Linux 4.15 Intel Xeon Gold vs. EPYC 7601 - Ubuntu

AMD EPYC 7601 vs. Xeon Gold benchmarks.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1802127-FO-1802119FO99
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 4 Tests
Chess Test Suite 5 Tests
Timed Code Compilation 3 Tests
C/C++ Compiler Tests 23 Tests
Compression Tests 2 Tests
CPU Massive 53 Tests
Creator Workloads 14 Tests
Cryptography 5 Tests
Encoding 4 Tests
Fortran Tests 2 Tests
HPC - High Performance Computing 12 Tests
Imaging 4 Tests
Java 2 Tests
Common Kernel Benchmarks 6 Tests
Machine Learning 4 Tests
Memory Test Suite 4 Tests
MPI Benchmarks 3 Tests
Multi-Core 22 Tests
OpenCL 3 Tests
OpenMPI Tests 3 Tests
Programmer / Developer System Benchmarks 4 Tests
Python 4 Tests
Raytracing 3 Tests
Renderers 5 Tests
Scientific Computing 5 Tests
Server 6 Tests
Server CPU Tests 25 Tests
Single-Threaded 20 Tests
Common Workstation Benchmarks 3 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

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
2 x Xeon Gold 6138
February 11 2018
 
EPYC 7601
February 11 2018
 
Invert Hiding All Results Option
 
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):


Linux 4.15 Intel Xeon Gold vs. EPYC 7601 - UbuntuProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay DriverCompilerFile-SystemScreen Resolution2 x Xeon Gold 6138EPYC 76012 x Intel Xeon Gold 6138 @ 3.70GHz (40 Cores / 80 Threads)TYAN S7106 (V1.00 BIOS)Intel Device 202096256MB256GB Samsung SSD 850 + 2000GB Seagate ST2000DM006-2DM1 + 2 x 120GB TOSHIBA-TR150ASPEED ASPEED FamilyVE228Intel I210 Gigabit ConnectionUbuntu 17.104.15.2-041502-generic (x86_64)GNOME Shell 3.26.1modesetting 1.19.5GCC 7.2.0ext41920x1080AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads)TYAN B8026T70AE24HR (V0.05.B10 BIOS)AMD Device 1450129024MB280GB INTEL SSDPE21D280GABroadcom Limited NetXtreme BCM5720 Gigabit PCIeOpenBenchmarking.orgCompiler Details- --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 Disk Details- 2 x Xeon Gold 6138: CFQ / data=ordered,errors=remount-ro,relatime,rw- EPYC 7601: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Details- 2 x Xeon Gold 6138: Scaling Governor: intel_pstate powersave- EPYC 7601: Scaling Governor: acpi-cpufreq ondemandPython Details- Python 2.7.14 + Python 3.6.3Security Details- 2 x Xeon Gold 6138: KPTI + __user pointer sanitization + Full generic retpoline Protection- EPYC 7601: __user pointer sanitization + Full AMD retpoline Protection

2 x Xeon Gold 6138 vs. EPYC 7601 ComparisonPhoronix Test SuiteBaseline+124.7%+124.7%+249.4%+249.4%+374.1%+374.1%440.3%115.9%91.1%73.2%64.7%45.5%42%41.5%36.8%36.2%31.6%26.4%24.5%21.8%21.4%21.3%20%19.3%19%18%17.8%14.6%12.7%9.2%8.7%5%4.3%3.8%3.8%3.5%3.5%2.5%3.M.M498.8%Socket ActivityMemory Copying213%OpenMP Stencil183.4%P.P.S151.8%M.S.A111.3%Blowfish107.1%2 - Process104.2%95.1%2 - Thread94.5%sqrt8 - Thread87.2%Float + SSE - 1D FFT Size 51286.3%4 - Thread78.1%8 - Process77.7%S.V.M.PR.4.b.P70.1%4 - Process65.1%P.D.STsearch64.2%1 - Process61%1 - Thread60.4%CPU Stress59.8%59.6%8 - 1658.6%G.C.S.F57.8%P.B.S57.7%P.R.W.S.S.M56.2%Float + SSE - 1D FFT Size 25653.6%ffs47.9%C.S.T46.2%O.M.Gffsll45%16 - 844.8%F.E.T44.3%Add - IntegerresizeM.P.B39.9%Read39.4%Add38.3%O.S38.3%Matrix Math37.9%XZ 0 - Compression37.5%G.Q.D.S36.9%Copy - Integer36.7%Triad36.7%Copy - Floating PointA.C.P35.8%Scale35.5%OpenMP LBM35.3%T.F.A.T.T34.5%16 - Process34.3%tanh33.8%MD532.4%WAV To MP332.2%Total Time31.8%Forking31.7%Add - Floating PointTime To Compile30.9%Elapsed Time30.1%16 - Thread29.7%1.H.M.2.D26.9%pthread_once26.8%AES-256 - EncryptStock - 1D FFT Size 3225.9%T.T.S.S25.9%json25.7%Time To Compile25.5%Time To Compile25.4%LPOPFloat + SSE - 2D FFT Size 6423%Total Time22.2%2048 x 2048 - Total Time22%auto-levelsLibdeflate 1 - Compression21.6%16 - 1621.3%L.A.TFloat + SSE - 1D FFT Size 6421.1%linux-4.15.tar.xz21.1%Float + SSE - 2D FFT Size 3220.7%Traditional DES20.6%Write20.3%Average - IntegerTotal Time19.9%R.M.W19.8%http19.8%Bsearch19.7%Blowfish - Encrypt19.3%Float + SSE - 1D FFT Size 3219.1%Static OMP Speedup18.3%12.A.2.B.S17.9%Average - Floating PointWAV To FLAC17.7%SADD17.6%Hsearch16.7%Stock - 1D FFT Size 6416.5%SET16.4%1000 Convex16.1%Raytests15.6%Copy14.9%OpenMP CUTCP14.7%Triad - Floating PointServer Room - CPU-only14.5%G.I.I.S14.4%Twofish - Encrypt14.3%WAV To Ogg14.2%1.A.2.B.S.4.T13.9%1.P.N.G13.5%Lsearch13.3%1000 Stack13.1%Masskrug - CPU-onlyConvex Trimesh12.4%KASUMI - Encrypt12.2%OpenMP CFD Solver12%garbage11.6%3000 Fall10.9%1.A.2.B.S.2.T10.9%Elapsed Time10.8%Semaphores10.7%CAST-256 - Encrypt10.6%Zstd 1 - Compression10.4%Scale - Integer10.4%Float + SSE - 1D FFT Size 12810.3%Cifar1010.3%LPUSH10.3%GET10%Total Time9.5%build9.5%Float + SSE - 2D FFT Size 512Brotli 0 - Compression9.1%OpenMP LavaMD9%D.T8.8%Scale - Floating PointSharpen8.6%Stock - 2D FFT Size 1288.3%Float + SSE - 2D FFT Size 1288%Stock - 1D FFT Size 1287.7%1.A.2.B.S7.7%HWB Color Space7.6%Stock - 2D FFT Size 647.1%Resizing6.8%136 Ragdolls6.6%Blur6.2%Boat - CPU-only6.1%Trace TimeCrypto4.8%4.8%Stock - 2D FFT Size 512Triad - Integer2P.P.AFloat + SSE - 2D FFT Size 256Vector Math3.4%S.W.P.S3%unsharp-maskStock - 1D FFT Size 2562.1%PolyBench-CStress-NGStress-NGParboilHimeno BenchmarkTimed MAFFT AlignmentBLAKE2John The RipperHackbenchXsbenchHackbenchglibc benchHackbenchFFTWHackbenchHackbenchStress-NGOpenSSLHackbenchTimed HMMer SearchStress-NGHackbenchHackbenchStress-NGNumpy BenchmarkSchbenchStress-NGPHPBenchTTSIOD 3D RendererFFTWglibc bench7-Zip CompressionParboilglibc benchSchbenchBork File EncrypterRAMspeed SMPGIMPGNU MPCCacheBenchStreamRodiniaStress-NGlzbenchStress-NGRAMspeed SMPCython benchmarkStreamRAMspeed SMPTSCPStreamParboilPyBenchHackbenchglibc benchJohn The RipperLAME MP3 EncodingStockfishStress-NGRAMspeed SMPTimed PHP CompilationCraftyHackbenchasmFishglibc benchBotanFFTWeSpeak Speech EngineGo BenchmarksTimed Linux Kernel CompilationTimed Apache CompilationRedisFFTWOpen FMM Nero2DAOBenchGIMPlzbenchebizzySchbenchGraphicsMagickFFTWUnpacking The Linux KernelFFTWJohn The RipperCacheBenchRAMspeed SMPGNU GMP GMPbenchCacheBenchGo BenchmarksStress-NGBotanScikit-LearnFFTWCLOMPR Benchmarkt-test1Multichase Pointer ChaserRAMspeed SMPFLAC Audio EncodingRedisStress-NGFFTWRedisBullet Physics EngineBullet Physics EngineStreamParboilRAMspeed SMPDarktableSunflow Rendering SystemBotanOgg EncodingMultichase Pointer ChaserPrimesieveStress-NGBullet Physics EngineDarktableBullet Physics EngineBotanRodiniaGo BenchmarksBullet Physics EngineMultichase Pointer ChaserN-QueensStress-NGBotanlzbenchRAMspeed SMPFFTWTensorflowRedisRedisC-RayGo BenchmarksFFTWlzbenchRodinialibjpeg-turbo tjbenchRAMspeed SMPGraphicsMagickFFTWFFTWFFTWMultichase Pointer ChaserGraphicsMagickFFTWGraphicsMagickBullet Physics EngineGraphicsMagickDarktablePOV-RayStress-NGHigh Performance Conjugate GradientFFTWRAMspeed SMPt-test1Timed MrBayes AnalysisFFTWStress-NGApache BenchmarkGIMPFFTW2 x Xeon Gold 6138EPYC 7601

Linux 4.15 Intel Xeon Gold vs. EPYC 7601 - Ubuntuunpack-linux: linux-4.15.tar.xzramspeed: Add - Integerramspeed: Copy - Integerramspeed: Scale - Integerramspeed: Triad - Integerramspeed: Average - Integerramspeed: Add - Floating Pointramspeed: Copy - Floating Pointramspeed: Scale - Floating Pointramspeed: Triad - Floating Pointramspeed: Average - Floating Pointstream: Copystream: Scalestream: Triadstream: Addt-test1: 1t-test1: 2mpcbench: Multi-Precision Benchmarkparboil: OpenMP LBMparboil: OpenMP CUTCPparboil: OpenMP Stencilparboil: OpenMP MRI Griddingrodinia: OpenMP LavaMDrodinia: OpenMP CFD Solverrodinia: OpenMP Streamclusterhpcg: clomp: Static OMP Speeduppolybench-c: 3 Matrix Multiplicationslzbench: XZ 0 - Compressionlzbench: Zstd 1 - Compressionlzbench: Brotli 0 - Compressionlzbench: Libdeflate 1 - Compressionfftw: Stock - 1D FFT Size 32fftw: Stock - 1D FFT Size 64fftw: Stock - 2D FFT Size 32fftw: Stock - 2D FFT Size 64fftw: Stock - 1D FFT Size 128fftw: Stock - 1D FFT Size 256fftw: Stock - 1D FFT Size 512fftw: Stock - 2D FFT Size 128fftw: Stock - 2D FFT Size 256fftw: Stock - 2D FFT Size 512fftw: Float + SSE - 1D FFT Size 32fftw: Float + SSE - 1D FFT Size 64fftw: Float + SSE - 2D FFT Size 32fftw: Float + SSE - 2D FFT Size 64fftw: Float + SSE - 1D FFT Size 128fftw: Float + SSE - 1D FFT Size 256fftw: Float + SSE - 1D FFT Size 512fftw: Float + SSE - 2D FFT Size 128fftw: Float + SSE - 2D FFT Size 256fftw: Float + SSE - 2D FFT Size 512hmmer: Pfam Database Searchmafft: Multiple Sequence Alignmentmrbayes: Primate Phylogeny Analysisblake2: gmpbench: Total Timego-benchmark: httpgo-benchmark: jsongo-benchmark: buildgo-benchmark: garbagebork: File Encryption Timecachebench: Readcachebench: Writecachebench: Read / Modify / Writebotan: KASUMI - Encryptbotan: AES-256 - Encryptbotan: Twofish - Encryptbotan: Blowfish - Encryptbotan: CAST-256 - Encryptnumpy: crafty: Elapsed Timetscp: AI Chess Performancejohn-the-ripper: Blowfishjohn-the-ripper: Traditional DESjohn-the-ripper: MD5nero2d: Total Timettsiod-renderer: Phong Rendering With Soft-Shadow Mappingx264: H.264 Video Encodinggraphics-magick: Blurgraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdinghimeno: Poisson Pressure Solvercompress-7zip: Compress Speed Testasmfish: 1024 Hash Memory, 26 Depthebizzy: build-apache: Time To Compilebuild-linux-kernel: Time To Compilebuild-php: Time To Compilec-ray: Total Timepovray: Trace Timeprimesieve: 1e12 Prime Number Generationstockfish: Total Timeaobench: 2048 x 2048 - Total Timebullet: Raytestsbullet: 3000 Fallbullet: 1000 Stackbullet: 1000 Convexbullet: 136 Ragdollsbullet: Prim Trimeshbullet: Convex Trimeshcython-bench: encode-flac: WAV To FLACencode-mp3: WAV To MP3encode-ogg: WAV To Oggespeak: Text-To-Speech Synthesishackbench: 1 - Threadhackbench: 2 - Threadhackbench: 4 - Threadhackbench: 8 - Threadhackbench: 1 - Processhackbench: 16 - Threadhackbench: 2 - Processhackbench: 4 - Processhackbench: 8 - Processhackbench: 16 - Processhackbench: 32 - Processn-queens: Elapsed Timerbenchmark: tachyon: Total Timeopenssl: RSA 4096-bit Performanceglibc-bench: ffsglibc-bench: sqrtglibc-bench: tanhglibc-bench: ffsllglibc-bench: pthread_oncemultichase: 4MB Array, 64 Byte Stridemultichase: 1GB Array, 256 Byte Stridemultichase: 256MB Array, 256 Byte Stridemultichase: 1GB Array, 256 Byte Stride, 2 Threadsmultichase: 1GB Array, 256 Byte Stride, 4 Threadstjbench: Decompression Throughputtensorflow: Cifar10darktable: Boat - CPU-onlydarktable: Masskrug - CPU-onlydarktable: Server Room - CPU-onlygimp: resizegimp: auto-levelsgimp: unsharp-maskredis: LPOPredis: SADDredis: LPUSHredis: GETredis: SETstress-ng: Cryptostress-ng: Bsearchstress-ng: Forkingstress-ng: Hsearchstress-ng: Lsearchstress-ng: Tsearchstress-ng: CPU Stressstress-ng: Semaphoresstress-ng: Matrix Mathstress-ng: Vector Mathstress-ng: Memory Copyingstress-ng: Socket Activitystress-ng: Context Switchingstress-ng: Glibc C String Functionsstress-ng: Glibc Qsort Data Sortingstress-ng: System V Message Passingxsbench: pybench: Total For Average Test Timesnginx: Static Web Page Servingapache: Static Web Page Servingphpbench: PHP Benchmark Suitescikit-learn: sunflow: Global Illumination + Image Synthesisschbench: 16 - 8schbench: 8 - 16schbench: 16 - 162 x Xeon Gold 6138EPYC 76016.3522046.2618646.4622172.7324243.6122361.2022618.6519142.7820075.6222145.4220948.76136262.66110173.06121357.36122725.7256.2717.54851729.302.325.54408.2028.699.7113.620.880.6310.49333723822039068.437841.639524.237433.877080.277279.307210.307584.506670.206421.901296916726317573151917947314204627027476222782157213.9510.3483.303.2747061978130564261689322013211376858.243089.7626148.4527457.1982.113502.42323.50253.06124.195188230736197411890724877214859133363737221.14744.19106.48155189188212892582.631396608261035094760926.1630.4549.883.1622.9610.51342244.322.754.605.334.913.011.071.2125.265.8632.426.7632.173.033.105.129.002.9023.412.644.598.1019.4228.515.010.75961.797861.833.268.9828.633.803.819.7878.7368.4177.5480.19154.9556.265.456.902.766.4810.1319.391396716.921664424.651410152.671793642.131469330.396103.6219966.8968922.29175731.11383.64643.8312460.391741434.70196635.6669426.915981.993521.3213294136.942248593.55458.045411993.696484332132123040.1418641.25537416172.480.971289114928439687.6931310.1025516.5120089.5325171.6026839.3129759.3926070.6621814.6025383.6624682.17118553.6881333.1488787.3688721.9847.6816.90608739.632.6615.70280.6231.2810.8818.830.840.7562.81243373501677201.006733.709498.306942.106573.307131.777195.077004.536788.806696.30108891380926302256181626720454248332543323064235528.474.7980.456.913924.5023691384214518490860715126984011.892216.0121744.5022910.7573.184425.49282.93212.12112.26828249256606918753652354612320700048130825.84476.41107.071461741761971081025.769554565107680115081632.8038.2065.283.4621.8711.93450954.073.185.106.035.703.211.091.3634.546.9042.877.7240.504.866.039.1216.854.6730.365.397.5814.3926.085.550.89884621.304.824.7038.305.514.839.7884.8080.6885.9691.34142.4062.055.786.123.164.588.3218.911739038.251415778.751278868.841630676.501262205.215825.3216685.9652324.20150628.51338.57392.207795.521573684.40142639.5967119.751911.2419027.441425100.82334.509375740.693323726177718106.90340836144.611.11186672366953355OpenBenchmarking.org

Unpacking The Linux Kernel

OpenBenchmarking.orgSeconds, Fewer Is BetterUnpacking The Linux Kernellinux-4.15.tar.xzEPYC 76012 x Xeon Gold 6138246810SE +/- 0.04, N = 4SE +/- 0.04, N = 47.696.35

RAMspeed SMP

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: IntegerEPYC 76012 x Xeon Gold 61387K14K21K28K35K31310.1022046.261. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerEPYC 76012 x Xeon Gold 61385K10K15K20K25K25516.5118646.461. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: IntegerEPYC 76012 x Xeon Gold 61385K10K15K20K25K20089.5322172.731. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: IntegerEPYC 76012 x Xeon Gold 61385K10K15K20K25K25171.6024243.611. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: IntegerEPYC 76012 x Xeon Gold 61386K12K18K24K30K26839.3122361.201. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Add - Benchmark: Floating PointEPYC 76012 x Xeon Gold 61386K12K18K24K30K29759.3922618.651. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating PointEPYC 76012 x Xeon Gold 61386K12K18K24K30K26070.6619142.781. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Scale - Benchmark: Floating PointEPYC 76012 x Xeon Gold 61385K10K15K20K25K21814.6020075.621. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Triad - Benchmark: Floating PointEPYC 76012 x Xeon Gold 61385K10K15K20K25K25383.6622145.421. (CC) gcc options: -O3 -march=native

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Average - Benchmark: Floating PointEPYC 76012 x Xeon Gold 61385K10K15K20K25K24682.1720948.761. (CC) gcc options: -O3 -march=native

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: CopyEPYC 76012 x Xeon Gold 613830K60K90K120K150KSE +/- 408.44, N = 5SE +/- 542.71, N = 5118553.68136262.661. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: ScaleEPYC 76012 x Xeon Gold 613820K40K60K80K100KSE +/- 480.06, N = 5SE +/- 1002.54, N = 581333.14110173.061. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: TriadEPYC 76012 x Xeon Gold 613830K60K90K120K150KSE +/- 306.99, N = 5SE +/- 296.75, N = 588787.36121357.361. (CC) gcc options: -O3 -march=native -fopenmp

OpenBenchmarking.orgMB/s, More Is BetterStream 2013-01-17Type: AddEPYC 76012 x Xeon Gold 613830K60K90K120K150KSE +/- 359.22, N = 5SE +/- 709.99, N = 588721.98122725.721. (CC) gcc options: -O3 -march=native -fopenmp

t-test1

This is a test of t-test1 for basic memory allocator benchmarks. Note this test profile is currently very basic and the overall time does include the warmup time of the custom t-test1 compilation. Improvements welcome. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1EPYC 76012 x Xeon Gold 61381326395265SE +/- 0.32, N = 3SE +/- 2.99, N = 647.6856.271. (CC) gcc options: -pthread

OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2EPYC 76012 x Xeon Gold 613848121620SE +/- 0.04, N = 3SE +/- 0.62, N = 616.9017.541. (CC) gcc options: -pthread

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 BenchmarkEPYC 76012 x Xeon Gold 61382K4K6K8K10KSE +/- 13.33, N = 3SE +/- 21.86, N = 360878517-mtune=k8 -march=k8-mtune=skylake -march=broadwell1. (CC) gcc options: -lm -O2 -pedantic -fomit-frame-pointer -m64 -MT -MD -MP -MF

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 LBMEPYC 76012 x Xeon Gold 6138918273645SE +/- 0.35, N = 3SE +/- 0.47, N = 639.6329.301. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP CUTCPEPYC 76012 x Xeon Gold 61380.59851.1971.79552.3942.9925SE +/- 0.01, N = 3SE +/- 0.01, N = 32.662.321. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP StencilEPYC 76012 x Xeon Gold 613848121620SE +/- 0.47, N = 6SE +/- 0.04, N = 315.705.541. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

OpenBenchmarking.orgSeconds, Fewer Is BetterParboil 2.5Test: OpenMP MRI GriddingEPYC 76012 x Xeon Gold 613890180270360450SE +/- 0.82, N = 3SE +/- 6.19, N = 5280.62408.201. (CXX) g++ options: -lm -lpthread -lgomp -ffast-math -fopenmp

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 LavaMDEPYC 76012 x Xeon Gold 6138714212835SE +/- 0.14, N = 3SE +/- 0.15, N = 331.2828.691. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP CFD SolverEPYC 76012 x Xeon Gold 61383691215SE +/- 0.03, N = 3SE +/- 0.17, N = 310.889.711. (CXX) g++ options: -O2 -lOpenCL

OpenBenchmarking.orgSeconds, Fewer Is BetterRodinia 2.4Test: OpenMP StreamclusterEPYC 76012 x Xeon Gold 6138510152025SE +/- 0.79, N = 6SE +/- 0.25, N = 618.8313.621. (CXX) g++ options: -O2 -lOpenCL

High Performance Conjugate Gradient

HPCG is the High Performance Conjugate Gradient and is a new scientific benchmark from Sandia National Lans focused for super-computer testing with modern real-world workloads compared to HPCC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgGFLOP/s, More Is BetterHigh Performance Conjugate Gradient 3.0EPYC 76012 x Xeon Gold 61380.1980.3960.5940.7920.99SE +/- 0.01, N = 4SE +/- 0.02, N = 30.840.88

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP SpeedupEPYC 76012 x Xeon Gold 61380.16880.33760.50640.67520.844SE +/- 0.02, N = 10SE +/- 0.00, N = 50.750.631. (CC) gcc options: --openmp -O3 -lm

PolyBench-C

OpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 3.2Test: 3 Matrix MultiplicationsEPYC 76012 x Xeon Gold 61381428425670SE +/- 0.35, N = 3SE +/- 0.07, N = 362.8110.491. (CC) gcc options: -O3 -march=native

lzbench

lzbench is an in-memory benchmark of various compressors. The file used for compression is a Linux kernel source tree tarball. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is Betterlzbench 2017-08-08Test: XZ 0 - Process: CompressionEPYC 76012 x Xeon Gold 613881624324024331. (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: DecompressionEPYC 76012 x Xeon Gold 61382040608010077911. (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: CompressionEPYC 76012 x Xeon Gold 6138801602403204003373721. (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: DecompressionEPYC 76012 x Xeon Gold 61382004006008001000SE +/- 0.33, N = 3SE +/- 0.33, N = 39179851. (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: CompressionEPYC 76012 x Xeon Gold 613880160240320400SE +/- 1.53, N = 3SE +/- 1.33, N = 33503821. (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: DecompressionEPYC 76012 x Xeon Gold 6138110220330440550SE +/- 1.15, N = 33944901. (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: CompressionEPYC 76012 x Xeon Gold 61384080120160200SE +/- 2.19, N = 3SE +/- 0.58, N = 31672031. (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: DecompressionEPYC 76012 x Xeon Gold 61382004006008001000SE +/- 3.00, N = 38119621. (CXX) g++ options: -lrt -static -lpthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -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: Stock - Size: 1D FFT Size 32EPYC 76012 x Xeon Gold 61382K4K6K8K10KSE +/- 380.74, N = 6SE +/- 18.37, N = 37201.009068.431. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 64EPYC 76012 x Xeon Gold 61382K4K6K8K10KSE +/- 13.61, N = 3SE +/- 3.74, N = 36733.707841.631. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 32EPYC 76012 x Xeon Gold 61382K4K6K8K10KSE +/- 2.30, N = 3SE +/- 18.69, N = 39498.309524.231. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 64EPYC 76012 x Xeon Gold 613816003200480064008000SE +/- 11.28, N = 3SE +/- 30.21, N = 36942.107433.871. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 128EPYC 76012 x Xeon Gold 613815003000450060007500SE +/- 40.12, N = 3SE +/- 31.94, N = 36573.307080.271. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 256EPYC 76012 x Xeon Gold 613816003200480064008000SE +/- 0.56, N = 3SE +/- 112.96, N = 37131.777279.301. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 512EPYC 76012 x Xeon Gold 613815003000450060007500SE +/- 17.16, N = 3SE +/- 116.30, N = 37195.077210.301. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 128EPYC 76012 x Xeon Gold 613816003200480064008000SE +/- 9.76, N = 3SE +/- 38.01, N = 37004.537584.501. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 256EPYC 76012 x Xeon Gold 613815003000450060007500SE +/- 13.94, N = 3SE +/- 13.95, N = 36788.806670.201. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 512EPYC 76012 x Xeon Gold 613814002800420056007000SE +/- 16.50, N = 3SE +/- 21.69, N = 36696.306421.901. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 32EPYC 76012 x Xeon Gold 61383K6K9K12K15KSE +/- 12.03, N = 3SE +/- 23.21, N = 310889129691. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 64EPYC 76012 x Xeon Gold 61384K8K12K16K20KSE +/- 132.23, N = 3SE +/- 171.97, N = 313809167261. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 32EPYC 76012 x Xeon Gold 61387K14K21K28K35KSE +/- 11.27, N = 3SE +/- 264.72, N = 326302317571. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 64EPYC 76012 x Xeon Gold 61387K14K21K28K35KSE +/- 173.71, N = 3SE +/- 192.48, N = 325618315191. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 128EPYC 76012 x Xeon Gold 61384K8K12K16K20KSE +/- 96.03, N = 3SE +/- 107.43, N = 316267179471. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 256EPYC 76012 x Xeon Gold 61387K14K21K28K35KSE +/- 190.33, N = 3SE +/- 729.72, N = 620454314201. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 1D FFT Size 512EPYC 76012 x Xeon Gold 613810K20K30K40K50KSE +/- 21.99, N = 3SE +/- 988.35, N = 624833462701. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 128EPYC 76012 x Xeon Gold 61386K12K18K24K30KSE +/- 14.77, N = 3SE +/- 18.49, N = 325433274761. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 256EPYC 76012 x Xeon Gold 61385K10K15K20K25KSE +/- 62.91, N = 3SE +/- 377.34, N = 623064222781. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 512EPYC 76012 x Xeon Gold 61385K10K15K20K25KSE +/- 41.33, N = 3SE +/- 139.80, N = 323552215721. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -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 SearchEPYC 76012 x Xeon Gold 613848121620SE +/- 0.02, N = 3SE +/- 0.08, N = 38.4713.951. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm

Timed MAFFT Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence AlignmentEPYC 76012 x Xeon Gold 61383691215SE +/- 0.05, N = 3SE +/- 0.08, N = 34.7910.341. (CC) gcc options: -O3 -lm -lpthread

Timed MrBayes Analysis

This test performs a bayesian analysis of a set of primate genome sequences in order to estimate their phylogeny. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MrBayes Analysis 3.1.2Primate Phylogeny AnalysisEPYC 76012 x Xeon Gold 613820406080100SE +/- 1.29, N = 3SE +/- 1.44, N = 380.4583.301. (CC) gcc options: -O3 -msse -mfpmath=sse -march=native -lm -pthread -lmpi

BLAKE2

OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 20170307EPYC 76012 x Xeon Gold 6138246810SE +/- 0.00, N = 3SE +/- 0.00, N = 36.913.271. (CC) gcc options: -O3 -march=native -lcrypto -lz

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 TimeEPYC 76012 x Xeon Gold 6138100020003000400050003924.504706.001. (CC) gcc options: -O3 -fomit-frame-pointer -lm

Go Benchmarks

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: httpEPYC 76012 x Xeon Gold 61385K10K15K20K25KSE +/- 87.22, N = 3SE +/- 310.82, N = 32369119781

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: jsonEPYC 76012 x Xeon Gold 6138800K1600K2400K3200K4000KSE +/- 55313.49, N = 3SE +/- 31437.69, N = 338421453056426

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: buildEPYC 76012 x Xeon Gold 61384000M8000M12000M16000M20000MSE +/- 52988091.14, N = 3SE +/- 90456298.03, N = 31849086071516893220132

OpenBenchmarking.orgNanoseconds/Operation, Fewer Is BetterGo BenchmarksTest: garbageEPYC 76012 x Xeon Gold 6138300K600K900K1200K1500KSE +/- 689.97, N = 3SE +/- 4498.18, N = 312698401137685

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 TimeEPYC 76012 x Xeon Gold 61383691215SE +/- 0.07, N = 3SE +/- 0.14, N = 411.898.24

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: ReadEPYC 76012 x Xeon Gold 61387001400210028003500SE +/- 0.03, N = 3SE +/- 30.02, N = 32216.013089.761. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteEPYC 76012 x Xeon Gold 61386K12K18K24K30KSE +/- 60.77, N = 3SE +/- 31.21, N = 321744.5026148.451. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteEPYC 76012 x Xeon Gold 61386K12K18K24K30KSE +/- 7.78, N = 3SE +/- 33.00, N = 322910.7527457.191. (CC) gcc options: -lrt

Botan

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.4.0Test: KASUMI - EncryptEPYC 76012 x Xeon Gold 613820406080100SE +/- 0.02, N = 3SE +/- 0.10, N = 373.1882.111. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.4.0Test: AES-256 - EncryptEPYC 76012 x Xeon Gold 61389001800270036004500SE +/- 4.29, N = 3SE +/- 2.15, N = 34425.493502.421. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.4.0Test: Twofish - EncryptEPYC 76012 x Xeon Gold 613870140210280350SE +/- 0.13, N = 3SE +/- 0.33, N = 3282.93323.501. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.4.0Test: Blowfish - EncryptEPYC 76012 x Xeon Gold 613860120180240300SE +/- 0.02, N = 3SE +/- 0.41, N = 3212.12253.061. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

OpenBenchmarking.orgMiB/s, More Is BetterBotan 2.4.0Test: CAST-256 - EncryptEPYC 76012 x Xeon Gold 6138306090120150SE +/- 0.03, N = 3SE +/- 0.01, N = 3112.26124.191. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt

Numpy Benchmark

OpenBenchmarking.orgNanoseconds, Fewer Is BetterNumpy BenchmarkEPYC 76012 x Xeon Gold 61382M4M6M8M10M82824925188230

Crafty

OpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed TimeEPYC 76012 x Xeon Gold 61381.6M3.2M4.8M6.4M8MSE +/- 7973.17, N = 3SE +/- 12492.54, N = 3566069173619741. (CC) gcc options: -lstdc++ -fprofile-use -pthread -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 PerformanceEPYC 76012 x Xeon Gold 6138300K600K900K1200K1500KSE +/- 810.76, N = 5SE +/- 512.80, N = 587536511890721. (CC) gcc options: -O3 -march=native

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 1.8.0Test: BlowfishEPYC 76012 x Xeon Gold 613810K20K30K40K50KSE +/- 89.71, N = 3SE +/- 2144.93, N = 623546487721. (CC) gcc options: -fopenmp -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0Test: Traditional DESEPYC 76012 x Xeon Gold 613830M60M90M120M150MSE +/- 4123319.82, N = 6SE +/- 1193319.23, N = 31232070001485913331. (CC) gcc options: -fopenmp -lcrypt

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0Test: MD5EPYC 76012 x Xeon Gold 6138140K280K420K560K700KSE +/- 1276.35, N = 3SE +/- 7389.58, N = 34813086373721. (CC) gcc options: -fopenmp -lcrypt

Open FMM Nero2D

This is a test of Nero2D, which is a two-dimensional TM/TE solver for Open FMM. Open FMM is a free collection of electromagnetic software for scattering at very large objects. This test profile times how long it takes to solve one of the included 2D examples. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen FMM Nero2D 2.0.2Total TimeEPYC 76012 x Xeon Gold 6138612182430SE +/- 0.33, N = 3SE +/- 0.08, N = 325.8421.141. (CXX) g++ options: -O2 -lfftw3 -llapack -lblas -lgfortran -lquadmath -lm -pthread -lmpi_cxx -lmpi

TTSIOD 3D Renderer

A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3aPhong Rendering With Soft-Shadow MappingEPYC 76012 x Xeon Gold 6138160320480640800SE +/- 8.10, N = 3SE +/- 6.23, N = 3476.41744.191. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++

x264

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-02-05H.264 Video EncodingEPYC 76012 x Xeon Gold 613820406080100SE +/- 0.42, N = 3SE +/- 0.70, N = 3107.07106.48-lavformat -lavcodec -lavutil -lswscale1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

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 1.3.19Operation: BlurEPYC 76012 x Xeon Gold 6138306090120150SE +/- 0.33, N = 31461551. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: SharpenEPYC 76012 x Xeon Gold 61384080120160200SE +/- 0.33, N = 31741891. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: ResizingEPYC 76012 x Xeon Gold 61384080120160200SE +/- 0.33, N = 3SE +/- 1.00, N = 31761881. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: HWB Color SpaceEPYC 76012 x Xeon Gold 613850100150200250SE +/- 0.33, N = 31972121. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Local Adaptive ThresholdingEPYC 76012 x Xeon Gold 613820406080100108891. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lgomp -lpthread

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverEPYC 76012 x Xeon Gold 61386001200180024003000SE +/- 2.85, N = 3SE +/- 4.65, N = 31025.762582.631. (CC) gcc options: -O3 -mavx2

7-Zip Compression

This is a test of 7-Zip using p7zip with its integrated benchmark feature. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 9.20.1Compress Speed TestEPYC 76012 x Xeon Gold 613830K60K90K120K150KSE +/- 895.07, N = 3SE +/- 301.96, N = 3955451396601. (CXX) g++ options: -pipe -lpthread

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 DepthEPYC 76012 x Xeon Gold 613820M40M60M80M100MSE +/- 363988.52, N = 3SE +/- 903069.70, N = 36510768082610350

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 0.3EPYC 76012 x Xeon Gold 6138200K400K600K800K1000KSE +/- 13590.79, N = 3SE +/- 3037.48, N = 311508169476091. (CC) gcc options: -pthread -lpthread -O3 -march=native

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 CompileEPYC 76012 x Xeon Gold 6138816243240SE +/- 0.20, N = 3SE +/- 0.01, N = 332.8026.16

Timed Linux Kernel Compilation

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

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.13Time To CompileEPYC 76012 x Xeon Gold 6138918273645SE +/- 0.73, N = 6SE +/- 0.74, N = 638.2030.45

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 CompileEPYC 76012 x Xeon Gold 61381530456075SE +/- 1.13, N = 4SE +/- 0.20, N = 365.2849.881. (CC) gcc options: -O2 -pedantic -ldl -lz -lm

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 TimeEPYC 76012 x Xeon Gold 61380.77851.5572.33553.1143.8925SE +/- 0.01, N = 3SE +/- 0.00, N = 33.463.161. (CC) gcc options: -lm -lpthread -O3

POV-Ray

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeEPYC 76012 x Xeon Gold 6138612182430SE +/- 0.05, N = 3SE +/- 0.14, N = 321.8722.96-lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

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 6.21e12 Prime Number GenerationEPYC 76012 x Xeon Gold 61383691215SE +/- 0.04, N = 3SE +/- 0.01, N = 311.9310.511. (CXX) g++ options: -O3 -rdynamic -lpthread

Stockfish

OpenBenchmarking.orgms, Fewer Is BetterStockfish 2014-11-26Total TimeEPYC 76012 x Xeon Gold 613810002000300040005000SE +/- 4.48, N = 3SE +/- 15.17, N = 3450934221. (CXX) g++ options: -lpthread -fno-exceptions -fno-rtti -ansi -pedantic -O3 -msse -msse3 -mpopcnt -flto

AOBench

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeEPYC 76012 x Xeon Gold 61381224364860SE +/- 1.26, N = 6SE +/- 0.19, N = 354.0744.321. (CC) gcc options: -lm -O3

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: RaytestsEPYC 76012 x Xeon Gold 61380.71551.4312.14652.8623.5775SE +/- 0.00, N = 3SE +/- 0.00, N = 33.182.751. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 FallEPYC 76012 x Xeon Gold 61381.14752.2953.44254.595.7375SE +/- 0.01, N = 3SE +/- 0.04, N = 35.104.601. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 StackEPYC 76012 x Xeon Gold 6138246810SE +/- 0.01, N = 3SE +/- 0.04, N = 36.035.331. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 ConvexEPYC 76012 x Xeon Gold 61381.28252.5653.84755.136.4125SE +/- 0.01, N = 3SE +/- 0.01, N = 35.704.911. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 RagdollsEPYC 76012 x Xeon Gold 61380.72231.44462.16692.88923.6115SE +/- 0.01, N = 3SE +/- 0.02, N = 33.213.011. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim TrimeshEPYC 76012 x Xeon Gold 61380.24530.49060.73590.98121.2265SE +/- 0.00, N = 3SE +/- 0.03, N = 31.091.071. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex TrimeshEPYC 76012 x Xeon Gold 61380.3060.6120.9181.2241.53SE +/- 0.00, N = 3SE +/- 0.00, N = 31.361.211. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Cython benchmark

Stress benchmark tests to measure time consumed by cython code Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterCython benchmark 0.27EPYC 76012 x Xeon Gold 6138816243240SE +/- 0.26, N = 3SE +/- 0.04, N = 334.5425.26

FLAC Audio Encoding

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

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.1WAV To FLACEPYC 76012 x Xeon Gold 6138246810SE +/- 0.01, N = 5SE +/- 0.01, N = 56.905.861. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm

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 MP3EPYC 76012 x Xeon Gold 61381020304050SE +/- 0.00, N = 3SE +/- 0.10, N = 342.8732.421. (CC) gcc options: -lncurses -lm

Ogg Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.3WAV To OggEPYC 76012 x Xeon Gold 6138246810SE +/- 0.12, N = 3SE +/- 0.02, N = 37.726.761. (CC) gcc options: -O2 -ffast-math -fsigned-char -logg

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 SynthesisEPYC 76012 x Xeon Gold 6138918273645SE +/- 0.30, N = 3SE +/- 0.45, N = 640.5032.171. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions

Hackbench

This is a benchmark of Hackbench, a test of the Linux kernel scheduler. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: ThreadEPYC 76012 x Xeon Gold 61381.09352.1873.28054.3745.4675SE +/- 0.23, N = 6SE +/- 0.08, N = 64.863.031. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: ThreadEPYC 76012 x Xeon Gold 6138246810SE +/- 0.09, N = 3SE +/- 0.09, N = 66.033.101. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: ThreadEPYC 76012 x Xeon Gold 61383691215SE +/- 0.11, N = 3SE +/- 0.01, N = 39.125.121. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ThreadEPYC 76012 x Xeon Gold 613848121620SE +/- 0.08, N = 3SE +/- 0.16, N = 316.859.001. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 1 - Type: ProcessEPYC 76012 x Xeon Gold 61381.05082.10163.15244.20325.254SE +/- 0.03, N = 3SE +/- 0.04, N = 34.672.901. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ThreadEPYC 76012 x Xeon Gold 6138714212835SE +/- 0.30, N = 3SE +/- 0.38, N = 430.3623.411. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 2 - Type: ProcessEPYC 76012 x Xeon Gold 61381.21282.42563.63844.85126.064SE +/- 0.02, N = 3SE +/- 0.02, N = 35.392.641. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 4 - Type: ProcessEPYC 76012 x Xeon Gold 6138246810SE +/- 0.14, N = 6SE +/- 0.04, N = 37.584.591. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 8 - Type: ProcessEPYC 76012 x Xeon Gold 613848121620SE +/- 0.18, N = 3SE +/- 0.16, N = 314.398.101. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 16 - Type: ProcessEPYC 76012 x Xeon Gold 6138612182430SE +/- 0.30, N = 3SE +/- 1.26, N = 626.0819.421. (CC) gcc options: -lpthread

OpenBenchmarking.orgSeconds, Fewer Is BetterHackbenchCount: 32 - Type: Process2 x Xeon Gold 6138714212835SE +/- 0.56, N = 628.511. (CC) gcc options: -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 TimeEPYC 76012 x Xeon Gold 61381.24882.49763.74644.99526.244SE +/- 0.01, N = 3SE +/- 0.00, N = 35.555.011. (CC) gcc options: -static -fopenmp -O3 -march=native

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 BenchmarkEPYC 76012 x Xeon Gold 61380.20220.40440.60660.80881.011SE +/- 0.0007, N = 3SE +/- 0.0012, N = 30.89880.75961. R scripting front-end version 3.4.2 (2017-09-28)

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 Xeon Gold 61380.40280.80561.20841.61122.014SE +/- 0.04, N = 61.791. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -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 1.1.0fRSA 4096-bit PerformanceEPYC 76012 x Xeon Gold 61382K4K6K8K10KSE +/- 15.90, N = 3SE +/- 46.23, N = 34621.307861.831. (CC) gcc options: -O3 -pthread -m64 -lssl -lcrypto -ldl

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: ffsEPYC 76012 x Xeon Gold 61381.08452.1693.25354.3385.4225SE +/- 0.00, N = 3SE +/- 0.00, N = 34.823.26

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: sqrtEPYC 76012 x Xeon Gold 61383691215SE +/- 0.00, N = 3SE +/- 0.00, N = 34.708.98

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: tanhEPYC 76012 x Xeon Gold 6138918273645SE +/- 0.01, N = 3SE +/- 0.01, N = 338.3028.63

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: ffsllEPYC 76012 x Xeon Gold 61381.23982.47963.71944.95926.199SE +/- 0.00, N = 3SE +/- 0.00, N = 35.513.80

OpenBenchmarking.orgnanoseconds, Fewer Is Betterglibc bench 1.0Benchmark: pthread_onceEPYC 76012 x Xeon Gold 61381.08682.17363.26044.34725.434SE +/- 0.00, N = 3SE +/- 0.01, N = 34.833.81

Multichase Pointer Chaser

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 4MB Array, 64 Byte StrideEPYC 76012 x Xeon Gold 61383691215SE +/- 0.00, N = 3SE +/- 0.07, N = 39.789.781. (CC) gcc options: -O2 -static -pthread -lrt

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte StrideEPYC 76012 x Xeon Gold 613820406080100SE +/- 0.65, N = 3SE +/- 0.12, N = 384.8078.731. (CC) gcc options: -O2 -static -pthread -lrt

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 256MB Array, 256 Byte StrideEPYC 76012 x Xeon Gold 613820406080100SE +/- 0.08, N = 3SE +/- 0.15, N = 380.6868.411. (CC) gcc options: -O2 -static -pthread -lrt

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stride, 2 ThreadsEPYC 76012 x Xeon Gold 613820406080100SE +/- 0.06, N = 3SE +/- 0.17, N = 385.9677.541. (CC) gcc options: -O2 -static -pthread -lrt

OpenBenchmarking.orgns, Fewer Is BetterMultichase Pointer ChaserTest: 1GB Array, 256 Byte Stride, 4 ThreadsEPYC 76012 x Xeon Gold 613820406080100SE +/- 0.11, N = 3SE +/- 0.09, N = 391.3480.191. (CC) gcc options: -O2 -static -pthread -lrt

libjpeg-turbo tjbench

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.1Test: Decompression ThroughputEPYC 76012 x Xeon Gold 6138306090120150SE +/- 0.03, N = 3SE +/- 0.35, N = 3142.40154.951. (CC) gcc options: -O3 -lm

Tensorflow

This is a benchmark of the Tensorflow deep learning framework using the CIFAR10 data set. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTensorflow 2017-02-03Build: Cifar10EPYC 76012 x Xeon Gold 61381428425670SE +/- 0.07, N = 3SE +/- 0.14, N = 362.0556.26

Darktable

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.2.5Test: Boat - Acceleration: CPU-onlyEPYC 76012 x Xeon Gold 61381.30052.6013.90155.2026.5025SE +/- 0.04, N = 3SE +/- 0.01, N = 35.785.45

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.2.5Test: Masskrug - Acceleration: CPU-onlyEPYC 76012 x Xeon Gold 6138246810SE +/- 0.04, N = 3SE +/- 0.18, N = 66.126.90

OpenBenchmarking.orgSeconds, Fewer Is BetterDarktable 2.2.5Test: Server Room - Acceleration: CPU-onlyEPYC 76012 x Xeon Gold 61380.7111.4222.1332.8443.555SE +/- 0.03, N = 3SE +/- 0.04, N = 33.162.76

GIMP

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.8.20Test: resizeEPYC 76012 x Xeon Gold 6138246810SE +/- 0.01, N = 3SE +/- 0.04, N = 34.586.48

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.8.20Test: auto-levelsEPYC 76012 x Xeon Gold 61383691215SE +/- 0.05, N = 3SE +/- 0.14, N = 58.3210.13

OpenBenchmarking.orgSeconds, Fewer Is BetterGIMP 2.8.20Test: unsharp-maskEPYC 76012 x Xeon Gold 6138510152025SE +/- 0.21, N = 3SE +/- 0.21, N = 318.9119.39

Redis

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPOPEPYC 76012 x Xeon Gold 6138400K800K1200K1600K2000KSE +/- 28001.21, N = 3SE +/- 22258.92, N = 31739038.251396716.921. (CC) gcc options: -ggdb -rdynamic -lm -pthread

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SADDEPYC 76012 x Xeon Gold 6138400K800K1200K1600K2000KSE +/- 25752.21, N = 6SE +/- 68287.40, N = 61415778.751664424.651. (CC) gcc options: -ggdb -rdynamic -lm -pthread

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: LPUSHEPYC 76012 x Xeon Gold 6138300K600K900K1200K1500KSE +/- 43714.65, N = 6SE +/- 55148.78, N = 61278868.841410152.671. (CC) gcc options: -ggdb -rdynamic -lm -pthread

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETEPYC 76012 x Xeon Gold 6138400K800K1200K1600K2000KSE +/- 43181.29, N = 6SE +/- 71102.11, N = 61630676.501793642.131. (CC) gcc options: -ggdb -rdynamic -lm -pthread

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SETEPYC 76012 x Xeon Gold 6138300K600K900K1200K1500KSE +/- 8325.34, N = 3SE +/- 49709.19, N = 61262205.211469330.391. (CC) gcc options: -ggdb -rdynamic -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: CryptoEPYC 76012 x Xeon Gold 613813002600390052006500SE +/- 36.60, N = 3SE +/- 38.08, N = 35825.326103.62-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: BsearchEPYC 76012 x Xeon Gold 61384K8K12K16K20KSE +/- 75.99, N = 3SE +/- 54.86, N = 316685.9619966.89-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: ForkingEPYC 76012 x Xeon Gold 613815K30K45K60K75KSE +/- 1375.07, N = 6SE +/- 1617.68, N = 652324.2068922.29-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: HsearchEPYC 76012 x Xeon Gold 613840K80K120K160K200KSE +/- 746.83, N = 3SE +/- 661.06, N = 3150628.51175731.11-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: LsearchEPYC 76012 x Xeon Gold 613880160240320400SE +/- 0.39, N = 3SE +/- 0.48, N = 3338.57383.64-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: TsearchEPYC 76012 x Xeon Gold 6138140280420560700SE +/- 4.62, N = 3SE +/- 0.69, N = 3392.20643.83-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: CPU StressEPYC 76012 x Xeon Gold 61383K6K9K12K15KSE +/- 73.89, N = 3SE +/- 43.19, N = 37795.5212460.39-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: SemaphoresEPYC 76012 x Xeon Gold 6138400K800K1200K1600K2000KSE +/- 1549.41, N = 3SE +/- 72674.04, N = 61573684.401741434.70-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Matrix MathEPYC 76012 x Xeon Gold 613840K80K120K160K200KSE +/- 222.56, N = 3SE +/- 793.88, N = 3142639.59196635.66-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Vector MathEPYC 76012 x Xeon Gold 613815K30K45K60K75KSE +/- 161.18, N = 3SE +/- 110.24, N = 367119.7569426.91-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Memory CopyingEPYC 76012 x Xeon Gold 613813002600390052006500SE +/- 3.42, N = 3SE +/- 89.90, N = 31911.245981.99-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Socket ActivityEPYC 76012 x Xeon Gold 61384K8K12K16K20KSE +/- 283.56, N = 6SE +/- 1770.10, N = 619027.443521.32-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Context Switching2 x Xeon Gold 61383M6M9M12M15MSE +/- 184516.53, N = 613294136.941. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc C String FunctionsEPYC 76012 x Xeon Gold 6138500K1000K1500K2000K2500KSE +/- 11626.70, N = 3SE +/- 25600.87, N = 31425100.822248593.55-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: Glibc Qsort Data SortingEPYC 76012 x Xeon Gold 6138100200300400500SE +/- 5.18, N = 3SE +/- 4.98, N = 3334.50458.04-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.07.26Test: System V Message PassingEPYC 76012 x Xeon Gold 61382M4M6M8M10MSE +/- 43583.13, N = 3SE +/- 55905.53, N = 39375740.695411993.69-laio1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc

Xsbench

XSBench is a mini-app representing a key computational kernel of the Monte Carlo neutronics application OpenMC. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgLookups/s, More Is BetterXsbench 2017-07-06EPYC 76012 x Xeon Gold 61381.4M2.8M4.2M5.6M7MSE +/- 55876.67, N = 6SE +/- 130483.08, N = 3332372664843321. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm

PyBench

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2008-08-14Total For Average Test TimesEPYC 76012 x Xeon Gold 6138400800120016002000SE +/- 2.31, N = 3SE +/- 11.68, N = 317771321

NGINX Benchmark

This is a test of ab, which is the Apache Benchmark program running against nginx. This test profile measures how many requests per second a given system can sustain when carrying out 2,000,000 requests with 500 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page Serving2 x Xeon Gold 61385K10K15K20K25KSE +/- 81.74, N = 323040.141. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

Apache Benchmark

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page ServingEPYC 76012 x Xeon Gold 61384K8K12K16K20KSE +/- 35.49, N = 3SE +/- 50.41, N = 318106.9018641.251. (CC) gcc options: -shared -fPIC -O2 -pthread

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 SuiteEPYC 76012 x Xeon Gold 6138120K240K360K480K600KSE +/- 1482.79, N = 3SE +/- 4360.77, N = 3340836537416

Scikit-Learn

Scikit-learn is a Python module for machine learning Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterScikit-Learn 0.17.1EPYC 76012 x Xeon Gold 61384080120160200SE +/- 0.01, N = 3SE +/- 0.17, N = 3144.61172.48

Sunflow Rendering System

OpenBenchmarking.orgSeconds, Fewer Is BetterSunflow Rendering System 0.07.2Global Illumination + Image SynthesisEPYC 76012 x Xeon Gold 61380.24980.49960.74940.99921.249SE +/- 0.02, N = 6SE +/- 0.03, N = 61.110.97

Schbench

This is a benchmark of Schbench, a Linux kernel scheduler benchmark developed by Facebook. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 8EPYC 76012 x Xeon Gold 61384K8K12K16K20KSE +/- 601.38, N = 6SE +/- 222.73, N = 318667128911. (CC) gcc options: -O2 -lpthread

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 8 - Workers Per Message Thread: 16EPYC 76012 x Xeon Gold 61385K10K15K20K25KSE +/- 469.33, N = 3SE +/- 206.06, N = 623669149281. (CC) gcc options: -O2 -lpthread

OpenBenchmarking.orgusec, 99.9th Latency Percentile, Fewer Is BetterSchbenchMessage Threads: 16 - Workers Per Message Thread: 16EPYC 76012 x Xeon Gold 613811K22K33K44K55KSE +/- 85.33, N = 3SE +/- 147.80, N = 353355439681. (CC) gcc options: -O2 -lpthread

176 Results Shown

Unpacking The Linux Kernel
RAMspeed SMP:
  Add - Integer
  Copy - Integer
  Scale - Integer
  Triad - Integer
  Average - Integer
  Add - Floating Point
  Copy - Floating Point
  Scale - Floating Point
  Triad - Floating Point
  Average - Floating Point
Stream:
  Copy
  Scale
  Triad
  Add
t-test1:
  1
  2
GNU MPC
Parboil:
  OpenMP LBM
  OpenMP CUTCP
  OpenMP Stencil
  OpenMP MRI Gridding
Rodinia:
  OpenMP LavaMD
  OpenMP CFD Solver
  OpenMP Streamcluster
High Performance Conjugate Gradient
CLOMP
PolyBench-C
lzbench
lzbench
lzbench
lzbench
lzbench
lzbench
lzbench
lzbench
FFTW:
  Stock - 1D FFT Size 32
  Stock - 1D FFT Size 64
  Stock - 2D FFT Size 32
  Stock - 2D FFT Size 64
  Stock - 1D FFT Size 128
  Stock - 1D FFT Size 256
  Stock - 1D FFT Size 512
  Stock - 2D FFT Size 128
  Stock - 2D FFT Size 256
  Stock - 2D FFT Size 512
  Float + SSE - 1D FFT Size 32
  Float + SSE - 1D FFT Size 64
  Float + SSE - 2D FFT Size 32
  Float + SSE - 2D FFT Size 64
  Float + SSE - 1D FFT Size 128
  Float + SSE - 1D FFT Size 256
  Float + SSE - 1D FFT Size 512
  Float + SSE - 2D FFT Size 128
  Float + SSE - 2D FFT Size 256
  Float + SSE - 2D FFT Size 512
Timed HMMer Search
Timed MAFFT Alignment
Timed MrBayes Analysis
BLAKE2
GNU GMP GMPbench
Go Benchmarks:
  http
  json
  build
  garbage
Bork File Encrypter
CacheBench:
  Read
  Write
  Read / Modify / Write
Botan:
  KASUMI - Encrypt
  AES-256 - Encrypt
  Twofish - Encrypt
  Blowfish - Encrypt
  CAST-256 - Encrypt
Numpy Benchmark
Crafty
TSCP
John The Ripper:
  Blowfish
  Traditional DES
  MD5
Open FMM Nero2D
TTSIOD 3D Renderer
x264
GraphicsMagick:
  Blur
  Sharpen
  Resizing
  HWB Color Space
  Local Adaptive Thresholding
Himeno Benchmark
7-Zip Compression
asmFish
ebizzy
Timed Apache Compilation
Timed Linux Kernel Compilation
Timed PHP Compilation
C-Ray
POV-Ray
Primesieve
Stockfish
AOBench
Bullet Physics Engine:
  Raytests
  3000 Fall
  1000 Stack
  1000 Convex
  136 Ragdolls
  Prim Trimesh
  Convex Trimesh
Cython benchmark
FLAC Audio Encoding
LAME MP3 Encoding
Ogg Encoding
eSpeak Speech Engine
Hackbench:
  1 - Thread
  2 - Thread
  4 - Thread
  8 - Thread
  1 - Process
  16 - Thread
  2 - Process
  4 - Process
  8 - Process
  16 - Process
  32 - Process
N-Queens
R Benchmark
Tachyon
OpenSSL
glibc bench:
  ffs
  sqrt
  tanh
  ffsll
  pthread_once
Multichase Pointer Chaser:
  4MB Array, 64 Byte Stride
  1GB Array, 256 Byte Stride
  256MB Array, 256 Byte Stride
  1GB Array, 256 Byte Stride, 2 Threads
  1GB Array, 256 Byte Stride, 4 Threads
libjpeg-turbo tjbench
Tensorflow
Darktable:
  Boat - CPU-only
  Masskrug - CPU-only
  Server Room - CPU-only
GIMP:
  resize
  auto-levels
  unsharp-mask
Redis:
  LPOP
  SADD
  LPUSH
  GET
  SET
Stress-NG:
  Crypto
  Bsearch
  Forking
  Hsearch
  Lsearch
  Tsearch
  CPU Stress
  Semaphores
  Matrix Math
  Vector Math
  Memory Copying
  Socket Activity
  Context Switching
  Glibc C String Functions
  Glibc Qsort Data Sorting
  System V Message Passing
Xsbench
PyBench
NGINX Benchmark
Apache Benchmark
PHPBench
Scikit-Learn
Sunflow Rendering System
Schbench:
  16 - 8
  8 - 16
  16 - 16