +/- 1.32, N = 3SE +/- 0.67, N = 3SE +/- 0.76, N = 3SE +/- 0.59, N = 31201471491491581581641641751. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Only2 x Xeon Gold 61382 x 22-Core POWER9 176 Threads2 x EPYC 7601Xeon Silver 4108EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72514K8K12K16K20KSE +/- 86.63, N = 3SE +/- 160.04, N = 3SE +/- 178.37, N = 3SE +/- 107.48, N = 3SE +/- 155.22, N = 3SE +/- 13.14, N = 3SE +/- 35.53, N = 3SE +/- 136.10, N = 3SE +/- 29.83, N = 3178051550215145150761480514499136681266111515-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

GNU GMP GMPbench

GMPbench is a test of the GMP 6.1.2 math library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGMPbench Score, More Is BetterGNU GMP GMPbench 6.1.2Total Time2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads10002000300040005000471039413940383937043700357335703268-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lm

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 32 - Solver Time2 x EPYC 7601EPYC 7601EPYC 755120406080100SE +/- 0.97, N = 6SE +/- 1.26, N = 5SE +/- 1.16, N = 366.4788.3190.501. Build Time Thu Nov 8 18:40:03 EST 2018;

PostgreSQL pgbench

This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Only2 x Xeon Gold 61382 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7551EPYC 7601EPYC 7401PEPYC 7351PXeon Silver 4108EPYC 7251130K260K390K520K650KSE +/- 1512.41, N = 3SE +/- 1721.99, N = 3SE +/- 3036.21, N = 3SE +/- 1536.25, N = 3SE +/- 3941.18, N = 3SE +/- 820.46, N = 3SE +/- 971.65, N = 3SE +/- 270.54, N = 3SE +/- 143.00, N = 3584554582611518285407453396841317536249578156504123039-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 20482 x Xeon Gold 6138EPYC 7601Xeon Silver 4108EPYC 7351PEPYC 7401P2 x EPYC 7601EPYC 7551EPYC 72514K8K12K16K20KSE +/- 268.19, N = 3SE +/- 43.92, N = 3SE +/- 34.03, N = 3SE +/- 183.27, N = 3SE +/- 28.67, N = 3SE +/- 126.72, N = 3SE +/- 118.60, N = 3SE +/- 99.14, N = 318805147611446214023138501336412744123151. (CC) gcc options: -pthread -O3 -march=native -lm

CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Write2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads6K12K18K24K30KSE +/- 1.72, N = 3SE +/- 0.48, N = 3SE +/- 0.29, N = 3SE +/- 5.33, N = 3SE +/- 0.14, N = 3SE +/- 17.12, N = 3SE +/- 0.70, N = 3SE +/- 23.89, N = 3SE +/- 0.59, N = 32579821915219092090120578205321985819802118691. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / Write2 x EPYC 7601EPYC 76012 x Xeon Gold 6138EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082 x 22-Core POWER9 176 Threads9K18K27K36K45KSE +/- 0.93, N = 3SE +/- 2.12, N = 3SE +/- 0.99, N = 3SE +/- 6.55, N = 3SE +/- 2.10, N = 3SE +/- 7.32, N = 3SE +/- 4.60, N = 3SE +/- 1.43, N = 3SE +/- 0.65, N = 34250542497422183990839842385013849534209214511. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read2 x 22-Core POWER9 176 Threads2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 725110002000300040005000SE +/- 0.26, N = 3SE +/- 0.54, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 34896312525332216221620812077200820081. (CC) gcc options: -lrt

BYTE Unix Benchmark

This is a test of BYTE. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 22 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads8M16M24M32M40MSE +/- 4427.74, N = 3SE +/- 391137.33, N = 3SE +/- 313116.33, N = 3SE +/- 265797.72, N = 3SE +/- 231609.59, N = 3SE +/- 106664.99, N = 3SE +/- 260711.56, N = 3SE +/- 477072.38, N = 4SE +/- 89617.34, N = 3378432573365245533474468314226113066977030656278304846832988297825038447-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 8192 MiBXeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7251EPYC 75512 x Xeon Gold 61382K4K6K8K10KSE +/- 1.48, N = 3SE +/- 24.54, N = 3SE +/- 26.41, N = 3SE +/- 6.27, N = 3SE +/- 14.40, N = 3SE +/- 48.28, N = 3SE +/- 10.71, N = 3SE +/- 24.61, N = 3808678247292712770987091650951251. (CC) gcc options: -O3 -march=native

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Classroom - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108200400600800100098.79164.62201.93209.46272.91342.86706.16944.28

Open Porous Media Git

This is a test of a DUNE (Distributed and Unified Numerics Environment) module called OPM Benchmarks from the Open Porous Media project. Open Porous Media is a set of open-source tools concerning simulation of flow and transport of fluids in porous media. This test profile builds OPM and its dependencies from upstream Git. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 322 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 755120406080100SE +/- 0.97, N = 6SE +/- 1.19, N = 3SE +/- 1.26, N = 5SE +/- 1.17, N = 368.3584.2590.5093.011. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;2. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;3. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;4. EPYC 7551: Build Time Thu Nov 8 18:40:03 EST 2018;

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Add2 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7551EPYC 725112K24K36K48K60KSE +/- 604.72, N = 3SE +/- 278.39, N = 3SE +/- 198.38, N = 3SE +/- 3639.91, N = 9SE +/- 1266.42, N = 12SE +/- 494.83, N = 12SE +/- 583.28, N = 12SE +/- 499.65, N = 12SE +/- 331.78, N = 12569984949449123447303078326975261762558422956-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm -rdynamic

Timed LLVM Compilation

This test times how long it takes to build the LLVM compiler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To Compile2 x EPYC 76012 x 22-Core POWER9 176 Threads2 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108160320480640800149171172236247282341640736

Timed Linux Kernel Compilation

This test times how long it takes to build the Linux kernel in a default configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.18Time To Compile2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108306090120150SE +/- 0.31, N = 12SE +/- 0.42, N = 12SE +/- 0.49, N = 9SE +/- 0.48, N = 10SE +/- 0.74, N = 3SE +/- 0.79, N = 5SE +/- 1.04, N = 3SE +/- 1.58, N = 3SE +/- 1.50, N = 326.4633.9442.9843.9851.5952.9062.80116.95134.05

Radiance Benchmark

This is a benchmark of NREL Radiance, a synthetic imaging system that is open-source and developed by the Lawrence Berkeley National Laboratory in California. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRadiance Benchmark 5.0Test: SMP Parallel2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410880160240320400259310315323329339347361

Stockfish

This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time2 x EPYC 76012 x 22-Core POWER9 176 Threads2 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410820M40M60M80M100MSE +/- 302657.40, N = 3SE +/- 653933.14, N = 3SE +/- 599656.72, N = 3SE +/- 186688.77, N = 3SE +/- 451949.77, N = 3SE +/- 474439.83, N = 3SE +/- 96861.51, N = 3SE +/- 85097.64, N = 3SE +/- 44988.37, N = 31009320628319023069815559570080735630869143541579330754121628240212717282-march=native -msse -msse3 -mpopcnt-mtune=power9 -mcpu=power9-march=native -msse -msse3 -mpopcnt-march=native -msse -msse3 -mpopcnt-march=native -msse -msse3 -mpopcnt-march=native -msse -msse3 -mpopcnt-march=native -msse -msse3 -mpopcnt1. (CXX) g++ options: -m64 -lpthread -O3 -fno-exceptions -std=c++11 -pedantic -flto

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 8192 MiBEPYC 76012 x EPYC 7601EPYC 7351PEPYC 7401PEPYC 7551EPYC 7251Xeon Silver 41082 x Xeon Gold 61383K6K9K12K15KSE +/- 3.39, N = 3SE +/- 2.15, N = 3SE +/- 3.69, N = 3SE +/- 63.39, N = 3SE +/- 160.57, N = 7SE +/- 63.38, N = 3SE +/- 2.61, N = 3SE +/- 2.43, N = 3126341256312553125091235611660846847801. (CC) gcc options: -O3 -march=native

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test2 x 22-Core POWER9 176 Threads2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410830K60K90K120K150KSE +/- 2843.17, N = 3SE +/- 2282.89, N = 3SE +/- 2850.88, N = 9SE +/- 1083.97, N = 3SE +/- 633.86, N = 3SE +/- 614.77, N = 3SE +/- 443.11, N = 3SE +/- 59.47, N = 3SE +/- 143.98, N = 31586001379141302399122085123776656003830627280111. (CXX) g++ options: -pipe -lpthread

NAMD

NAMD is a parallel molecular dynamics code designed for high-performance simulation of large biomolecular systems. NAMD was developed by the Theoretical and Computational Biophysics Group in the Beckman Institute for Advanced Science and Technology at the University of Illinois at Urbana-Champaign. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgdays/ns, Fewer Is BetterNAMD 2.13b1ATPase Simulation - 327,506 Atoms2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41080.8561.7122.5683.4244.28SE +/- 0.00747, N = 12SE +/- 0.00243, N = 3SE +/- 0.00124, N = 3SE +/- 0.00095, N = 3SE +/- 0.00184, N = 3SE +/- 0.00183, N = 3SE +/- 0.00301, N = 3SE +/- 0.00272, N = 30.458280.651180.908850.933371.212151.507553.085253.80433

Minion

Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Solitaire2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads20406080100SE +/- 0.25, N = 3SE +/- 0.54, N = 3SE +/- 0.38, N = 3SE +/- 0.02, N = 3SE +/- 0.33, N = 3SE +/- 0.49, N = 3SE +/- 0.35, N = 3SE +/- 0.47, N = 3SE +/- 0.29, N = 375.0787.4287.9091.8892.4292.5595.9498.1099.171. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Prepend2 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 ThreadsEPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P14K28K42K56K70KSE +/- 99.58, N = 3SE +/- 341.55, N = 3SE +/- 758.35, N = 12SE +/- 1919.55, N = 12SE +/- 663.14, N = 3SE +/- 2955.21, N = 12SE +/- 1105.77, N = 12SE +/- 1281.01, N = 12SE +/- 82.78, N = 3665495517153344504054485537074289552662326435-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm -rdynamic

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 32 - Solver Time2 x Xeon Gold 613820406080100SE +/- 1.15, N = 382.031. Build Time Wed Nov 14 07:09:02 EST 2018;

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: Fishy Cat - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410814028042056070083.63117.62139.91146.34181.96221.45466.16651.91

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Set2 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsXeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 725112K24K36K48K60KSE +/- 294.71, N = 3SE +/- 310.97, N = 3SE +/- 195.73, N = 3SE +/- 784.66, N = 12SE +/- 371.58, N = 7SE +/- 476.79, N = 12SE +/- 86.23, N = 3SE +/- 47.62, N = 3SE +/- 545.53, N = 12567384959349292411892903026455252502497323442-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm -rdynamic

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 16 - Solver Time2 x Xeon Gold 6138EPYC 7401PEPYC 7351P20406080100SE +/- 0.04, N = 3SE +/- 0.40, N = 3SE +/- 0.49, N = 373.5674.1480.781. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;2. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018;3. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018;

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests to stress the system's CPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Noise-Gaussian2 x EPYC 76012 x Xeon Gold 6138EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41084080120160200SE +/- 0.67, N = 3SE +/- 1.52, N = 1218418016515815814913510586-march=native-march=native -lwebp -lwebpmux-march=native-mtune=power9 -mcpu=power9 -lwebp -lwebpmux-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

Timed PHP Compilation

This test times how long it takes to build PHP 5 with the Zend engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To Compile2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410820406080100SE +/- 0.14, N = 3SE +/- 0.06, N = 3SE +/- 0.22, N = 3SE +/- 0.23, N = 3SE +/- 0.12, N = 3SE +/- 0.33, N = 3SE +/- 0.41, N = 3SE +/- 0.28, N = 360.2970.3673.1977.0577.5281.5699.04102.631. (CC) gcc options: -O3 -march=native -pedantic -ldl -lz -lm

R Benchmark

This test is a quick-running survey of general R performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterR BenchmarkXeon Silver 4108EPYC 7251EPYC 7351P2 x Xeon Gold 6138EPYC 7401PEPYC 76012 x EPYC 7601EPYC 75512 x 22-Core POWER9 176 Threads0.14590.29180.43770.58360.7295SE +/- 0.0005, N = 3SE +/- 0.0028, N = 3SE +/- 0.0020, N = 3SE +/- 0.0056, N = 3SE +/- 0.0005, N = 3SE +/- 0.0019, N = 3SE +/- 0.0042, N = 3SE +/- 0.0016, N = 3SE +/- 0.0042, N = 30.28990.29310.39080.43080.44550.46380.47280.48920.64831. R scripting front-end version 3.5.1 (2018-07-02)

Open Porous Media Git

This is a test of a DUNE (Distributed and Unified Numerics Environment) module called OPM Benchmarks from the Open Porous Media project. Open Porous Media is a set of open-source tools concerning simulation of flow and transport of fluids in porous media. This test profile builds OPM and its dependencies from upstream Git. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 162 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7401PEPYC 7551EPYC 7351P20406080100SE +/- 0.35, N = 3SE +/- 0.05, N = 3SE +/- 0.79, N = 3SE +/- 0.40, N = 3SE +/- 0.35, N = 3SE +/- 0.49, N = 356.3775.5075.7475.9980.9082.661. 2 x EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;2. 2 x Xeon Gold 6138: Build Time Wed Nov 14 07:09:02 EST 2018;3. EPYC 7601: Build Time Thu Nov 8 18:40:03 EST 2018;4. EPYC 7401P: Build Time Thu Nov 8 18:40:03 EST 2018;5. EPYC 7551: Build Time Thu Nov 8 18:40:03 EST 2018;6. EPYC 7351P: Build Time Thu Nov 8 18:40:03 EST 2018;

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Supercar2 x Xeon Gold 6138EPYC 7601EPYC 75512 x EPYC 7601EPYC 7401PEPYC 7351PXeon Silver 4108EPYC 7251246810SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 9SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 37.805.975.605.444.643.551.661.61

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 16 - Solver Time2 x EPYC 7601EPYC 7601EPYC 755120406080100SE +/- 0.35, N = 3SE +/- 0.78, N = 3SE +/- 0.36, N = 354.7873.8878.841. Build Time Thu Nov 8 18:40:03 EST 2018;

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context Switching2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41085M10M15M20M25MSE +/- 644813.65, N = 12SE +/- 904286.44, N = 9SE +/- 228446.84, N = 12SE +/- 132910.28, N = 7SE +/- 498192.34, N = 12SE +/- 120495.49, N = 3SE +/- 38957.95, N = 3SE +/- 57635.42, N = 4SE +/- 53788.68, N = 421250062171189261116006110765409104228698529514656833334124703229231-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Replace2 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7551EPYC 725114K28K42K56K70KSE +/- 505.28, N = 3SE +/- 219.66, N = 3SE +/- 257.48, N = 3SE +/- 678.19, N = 4SE +/- 3266.89, N = 12SE +/- 1847.72, N = 9SE +/- 46.91, N = 3SE +/- 131.36, N = 3SE +/- 572.82, N = 12674735452652743455764177829881267002639925260-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm -rdynamic

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Append2 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7551EPYC 725114K28K42K56K70KSE +/- 671.32, N = 12SE +/- 96.81, N = 3SE +/- 190.56, N = 3SE +/- 902.50, N = 3SE +/- 92.84, N = 3SE +/- 1229.56, N = 12SE +/- 147.85, N = 3SE +/- 48.80, N = 3SE +/- 1336.06, N = 9673765468652605450522984328893264872619126038-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm -rdynamic

Open Porous Media Git

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 64 - Solver Time2 x EPYC 76011326395265SE +/- 0.70, N = 356.551. Build Time Thu Nov 8 18:40:03 EST 2018;

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen Porous Media GitOPM Benchmark: Flow MPI Norne - Threads: 642 x EPYC 76011326395265SE +/- 0.70, N = 358.721. Build Time Thu Nov 8 18:40:03 EST 2018;

AOBench

AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total Time2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads1326395265SE +/- 0.69, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.56, N = 12SE +/- 0.01, N = 335.7043.1844.4744.5147.3347.4549.1649.6559.87-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -lm -O3

IndigoBench

This is a test of Indigo Renderer's IndigoBench benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgM samples/s, More Is BetterIndigoBench 4.0.64Scene: Bedroom2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41080.80551.6112.41653.2224.0275SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.583.342.942.812.201.690.780.69

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Get2 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7601EPYC 75512 x EPYC 7601EPYC 7251EPYC 7351P20K40K60K80K100KSE +/- 1607.29, N = 12SE +/- 575.65, N = 3SE +/- 1052.87, N = 3SE +/- 428.81, N = 3SE +/- 1665.36, N = 12SE +/- 391.67, N = 3SE +/- 2109.32, N = 12SE +/- 5519.25, N = 12SE +/- 1176.88, N = 12967908131775241668006195755388539965003945533-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm -rdynamic

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiBXeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7551EPYC 72512 x Xeon Gold 61382K4K6K8K10KSE +/- 2.08, N = 3SE +/- 30.15, N = 3SE +/- 11.95, N = 3SE +/- 10.13, N = 3SE +/- 15.07, N = 3SE +/- 16.70, N = 3SE +/- 37.42, N = 3SE +/- 18.94, N = 3806776507150706270077001687851131. (CC) gcc options: -O3 -march=native

Chaos Group V-RAY

This is a test of Chaos Group's V-RAY benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterChaos Group V-RAY 1.1.0Mode: CPU2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108306090120150SE +/- 0.20, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 3SE +/- 0.18, N = 3SE +/- 0.26, N = 3SE +/- 0.46, N = 3SE +/- 0.72, N = 324.5731.5038.9039.5048.1459.28116.86138.07

Minion

Minion is an open-source constraint solver that is designed to be very scalable. This test profile uses Minion's integrated benchmarking problems to solve. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMinion 1.8Benchmark: Graceful2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082 x 22-Core POWER9 176 Threads1530456075SE +/- 0.00, N = 3SE +/- 0.19, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 3SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.18, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 354.4556.7656.8160.1960.2862.4063.7966.9868.581. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 20482 x 22-Core POWER9 176 Threads2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7351PXeon Silver 4108EPYC 7401PEPYC 7551EPYC 725113002600390052006500SE +/- 11.43, N = 3SE +/- 49.59, N = 3SE +/- 3.39, N = 3SE +/- 19.00, N = 3SE +/- 33.05, N = 3SE +/- 19.86, N = 3SE +/- 28.93, N = 3SE +/- 14.74, N = 3SE +/- 36.27, N = 36088591959035781530152385215512748501. (CC) gcc options: -pthread -O3 -march=native -lm

GraphicsMagick

This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests to stress the system's CPU. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Sharpen2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsEPYC 7351PEPYC 7251Xeon Silver 41084080120160200SE +/- 0.88, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 318218217016315414813911189-march=native -lwebp -lwebpmux-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9 -lwebp -lwebpmux-march=native-march=native-march=native1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Enhanced2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsEPYC 7351PEPYC 7251Xeon Silver 41084080120160200SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 1.00, N = 3197188181172167155153128110-march=native -lwebp -lwebpmux-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9 -lwebp -lwebpmux-march=native-march=native-march=native1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Swirl2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351P2 x 22-Core POWER9 176 ThreadsEPYC 7251Xeon Silver 410850100150200250SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3208194191182179169165155142-march=native -lwebp -lwebpmux-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9 -lwebp -lwebpmux-march=native-march=native1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Rotate2 x Xeon Gold 61382 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7551Xeon Silver 4108EPYC 7401PEPYC 7351PEPYC 725150100150200250SE +/- 0.33, N = 3208198188187178176176171171-march=native -lwebp -lwebpmux-mtune=power9 -mcpu=power9 -lwebp -lwebpmux-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color Space2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351P2 x 22-Core POWER9 176 ThreadsEPYC 7251Xeon Silver 410850100150200250SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 1.76, N = 3226208206197193187184182176-march=native -lwebp -lwebpmux-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9 -lwebp -lwebpmux-march=native-march=native1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

Rust Mandelbrot

This test profile is of the combined time for the serial and parallel Mandelbrot sets written in Rustlang via willi-kappler/mandel-rust. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRust MandelbrotTime To Complete Serial/Parallel Mandelbrot2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351P2 x 22-Core POWER9 176 ThreadsEPYC 7251Xeon Silver 410820406080100SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 347.4748.1349.9953.1654.5659.5068.8570.6982.761. (CC) gcc options: -m64 -pie -nodefaultlibs

Apache Benchmark

This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page Serving2 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsXeon Silver 4108EPYC 7351PEPYC 76012 x EPYC 7601EPYC 7401PEPYC 7551EPYC 72515K10K15K20K25KSE +/- 195.16, N = 3SE +/- 191.16, N = 3SE +/- 26.94, N = 3SE +/- 24.57, N = 3SE +/- 313.51, N = 3SE +/- 239.14, N = 3SE +/- 116.37, N = 3SE +/- 47.09, N = 3SE +/- 42.54, N = 3223602140318608164441636315955159231572515364-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -shared -fPIC -pthread -O3

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 4096 MiBEPYC 7601EPYC 7401P2 x EPYC 7601EPYC 7351PEPYC 7251EPYC 7551Xeon Silver 41082 x Xeon Gold 61383K6K9K12K15KSE +/- 1.68, N = 3SE +/- 5.00, N = 3SE +/- 7.46, N = 3SE +/- 213.76, N = 12SE +/- 2.01, N = 3SE +/- 8.05, N = 3SE +/- 19.11, N = 3SE +/- 2.97, N = 3126471261312577119911173011253847047921. (CC) gcc options: -O3 -march=native

Blender

Blender is an open-source 3D creation software project. This test is of Blender's Cycles benchmark with various sample files. GPU computing via OpenCL or CUDA is supported. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBlender 2.79aBlend File: BMW27 - Compute: CPU-Only2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41089018027036045058.0276.84101.93105.36132.74164.43335.06408.69

m-queens

A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.2Time To Solve2 x EPYC 7601EPYC 76012 x Xeon Gold 6138EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41084080120160200SE +/- 0.02, N = 3SE +/- 0.09, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.37, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 313.6327.2228.1028.3535.8649.7799.12177.571. (CXX) g++ options: -fopenmp -O3 -march=native -O2

Memcached mcperf

This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Delete2 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 725120K40K60K80K100KSE +/- 982.97, N = 3SE +/- 422.79, N = 3SE +/- 347.42, N = 3SE +/- 265.83, N = 3SE +/- 1632.16, N = 12SE +/- 1876.44, N = 12SE +/- 574.84, N = 10SE +/- 200.38, N = 3SE +/- 1332.03, N = 12974518166074707639446349961324543994293340913-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm -rdynamic

GNU MPC

GNU MPC is a C library for the arithmetic of complex numbers. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGlobal Score, More Is BetterGNU MPC 1.1.0Multi-Precision Benchmark2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads2K4K6K8K10KSE +/- 3.33, N = 3SE +/- 6.67, N = 3SE +/- 10.00, N = 3SE +/- 10.00, N = 3SE +/- 12.02, N = 3SE +/- 5.77, N = 3871370736190614058105780560355905460-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -lm -O3 -MT -MD -MP -MF

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: LU.C2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7401PEPYC 7351PEPYC 7551EPYC 7251Xeon Silver 410820K40K60K80K100KSE +/- 702.85, N = 3SE +/- 423.98, N = 3SE +/- 352.29, N = 3SE +/- 675.58, N = 3SE +/- 592.65, N = 3SE +/- 75.17, N = 3SE +/- 30.95, N = 3SE +/- 57.61, N = 3114877768685996956107448153674225279178361. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket Activity2 x 22-Core POWER9 176 Threads2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41086K12K18K24K30KSE +/- 159.34, N = 3SE +/- 343.02, N = 12SE +/- 347.42, N = 3SE +/- 289.93, N = 3SE +/- 109.45, N = 3SE +/- 196.37, N = 3SE +/- 130.34, N = 3SE +/- 106.95, N = 3SE +/- 35.04, N = 122858225458189761739016608133991099256523314-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel2 x EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401P2 x Xeon Gold 6138EPYC 7351PEPYC 7251Xeon Silver 4108306090120150SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 1.15, N = 9SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 311.2117.9921.9723.1128.7130.7040.3480.34121.78-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -lm -lpthread -O3

lzbench

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: Decompression2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsEPYC 7351PEPYC 7251204060801008876767471717069691. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: Compression2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads816243240SE +/- 0.33, N = 33328252524232323211. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

x265

This is a simple test of the x265 encoder run on the CPU with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 2.8H.265 Video Encoding2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 7251816243240SE +/- 0.10, N = 3SE +/- 0.08, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 334.8920.1113.5011.7011.3011.0810.637.161. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma

Gzip Compression

This test measures the time needed to archive/compress two copies of the Linux 4.13 kernel source tree using Gzip compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGzip CompressionLinux Source Tree Archiving To .tar.gz2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsXeon Silver 4108EPYC 7351PEPYC 72511224364860SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.08, N = 338.9045.4845.5148.3749.0649.4549.6552.2053.14

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Traditional DES2 x EPYC 76012 x Xeon Gold 6138EPYC 7551EPYC 7601EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410860M120M180M240M300MSE +/- 1261993.31, N = 3SE +/- 277696.08, N = 3SE +/- 250141.96, N = 3SE +/- 1770832.28, N = 7SE +/- 359575.21, N = 3SE +/- 104747.85, N = 3SE +/- 30805.84, N = 3SE +/- 31306.73, N = 32582376671547843331379310001368218571071150008363666743180000277856671. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

ebizzy

This is a test of ebizzy, a program to generate workloads resembling web server workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.32 x EPYC 7601EPYC 7551EPYC 7601EPYC 7401P2 x Xeon Gold 6138EPYC 7351PEPYC 7251Xeon Silver 4108400K800K1200K1600K2000KSE +/- 28692.91, N = 12SE +/- 22818.33, N = 3SE +/- 13270.20, N = 8SE +/- 1972.15, N = 3SE +/- 12714.82, N = 12SE +/- 3875.74, N = 3SE +/- 3209.41, N = 3SE +/- 4847.40, N = 1217267991178219113906811146319698249301784612952111481. (CC) gcc options: -pthread -lpthread -O3 -march=native

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP Streamcluster2 x Xeon Gold 6138EPYC 7351PEPYC 7401PEPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 72512 x 22-Core POWER9 176 Threads714212835SE +/- 0.25, N = 12SE +/- 0.17, N = 3SE +/- 0.61, N = 9SE +/- 0.59, N = 12SE +/- 0.24, N = 3SE +/- 0.02, N = 3SE +/- 1.66, N = 9SE +/- 0.35, N = 7SE +/- 0.08, N = 313.2915.0917.2518.3120.6421.1221.4826.7328.571. (CXX) g++ options: -O2 -lOpenCL

Timed ImageMagick Compilation

This test times how long it takes to build ImageMagick. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compile2 x Xeon Gold 61382 x EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41081326395265SE +/- 0.10, N = 3SE +/- 0.31, N = 3SE +/- 0.28, N = 3SE +/- 0.12, N = 3SE +/- 0.34, N = 12SE +/- 0.10, N = 3SE +/- 0.17, N = 3SE +/- 0.16, N = 3SE +/- 0.20, N = 322.8323.2724.6528.0229.7730.8833.4749.9157.23

Tesseract OCR

Tesseract-OCR is the open-source optical character recognition (OCR) engine for the conversion of text within images to raw text output. This test profile relies upon a system-supplied Tesseract installation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTesseract OCR 4.0.0-beta.3-249-g607eTime To OCR 7 Images2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads1122334455SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.14, N = 3SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 333.5739.6042.4043.9944.5044.9845.5246.4047.73

eSpeak Speech Engine

This test times how long it takes the eSpeak speech synthesizer to read Project Gutenberg's The Outline of Science and output to a WAV file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak Speech Engine 1.48.04Text-To-Speech Synthesis2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads1224364860SE +/- 0.22, N = 3SE +/- 0.23, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.05, N = 331.3238.4640.1440.1442.6242.7144.1544.1751.451. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions

POV-Ray

This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace Time2 x EPYC 76012 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410820406080100SE +/- 0.16, N = 3SE +/- 0.10, N = 3SE +/- 0.10, N = 3SE +/- 0.14, N = 3SE +/- 0.11, N = 3SE +/- 0.12, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.07, N = 312.8219.0220.3322.6123.0128.9636.6971.23109.43-march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-march=native -lSDL -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-mtune=power9 -mcpu=power9 -R/usr/lib -lSDL -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-march=native -lXpm -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread-march=native -lXpm1. (CXX) g++ options: -pipe -O3 -ffast-math -pthread -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Composite2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7251Xeon Silver 4108EPYC 7351P2 x 22-Core POWER9 176 Threads5001000150020002500SE +/- 5.38, N = 4SE +/- 1.60, N = 4SE +/- 0.86, N = 4SE +/- 5.49, N = 4SE +/- 8.37, N = 4SE +/- 1.85, N = 4SE +/- 11.04, N = 4SE +/- 21.22, N = 4SE +/- 4.09, N = 4217719911990186318591802178017801164

Sunflow Rendering System

This test runs benchmarks of the Sunflow Rendering System. The Sunflow Rendering System is an open-source render engine for photo-realistic image synthesis with a ray-tracing core. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image Synthesis2 x Xeon Gold 6138EPYC 7601EPYC 7401PEPYC 75512 x EPYC 7601EPYC 7351P2 x 22-Core POWER9 176 ThreadsEPYC 7251Xeon Silver 41080.54451.0891.63352.1782.7225SE +/- 0.01, N = 3SE +/- 0.01, N = 6SE +/- 0.02, N = 12SE +/- 0.02, N = 12SE +/- 0.04, N = 9SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 12SE +/- 0.03, N = 50.991.021.131.251.271.322.002.302.42

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Compile2 x 22-Core POWER9 176 Threads2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 7251Xeon Silver 41085001000150020002500SE +/- 7.21, N = 3SE +/- 4.15, N = 3SE +/- 5.23, N = 3SE +/- 2.35, N = 3SE +/- 1.71, N = 3SE +/- 4.69, N = 3SE +/- 3.99, N = 3SE +/- 0.99, N = 3SE +/- 55.98, N = 12234316851559155114711443143914011217

Cryptsetup

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetupPBKDF2-whirlpool2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P200K400K600K800K1000KSE +/- 432.67, N = 3SE +/- 284.00, N = 3SE +/- 1752.33, N = 3SE +/- 1381.99, N = 3SE +/- 956.51, N = 3SE +/- 207.00, N = 3SE +/- 945.21, N = 3825217668450629397628401590420587330570912569262

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetup 2.0.4PBKDF2-sha5122 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads300K600K900K1200K1500KSE +/- 13365.14, N = 3SE +/- 4147.67, N = 3SE +/- 1482.13, N = 3SE +/- 958.40, N = 3SE +/- 1774.58, N = 3SE +/- 2932.33, N = 3SE +/- 1216.16, N = 3SE +/- 1997.34, N = 314045991140200939028932898879193878224850659849287817921

GNU Octave Benchmark

This test profile measures how long it takes to complete several reference GNU Octave files via octave-benchmark. GNU Octave is used for numerical computations and is an open-source alternative to MATLAB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGNU Octave Benchmark 4.4.12 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7351PEPYC 7401PEPYC 7551EPYC 72512 x Xeon Gold 6138Xeon Silver 4108612182430SE +/- 0.10, N = 3SE +/- 0.27, N = 3SE +/- 0.41, N = 3SE +/- 0.21, N = 12SE +/- 0.25, N = 12SE +/- 0.13, N = 3SE +/- 0.34, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 316.7320.9020.9221.1221.1522.6622.7523.4725.61

PyBench

This test profile reports the total time of the different average timed test results from PyBench. PyBench reports average test times for different functions such as BuiltinFunctionCalls and NestedForLoops, with this total result providing a rough estimate as to Python's average performance on a given system. This test profile runs PyBench each time for 20 rounds. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2018-02-16Total For Average Test Times2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads400800120016002000SE +/- 0.58, N = 3SE +/- 4.81, N = 3SE +/- 0.88, N = 3SE +/- 2.85, N = 3SE +/- 2.52, N = 3SE +/- 4.26, N = 3SE +/- 0.67, N = 3SE +/- 1.33, N = 3SE +/- 4.37, N = 3113014051514151816141615166816681815

lzbench

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: Decompression2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads110220330440550SE +/- 0.33, N = 3SE +/- 3.00, N = 34874214003973713703613552911. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Brotli 0 - Process: Compression2 x Xeon Gold 61382 x EPYC 7601EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410880160240320400SE +/- 1.67, N = 3SE +/- 1.33, N = 33593423393203193193063063001. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Cryptsetup

OpenBenchmarking.orgIterations Per Second, More Is BetterCryptsetup 2.0.4PBKDF2-whirlpool2 x 22-Core POWER9 176 Threads90K180K270K360K450KSE +/- 243.33, N = 3437393

lzbench

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: Decompression2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads2004006008001000SE +/- 4.00, N = 39468048047887597547337293531. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Libdeflate 1 - Process: Compression2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads4080120160200SE +/- 1.20, N = 3SE +/- 1.15, N = 3SE +/- 0.58, N = 32001741731661631621581561151. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Crafty

This is a performance test of Crafty, an advanced open-source chess engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72511.6M3.2M4.8M6.4M8MSE +/- 11682.27, N = 3SE +/- 5723.46, N = 3SE +/- 19129.54, N = 3SE +/- 8127.53, N = 3SE +/- 3869.93, N = 3SE +/- 5830.78, N = 3SE +/- 8901.18, N = 3SE +/- 2097.91, N = 3740333560065735710603568972554315205371574521439051469181. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

lzbench

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: Decompression2 x Xeon Gold 61382 x EPYC 7601EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7551EPYC 7401PXeon Silver 4108EPYC 7251EPYC 7351P2004006008001000SE +/- 1.00, N = 3SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 39178288267977827767707517501. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: Zstd 1 - Process: Compression2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads80160240320400SE +/- 0.33, N = 33593263253053032982922922811. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3

Node.js Octane Benchmark

A Node.js version of the JavaScript Octane Benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterNode.js Octane Benchmark2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads8K16K24K32K40KSE +/- 171.31, N = 3SE +/- 36.71, N = 3SE +/- 29.10, N = 3SE +/- 40.22, N = 3SE +/- 104.41, N = 3SE +/- 56.59, N = 3SE +/- 84.58, N = 3SE +/- 32.66, N = 3SE +/- 111.34, N = 33675929739295432924227391272642622825686218501. Nodejs v8.11.4

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 10242 x Xeon Gold 6138EPYC 7601EPYC 7401P2 x EPYC 7601EPYC 7351PEPYC 7551Xeon Silver 4108EPYC 72515K10K15K20K25KSE +/- 91.92, N = 3SE +/- 52.59, N = 3SE +/- 165.68, N = 3SE +/- 162.82, N = 3SE +/- 28.83, N = 3SE +/- 115.55, N = 3SE +/- 265.38, N = 3SE +/- 205.54, N = 323220204591956119018188941794417524144861. (CC) gcc options: -pthread -O3 -march=native -lm

Y-Cruncher

Y-Cruncher is a multi-threaded Pi benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterY-Cruncher 0.7.5.9481Calculating 500M Pi Digits2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41081326395265SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.23, N = 3SE +/- 0.02, N = 312.6615.6119.3321.5623.0429.1853.4256.50

Zstd Compression

This test measures the time needed to compress a sample file (an Ubuntu file-system image) using Zstd compression. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 192 x Xeon Gold 61382 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PXeon Silver 4108EPYC 7251612182430SE +/- 0.17, N = 3SE +/- 0.18, N = 5SE +/- 0.31, N = 12SE +/- 0.23, N = 3SE +/- 0.24, N = 3SE +/- 0.26, N = 12SE +/- 0.24, N = 3SE +/- 0.04, N = 3SE +/- 0.34, N = 710.9711.8313.4514.0014.6715.0615.8023.1426.99-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -pthread -lz -llzma

Timed Apache Compilation

This test times how long it takes to build the Apache HTTP Server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.7Time To Compile2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351P2 x 22-Core POWER9 176 ThreadsEPYC 7251Xeon Silver 4108816243240SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.11, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.12, N = 3SE +/- 0.09, N = 325.0425.9428.8629.4830.2630.2932.4133.9335.89

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CPU Stress2 x EPYC 76012 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PXeon Silver 4108EPYC 72513K6K9K12K15KSE +/- 83.96, N = 3SE +/- 152.09, N = 3SE +/- 22.81, N = 3SE +/- 94.71, N = 3SE +/- 23.85, N = 3SE +/- 78.60, N = 3SE +/- 18.96, N = 3SE +/- 0.76, N = 3SE +/- 0.84, N = 3158081354711656770073685797418922082050-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Aircrack-ng

Aircrack-ng is a tool for assessing WiFi/WLAN network security. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgk/s, More Is BetterAircrack-ng 1.32 x EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 725120K40K60K80K100KSE +/- 40.45, N = 3SE +/- 48.90, N = 3SE +/- 57.98, N = 3SE +/- 30.75, N = 3SE +/- 184.27, N = 3SE +/- 15.90, N = 3SE +/- 8.74, N = 381871485744073638667307922195811007-masm=intel -march=native-mtune=power9 -mcpu=power9-masm=intel -march=native-masm=intel -march=native-masm=intel -march=native-masm=intel -march=native1. (CXX) g++ options: -O3 -fvisibility=hidden -lpthread -lcrypto -lz -ldl -lm -pthread

Stress-NG

Stress-NG is a Linux stress tool developed by Colin King of Canonical. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Matrix Math2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410860K120K180K240K300KSE +/- 512.47, N = 3SE +/- 1611.57, N = 3SE +/- 180.14, N = 3SE +/- 196.62, N = 3SE +/- 191.50, N = 3SE +/- 311.54, N = 3SE +/- 313.84, N = 3SE +/- 137.48, N = 3SE +/- 419.82, N = 3293419217318137445132994113069103356841854184635402-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Crypto2 x EPYC 76012 x 22-Core POWER9 176 Threads2 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41083K6K9K12K15KSE +/- 16.31, N = 3SE +/- 65.89, N = 3SE +/- 38.00, N = 3SE +/- 37.19, N = 3SE +/- 4.37, N = 3SE +/- 46.58, N = 3SE +/- 0.24, N = 3SE +/- 0.69, N = 3SE +/- 0.72, N = 3119528285620359185663449432151609980-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Vector Math2 x EPYC 76012 x 22-Core POWER9 176 Threads2 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410830K60K90K120K150KSE +/- 1218.29, N = 3SE +/- 36.72, N = 3SE +/- 1209.22, N = 3SE +/- 102.55, N = 3SE +/- 66.12, N = 3SE +/- 78.64, N = 3SE +/- 2.38, N = 3SE +/- 3.26, N = 3SE +/- 1.41, N = 31360629517376477686916434851190369101847712411-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

Stream

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Copy2 x EPYC 76012 x Xeon Gold 6138EPYC 7351PEPYC 7401PEPYC 7251EPYC 7601Xeon Silver 410830K60K90K120K150KSE +/- 1329.22, N = 20SE +/- 1526.86, N = 20SE +/- 9.78, N = 5SE +/- 457.05, N = 5SE +/- 229.10, N = 5SE +/- 933.91, N = 5SE +/- 89.00, N = 515869713044386857844088340982083637951. (CC) gcc options: -O3 -march=native -fopenmp

Swet

Swet is a synthetic CPU/RAM benchmark, includes multi-processor test cases. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgOperations Per Second, More Is BetterSwet 1.5.16Average2 x Xeon Gold 6138EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401P2 x EPYC 7601EPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads130M260M390M520M650MSE +/- 5231349.71, N = 3SE +/- 2499215.04, N = 3SE +/- 4615543.22, N = 3SE +/- 4965131.60, N = 3SE +/- 1474249.14, N = 3SE +/- 4256708.53, N = 3SE +/- 4610229.20, N = 3SE +/- 5491403.58, N = 3SE +/- 771673.37, N = 36141210475288748165269958275069695135050760734918692214850047124793669752934539291. (CC) gcc options: -lm -lpthread -lcurses -lrt

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Composite2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads5001000150020002500SE +/- 5.59, N = 3SE +/- 10.14, N = 3SE +/- 4.34, N = 3SE +/- 2.52, N = 3SE +/- 0.68, N = 3SE +/- 2.09, N = 3SE +/- 4.56, N = 3SE +/- 1.51, N = 3SE +/- 0.73, N = 3244619421940191318691859180513471255-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lm

Mencoder

This test uses mplayer's mencoder utility and the libavcodec family for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterMencoder 1.3.0AVI To LAVC2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads1632486480SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 318.7222.0422.1123.3623.5523.5624.4424.9870.21-fpie -pie -lasound -lfreetype -lfontconfig -lmad -lvorbisenc -lvorbis -logg-fpie -pie -lfreetype -lfontconfig-fpie -pie -lfreetype -lfontconfig-fpie -pie -lfreetype -lfontconfig-fpie -pie -lfreetype -lfontconfig-fpie -pie -lfreetype -lfontconfig-fpie -pie -lfreetype -lfontconfig-fpie -pie -lfreetype -lfontconfig-lasound -lmad -lvorbisenc -lvorbis -logg -std=gnu99 -O3 -mtune=power9 -mcpu=power9 -fno-tree-vectorize -maltivec -mabi=altivec -MMD -MP1. (CC) gcc options: -lncurses -lrt -lpng -lz -ljpeg -ldl -lpthread -lbz2 -rdynamic -lm

John The Ripper

This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Blowfish2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410815K30K45K60K75KSE +/- 1082.68, N = 3SE +/- 312.53, N = 3SE +/- 87.49, N = 3SE +/- 12.66, N = 3SE +/- 663.77, N = 12SE +/- 79.88, N = 3SE +/- 46.49, N = 3SE +/- 3.67, N = 37159148691275912662123048194221010780051. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2

LuaJIT

This test profile is a collection of Lua scripts/benchmarks run against a locally-built copy of LuaJIT upstream. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.0.5Test: Composite2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 725130060090012001500SE +/- 0.60, N = 3SE +/- 2.06, N = 3SE +/- 3.64, N = 3SE +/- 2.00, N = 3SE +/- 1.42, N = 3SE +/- 1.41, N = 3SE +/- 0.97, N = 3SE +/- 3.02, N = 313561131112410821071106610268771. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector

FLAC Audio Encoding

This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLAC2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads1020304050SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 59.2811.4912.3412.3713.1413.1813.6413.6644.21-march=native -logg-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9 -logg1. (CXX) g++ options: -O3 -fvisibility=hidden -lm

Rodinia

Rodinia is a suite focused upon accelerating compute-intensive applications with accelerators. CUDA, OpenMP, and OpenCL parallel models are supported by the included applications. This profile utilizes the OpenCL and OpenMP test binaries at the moment. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP LavaMD2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41081632486480SE +/- 0.16, N = 3SE +/- 0.16, N = 3SE +/- 0.06, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 38.1213.2815.3915.4416.8419.8126.0651.1571.701. (CXX) g++ options: -O2 -lOpenCL

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.6Test: auto-levels2 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351P2 x Xeon Gold 6138EPYC 7251EPYC 7551Xeon Silver 41082 x 22-Core POWER9 176 Threads1020304050SE +/- 0.04, N = 3SE +/- 0.15, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 322.3922.9723.0723.2123.7023.7624.0726.0542.54

PHPBench

PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. The number of iterations used is 1,000,000. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark Suite2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7401PEPYC 7551EPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads130K260K390K520K650KSE +/- 1066.61, N = 3SE +/- 753.79, N = 3SE +/- 59.48, N = 3SE +/- 895.53, N = 3SE +/- 476.01, N = 3SE +/- 1386.84, N = 3SE +/- 800.35, N = 3SE +/- 348.37, N = 3SE +/- 1135.83, N = 3592004479730399660397929372745371645362866362169332659

Go Benchmarks

Benchmark for monitoring real time performance of the Go implementation for HTTP, JSON and garbage testing per iteration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: build2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7351PEPYC 7401PEPYC 7551EPYC 72512 x 22-Core POWER9 176 Threads6000M12000M18000M24000M30000MSE +/- 69188517.89, N = 3SE +/- 38735390.67, N = 3SE +/- 43011538.78, N = 3SE +/- 210856599.47, N = 3SE +/- 71197974.92, N = 3SE +/- 18848230.79, N = 3SE +/- 18911874.89, N = 3SE +/- 79725993.11, N = 3SE +/- 441335412.66, N = 4211600668422205870568222955552367233295573822360678487423648119496238758722852389454693028106987728

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADD2 x Xeon Gold 6138EPYC 7601Xeon Silver 41082 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads400K800K1200K1600K2000KSE +/- 46193.94, N = 12SE +/- 16774.42, N = 3SE +/- 30871.66, N = 12SE +/- 24288.76, N = 4SE +/- 2539.67, N = 3SE +/- 29072.20, N = 3SE +/- 15101.94, N = 3SE +/- 16974.58, N = 12SE +/- 1492.96, N = 31968923165688616549491652577159490415316951474510138456413015221. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integer2 x Xeon Gold 61382 x EPYC 7601EPYC 7401PEPYC 7351PEPYC 7601EPYC 7251Xeon Silver 41086K12K18K24K30K299772974228445282532711326326254521. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerEPYC 7401P2 x EPYC 7601EPYC 7351PEPYC 7601EPYC 72512 x Xeon Gold 6138Xeon Silver 41087K14K21K28K35K340643383433774315613060330552258571. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Integer2 x EPYC 76012 x Xeon Gold 6138EPYC 7351PEPYC 7401PEPYC 7601EPYC 7251Xeon Silver 41086K12K18K24K30K295042926527313268392661326554255451. (CC) gcc options: -O3 -march=native

Rust Prime Benchmark

Based on petehunt/rust-benchmark, this is a prime number benchmark that is multi-threaded and written in Rustlang. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterRust Prime BenchmarkPrime Number Test To 200,000,0002 x 22-Core POWER9 176 Threads2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7351PEPYC 72511326395265SE +/- 0.05, N = 12SE +/- 0.07, N = 4SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 33.544.488.1415.6317.0222.6523.0329.0757.821. (CC) gcc options: -m64 -pie -nodefaultlibs

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating Point2 x EPYC 7601Xeon Silver 4108EPYC 7251EPYC 7351PEPYC 7401P2 x Xeon Gold 6138EPYC 7601EPYC 75516K12K18K24K30K25949250522373023605234862345723388217441. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating Point2 x EPYC 7601EPYC 7401PEPYC 7601EPYC 7351PEPYC 72512 x Xeon Gold 6138Xeon Silver 4108EPYC 75517K14K21K28K35K31026291012885928674272972659225497245311. (CC) gcc options: -O3 -march=native

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.6Test: rotate2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351P2 x Xeon Gold 6138EPYC 7251Xeon Silver 41082 x 22-Core POWER9 176 Threads714212835SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.07, N = 317.8019.1420.1220.1820.4920.7121.9422.8929.31

RAMspeed SMP

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating Point2 x EPYC 7601EPYC 7401PEPYC 7351PEPYC 7601EPYC 7251EPYC 75512 x Xeon Gold 6138Xeon Silver 41086K12K18K24K30K29983286642851328314279502736126785256361. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating Point2 x EPYC 7601EPYC 7351PEPYC 7251EPYC 7401PEPYC 7551EPYC 76012 x Xeon Gold 6138Xeon Silver 41088K16K24K32K40K35322332783272332465319743157126862256551. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating Point2 x Xeon Gold 61382 x EPYC 7601EPYC 7401PEPYC 7601EPYC 7251EPYC 7551EPYC 7351PXeon Silver 41087K14K21K28K35K30702305802840028014275732734726811255551. (CC) gcc options: -O3 -march=native

Primesieve

Primesieve generates prime numbers using a highly optimized sieve of Eratosthenes implementation. Primesieve benchmarks the CPU's L1/L2 cache performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.11e12 Prime Number Generation2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41081122334455SE +/- 0.03, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.12, N = 3SE +/- 0.04, N = 36.348.8812.7012.9316.4216.8320.6143.0147.66-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native1. (CXX) g++ options: -O3 -lpthread

OpenSSL

OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performance2 x EPYC 76012 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PXeon Silver 4108EPYC 72512K4K6K8K10KSE +/- 14.27, N = 3SE +/- 11.30, N = 3SE +/- 40.66, N = 3SE +/- 19.16, N = 3SE +/- 4.04, N = 3SE +/- 32.65, N = 3SE +/- 0.55, N = 3SE +/- 1.20, N = 3SE +/- 0.49, N = 3922577457377455443623503248312861242-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

GnuPG

This test times how long it takes to encrypt a file using GnuPG. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGnuPGLinux 4.3 Package File Encryption2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7251EPYC 7351P510152025SE +/- 0.25, N = 3SE +/- 0.27, N = 4SE +/- 0.35, N = 3SE +/- 0.35, N = 3SE +/- 0.27, N = 4SE +/- 0.31, N = 3SE +/- 0.32, N = 3SE +/- 0.30, N = 4SE +/- 0.34, N = 314.4217.2317.3617.8218.3918.5818.7418.9919.45

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SET2 x Xeon Gold 61382 x EPYC 7601Xeon Silver 4108EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads400K800K1200K1600K2000KSE +/- 18319.51, N = 11SE +/- 25872.16, N = 3SE +/- 27918.55, N = 12SE +/- 18354.77, N = 3SE +/- 19395.95, N = 3SE +/- 21411.56, N = 4SE +/- 18027.86, N = 3SE +/- 2556.44, N = 3SE +/- 4793.10, N = 31784172139631213916771367859131866513103921308263112318610866051. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Sudokut

This is a test of Sudokut, which is a Sudoku puzzle solver written in Tcl. This test measures how long it takes to solve 100 Sudoku puzzles. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSudokut 0.4Total Time2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7551EPYC 7401PEPYC 7251EPYC 7351P510152025SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 311.1113.8318.0718.7819.4419.9119.9220.3020.59

dcraw

This test times how long it takes to convert several high-resolution RAW NEF image files to PPM image format using dcraw. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterdcrawRAW To PPM Image Conversion2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 313.0415.9416.1516.3317.1817.2517.7617.8119.98-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lm

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: EP.C2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PXeon Silver 4108EPYC 7251400800120016002000SE +/- 0.70, N = 3SE +/- 10.17, N = 3SE +/- 0.67, N = 3SE +/- 0.51, N = 3SE +/- 1.22, N = 3SE +/- 1.08, N = 3SE +/- 1.69, N = 3SE +/- 0.03, N = 3177716278928356904812592411. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiBXeon Silver 41082 x EPYC 7601EPYC 7551EPYC 7601EPYC 7401PEPYC 7351PEPYC 72512 x Xeon Gold 61382K4K6K8K10KSE +/- 1.29, N = 3SE +/- 34.11, N = 3SE +/- 7.99, N = 3SE +/- 4.06, N = 3SE +/- 3.27, N = 3SE +/- 5.81, N = 3SE +/- 5.39, N = 3SE +/- 21.51, N = 3803176007144710069946977684749231. (CC) gcc options: -O3 -march=native

x264

This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video Encoding2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72512 x 22-Core POWER9 176 ThreadsXeon Silver 4108306090120150SE +/- 12.24, N = 9SE +/- 2.11, N = 3SE +/- 0.50, N = 3SE +/- 0.53, N = 3SE +/- 1.47, N = 12SE +/- 0.39, N = 3SE +/- 0.23, N = 3SE +/- 2.16, N = 10SE +/- 0.23, N = 3131.75112.63106.75106.1399.5093.6655.9149.3635.48-lavformat -lavcodec -lavutil -lswscale -m64 -march=native-lavformat -lavcodec -lavutil -lswscale -m64 -march=native-lavformat -lavcodec -lavutil -lswscale -m64 -march=native-lavformat -lavcodec -lavutil -lswscale -m64 -march=native-lavformat -lavcodec -lavutil -lswscale -m64 -march=native-lavformat -lavcodec -lavutil -lswscale -m64 -march=native-lavformat -lavcodec -lavutil -lswscale -m64 -march=native-lavformat -lavcodec -lavutil -lswscale -mtune=power9 -mcpu=power9 -maltivec -mabi=altivec -mvsx-m64 -march=native1. (CC) gcc options: -ldl -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSH2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads400K800K1200K1600K2000KSE +/- 13534.43, N = 3SE +/- 11136.38, N = 3SE +/- 3726.29, N = 3SE +/- 14251.32, N = 3SE +/- 13067.87, N = 3SE +/- 19390.48, N = 3SE +/- 21415.56, N = 12SE +/- 19273.98, N = 3SE +/- 2532.17, N = 317243521381396121509011974691119292110729110647699862858881141. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 10242 x Xeon Gold 61382 x EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7401PEPYC 7351PEPYC 7551Xeon Silver 4108EPYC 725116003200480064008000SE +/- 4.37, N = 3SE +/- 19.93, N = 3SE +/- 23.58, N = 3SE +/- 39.74, N = 3SE +/- 19.47, N = 3SE +/- 7.61, N = 3SE +/- 18.94, N = 3SE +/- 45.92, N = 3SE +/- 74.35, N = 37572662365966587624960015803566054181. (CC) gcc options: -pthread -O3 -march=native -lm

GIMP

GIMP is an open-source image manipulaton program. This test profile will use the system-provided GIMP program otherwise on Windows relys upon a pre-packaged Windows binary from upstream GIMP.org. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.10.6Test: resize2 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7551EPYC 72512 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 Threads48121620SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 312.3412.8613.2313.4813.4814.4815.3816.4917.95

Redis

Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GET2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7551EPYC 7601EPYC 7401PEPYC 7351P2 x 22-Core POWER9 176 ThreadsEPYC 7251500K1000K1500K2000K2500KSE +/- 12798.88, N = 3SE +/- 28285.41, N = 3SE +/- 21300.51, N = 3SE +/- 19052.51, N = 3SE +/- 12124.99, N = 3SE +/- 10607.60, N = 3SE +/- 26137.53, N = 12SE +/- 16810.41, N = 3SE +/- 10123.48, N = 32475379194131919028261869551183839617312321716532162284415465251. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Bork File Encrypter

Bork is a small, cross-platform file encryption utility. It is written in Java and designed to be included along with the files it encrypts for long-term storage. This test measures the amount of time it takes to encrypt a sample file. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBork File Encrypter 1.4File Encryption Time2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads510152025SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 37.659.9012.2112.2312.8713.0213.4413.4922.15

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 40962 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P12K24K36K48K60KSE +/- 328.49, N = 3SE +/- 1332.84, N = 12SE +/- 42.58, N = 3SE +/- 244.62, N = 3SE +/- 7.97, N = 3SE +/- 134.20, N = 3SE +/- 153.98, N = 3SE +/- 336.87, N = 355983302702723326877255142507524551244031. (CC) gcc options: -pthread -O3 -march=native -lm

FFmpeg

This test uses FFmpeg for testing the system's audio/video encoding performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 4.0.2H.264 HD To NTSC DVEPYC 7601EPYC 7351PEPYC 7401PEPYC 7551EPYC 7251Xeon Silver 4108510152025SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 310.5110.6810.7010.8311.2418.34-llzma1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lxcb-shape -lxcb-xfixes -pthread -lbz2 -O3 -march=native -std=c11 -fomit-frame-pointer -fPIC -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT

DaCapo Benchmark

This test runs the DaCapo Benchmarks written in Java and intended to test system/CPU performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgmsec, Fewer Is BetterDaCapo Benchmark 9.12-MR1Java Test: Jython2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7351PEPYC 725116003200480064008000SE +/- 8.54, N = 4SE +/- 29.70, N = 4SE +/- 83.82, N = 4SE +/- 94.68, N = 4SE +/- 48.95, N = 4SE +/- 26.42, N = 4SE +/- 94.65, N = 4SE +/- 47.64, N = 4437852786437674368136942698570757435

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP32 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351PXeon Silver 41082 x 22-Core POWER9 176 Threads48121620SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 39.9110.5110.5111.1811.2011.5911.5912.3215.89-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lncurses -lm

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 1024 MiBEPYC 75512 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082 x Xeon Gold 61383K6K9K12K15KSE +/- 45.65, N = 3SE +/- 6.11, N = 3SE +/- 1.14, N = 3SE +/- 2.86, N = 3SE +/- 1.31, N = 3SE +/- 37.55, N = 3SE +/- 1.29, N = 3SE +/- 17.22, N = 3128671275712722126891260711828837647921. (CC) gcc options: -O3 -march=native

Timed MAFFT Alignment

This test performs an alignment of 100 pyruvate decarboxylase sequences. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence AlignmentEPYC 7351PEPYC 76012 x EPYC 76012 x Xeon Gold 6138EPYC 7401PEPYC 7551EPYC 72512 x 22-Core POWER9 176 ThreadsXeon Silver 41081.09132.18263.27394.36525.4565SE +/- 0.05, N = 12SE +/- 0.03, N = 3SE +/- 0.05, N = 12SE +/- 0.06, N = 12SE +/- 0.06, N = 5SE +/- 0.10, N = 9SE +/- 0.13, N = 11SE +/- 0.26, N = 11SE +/- 0.04, N = 33.433.453.453.503.653.954.074.304.851. (CC) gcc options: -std=c99 -O3 -lm -lpthread

N-Queens

This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed Time2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108714212835SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.784.845.295.586.849.7319.4230.231. (CC) gcc options: -static -fopenmp -O3 -march=native

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 20482 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 725113K26K39K52K65KSE +/- 279.19, N = 3SE +/- 1432.58, N = 12SE +/- 58.67, N = 3SE +/- 185.90, N = 3SE +/- 60.64, N = 3SE +/- 199.16, N = 3SE +/- 19.92, N = 3SE +/- 59.33, N = 360079321492724027128256052543024743247241. (CC) gcc options: -pthread -O3 -march=native -lm

Sysbench

This is a benchmark of Sysbench with CPU and memory sub-tests. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPU2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410820K40K60K80K100KSE +/- 80.32, N = 3SE +/- 350.34, N = 3SE +/- 135.35, N = 3SE +/- 114.17, N = 3SE +/- 36.44, N = 3SE +/- 5.28, N = 3SE +/- 3.34, N = 3SE +/- 1.14, N = 38874960216447224223934901241521210196421. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=native -rdynamic -ldl -laio -lm

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database Search2 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72512 x Xeon Gold 6138Xeon Silver 410848121620SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.02, N = 3SE +/- 0.16, N = 36.737.928.038.238.379.2012.2814.321. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 512EPYC 76012 x EPYC 76012 x Xeon Gold 6138EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41085K10K15K20K25KSE +/- 16.42, N = 3SE +/- 12.50, N = 3SE +/- 60.05, N = 3SE +/- 21.39, N = 3SE +/- 51.96, N = 3SE +/- 38.39, N = 3SE +/- 76.85, N = 3SE +/- 131.09, N = 323368233392316021925218802116720754185531. (CC) gcc options: -pthread -O3 -march=native -lm

Darktable

Darktable is an open-source photography / workflow application this will use any system-installed Darktable program or on Windows will automatically download the pre-built binary from the project. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.4.4Test: Masskrug - Acceleration: CPU-only2 x Xeon Gold 6138EPYC 7601EPYC 7401PEPYC 7551EPYC 7351P2 x EPYC 7601Xeon Silver 4108EPYC 72513691215SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.01, N = 3SE +/- 0.14, N = 35.386.076.426.496.987.138.8810.21

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 512 MiBXeon Silver 41082 x EPYC 7601EPYC 7551EPYC 7601EPYC 7401PEPYC 7351PEPYC 72512 x Xeon Gold 61382K4K6K8K10KSE +/- 19.50, N = 3SE +/- 5.16, N = 3SE +/- 13.37, N = 3SE +/- 4.86, N = 3SE +/- 6.17, N = 3SE +/- 5.44, N = 3SE +/- 6.49, N = 3SE +/- 15.97, N = 3797475997145714370527040688549051. (CC) gcc options: -O3 -march=native

Ogg Encoding

This test times how long it takes to encode a sample WAV file to Ogg format using vorbis-tools, libvorbis, and libogg. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.3WAV To Ogg2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P246810SE +/- 0.05, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 36.727.577.618.078.168.368.381. (CC) gcc options: -O2 -ffast-math -fsigned-char -O3 -march=native -logg

Smallpt

Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 Samples2 x EPYC 76012 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsEPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 4108510152025SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 32.574.094.104.514.685.797.9215.3520.49-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CXX) g++ options: -fopenmp -O3

Git

This test measures the time needed to carry out some sample Git operations on an example, static repository that happens to be a copy of the GNOME GTK tool-kit repository. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterGitTime To Complete Common Git Commands2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads246810SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.10, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.03, N = 36.207.107.157.457.507.637.867.938.671. git version 2.19.1

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 10242 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 725113K26K39K52K65KSE +/- 168.06, N = 3SE +/- 1582.83, N = 9SE +/- 73.92, N = 3SE +/- 55.97, N = 3SE +/- 35.80, N = 3SE +/- 67.10, N = 3SE +/- 125.44, N = 3SE +/- 118.17, N = 360471386782698226946253722514924331243021. (CC) gcc options: -pthread -O3 -march=native -lm

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNs Per Event, Fewer Is BetterOSBenchTest: Memory Allocations2 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401P2 x Xeon Gold 6138EPYC 7351PEPYC 7251Xeon Silver 410820406080100SE +/- 0.72, N = 12SE +/- 0.21, N = 3SE +/- 0.08, N = 3SE +/- 0.15, N = 3SE +/- 0.04, N = 3SE +/- 0.14, N = 3SE +/- 0.22, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 365.3892.4793.4894.8996.1996.4396.6898.2499.49-mtune=power9 -mcpu=power9 -lm-march=native -lm-march=native -lm-march=native -lm-march=native -lm-march=native -lm-march=native -lm-march=native -lm-march=native1. (CC) gcc options: -O3

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 322 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72513K6K9K12K15KSE +/- 6.17, N = 3SE +/- 149.77, N = 12SE +/- 114.40, N = 3SE +/- 110.80, N = 12SE +/- 1.25, N = 3SE +/- 74.27, N = 3SE +/- 114.53, N = 12SE +/- 102.38, N = 1214926118309982980294639410885186351. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 40962 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsXeon Silver 4108EPYC 7251EPYC 7351P2K4K6K8K10KSE +/- 97.54, N = 3SE +/- 57.58, N = 3SE +/- 38.36, N = 3SE +/- 7.47, N = 3SE +/- 11.98, N = 3SE +/- 33.82, N = 3SE +/- 63.56, N = 3SE +/- 13.90, N = 3SE +/- 23.73, N = 38743787978787451735173187316717971511. (CC) gcc options: -pthread -O3 -march=native -lm

libjpeg-turbo tjbench

tjbench is a JPEG decompression/compression benchmark part of libjpeg-turbo. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.3Test: Decompression Throughput2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads4080120160200SE +/- 0.17, N = 3SE +/- 0.02, N = 3SE +/- 1.27, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 3SE +/- 0.14, N = 3SE +/- 1.38, N = 3SE +/- 1.11, N = 3SE +/- 0.02, N = 3163147146138137133132132106-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lm

PolyBench-C

PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: Correlation Computation2 x EPYC 7601EPYC 76012 x Xeon Gold 6138EPYC 7401PEPYC 7551EPYC 7351PEPYC 7251Xeon Silver 4108246810SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 35.465.475.755.775.826.006.057.111. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: Covariance Computation2 x EPYC 7601EPYC 76012 x Xeon Gold 6138EPYC 7401PEPYC 7551EPYC 7351PEPYC 7251Xeon Silver 4108246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.445.485.755.765.806.016.047.101. (CC) gcc options: -O3 -march=native

Bullet Physics Engine

This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Raytests2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads1.11832.23663.35494.47325.5915SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 32.673.143.143.293.343.353.473.484.97-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 2562 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 72517K14K21K28K35KSE +/- 535.19, N = 12SE +/- 214.30, N = 3SE +/- 30.28, N = 3SE +/- 51.01, N = 3SE +/- 31.25, N = 3SE +/- 60.62, N = 3SE +/- 40.93, N = 3SE +/- 115.24, N = 334786254092071820641194901945118827186221. (CC) gcc options: -pthread -O3 -march=native -lm

OSBench

OSBench is a collection of micro-benchmarks for measuring operating system primitives like time to create threads/processes, launching programs, creating files, and memory allocation. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgus Per Event, Fewer Is BetterOSBenchTest: Create Files2 x Xeon Gold 6138Xeon Silver 4108EPYC 7601EPYC 75512 x EPYC 7601EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads816243240SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.08, N = 3SE +/- 0.07, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 316.0517.9818.8819.5519.5519.9920.4921.0332.71-march=native -lm-march=native-march=native -lm-march=native -lm-march=native -lm-march=native -lm-march=native -lm-march=native -lm-mtune=power9 -mcpu=power9 -lm1. (CC) gcc options: -O3

NAS Parallel Benchmarks

NPB, NAS Parallel Benchmarks, is a benchmark developed by NASA for high-end computer systems. This test profile currently uses the MPI version of NPB. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgTotal Mop/s, More Is BetterNAS Parallel Benchmarks 3.3Test / Class: LU.A2 x EPYC 76012 x Xeon Gold 6138EPYC 7601EPYC 7401PEPYC 7551EPYC 7351PEPYC 7251Xeon Silver 410830K60K90K120K150KSE +/- 725.20, N = 3SE +/- 886.73, N = 3SE +/- 38.80, N = 3SE +/- 1428.44, N = 12SE +/- 211.73, N = 3SE +/- 1902.85, N = 12SE +/- 124.40, N = 3SE +/- 20.75, N = 3133328861257076460871548464335323683191731. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 512 MiBEPYC 75512 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082 x Xeon Gold 61383K6K9K12K15KSE +/- 2.69, N = 3SE +/- 1.99, N = 3SE +/- 0.98, N = 3SE +/- 4.38, N = 3SE +/- 0.99, N = 3SE +/- 1.84, N = 3SE +/- 7.38, N = 3SE +/- 1.11, N = 3129451283912749127231266711891845348291. (CC) gcc options: -O3 -march=native

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 2562 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41085K10K15K20K25KSE +/- 38.49, N = 3SE +/- 34.33, N = 3SE +/- 121.76, N = 3SE +/- 76.96, N = 3SE +/- 80.86, N = 3SE +/- 17.32, N = 3SE +/- 337.65, N = 324425229202278121574214752073920730193101. (CC) gcc options: -pthread -O3 -march=native -lm

Optcarrot

Optcarrot is an NES emulator benchmark for the Ruby language. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterOptcarrotOptimized Benchmark2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads306090120150SE +/- 0.20, N = 4SE +/- 0.63, N = 4SE +/- 0.67, N = 4SE +/- 0.14, N = 4SE +/- 0.14, N = 4SE +/- 0.11, N = 4SE +/- 0.09, N = 4SE +/- 0.17, N = 4SE +/- 0.03, N = 4114.6792.9160.7459.8257.3556.7955.7154.9949.071. 2 x Xeon Gold 6138: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]2. Xeon Silver 4108: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]3. EPYC 7601: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]4. 2 x EPYC 7601: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]5. EPYC 7551: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]6. EPYC 7401P: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]7. EPYC 7351P: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]8. EPYC 7251: ruby 2.5.1p57 (2018-03-29 revision 63029) [x86_64-linux-gnu]9. 2 x 22-Core POWER9 176 Threads: ruby 2.5.1p57 (2018-03-29 revision 63029) [powerpc64le-linux-gnu]

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 5122 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P11K22K33K44K55KSE +/- 25.41, N = 3SE +/- 441.60, N = 7SE +/- 106.81, N = 3SE +/- 30.27, N = 3SE +/- 95.84, N = 3SE +/- 205.23, N = 3SE +/- 124.63, N = 3SE +/- 44.88, N = 349508354042514324876234962336822612225651. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 5122 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7351PXeon Silver 4108EPYC 725117003400510068008500SE +/- 79.27, N = 3SE +/- 29.10, N = 3SE +/- 8.96, N = 3SE +/- 5.90, N = 3SE +/- 11.10, N = 3SE +/- 7.39, N = 3SE +/- 8.00, N = 3SE +/- 14.48, N = 3SE +/- 20.19, N = 37761754575017120706670556858644063151. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 20482 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsXeon Silver 4108EPYC 7251EPYC 7351P2K4K6K8K10KSE +/- 71.15, N = 3SE +/- 41.75, N = 3SE +/- 35.10, N = 3SE +/- 20.79, N = 3SE +/- 2.04, N = 3SE +/- 38.68, N = 3SE +/- 100.55, N = 3SE +/- 5.51, N = 3SE +/- 45.42, N = 39016798479677522747473507342727672101. (CC) gcc options: -pthread -O3 -march=native -lm

Tachyon

This is a test of the threaded Tachyon, a parallel ray-tracing system. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total Time2 x EPYC 7601EPYC 7551EPYC 76012 x Xeon Gold 6138EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41083691215SE +/- 0.02, N = 12SE +/- 0.02, N = 3SE +/- 0.04, N = 4SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 31.482.372.372.492.863.947.699.781. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 642 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7351PEPYC 72514K8K12K16K20KSE +/- 202.32, N = 3SE +/- 57.51, N = 3SE +/- 44.76, N = 3SE +/- 99.65, N = 3SE +/- 103.85, N = 3SE +/- 527.45, N = 12SE +/- 20.27, N = 3SE +/- 54.37, N = 316593134581342012717127071261112165120621. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 322 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72518K16K24K32K40KSE +/- 682.47, N = 12SE +/- 92.02, N = 3SE +/- 12.35, N = 3SE +/- 22.84, N = 3SE +/- 12.60, N = 3SE +/- 5.78, N = 3SE +/- 8.14, N = 3SE +/- 4.73, N = 337123305752570425666241252407523287232841. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 2562 x Xeon Gold 6138EPYC 76012 x EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082K4K6K8K10KSE +/- 20.18, N = 3SE +/- 3.90, N = 3SE +/- 32.99, N = 3SE +/- 13.47, N = 3SE +/- 13.08, N = 3SE +/- 48.04, N = 3SE +/- 14.67, N = 3SE +/- 85.65, N = 7SE +/- 6.86, N = 37973770776887242721471446969682565781. (CC) gcc options: -pthread -O3 -march=native -lm

Parboil

The Parboil Benchmarks from the IMPACT Research Group at University of Illinois are a set of throughput computing applications for looking at computing architecture and compilers. Parboil test-cases support OpenMP, OpenCL, and CUDA multi-processing environments. However, at this time the test profile is just making use of the OpenMP and OpenCL test workloads. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPEPYC 76012 x Xeon Gold 61382 x EPYC 7601EPYC 7551EPYC 7401P2 x 22-Core POWER9 176 ThreadsEPYC 7351PEPYC 7251Xeon Silver 4108246810SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.11, N = 12SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 31.851.871.901.962.362.692.824.957.801. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp

PolyBench-C

PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: 3 Matrix Multiplications2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41081.00352.0073.01054.0145.0175SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 33.263.643.663.723.873.884.324.461. (CC) gcc options: -O3 -march=native

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 10242 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 ThreadsXeon Silver 41082K4K6K8K10KSE +/- 47.78, N = 3SE +/- 4.44, N = 3SE +/- 7.34, N = 3SE +/- 6.48, N = 3SE +/- 19.94, N = 3SE +/- 2.11, N = 3SE +/- 6.43, N = 3SE +/- 22.02, N = 3SE +/- 71.02, N = 39321851285077999796677077703757175681. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 322 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads3K6K9K12K15KSE +/- 24.61, N = 3SE +/- 12.06, N = 3SE +/- 12.03, N = 3SE +/- 144.76, N = 5SE +/- 2.68, N = 3SE +/- 6.86, N = 3SE +/- 9.41, N = 3SE +/- 13.43, N = 3SE +/- 123.10, N = 1212779106401062610140999799719648959188031. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 1282 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72515K10K15K20K25KSE +/- 418.34, N = 3SE +/- 245.69, N = 3SE +/- 13.92, N = 3SE +/- 33.78, N = 3SE +/- 45.95, N = 3SE +/- 12.39, N = 3SE +/- 25.40, N = 3SE +/- 80.88, N = 321540163471618416160151751516614638145791. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 642 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7401PEPYC 75512 x 22-Core POWER9 176 ThreadsEPYC 7351PEPYC 72512K4K6K8K10KSE +/- 75.64, N = 3SE +/- 26.89, N = 3SE +/- 16.83, N = 3SE +/- 135.30, N = 3SE +/- 6.97, N = 3SE +/- 24.19, N = 3SE +/- 14.92, N = 3SE +/- 8.42, N = 3SE +/- 17.75, N = 310137827777817652728972837072707170491. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 1282 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7401PXeon Silver 4108EPYC 7251EPYC 7351PEPYC 75516K12K18K24K30KSE +/- 228.34, N = 3SE +/- 38.53, N = 3SE +/- 82.15, N = 3SE +/- 64.58, N = 3SE +/- 59.42, N = 3SE +/- 51.87, N = 3SE +/- 122.86, N = 3SE +/- 21.31, N = 328501250972502423452229492269022609206631. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 642 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P7K14K21K28K35KSE +/- 322.58, N = 3SE +/- 312.71, N = 3SE +/- 21.30, N = 3SE +/- 40.48, N = 3SE +/- 70.97, N = 3SE +/- 54.06, N = 3SE +/- 32.97, N = 3SE +/- 5.24, N = 332447258782550925417238882385723052230481. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 642 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P2 x 22-Core POWER9 176 Threads3K6K9K12K15KSE +/- 2.65, N = 3SE +/- 91.03, N = 3SE +/- 8.58, N = 3SE +/- 106.80, N = 3SE +/- 1.39, N = 3SE +/- 12.00, N = 3SE +/- 3.94, N = 3SE +/- 5.93, N = 3SE +/- 6.67, N = 311866950778947790741174117157715168251. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 5122 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7401P2 x 22-Core POWER9 176 ThreadsEPYC 7551EPYC 7351PEPYC 72512K4K6K8K10KSE +/- 67.87, N = 3SE +/- 7.17, N = 3SE +/- 29.16, N = 3SE +/- 38.44, N = 3SE +/- 7.78, N = 3SE +/- 43.59, N = 3SE +/- 35.70, N = 3SE +/- 28.83, N = 3SE +/- 28.29, N = 39441829082307833776277357724746274581. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1282 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 41082 x 22-Core POWER9 176 ThreadsEPYC 7401PEPYC 7551EPYC 7251EPYC 7351P2K4K6K8K10KSE +/- 4.79, N = 3SE +/- 18.87, N = 3SE +/- 4.01, N = 3SE +/- 62.88, N = 3SE +/- 0.62, N = 3SE +/- 4.97, N = 3SE +/- 24.98, N = 3SE +/- 30.56, N = 3SE +/- 17.41, N = 39006777677757377727672567255708970531. (CC) gcc options: -pthread -O3 -march=native -lm

TSCP

This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performance2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P300K600K900K1200K1500KSE +/- 625.35, N = 5SE +/- 1453.67, N = 5SE +/- 2138.20, N = 5SE +/- 674.17, N = 5SE +/- 2113.08, N = 5SE +/- 1594.13, N = 5SE +/- 1315.49, N = 5SE +/- 433.33, N = 511860009602218547358531278038428000967731397720471. (CC) gcc options: -O3 -march=native

FFTW

FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1282 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 76012 x 22-Core POWER9 176 ThreadsEPYC 7551EPYC 7401PEPYC 7251EPYC 7351P2K4K6K8K10KSE +/- 102.73, N = 3SE +/- 50.56, N = 3SE +/- 29.00, N = 3SE +/- 12.89, N = 3SE +/- 11.93, N = 3SE +/- 78.20, N = 3SE +/- 36.41, N = 3SE +/- 7.85, N = 3SE +/- 29.20, N = 39827787975487505720371076950682367721. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 2562 x Xeon Gold 61382 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7251EPYC 7351P2K4K6K8K10KSE +/- 67.52, N = 3SE +/- 29.31, N = 3SE +/- 35.12, N = 3SE +/- 31.92, N = 3SE +/- 24.61, N = 3SE +/- 48.89, N = 3SE +/- 51.13, N = 3SE +/- 33.97, N = 3SE +/- 54.99, N = 39489825181878091766475977589738973461. (CC) gcc options: -pthread -O3 -march=native -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 322 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 72512 x 22-Core POWER9 176 ThreadsEPYC 7351P3K6K9K12K15KSE +/- 138.99, N = 3SE +/- 140.16, N = 3SE +/- 11.35, N = 3SE +/- 4.41, N = 3SE +/- 10.33, N = 3SE +/- 11.05, N = 3SE +/- 6.78, N = 3SE +/- 30.24, N = 3SE +/- 0.00, N = 312627101791016910163956095379225747872111. (CC) gcc options: -pthread -O3 -march=native -lm

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sin2 x Xeon Gold 6138Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601EPYC 7251EPYC 7351P4080120160200SE +/- 0.06, N = 3SE +/- 0.23, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3105117132132136136143164

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: cos2 x Xeon Gold 6138Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601EPYC 7251EPYC 7351P4080120160200SE +/- 0.07, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3106117132132137137144164

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy, Fixed Block Size - Array Size: 128 MiBXeon Silver 41082 x EPYC 7601EPYC 7551EPYC 7601EPYC 7401PEPYC 7351PEPYC 72512 x Xeon Gold 61382K4K6K8K10KSE +/- 2.79, N = 3SE +/- 6.53, N = 3SE +/- 5.34, N = 3SE +/- 6.21, N = 3SE +/- 3.11, N = 3SE +/- 2.83, N = 3SE +/- 2.48, N = 3SE +/- 4.45, N = 3798968756278625861956164606849501. (CC) gcc options: -O3 -march=native

glibc bench

The GNU C Library project provides the core libraries for the GNU system and GNU/Linux systems, as well as many other systems that use Linux as the kernel. These libraries provide critical APIs including ISO C11, POSIX.1-2008, BSD, OS-specific APIs and more. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanh2 x Xeon Gold 6138Xeon Silver 4108EPYC 7401PEPYC 75512 x EPYC 7601EPYC 7601EPYC 7251EPYC 7351P918273645SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.11, N = 3SE +/- 0.81, N = 12SE +/- 0.00, N = 3SE +/- 0.02, N = 327.8730.9633.3333.3434.5035.1936.2041.41

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_once2 x Xeon Gold 6138Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601EPYC 7251EPYC 7351P1.30952.6193.92855.2386.5475SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.804.224.694.694.834.835.095.82

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffs2 x Xeon Gold 6138Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601EPYC 7251EPYC 7351P1.30732.61463.92195.22926.5365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.273.634.684.684.824.825.085.81

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsll2 x Xeon Gold 6138Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601EPYC 7251EPYC 7351P1.30732.61463.92195.22926.5365SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.263.634.684.684.824.825.085.81

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtEPYC 7401PEPYC 7551EPYC 76012 x EPYC 7601EPYC 7251EPYC 7351P2 x Xeon Gold 6138Xeon Silver 41083691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 34.554.554.704.704.955.658.989.98

MBW

This is a basic/simple memory (RAM) bandwidth benchmark for memory copy operations. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMiB/s, More Is BetterMBW 2018-09-08Test: Memory Copy - Array Size: 128 MiBEPYC 75512 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082 x Xeon Gold 61383K6K9K12K15KSE +/- 1.60, N = 3SE +/- 1.74, N = 3SE +/- 8.53, N = 3SE +/- 4.25, N = 3SE +/- 4.63, N = 3SE +/- 2.19, N = 3SE +/- 13.65, N = 3SE +/- 1.77, N = 3129851294312807127291266011908852249801. (CC) gcc options: -O3 -march=native

Java SciMark

This test runs the Java version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This benchmark is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Jacobi Successive Over-Relaxation2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082 x 22-Core POWER9 176 Threads30060090012001500SE +/- 5.90, N = 4SE +/- 0.40, N = 4SE +/- 0.62, N = 4SE +/- 0.27, N = 4SE +/- 0.12, N = 4SE +/- 0.18, N = 4SE +/- 0.10, N = 4SE +/- 4.20, N = 4SE +/- 0.16, N = 414151346134612641262122012191154797

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Dense LU Matrix Factorization2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads11002200330044005500SE +/- 31.04, N = 4SE +/- 46.87, N = 4SE +/- 8.68, N = 4SE +/- 10.41, N = 4SE +/- 31.76, N = 4SE +/- 33.70, N = 4SE +/- 13.67, N = 4SE +/- 11.21, N = 4SE +/- 12.22, N = 4512842453861385735953579349634882342

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Sparse Matrix Multiply2 x EPYC 7601EPYC 76012 x Xeon Gold 6138EPYC 7551EPYC 7401PEPYC 7251EPYC 7351PXeon Silver 41082 x 22-Core POWER9 176 Threads5001000150020002500SE +/- 0.54, N = 4SE +/- 0.63, N = 4SE +/- 2.01, N = 4SE +/- 0.56, N = 4SE +/- 0.35, N = 4SE +/- 0.74, N = 4SE +/- 0.65, N = 4SE +/- 2.59, N = 4SE +/- 0.60, N = 4209820972055197019671901189916631028

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Fast Fourier TransformEPYC 76012 x EPYC 76012 x Xeon Gold 6138EPYC 7401PEPYC 7551EPYC 7251EPYC 7351PXeon Silver 41082 x 22-Core POWER9 176 Threads30060090012001500SE +/- 9.53, N = 4SE +/- 1.67, N = 4SE +/- 10.59, N = 4SE +/- 7.82, N = 4SE +/- 9.27, N = 4SE +/- 4.80, N = 4SE +/- 109.56, N = 4SE +/- 3.47, N = 4SE +/- 8.55, N = 414231413137913331330128611701102896

OpenBenchmarking.orgMflops, More Is BetterJava SciMark 2.0Computational Test: Monte Carlo2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x Xeon Gold 61382 x 22-Core POWER9 176 ThreadsXeon Silver 410830060090012001500SE +/- 2.92, N = 4SE +/- 0.14, N = 4SE +/- 0.00, N = 4SE +/- 2.34, N = 4SE +/- 0.12, N = 4SE +/- 0.00, N = 4SE +/- 0.11, N = 4SE +/- 0.17, N = 4SE +/- 0.36, N = 4123512301155115511141114911756737

Bullet Physics Engine

This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex Trimesh2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads0.45450.9091.36351.8182.2725SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.171.341.341.431.441.451.481.492.02-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim Trimesh2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7401PEPYC 7551Xeon Silver 4108EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads0.34880.69761.04641.39521.744SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.991.141.141.211.211.221.261.271.55-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 Ragdolls2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads0.94051.8812.82153.7624.7025SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 32.693.113.123.303.313.323.443.804.18-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Convex2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PXeon Silver 4108EPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 34.635.355.355.695.705.705.926.208.82-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Stack2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 34.695.795.815.846.166.176.427.057.72-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 Fall2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads246810SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 34.235.055.065.265.335.365.556.206.32-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxation2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 41082 x 22-Core POWER9 176 Threads400800120016002000SE +/- 0.09, N = 3SE +/- 0.17, N = 3SE +/- 1.86, N = 3SE +/- 0.28, N = 3SE +/- 0.29, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.34, N = 3SE +/- 0.06, N = 3186716881686158615821530152615111248-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorization2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7401PEPYC 7551EPYC 7351P2 x 22-Core POWER9 176 ThreadsEPYC 725113002600390052006500SE +/- 24.65, N = 3SE +/- 72.81, N = 3SE +/- 0.36, N = 3SE +/- 11.60, N = 3SE +/- 12.85, N = 3SE +/- 4.87, N = 3SE +/- 10.24, N = 3SE +/- 2.48, N = 3SE +/- 4.16, N = 3585648444796475546424640448634402293-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power9-march=native1. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiply2 x Xeon Gold 6138EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PXeon Silver 4108EPYC 72512 x 22-Core POWER9 176 Threads6001200180024003000SE +/- 2.94, N = 3SE +/- 22.23, N = 3SE +/- 28.59, N = 3SE +/- 4.24, N = 3SE +/- 3.30, N = 3SE +/- 13.38, N = 3SE +/- 3.73, N = 3SE +/- 9.64, N = 3SE +/- 0.21, N = 3300924412398238523422302222422031120-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform2 x Xeon Gold 6138Xeon Silver 41082 x 22-Core POWER9 176 Threads2 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7251EPYC 7351P150300450600750SE +/- 2.13, N = 3SE +/- 0.43, N = 3SE +/- 1.45, N = 3SE +/- 0.16, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 3SE +/- 0.12, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3685411305227219210208206203-march=native-march=native-mtune=power9 -mcpu=power9-march=native-march=native-march=native-march=native-march=native-march=native1. (CC) gcc options: -O3 -lm

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlo2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 72512 x 22-Core POWER9 176 Threads2004006008001000SE +/- 0.22, N = 3SE +/- 0.30, N = 3SE +/- 0.06, N = 3SE +/- 0.47, N = 3SE +/- 0.08, N = 3SE +/- 0.16, N = 3SE +/- 0.17, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3816661556556523521504504162-march=native-march=native-march=native-march=native-march=native-march=native-march=native-march=native-mtune=power9 -mcpu=power91. (CC) gcc options: -O3 -lm

LuaJIT

This test profile is a collection of Lua scripts/benchmarks run against a locally-built copy of LuaJIT upstream. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.0.5Test: Jacobi Successive Over-Relaxation2 x EPYC 7601EPYC 76012 x Xeon Gold 6138EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251Xeon Silver 410830060090012001500SE +/- 0.24, N = 3SE +/- 0.16, N = 3SE +/- 0.26, N = 3SE +/- 0.21, N = 3SE +/- 0.02, N = 3SE +/- 0.06, N = 3SE +/- 0.16, N = 3SE +/- 0.24, N = 3142314221388133613341289128411251. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.0.5Test: Dense LU Matrix Factorization2 x Xeon Gold 6138EPYC 76012 x EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 72517001400210028003500SE +/- 3.91, N = 3SE +/- 14.00, N = 3SE +/- 13.01, N = 3SE +/- 9.44, N = 3SE +/- 6.54, N = 3SE +/- 7.32, N = 3SE +/- 4.68, N = 3SE +/- 8.94, N = 3320226952672262225642543243417131. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.0.5Test: Sparse Matrix Multiply2 x Xeon Gold 6138Xeon Silver 4108EPYC 76012 x EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 725130060090012001500SE +/- 0.87, N = 3SE +/- 0.54, N = 3SE +/- 4.48, N = 3SE +/- 6.85, N = 3SE +/- 2.97, N = 3SE +/- 0.20, N = 3SE +/- 1.77, N = 3SE +/- 6.24, N = 311899589188998688688388291. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.0.5Test: Fast Fourier Transform2 x Xeon Gold 6138Xeon Silver 41082 x EPYC 7601EPYC 7601EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251120240360480600SE +/- 0.29, N = 3SE +/- 0.57, N = 3SE +/- 0.13, N = 3SE +/- 0.35, N = 3SE +/- 0.62, N = 3SE +/- 0.23, N = 3SE +/- 0.10, N = 3SE +/- 0.17, N = 35373322482382312292242171. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector

OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.0.5Test: Monte Carlo2 x Xeon Gold 61382 x EPYC 7601EPYC 7601Xeon Silver 4108EPYC 7551EPYC 7401PEPYC 7351PEPYC 7251100200300400500SE +/- 0.29, N = 3SE +/- 0.06, N = 3SE +/- 0.05, N = 3SE +/- 0.16, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.60, N = 3SE +/- 0.13, N = 34623803803753573563453431. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -march=native -U_FORTIFY_SOURCE -fno-stack-protector

Stream

This benchmark tests the system memory (RAM) performance. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Add2 x EPYC 76012 x Xeon Gold 6138EPYC 7351PEPYC 7401PEPYC 7251EPYC 7601Xeon Silver 410840K80K120K160K200KSE +/- 1994.93, N = 5SE +/- 1051.54, N = 5SE +/- 20.37, N = 5SE +/- 417.61, N = 5SE +/- 165.28, N = 5SE +/- 1153.78, N = 5SE +/- 55.56, N = 517409111479099688969369432893632491691. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Triad2 x EPYC 76012 x Xeon Gold 6138EPYC 7351PEPYC 7401PEPYC 7251EPYC 7601Xeon Silver 410840K80K120K160K200KSE +/- 2485.73, N = 5SE +/- 2206.28, N = 5SE +/- 9.67, N = 5SE +/- 590.87, N = 5SE +/- 453.73, N = 5SE +/- 1186.43, N = 5SE +/- 53.43, N = 5176076111538100146972249402093875490181. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: Scale2 x EPYC 76012 x Xeon Gold 6138EPYC 7351PEPYC 7401PEPYC 7251EPYC 7601Xeon Silver 410830K60K90K120K150KSE +/- 1900.60, N = 5SE +/- 384.23, N = 5SE +/- 11.68, N = 5SE +/- 133.33, N = 5SE +/- 10.28, N = 5SE +/- 1054.13, N = 5SE +/- 46.94, N = 515469110917286788850768374982672445601. (CC) gcc options: -O3 -march=native -fopenmp

Compile Bench

Compilebench tries to age a filesystem by simulating some of the disk IO common in creating, compiling, patching, stating and reading kernel trees. It indirectly measures how well filesystems can maintain directory locality as the disk fills up and directories age. This current test is setup to use the makej mode with 10 initial directories Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCompile Bench 0.6Test: Read Compiled Tree2 x Xeon Gold 61382 x EPYC 7601EPYC 7601EPYC 7401PEPYC 7351PEPYC 7551Xeon Silver 4108EPYC 72512 x 22-Core POWER9 176 Threads5001000150020002500SE +/- 13.50, N = 3SE +/- 31.91, N = 3SE +/- 0.00, N = 3SE +/- 5.75, N = 3SE +/- 4.64, N = 3SE +/- 5.86, N = 3SE +/- 25.29, N = 3SE +/- 9.33, N = 3SE +/- 8.76, N = 3253523792334220721692158214921361583

244 Results Shown

MariaDB
Numpy Benchmark
Blender
Open Porous Media Git
Blender
VP9 libvpx Encoding
Open Porous Media Git
Blender
FFTW
Timed GCC Compilation
Radiance Benchmark
Blender
Open Porous Media Git
Blender
Open Porous Media Git
Open Porous Media Git
Open Porous Media Git
FFTW
Tinymembench
Tinymembench
RAR Compression
Blender
asmFish
Fhourstones
Blender
Hierarchical INTegration
Minion
PostgreSQL pgbench
GNU GMP GMPbench
Open Porous Media Git
PostgreSQL pgbench
FFTW
CacheBench:
  Write
  Read / Modify / Write
  Read
BYTE Unix Benchmark
MBW
Blender
Open Porous Media Git
Memcached mcperf
Timed LLVM Compilation
Timed Linux Kernel Compilation
Radiance Benchmark
Stockfish
MBW
7-Zip Compression
NAMD
Minion
Memcached mcperf
Open Porous Media Git
Blender
Memcached mcperf
Open Porous Media Git
GraphicsMagick
Timed PHP Compilation
R Benchmark
Open Porous Media Git
IndigoBench
Open Porous Media Git
Stress-NG
Memcached mcperf:
  Replace
  Append
Open Porous Media Git
Open Porous Media Git
AOBench
IndigoBench
Memcached mcperf
MBW
Chaos Group V-RAY
Minion
FFTW
GraphicsMagick:
  Sharpen
  Enhanced
  Swirl
  Rotate
  HWB Color Space
Rust Mandelbrot
Apache Benchmark
MBW
Blender
m-queens
Memcached mcperf
GNU MPC
NAS Parallel Benchmarks
Stress-NG
C-Ray
lzbench
lzbench
x265
Gzip Compression
John The Ripper
ebizzy
Rodinia
Timed ImageMagick Compilation
Tesseract OCR
eSpeak Speech Engine
POV-Ray
Java SciMark
Sunflow Rendering System
Compile Bench
Cryptsetup
Cryptsetup
GNU Octave Benchmark
PyBench
lzbench
lzbench
Cryptsetup:
  PBKDF2-whirlpool
  Libdeflate 1 - Decompression
lzbench
Crafty
lzbench
lzbench
Node.js Octane Benchmark
FFTW
Y-Cruncher
Zstd Compression
Timed Apache Compilation
Stress-NG
Aircrack-ng
Stress-NG:
  Matrix Math
  Crypto
  Vector Math
Stream
Swet
SciMark
Mencoder
John The Ripper
LuaJIT
FLAC Audio Encoding
Rodinia
GIMP
PHPBench
Go Benchmarks
Redis
RAMspeed SMP:
  Copy - Integer
  Add - Integer
  Average - Integer
Rust Prime Benchmark
RAMspeed SMP:
  Scale - Floating Point
  Average - Floating Point
GIMP
RAMspeed SMP:
  Triad - Floating Point
  Add - Floating Point
  Copy - Floating Point
Primesieve
OpenSSL
GnuPG
Redis
Sudokut
dcraw
NAS Parallel Benchmarks
MBW
x264
Redis
FFTW
GIMP
Redis
Bork File Encrypter
FFTW
FFmpeg
DaCapo Benchmark
LAME MP3 Encoding
MBW
Timed MAFFT Alignment
N-Queens
FFTW
Sysbench
Timed HMMer Search
FFTW
Darktable
MBW
Ogg Encoding
Smallpt
Git
FFTW
OSBench
FFTW:
  Float + SSE - 1D FFT Size 32
  Stock - 1D FFT Size 4096
libjpeg-turbo tjbench
PolyBench-C:
  Correlation Computation
  Covariance Computation
Bullet Physics Engine
FFTW
OSBench
NAS Parallel Benchmarks
MBW
FFTW
Optcarrot
FFTW:
  Float + SSE - 1D FFT Size 512
  Stock - 2D FFT Size 512
  Stock - 1D FFT Size 2048
Tachyon
FFTW:
  Float + SSE - 1D FFT Size 64
  Float + SSE - 2D FFT Size 32
  Stock - 2D FFT Size 256
Parboil
PolyBench-C
FFTW:
  Stock - 1D FFT Size 1024
  Stock - 2D FFT Size 32
  Float + SSE - 1D FFT Size 128
  Stock - 2D FFT Size 64
  Float + SSE - 2D FFT Size 128
  Float + SSE - 2D FFT Size 64
  Stock - 1D FFT Size 64
  Stock - 1D FFT Size 512
  Stock - 2D FFT Size 128
TSCP
FFTW:
  Stock - 1D FFT Size 128
  Stock - 1D FFT Size 256
  Stock - 1D FFT Size 32
glibc bench:
  sin
  cos
MBW
glibc bench:
  tanh
  pthread_once
  ffs
  ffsll
  sqrt
MBW
Java SciMark:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
  Monte Carlo
Bullet Physics Engine:
  Convex Trimesh
  Prim Trimesh
  136 Ragdolls
  1000 Convex
  1000 Stack
  3000 Fall
SciMark:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
  Monte Carlo
LuaJIT:
  Jacobi Successive Over-Relaxation
  Dense LU Matrix Factorization
  Sparse Matrix Multiply
  Fast Fourier Transform
  Monte Carlo
Stream:
  Add
  Triad
  Scale
Compile Bench