Cascade Lake Compiler Benchmarks

2 x Intel Xeon Platinum 8280 testing for a future article.

HTML result view exported from: https://openbenchmarking.org/result/1904014-HV-CASCADELA24&sor&grr.

ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverCompilerFile-SystemScreen ResolutionGCC 8.3.0GCC 9.0.1 march=skylake march=native march=skylake march=native2 x Intel Xeon Platinum 8280 @ 4.00GHz (56 Cores / 112 Threads)GIGABYTE MD61-SC2-00 v01000100 (T15 BIOS)Intel Sky Lake-E DMI3 Registers386048MBSamsung SSD 970 PRO 512GBASPEED FamilyVE2282 x Intel X722 for 1GbE + 2 x QLogic FastLinQ QL41000 10/25/40/50GbEUbuntu 18.045.1.0-999-generic (x86_64) 20190329GNOME Shell 3.28.3X Server 1.20.1modesetting 1.20.1GCC 8.3.0ext41920x1080GCC 9.0.1 20190324OpenBenchmarking.orgEnvironment Details- GCC 8.3.0: march=skylake: CXXFLAGS=-O3-march=skylake CFLAGS=-O3-march=skylake- GCC 8.3.0: march=native: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- GCC 9.0.1: march=skylake: CXXFLAGS=-O3-march=skylake CFLAGS=-O3-march=skylake- GCC 9.0.1: march=native: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Details- --disable-multilib --enable-checking=releaseProcessor Details- Scaling Governor: intel_pstate powersavePython Details- Python 2.7.15rc1 + Python 3.6.7Security Details- __user pointer sanitization + Enhanced IBRS IBPB: conditional RSB filling + SSB disabled via prctl and seccomp

pgbench: Buffer Test - Normal Load - Read Writefftw: Float + SSE - 2D FFT Size 4096vpxenc: vpxenc VP9 1080p Video Encodepgbench: Buffer Test - Normal Load - Read Onlyfftw: Stock - 2D FFT Size 4096byte: Dhrystone 2mcperf: Setcompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9apache-siege: 250nginx: Static Web Page Servingcompress-7zip: Compress Speed Testgraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Enhancedgraphics-magick: Swirlgraphics-magick: Sharpengraphics-magick: Rotategraphics-magick: Noise-Gaussianbuild-php: Time To Compilehimeno: Poisson Pressure Solverapache: Static Web Page Servingbuild-llvm: Time To Compileaobench: 2048 x 2048 - Total Timemcperf: Getscimark2: Compositeluajit: Compositettsiod-renderer: Phong Rendering With Soft-Shadow Mappingcompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19openssl: RSA 4096-bit Performancebuild-imagemagick: Time To Compilesysbench: Memorysvt-av1: 1080p 8-bit YUV To AV1 Video Encodemafft: Multiple Sequence Alignmentc-ray: Total Time - 4K, 16 Rays Per Pixelsysbench: CPUencode-mp3: WAV To MP3t-test1: 2svt-hevc: 1080p 8-bit YUV To HEVC Video Encodeprimesieve: 1e12 Prime Number Generationsvt-vp9: 1080p 8-bit YUV To VP9 Video Encodescimark2: Jacobi Successive Over-Relaxationscimark2: Dense LU Matrix Factorizationscimark2: Sparse Matrix Multiplyscimark2: Fast Fourier Transformscimark2: Monte CarloGCC 8.3.0GCC 9.0.1 march=skylake march=native march=skylake march=native56671698023.679479535739381137222191492.06346213024824518120824622622921322820450.3729992561711239.3457526248514709929.241353918.901236392821.914.8611.29950949.497.692724.6427320185675311173988280751736023.829438366048369840276364591.38347673040124248220924722422821222920350.6530112535311438.93106156252714619919.151381218.671218155621.715.0411.47973599.377.662674.75280201458413156740881116841823123.699362005586375645402418791.19338563013424320720724522322621522620159.2030252490412138.1058709252614619.171381719.861265081221.814.8610.631041879.197.70262274200858943168741821112741881523.929545735616369405572461891.14349733020824082821024322122621422720058.8330212524412238.0357151257214689.181380319.951222940521.625.0211.36955979.167.78270273201760163190757878OpenBenchmarking.org

PostgreSQL pgbench

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

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Writemarch=skylakemarch=native3K6K9K12K15KSE +/- 85.69, N = 3SE +/- 147.52, N = 5SE +/- 686.85, N = 9SE +/- 159.16, N = 91168411274807556671. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

FFTW

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

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 4096march=nativemarch=skylake4K8K12K16K20KSE +/- 70.17, N = 3SE +/- 258.29, N = 3SE +/- 230.56, N = 4SE +/- 140.87, N = 3188151823117360169801. (CC) gcc options: -pthread -O3 -lm

VP9 libvpx Encoding

vpxenc VP9 1080p Video Encode

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video Encodemarch=nativemarch=skylake612182430SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.08, N = 323.9223.6923.8223.671. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11

PostgreSQL pgbench

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

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Onlymarch=nativemarch=skylake200K400K600K800K1000KSE +/- 6868.19, N = 3SE +/- 3479.46, N = 3SE +/- 3387.19, N = 3SE +/- 3135.06, N = 39545739362009479539438361. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

FFTW

Build: Stock - Size: 2D FFT Size 4096

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096march=nativemarch=skylake13002600390052006500SE +/- 26.29, N = 3SE +/- 20.07, N = 3SE +/- 60.35, N = 3SE +/- 20.26, N = 360485739561655861. (CC) gcc options: -pthread -O3 -lm

BYTE Unix Benchmark

Computational Test: Dhrystone 2

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgLPS, More Is BetterBYTE Unix Benchmark 3.6Computational Test: Dhrystone 2march=skylakemarch=native8M16M24M32M40MSE +/- 10225.91, N = 3SE +/- 474333.35, N = 3SE +/- 377791.76, N = 8SE +/- 583207.23, N = 3381137223698402737564540369405571. (CC) gcc options: -O3

Memcached mcperf

Method: Set

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Setmarch=nativemarch=skylake14K28K42K56K70KSE +/- 175.77, N = 3SE +/- 588.06, N = 15SE +/- 120.94, N = 3SE +/- 458.51, N = 15636452191424618241871. (CC) gcc options: -O3 -lm -rdynamic

XZ Compression

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

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9march=nativemarch=skylake20406080100SE +/- 0.34, N = 3SE +/- 0.07, N = 3SE +/- 0.11, N = 3SE +/- 0.49, N = 391.1491.1991.3892.061. (CC) gcc options: -pthread -fvisibility=hidden -O3

Apache Siege

Concurrent Users: 250

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgTransactions Per Second, More Is BetterApache Siege 2.4.29Concurrent Users: 250march=nativemarch=skylake7K14K21K28K35KSE +/- 297.80, N = 3SE +/- 163.73, N = 3SE +/- 1.61, N = 3SE +/- 49.85, N = 3349733385634767346211. (CC) gcc options: -O3 -lpthread -ldl -lssl -lcrypto

NGINX Benchmark

Static Web Page Serving

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page Servingmarch=nativemarch=skylake7K14K21K28K35KSE +/- 93.79, N = 3SE +/- 259.73, N = 3SE +/- 135.91, N = 3SE +/- 190.51, N = 3304013024830208301341. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

7-Zip Compression

Compress Speed Test

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Testmarch=skylakemarch=native50K100K150K200K250KSE +/- 3134.80, N = 3SE +/- 2108.59, N = 3SE +/- 1622.74, N = 3SE +/- 3483.43, N = 32451812424822432072408281. (CXX) g++ options: -pipe -lpthread

GraphicsMagick

Operation: Resizing

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Resizingmarch=nativemarch=skylake50100150200250SE +/- 0.67, N = 3SE +/- 2.03, N = 3SE +/- 1.00, N = 32102072092081. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: HWB Color Space

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color Spacemarch=nativemarch=skylake50100150200250SE +/- 0.33, N = 32472462452431. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Enhanced

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Enhancedmarch=skylakemarch=native50100150200250SE +/- 0.33, N = 32262242232211. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Swirl

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Swirlmarch=skylakemarch=native50100150200250SE +/- 0.33, N = 32292282262261. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Sharpen

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Sharpenmarch=skylakemarch=native50100150200250SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 32152142132121. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Rotate

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Rotatemarch=nativemarch=skylake50100150200250SE +/- 0.33, N = 3SE +/- 0.58, N = 32292282272261. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Noise-Gaussian

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Noise-Gaussianmarch=skylakemarch=native4080120160200SE +/- 0.33, N = 3SE +/- 0.58, N = 32042032012001. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

Timed PHP Compilation

Time To Compile

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To Compilemarch=skylakemarch=native1326395265SE +/- 0.08, N = 3SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.29, N = 350.3750.6558.8359.201. (CC) gcc options: -O3 -pedantic -ldl -lz -lm

Himeno Benchmark

Poisson Pressure Solver

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solvermarch=skylakemarch=native6001200180024003000SE +/- 1.50, N = 3SE +/- 1.25, N = 3SE +/- 1.80, N = 3SE +/- 3.29, N = 330253021301129991. (CC) gcc options: -O3 -mavx2

Apache Benchmark

Static Web Page Serving

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page Servingmarch=skylakemarch=native5K10K15K20K25KSE +/- 144.39, N = 3SE +/- 391.00, N = 3SE +/- 205.57, N = 3SE +/- 90.86, N = 3256172535325244249041. (CC) gcc options: -shared -fPIC -pthread -O3

Timed LLVM Compilation

Time To Compile

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To Compilemarch=skylakemarch=native306090120150112114121122

AOBench

Size: 2048 x 2048 - Total Time

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total Timemarch=nativemarch=skylake918273645SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.07, N = 338.0338.1038.9339.341. (CC) gcc options: -lm -O3

Memcached mcperf

Method: Get

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: Getmarch=nativemarch=skylake20K40K60K80K100KSE +/- 2971.56, N = 12SE +/- 190.50, N = 3SE +/- 779.46, N = 3SE +/- 413.74, N = 31061565752658709571511. (CC) gcc options: -O3 -lm -rdynamic

SciMark

Computational Test: Composite

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Compositemarch=nativemarch=skylake6001200180024003000SE +/- 2.29, N = 3SE +/- 7.86, N = 3SE +/- 2.04, N = 3SE +/- 0.68, N = 325722526252724851. (CC) gcc options: -O3 -lm

LuaJIT

Test: Composite

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgMflops, More Is BetterLuaJIT 2.1-gitTest: Compositemarch=skylakemarch=native30060090012001500SE +/- 0.85, N = 3SE +/- 2.17, N = 3SE +/- 0.47, N = 3SE +/- 2.50, N = 314701461146814611. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -O3 -U_FORTIFY_SOURCE -fno-stack-protector

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3bPhong Rendering With Soft-Shadow Mappingmarch=skylakemarch=native2004006008001000SE +/- 9.26, N = 3SE +/- 16.23, N = 3992991-march=skylake-march=native1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++

Zstd Compression

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

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19march=nativemarch=skylake3691215SE +/- 0.08, N = 3SE +/- 0.08, N = 15SE +/- 0.11, N = 6SE +/- 0.12, N = 39.159.249.179.181. (CC) gcc options: -O3 -pthread -lz -llzma

OpenSSL

RSA 4096-bit Performance

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit Performancemarch=skylakemarch=native3K6K9K12K15KSE +/- 78.65, N = 3SE +/- 65.79, N = 3SE +/- 24.15, N = 3SE +/- 66.33, N = 3138171380313812135391. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl

Timed ImageMagick Compilation

Time To Compile

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To Compilemarch=nativemarch=skylake510152025SE +/- 0.21, N = 3SE +/- 0.13, N = 3SE +/- 0.11, N = 3SE +/- 0.20, N = 318.6718.9019.8619.95

Sysbench

Test: Memory

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: Memorymarch=skylakemarch=native3M6M9M12M15MSE +/- 131322.62, N = 15SE +/- 64373.82, N = 3SE +/- 145092.14, N = 6SE +/- 184110.45, N = 3126508121222940512363928121815561. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -rdynamic -ldl -laio -lm

SVT-AV1

1080p 8-bit YUV To AV1 Video Encode

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2019-03-071080p 8-bit YUV To AV1 Video Encodemarch=skylakemarch=native510152025SE +/- 0.13, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.19, N = 321.9121.7121.8121.621. (CXX) g++ options: -O3 -pie -lpthread -lm

Timed MAFFT Alignment

Multiple Sequence Alignment

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence Alignmentmarch=skylakemarch=native1.1342.2683.4024.5365.67SE +/- 0.08, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 15SE +/- 0.08, N = 154.865.044.865.021. (CC) gcc options: -std=c99 -O3 -lm -lpthread

C-Ray

Total Time - 4K, 16 Rays Per Pixel

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per Pixelmarch=skylakemarch=native3691215SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.13, N = 3SE +/- 0.02, N = 310.6311.3611.2911.471. (CC) gcc options: -lm -lpthread -O3

Sysbench

Test: CPU

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgEvents Per Second, More Is BetterSysbench 2018-07-28Test: CPUmarch=skylakemarch=native20K40K60K80K100KSE +/- 637.76, N = 3SE +/- 353.99, N = 3SE +/- 640.85, N = 3SE +/- 1122.18, N = 31041879559797359950941. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -rdynamic -ldl -laio -lm

LAME MP3 Encoding

WAV To MP3

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3march=nativemarch=skylake3691215SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 39.169.199.379.491. (CC) gcc options: -O3 -lm

t-test1

Threads: 2

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2march=nativemarch=skylake246810SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 37.667.697.707.781. (CC) gcc options: -pthread -O3

SVT-HEVC

1080p 8-bit YUV To HEVC Video Encode

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video Encodemarch=skylakemarch=native60120180240300SE +/- 3.64, N = 3SE +/- 3.43, N = 5SE +/- 4.02, N = 3SE +/- 2.08, N = 152722672702621. (CC) gcc options: -O3 -fPIE -fPIC -O2 -flto -fvisibility=hidden -march=native -pie -rdynamic -lpthread -lrt

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.41e12 Prime Number Generationmarch=skylakemarch=native1.06882.13763.20644.27525.344SE +/- 0.01, N = 3SE +/- 0.01, N = 34.644.75-march=skylake-march=native1. (CXX) g++ options: -O3 -lpthread

SVT-VP9

1080p 8-bit YUV To VP9 Video Encode

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video Encodemarch=nativemarch=skylake60120180240300SE +/- 0.37, N = 3SE +/- 1.64, N = 3SE +/- 0.94, N = 3SE +/- 3.39, N = 42802732742731. (CC) gcc options: -O3 -fPIE -fPIC -O2 -flto -fvisibility=hidden -mavx -pie -rdynamic -lpthread -lrt -lm

SciMark

Computational Test: Jacobi Successive Over-Relaxation

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxationmarch=skylakemarch=native400800120016002000SE +/- 0.19, N = 3SE +/- 1.23, N = 3SE +/- 0.16, N = 3SE +/- 3.80, N = 320182014201720081. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Dense LU Matrix Factorization

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorizationmarch=nativemarch=skylake13002600390052006500SE +/- 9.57, N = 3SE +/- 20.51, N = 3SE +/- 10.82, N = 3SE +/- 0.75, N = 360165894584156751. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Sparse Matrix Multiply

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiplymarch=nativemarch=skylake7001400210028003500SE +/- 1.03, N = 3SE +/- 10.01, N = 3SE +/- 2.15, N = 3SE +/- 2.06, N = 331903168315631111. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Fast Fourier Transform

GCC 9.0.1GCC 8.3.0OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transformmarch=nativemarch=skylake160320480640800SE +/- 3.19, N = 3SE +/- 5.68, N = 3SE +/- 0.90, N = 3SE +/- 0.69, N = 37577417407391. (CC) gcc options: -O3 -lm

SciMark

Computational Test: Monte Carlo

GCC 8.3.0GCC 9.0.1OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlomarch=skylakemarch=native2004006008001000SE +/- 0.01, N = 3SE +/- 0.21, N = 3SE +/- 1.90, N = 3SE +/- 58.38, N = 38828818788211. (CC) gcc options: -O3 -lm

Phoronix Test Suite v10.8.5