AMD EPYC Compiler Tuning

GCC 9 compiler tuning benchmarks by Michael Larabel for a future article on Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1902194-SP-AMDEPYCCO19&sor&grs.

AMD EPYC Compiler TuningProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen Resolution-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O2 -flto-O3-O3 -march=znver1-O3 -march=znver1 -flto-Ofast -march=znver12 x AMD EPYC 7601 32-Core (64 Cores / 128 Threads)Dell 02MJ3T (1.2.5 BIOS)AMD Family 17h16 x 32 GB DDR4-2400MT/s 36ASF4G72PZ-2G6D2120GB SSDSCKJB120G7R + 20 x 500GB Samsung SSD 860Matrox G200eW3VE2282 x Broadcom BCM57416 NetXtreme-E 10GBase-T RDMA + 2 x Broadcom NetXtreme BCM5720 PCIeUbuntu 18.045.0.0-050000rc6-generic (x86_64) 20190210GNOME Shell 3.28.3X ServerGCC 9.0.1 20190210ext41600x1200OpenBenchmarking.orgEnvironment Details- -O0: CXXFLAGS=-O0 CFLAGS=-O0- -Og: CXXFLAGS=-Og CFLAGS=-Og- -O1: CXXFLAGS=-O1 CFLAGS=-O1- -O2: CXXFLAGS=-O2 CFLAGS=-O2- -O2 -ftree-vectorize -ftree-slp-vectorize: CXXFLAGS=-O2-ftree-vectorize-ftree-slp-vectorize CFLAGS=-O2-ftree-vectorize-ftree-slp-vectorize- -O2 -march=znver1: CXXFLAGS=-O2-march=znver1 CFLAGS=-O2-march=znver1- -O2 -flto: CXXFLAGS=-O2-flto CFLAGS=-O2-flto- -O3: CXXFLAGS=-O3 CFLAGS=-O3- -O3 -march=znver1: CXXFLAGS=-O3-march=znver1 CFLAGS=-O3-march=znver1- -O3 -march=znver1 -flto: CXXFLAGS=-O3 march=znver1-flto CFLAGS=-O3-march=znver1-flto- -Ofast -march=znver1: CXXFLAGS=-Ofast-march=znver1 CFLAGS=-Ofast-march=znver1Compiler Details- --disable-multilib --enable-checking=releaseSecurity Details- __user pointer sanitization + Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + SSB disabled via prctl and seccomp

AMD EPYC Compiler Tuningencode-flac: WAV To FLACfftw: Float + SSE - 2D FFT Size 4096build-php: Time To Compilescimark2: Sparse Matrix Multiplyscimark2: Compositec-ray: Total Time - 4K, 16 Rays Per Pixelencode-mp3: WAV To MP3fftw: Stock - 2D FFT Size 4096build-imagemagick: Time To Compilehimeno: Poisson Pressure Solverbuild-apache: Time To Compilegraphics-magick: Sharpengraphics-magick: Enhancedgraphics-magick: HWB Color Spacegraphics-magick: Swirlgraphics-magick: Noise-Gaussianscimark2: Jacobi Successive Over-Relaxationscimark2: Monte Carlographics-magick: Rotateaobench: 2048 x 2048 - Total Timegraphics-magick: Resizingpgbench: Buffer Test - Single Thread - Read Onlyhmmer: Pfam Database Searchx264: H.264 Video Encodingpgbench: Buffer Test - Normal Load - Read Writetjbench: Decompression Throughputpgbench: Buffer Test - Single Thread - Read Writescimark2: Fast Fourier Transformpgbench: Buffer Test - Normal Load - Read Onlyjohn-the-ripper: Traditional DESbullet: 1000 Stackhint: DOUBLEbullet: 136 Ragdollssvt-vp9: 1080p 8-bit YUV To VP9 Video Encodebullet: 1000 Convexvpxenc: vpxenc VP9 1080p Video Encodesvt-av1: 1080p 8-bit YUV To AV1 Video Encodevpxenc: vpxenc VP9 1080p Video Encodex265: H.265 1080p Video Encodingbullet: 3000 Fallbullet: Raytestsstockfish: Total Timebullet: Convex Trimeshbullet: Prim Trimeshsvt-av1: 1080p 8-bit YUV To AV1 Video Encodehint: FLOATtscp: AI Chess Performancectx-clock: Context Switch Timecompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19john-the-ripper: Blowfishscimark2: Dense LU Matrix Factorization-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O2 -flto-O3-O3 -march=znver1-O3 -march=znver1 -flto-Ofast -march=znver196.77219315.1951643444.9241.7917085.2338311.43829010296928321089892.507490639.0210245851118862014197002182320006.005985453423.145.361.6912.5035.005.143.111058681751.351.115.8826740444586545923.121517951215.581264221.422188120528.6416.7843667.8977214.5915617319518116891921018177.41120133337.39142376714110802575072032392893336.025972342663.1492.685.3720.391.7312.5234.765.153.111057096901.351.115.8626736867186518713214.3956453253915.011346829.052411151928.7414.32463218.4278517.5118018721019417991957619156.61126133036.93145430113910652265151022570672006.005850600293.155.371.7012.5335.625.163.121056980921.351.115.8726845557886410214.1165995346613.651339152.172527136925.8414.07462523.63101723.8218118921119518091956019155.54131149316.62144416714010372305153402574076676.015994816053.145.371.6912.5434.555.143.121044804221.351.115.8126731197086437314.4862718260913.701328552.582515172425.7710.96480523.91100724.0318018821219617891956019055.53128153536.82144423913911252315296992570580005.986025352973.1594.825.3720.341.6712.5635.415.143.111041978651.351.115.8926717214586491613213.6763586439613.891334651.962584150121.5814.00507423.78100123.82183191211196180101655719154.35127151116.54144427214210602295104252559570005.806175166263.0595.915.1920.051.7012.4234.805.083.101060842761.321.115.8426726802386491514.7161309323113.64132142299130725.9614.14509198.67102226.5018319021419618091856819155.52128148516.56409514011272325205702607366676.326266404003.2495.795.401.6935.075.213.051045366051.331.095.9026817340086410113214.0865117251513.611355578.192475180012.6010.84475125.06100826.08174181203189172142756018353.53118150996.57147426214110792324905512538685836.055954280473.155.381.7312.3135.215.163.111041218401.351.115.9026731564786491513.6665806430713.851275278.132482196111.3510.57500624.88101125.94183191210195180168955719051.49127151886.29144506814411452275050312600196675.805892899263.065.181.6812.4135.575.073.091064979941.321.115.8926850647286573214.3766823485114.21131102052174711.3110.385571118.48100028.621831862091941781675148018852.08125160126.164319144107423045425625477733361864410197.2620.861.7112.755.8426723940586301813213.1658764330013.95131662579182510.409.80488525.21102226.11182193209196187167656118951.73124153526.00144410214411252215083842587706675.806053318333.0697.805.1820.131.7012.3734.915.093.091065072441.321.115.9126705540786437313.77628414089OpenBenchmarking.org

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLAC-O3-O2 -flto-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O2 -march=znver1-Ofast -march=znver1-O3 -march=znver1 -flto-O1-Og-O020406080100SE +/- 0.12, N = 5SE +/- 0.11, N = 5SE +/- 0.08, N = 5SE +/- 0.14, N = 5SE +/- 0.10, N = 5SE +/- 0.09, N = 5SE +/- 0.08, N = 5SE +/- 0.10, N = 5SE +/- 0.09, N = 5SE +/- 0.11, N = 5SE +/- 0.12, N = 513.6113.6413.6513.7013.8513.8913.9514.2115.0115.5896.77-O01. (CXX) g++ options: -fvisibility=hidden -logg -lm

FFTW

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

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 4096-O3-O1-O2-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-Og-O03K6K9K12K15KSE +/- 115.66, N = 3SE +/- 70.29, N = 3SE +/- 160.95, N = 3SE +/- 15.71, N = 3SE +/- 72.78, N = 3SE +/- 134.39, N = 3SE +/- 160.71, N = 8SE +/- 49.65, N = 3SE +/- 78.62, N = 3SE +/- 165.58, N = 3SE +/- 1.00, N = 3135551346813391133461328513214131661311012752126422193-O3-O1-O2-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-Og-O01. (CC) gcc options: -pthread -lm

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To Compile-O0-Og-O1-O2 -march=znver1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O320406080100SE +/- 0.02, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.25, N = 3SE +/- 0.18, N = 3SE +/- 0.26, N = 3SE +/- 0.33, N = 3SE +/- 0.22, N = 315.1921.4229.0551.9652.1752.5878.1378.19-Og-O1-O2 -march=znver1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O31. (CC) gcc options: -pedantic -ldl -lz -lm

SciMark

Computational Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiply-O2 -march=znver1-Ofast -march=znver1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O3-O1-O2 -flto-Og-O3 -march=znver1 -flto-O06001200180024003000SE +/- 14.53, N = 3SE +/- 12.59, N = 3SE +/- 11.61, N = 3SE +/- 12.19, N = 3SE +/- 10.26, N = 3SE +/- 3.37, N = 3SE +/- 59.22, N = 3SE +/- 5.41, N = 3SE +/- 3.66, N = 3SE +/- 2.13, N = 3SE +/- 5.25, N = 32584257925272515248224752411229921882052516-O2 -march=znver1-Ofast -march=znver1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O3-O1-O2 -flto-Og-O3 -march=znver1 -flto-O01. (CC) gcc options: -lm

SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Composite-O3 -march=znver1-Ofast -march=znver1-O3-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O2 -march=znver1-O2-O2 -flto-Og-O0400800120016002000SE +/- 11.89, N = 3SE +/- 20.59, N = 3SE +/- 7.96, N = 3SE +/- 35.09, N = 3SE +/- 8.94, N = 3SE +/- 6.18, N = 3SE +/- 23.45, N = 5SE +/- 12.17, N = 3SE +/- 24.31, N = 3SE +/- 18.65, N = 5SE +/- 5.30, N = 31961182518001747172415191501136913071205434-O3 -march=znver1-Ofast -march=znver1-O3-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O2 -march=znver1-O2-O2 -flto-Og-O01. (CC) gcc options: -lm

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixel-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-O3-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O2 -flto-Og-O1-O01020304050SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.09, N = 310.4011.3111.3512.6021.5825.7725.8425.9628.6428.7444.92-Ofast -march=znver1-march=znver1 -flto-march=znver1-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O2 -flto-Og-O1-O01. (CC) gcc options: -lm -lpthread -O3

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-O3-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O2-O2 -flto-O1-Og-O01020304050SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 39.8010.3810.5710.8410.9614.0014.0714.1414.3216.7841.79-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-O3-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O2-O2 -flto-O1-Og-O01. (CC) gcc options: -lm

FFTW

Build: Stock - Size: 2D FFT Size 4096

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096-O3 -march=znver1 -flto-O2 -flto-O2 -march=znver1-O3 -march=znver1-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3-O1-O2-Og-O012002400360048006000SE +/- 26.34, N = 3SE +/- 5.87, N = 3SE +/- 13.33, N = 3SE +/- 47.88, N = 3SE +/- 10.24, N = 3SE +/- 26.82, N = 3SE +/- 41.07, N = 3SE +/- 6.37, N = 3SE +/- 2.28, N = 3SE +/- 11.16, N = 3SE +/- 5.17, N = 355715091507450064885480547514632462543661708-O3 -march=znver1 -flto-O2 -flto-O2 -march=znver1-O3 -march=znver1-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3-O1-O2-Og-O01. (CC) gcc options: -pthread -lm

Timed ImageMagick Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compile-O0-Og-O1-O2-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O3-Ofast -march=znver1-O2 -flto-O3 -march=znver1 -flto306090120150SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.21, N = 8SE +/- 0.10, N = 3SE +/- 0.45, N = 3SE +/- 0.20, N = 3SE +/- 0.30, N = 3SE +/- 0.44, N = 3SE +/- 0.34, N = 3SE +/- 0.98, N = 3SE +/- 0.45, N = 35.237.8918.4223.6323.7823.9124.8825.0625.2198.67118.48

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-Ofast -march=znver1-O2 -flto-O2-O3 -march=znver1-O3-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O3 -march=znver1 -flto-O1-Og-O02004006008001000SE +/- 8.54, N = 3SE +/- 2.58, N = 3SE +/- 5.25, N = 3SE +/- 0.08, N = 3SE +/- 6.27, N = 3SE +/- 7.21, N = 3SE +/- 2.90, N = 3SE +/- 2.81, N = 3SE +/- 5.78, N = 3SE +/- 4.02, N = 3SE +/- 0.11, N = 310221022101710111008100710011000785772383-Ofast -march=znver1-O2 -flto-O2-march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-march=znver1 -flto-O1-Og-O01. (CC) gcc options: -O3 -mavx2

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.7Time To Compile-O0-Og-O1-O2-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O3-Ofast -march=znver1-O2 -flto-O3 -march=znver1 -flto714212835SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 311.4314.5917.5123.8223.8224.0325.9426.0826.1126.5028.62

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Sharpen-O3 -march=znver1 -flto-O3 -march=znver1-O2 -flto-O2 -march=znver1-Ofast -march=znver1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O3-Og-O04080120160200SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 318318318318318218118018017415682-O3 -march=znver1 -flto-O3 -march=znver1-O2 -flto-O2 -march=znver1-Ofast -march=znver1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O3-Og-O01. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Enhanced

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Enhanced-Ofast -march=znver1-O3 -march=znver1-O2 -march=znver1-O2 -flto-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O3 -march=znver1 -flto-O3-Og-O04080120160200SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 3.18, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 319319119119018918818718618117390-Ofast -march=znver1-O3 -march=znver1-O2 -march=znver1-O2 -flto-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O3 -march=znver1 -flto-O3-Og-O01. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -ldl -lpthread

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color Space-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O2-O3 -march=znver1-O1-Ofast -march=znver1-O3 -march=znver1 -flto-O3-Og-O050100150200250SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 3214212211211210210209209203195102-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O2-O3 -march=znver1-O1-Ofast -march=znver1-O3 -march=znver1 -flto-O3-Og-O01. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Swirl

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Swirl-Ofast -march=znver1-O2 -flto-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O2-O3 -march=znver1 -flto-O1-O3-Og-O04080120160200SE +/- 0.67, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 319619619619619519519419418918196-Ofast -march=znver1-O2 -flto-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O2-O3 -march=znver1 -flto-O1-O3-Og-O01. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Noise-Gaussian

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Noise-Gaussian-Ofast -march=znver1-O3 -march=znver1-O2 -flto-O2 -march=znver1-O2-O1-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O3-Og-O04080120160200SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 1.20, N = 3SE +/- 0.58, N = 3SE +/- 0.88, N = 3SE +/- 0.58, N = 318718018018018017917817817216892-Ofast -march=znver1-O3 -march=znver1-O2 -flto-O2 -march=znver1-O2-O1-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O3-Og-O01. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -ldl -lpthread

SciMark

Computational Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxation-O3 -march=znver1-Ofast -march=znver1-O3 -march=znver1 -flto-O3-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O1-Og-O2 -flto-O0400800120016002000SE +/- 0.21, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.15, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.31, N = 3SE +/- 0.08, N = 3SE +/- 0.35, N = 316891676167514271016919919919919918832-O3 -march=znver1-Ofast -march=znver1-O3 -march=znver1 -flto-O3-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O1-Og-O2 -flto-O01. (CC) gcc options: -lm

SciMark

Computational Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlo-O3 -march=znver1 -flto-O1-O2 -flto-Ofast -march=znver1-O3-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O3 -march=znver1-O2 -march=znver1-Og-O030060090012001500SE +/- 0.33, N = 3SE +/- 0.27, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 0.11, N = 3SE +/- 0.22, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.28, N = 3SE +/- 0.03, N = 31480576568561560560560557557210108-O3 -march=znver1 -flto-O1-O2 -flto-Ofast -march=znver1-O3-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O3 -march=znver1-O2 -march=znver1-Og1. (CC) gcc options: -lm

GraphicsMagick

Operation: Rotate

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Rotate-O2 -flto-O2 -march=znver1-O2-O1-O3 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O3 -march=znver1 -flto-O3-Og-O04080120160200SE +/- 0.33, N = 319119119119119019018918818318198-O2 -flto-O2 -march=znver1-O2-O1-O3 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O3 -march=znver1 -flto-O3-Og-O01. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -ldl -lpthread

AOBench

Size: 2048 x 2048 - Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total Time-O3 -march=znver1-Ofast -march=znver1-O3 -march=znver1 -flto-O3-O2 -march=znver1-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O1-Og-O020406080100SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 351.4951.7352.0853.5354.3555.5255.5355.5456.6177.4192.50-march=znver1-Ofast -march=znver1-march=znver1 -flto-O2 -march=znver1-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O1-Og-O01. (CC) gcc options: -lm -O3

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Resizing-O2-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O2 -march=znver1-O1-O3 -march=znver1 -flto-Ofast -march=znver1-Og-O3-O0306090120150SE +/- 2.52, N = 3SE +/- 1.50, N = 12SE +/- 1.53, N = 3SE +/- 1.94, N = 5SE +/- 1.43, N = 12SE +/- 1.50, N = 8SE +/- 1.32, N = 10SE +/- 1.40, N = 8SE +/- 1.20, N = 313112812812712712612512412011874-O2-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1-O2 -march=znver1-O1-O3 -march=znver1 -flto-Ofast -march=znver1-Og-O3-O01. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -ldl -lpthread

PostgreSQL pgbench

Scaling: Buffer Test - Test: Single Thread - Mode: Read Only

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Only-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O3 -march=znver1-O2 -march=znver1-O3-O2-O2 -flto-Og-O1-O03K6K9K12K15KSE +/- 224.15, N = 6SE +/- 295.94, N = 3SE +/- 125.79, N = 3SE +/- 101.16, N = 3SE +/- 122.77, N = 3SE +/- 32.93, N = 3SE +/- 48.94, N = 3SE +/- 172.87, N = 3SE +/- 149.12, N = 3SE +/- 119.98, N = 3SE +/- 69.77, N = 3160121535315352151881511115099149311485113333133039063-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O3 -march=znver1-O2 -march=znver1-O3-O2-O2 -flto-Og-O1-O01. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database Search-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-O2 -march=znver1-O2 -flto-O3-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-Og-O03691215SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 3SE +/- 0.05, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 3SE +/- 0.14, N = 36.006.166.296.546.566.576.626.826.937.399.02-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-O2 -march=znver1-O2 -flto-O3-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-Og-O01. (CC) gcc options: -pthread -lhmmer -lsquid -lm

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video Encoding-O3-O1-Ofast -march=znver1-O3 -march=znver1-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-Og-O0306090120150SE +/- 0.81, N = 3SE +/- 1.49, N = 3SE +/- 0.52, N = 3SE +/- 1.78, N = 3SE +/- 1.40, N = 3SE +/- 0.47, N = 3SE +/- 0.97, N = 3SE +/- 1.09, N = 3SE +/- 0.12, N = 3147145144144144144144142102-O1-Ofast -march=znver1-march=znver1-O2 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-Og-O01. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Write-O3 -march=znver1-O0-O3 -march=znver1 -flto-O1-O2 -march=znver1-O3-O2 -ftree-vectorize -ftree-slp-vectorize-O2-Ofast -march=znver1-O2 -flto-Og11002200330044005500SE +/- 50.49, N = 3SE +/- 29.67, N = 3SE +/- 66.20, N = 5SE +/- 71.59, N = 9SE +/- 12.79, N = 3SE +/- 29.58, N = 3SE +/- 55.61, N = 6SE +/- 49.50, N = 9SE +/- 66.04, N = 9SE +/- 26.99, N = 3SE +/- 47.02, N = 350684585431943014272426242394167410240953767-O3 -march=znver1-O0-O3 -march=znver1 -flto-O1-O2 -march=znver1-O3-O2 -ftree-vectorize -ftree-slp-vectorize-O2-Ofast -march=znver1-O2 -flto-Og1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

libjpeg-turbo tjbench

Test: Decompression Throughput

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.3Test: Decompression Throughput-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-O2 -march=znver1-O3-Og-O2 -flto-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O0306090120150SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 3SE +/- 0.91, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.67, N = 3SE +/- 0.06, N = 3SE +/- 0.03, N = 3SE +/- 0.76, N = 3144144144142141141140140139139111-Ofast -march=znver1-O3 -march=znver1 -flto-O3 -march=znver1-O2 -march=znver1-O3-Og-O2 -flto-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O01. (CC) gcc options: -lm

PostgreSQL pgbench

Scaling: Buffer Test - Test: Single Thread - Mode: Read Write

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Write-O3 -march=znver1-O2 -flto-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-Og-O3-O3 -march=znver1 -flto-O1-O2 -march=znver1-O2-O02004006008001000SE +/- 19.20, N = 3SE +/- 3.41, N = 3SE +/- 19.14, N = 3SE +/- 1.22, N = 3SE +/- 4.15, N = 3SE +/- 12.77, N = 8SE +/- 9.80, N = 3SE +/- 8.54, N = 3SE +/- 12.77, N = 9SE +/- 17.89, N = 3SE +/- 6.16, N = 31145112711251125108010791074106510601037886-O3 -march=znver1-O2 -flto-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-Og-O3-O3 -march=znver1 -flto-O1-O2 -march=znver1-O2-O01. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

SciMark

Computational Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform-Og-O3-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1 -flto-O2-O2 -march=znver1-O3 -march=znver1-O1-Ofast -march=znver1-O060120180240300SE +/- 2.03, N = 3SE +/- 0.51, N = 3SE +/- 2.57, N = 3SE +/- 0.71, N = 3SE +/- 1.03, N = 3SE +/- 0.61, N = 3SE +/- 1.88, N = 3SE +/- 0.03, N = 3SE +/- 0.44, N = 3SE +/- 1.04, N = 3SE +/- 1.00, N = 3257232232231230230229227226221201-Og-O3-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O3 -march=znver1 -flto-O2-O2 -march=znver1-O3 -march=znver1-O1-Ofast -march=znver1-O01. (CC) gcc options: -lm

PostgreSQL pgbench

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

OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Only-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto-O2-O1-O2 -march=znver1-Ofast -march=znver1-Og-O3 -march=znver1-O3-O3 -march=znver1 -flto-O0110K220K330K440K550KSE +/- 3875.50, N = 3SE +/- 4765.38, N = 3SE +/- 2768.55, N = 3SE +/- 6061.06, N = 3SE +/- 5952.34, N = 3SE +/- 1629.04, N = 3SE +/- 3395.99, N = 3SE +/- 3819.62, N = 3SE +/- 8068.95, N = 9SE +/- 7546.41, N = 4SE +/- 4794.85, N = 3529699520570515340515102510425508384507203505031490551454256419700-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto-O2-O1-O2 -march=znver1-Ofast -march=znver1-Og-O3 -march=znver1-O3-O3 -march=znver1 -flto-O01. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

John The Ripper

Test: Traditional DES

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Traditional DES-O2 -flto-O3 -march=znver1-Ofast -march=znver1-O2-O1-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O3 -march=znver1 -flto-O3-Og-O060M120M180M240M300MSE +/- 642920.77, N = 3SE +/- 2346357.84, N = 3SE +/- 1656338.97, N = 3SE +/- 2178423.16, N = 3SE +/- 2774527.11, N = 10SE +/- 2839112.24, N = 3SE +/- 2041895.52, N = 3SE +/- 1374420.40, N = 3SE +/- 3859011.69, N = 12SE +/- 2445677.03, N = 3SE +/- 2756947.41, N = 32607366672600196672587706672574076672570672002570580002559570002547773332538685832392893332182320001. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt

Bullet Physics Engine

Test: 1000 Stack

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Stack-O2 -march=znver1-O3 -march=znver1-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O0-O1-O2-Og-O3-O2 -flto246810SE +/- 0.01, N = 3SE +/- 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 +/- 0.04, N = 3SE +/- 0.02, N = 35.805.805.805.986.006.006.016.026.056.32-O2 -march=znver1-march=znver1-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O0-O1-O2-Og-O2 -flto1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Hierarchical INTegration

Test: DOUBLE

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: DOUBLE-O2 -flto-O3 -march=znver1 -flto-O2 -march=znver1-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O0-Og-O3-O3 -march=znver1-O1130M260M390M520M650MSE +/- 10585229.89, N = 3SE +/- 7234705.24, N = 9SE +/- 9814749.06, N = 4SE +/- 7419115.18, N = 3SE +/- 2338894.48, N = 3SE +/- 6546514.72, N = 3SE +/- 8177784.85, N = 3SE +/- 9099115.17, N = 9SE +/- 1832535.45, N = 3SE +/- 7042504.19, N = 3SE +/- 1617493.63, N = 3626640400618644101617516626605331833602535297599481605598545342597234266595428047589289926585060029-O2 -flto-march=znver1 -flto-O2 -march=znver1-Ofast -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O0-Og-march=znver1-O11. (CC) gcc options: -O3 -march=native -lm

Bullet Physics Engine

Test: 136 Ragdolls

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 Ragdolls-O2 -march=znver1-O3 -march=znver1-Ofast -march=znver1-O0-Og-O2-O1-O2 -ftree-vectorize -ftree-slp-vectorize-O3-O2 -flto0.7291.4582.1872.9163.645SE +/- 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 = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 33.053.063.063.143.143.143.153.153.153.24-O2 -march=znver1-march=znver1-Ofast -march=znver1-O0-Og-O2-O1-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

SVT-VP9

1080p 8-bit YUV To VP9 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video Encode-Ofast -march=znver1-O3 -march=znver1 -flto-O2 -march=znver1-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-Og20406080100SE +/- 0.30, N = 3SE +/- 0.50, N = 3SE +/- 0.18, N = 3SE +/- 0.75, N = 3SE +/- 1.09, N = 3SE +/- 1.17, N = 397.8097.2695.9195.7994.8292.68-Ofast -march=znver1-O3 -march=znver1-march=native-ftree-vectorize -ftree-slp-vectorize-Og1. (CC) gcc options: -fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx -pie -rdynamic -lpthread -lrt -lm

Bullet Physics Engine

Test: 1000 Convex

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Convex-O3 -march=znver1-Ofast -march=znver1-O2 -march=znver1-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O3-O2 -flto1.2152.433.6454.866.075SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 35.185.185.195.365.375.375.375.375.385.40-march=znver1-Ofast -march=znver1-O2 -march=znver1-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

VP9 libvpx Encoding

vpxenc VP9 1080p Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video Encode-O3 -march=znver1 -flto-Og-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O2 -march=znver1510152025SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 320.8620.3920.3420.1320.05

SVT-AV1

1080p 8-bit YUV To AV1 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2019-02-031080p 8-bit YUV To AV1 Video Encode-O3-Og-O3 -march=znver1 -flto-Ofast -march=znver1-O2 -march=znver1-O1-O2 -flto-O2-O0-O3 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize0.38930.77861.16791.55721.9465SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 6SE +/- 0.02, N = 9SE +/- 0.03, N = 3SE +/- 0.02, N = 8SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 31.731.731.711.701.701.701.691.691.691.681.671. (CC) gcc options: -mavx2 -fPIE -fPIC -O2 -pie -lpthread -lm

VP9 libvpx Encoding

vpxenc VP9 1080p Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video Encode-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-O2-O1-Og-O0-O2 -march=znver1-O3 -march=znver1-Ofast -march=znver1-O33691215SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.18, N = 512.7512.5612.5412.5312.5212.5012.4212.4112.3712.31

x265

H.265 1080p Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video Encoding-O1-O3 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3-O2 -flto-O0-Ofast -march=znver1-O2 -march=znver1-Og-O2816243240SE +/- 0.37, N = 11SE +/- 0.18, N = 3SE +/- 0.46, N = 3SE +/- 0.41, N = 3SE +/- 0.38, N = 3SE +/- 0.67, N = 3SE +/- 0.01, N = 3SE +/- 0.09, N = 3SE +/- 0.58, N = 3SE +/- 0.24, N = 335.6235.5735.4135.2135.0735.0034.9134.8034.7634.55-O1-march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto-O0-Ofast -march=znver1-O2 -march=znver1-Og-O21. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma

Bullet Physics Engine

Test: 3000 Fall

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 Fall-O3 -march=znver1-O2 -march=znver1-Ofast -march=znver1-O0-O2-O2 -ftree-vectorize -ftree-slp-vectorize-Og-O1-O3-O2 -flto1.17232.34463.51694.68925.8615SE +/- 0.01, 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 +/- 0.02, N = 3SE +/- 0.01, N = 35.075.085.095.145.145.145.155.165.165.21-march=znver1-O2 -march=znver1-Ofast -march=znver1-O0-O2-O2 -ftree-vectorize -ftree-slp-vectorize-Og-O1-O2 -flto1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Raytests

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Raytests-O2 -flto-O3 -march=znver1-Ofast -march=znver1-O2 -march=znver1-O0-Og-O2 -ftree-vectorize -ftree-slp-vectorize-O3-O1-O20.7021.4042.1062.8083.51SE +/- 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 = 3SE +/- 0.00, N = 33.053.093.093.103.113.113.113.113.123.12-O2 -flto-march=znver1-Ofast -march=znver1-O2 -march=znver1-O0-Og-O2 -ftree-vectorize -ftree-slp-vectorize-O1-O21. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Stockfish

Total Time

OpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time-Ofast -march=znver1-O3 -march=znver1-O2 -march=znver1-O0-Og-O1-O2 -flto-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O320M40M60M80M100MSE +/- 460638.54, N = 3SE +/- 402849.09, N = 3SE +/- 324013.38, N = 3SE +/- 1595135.10, N = 3SE +/- 823190.91, N = 3SE +/- 549524.55, N = 3SE +/- 579693.09, N = 3SE +/- 1016511.53, N = 3SE +/- 468403.16, N = 3SE +/- 673773.08, N = 3106507244106497994106084276105868175105709690105698092104536605104480422104197865104121840-Ofast -march=znver1-march=znver1-O2 -march=znver1-O0-Og-O1-O2-O2-O2 -ftree-vectorize -ftree-slp-vectorize1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

Bullet Physics Engine

Test: Convex Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex Trimesh-O2 -march=znver1-O3 -march=znver1-Ofast -march=znver1-O2 -flto-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O30.30380.60760.91141.21521.519SE +/- 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 = 3SE +/- 0.00, N = 31.321.321.321.331.351.351.351.351.351.35-O2 -march=znver1-march=znver1-Ofast -march=znver1-O2 -flto-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Prim Trimesh

OpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim Trimesh-O2 -flto-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-O3-O3 -march=znver1-Ofast -march=znver10.24980.49960.74940.99921.249SE +/- 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 = 3SE +/- 0.00, N = 31.091.111.111.111.111.111.111.111.111.11-O2 -flto-O0-Og-O1-O2-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-march=znver1-Ofast -march=znver11. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

SVT-AV1

1080p 8-bit YUV To AV1 Video Encode

OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2019-02-151080p 8-bit YUV To AV1 Video Encode-Ofast -march=znver1-O3-O2 -flto-O3 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O0-O1-Og-O3 -march=znver1 -flto-O2 -march=znver1-O21.32982.65963.98945.31926.649SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.05, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 35.915.905.905.895.895.885.875.865.845.845.811. (CC) gcc options: -mavx -fPIE -fPIC -O2 -pie -lpthread -lm

Hierarchical INTegration

Test: FLOAT

OpenBenchmarking.orgQUIPs, More Is BetterHierarchical INTegration 1.0Test: FLOAT-O3 -march=znver1-O1-O2 -flto-O0-Og-O3-O2-O2 -march=znver1-O3 -march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver160M120M180M240M300MSE +/- 1208988.13, N = 3SE +/- 1109543.66, N = 3SE +/- 1057235.60, N = 3SE +/- 321625.93, N = 3SE +/- 144731.32, N = 3SE +/- 219028.41, N = 3SE +/- 232284.24, N = 3SE +/- 211192.91, N = 3SE +/- 67545.97, N = 3SE +/- 54052.05, N = 3SE +/- 193963.83, N = 3268506472268455578268173400267404445267368671267315647267311970267268023267239405267172145267055407-march=znver1-O1-O2 -flto-O0-Og-O2-O2 -march=znver1-march=znver1 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver11. (CC) gcc options: -O3 -march=native -lm

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performance-O3 -march=znver1-O0-Og-O2 -ftree-vectorize -ftree-slp-vectorize-O3-O2 -march=znver1-Ofast -march=znver1-O2-O1-O2 -flto-O3 -march=znver1 -flto200K400K600K800K1000KSE +/- 667.00, N = 5SE +/- 333.13, N = 5SE +/- 333.13, N = 5SE +/- 508.06, N = 5SE +/- 272.00, N = 5SE +/- 272.00, N = 5SE +/- 507.80, N = 5SE +/- 507.80, N = 5SE +/- 542.88, N = 5SE +/- 331.91, N = 5SE +/- 270.20, N = 5865732865459865187864916864915864915864373864373864102864101863018-march=znver1-O0-Og-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -march=znver1-Ofast -march=znver1-O2-O1-O2 -flto-march=znver1 -flto1. (CC) gcc options: -O3 -march=native

ctx_clock

Context Switch Time

OpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch Time-Og-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto-O3 -march=znver1 -flto306090120150132132132132-Og-O2 -ftree-vectorize -ftree-slp-vectorize-O2 -flto-O3 -march=znver1 -flto1. (CC) gcc options:

Zstd Compression

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

OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19-O3 -march=znver1 -flto-O3-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O2 -flto-O1-O3 -march=znver1-Og-O2-O2 -march=znver1-O0612182430SE +/- 0.24, N = 11SE +/- 0.38, N = 12SE +/- 0.33, N = 12SE +/- 0.21, N = 12SE +/- 0.31, N = 12SE +/- 0.25, N = 12SE +/- 0.44, N = 12SE +/- 0.29, N = 12SE +/- 0.49, N = 9SE +/- 0.35, N = 12SE +/- 0.38, N = 413.1613.6613.6713.7714.0814.1114.3714.3914.4814.7123.12-O3 -march=znver1 -flto-O3-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O2 -flto-O1-O3 -march=znver1-Og-O2-O2 -march=znver1-O01. (CC) gcc options: -pthread -lz -llzma

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0-jumbo-1Test: Blowfish-O3 -march=znver1-O1-O3-O2 -flto-O2 -ftree-vectorize -ftree-slp-vectorize-Ofast -march=znver1-O2-O2 -march=znver1-O3 -march=znver1 -flto-Og-O014K28K42K56K70KSE +/- 1082.96, N = 12SE +/- 1098.57, N = 4SE +/- 1049.43, N = 3SE +/- 1395.50, N = 12SE +/- 1953.49, N = 12SE +/- 1454.31, N = 11SE +/- 1387.83, N = 12SE +/- 1967.27, N = 12SE +/- 1598.30, N = 12SE +/- 1339.16, N = 9SE +/- 215.16, N = 1266823659956580665117635866284162718613095876456453151791. (CC) gcc options: -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt

SciMark

Computational Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorization-O3 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3-Ofast -march=znver1-O1-O3 -march=znver1 -flto-O2 -march=znver1-O2-Og-O2 -flto-O010002000300040005000SE +/- 65.35, N = 3SE +/- 57.07, N = 3SE +/- 42.05, N = 3SE +/- 107.53, N = 3SE +/- 32.13, N = 3SE +/- 178.79, N = 3SE +/- 173.68, N = 3SE +/- 54.41, N = 3SE +/- 139.26, N = 3SE +/- 129.41, N = 3SE +/- 30.37, N = 34851439643074089346633003231260925392515512-O3 -march=znver1-O2 -ftree-vectorize -ftree-slp-vectorize-O3-Ofast -march=znver1-O1-O3 -march=znver1 -flto-O2 -march=znver1-O2-Og-O2 -flto-O01. (CC) gcc options: -lm

Phoronix Test Suite v10.8.4