7980XE vs. 2990WX - GCC 9 vs. Clang 8 Compiler Benchmarks

GCC 9 vs. Clang 8 compiler benchmarks by Michael Larabel for a future article...

HTML result view exported from: https://openbenchmarking.org/result/1905083-HV-GCC9CLANG19&grr&sro.

ProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen Resolution7980XE2990WX GCC 8.3 GCC 9.1 Clang 8 GCC 8.3 GCC 9.1 Clang 8Intel Core i9-7980XE @ 4.20GHz (18 Cores / 36 Threads)ASUS PRIME X299-A (1704 BIOS)Intel Sky Lake-E DMI3 Registers16384MBSamsung SSD 970 EVO 500GBNVIDIA NV120 12GBRealtek ALC1220ASUS PB278Intel I219-VUbuntu 18.044.18.0-18-generic (x86_64)GNOME Shell 3.28.3X Server 1.20.1modesetting 1.20.14.3 Mesa 18.2.8GCC 8.3.0ext42560x1440GCC 9.1.0Clang 8.0.1-svn359952-1~exp1~20190504004906.65AMD Ryzen Threadripper 2990WX 32-Core @ 3.00GHz (32 Cores / 64 Threads)ASUS ROG ZENITH EXTREME (1701 BIOS)AMD 17h32768MBAMD Radeon RX 64 8GB (1590/800MHz)ASUS VP28UIntel I211 + Qualcomm Atheros QCA6174 802.11ac + Wilocity Wil6200 802.11adamdgpu 18.1.04.5 Mesa 18.2.8 (LLVM 7.0.0)GCC 8.3.03840x2160GCC 9.1.0Clang 8.0.1-svn359952-1~exp1~20190504004906.65OpenBenchmarking.orgEnvironment Details- CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Details- 7980XE: GCC 8.3: --disable-multilib --enable-checking=release- 7980XE: GCC 9.1: --disable-multilib --enable-checking=release- 2990WX: GCC 8.3: --disable-multilib --enable-checing=release- 2990WX: GCC 9.1: --disable-multilib --enable-checing=releaseProcessor Details- 7980XE: GCC 8.3: Scaling Governor: intel_pstate powersave- 7980XE: GCC 9.1: Scaling Governor: intel_pstate powersave- 7980XE: Clang 8: Scaling Governor: intel_pstate powersave- 2990WX: GCC 8.3: Scaling Governor: acpi-cpufreq ondemand- 2990WX: GCC 9.1: Scaling Governor: acpi-cpufreq ondemand- 2990WX: Clang 8: Scaling Governor: acpi-cpufreq ondemandPython Details- Python 2.7.15rc1 + Python 3.6.7Security Details- 7980XE: GCC 8.3: KPTI + __user pointer sanitization + disabled STIBP: disabled + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- 7980XE: GCC 9.1: KPTI + __user pointer sanitization + disabled STIBP: disabled + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- 7980XE: Clang 8: KPTI + __user pointer sanitization + disabled STIBP: disabled + PTE Inversion; VMX: conditional cache flushes SMT vulnerable- 2990WX: GCC 8.3: __user pointer sanitization + Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + SSB disabled via prctl and seccomp- 2990WX: GCC 9.1: __user pointer sanitization + Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + SSB disabled via prctl and seccomp- 2990WX: Clang 8: __user pointer sanitization + Full AMD retpoline IBPB: conditional STIBP: disabled RSB filling + SSB disabled via prctl and seccomp

cpp-perf-bench: Rand Numberscpp-perf-bench: Math Libraryfftw: Float + SSE - 2D FFT Size 4096vpxenc: vpxenc VP9 1080p Video Encodefftw: Stock - 2D FFT Size 4096aom-av1: AV1 Video Encodingpgbench: Buffer Test - Normal Load - Read Onlypgbench: Buffer Test - Normal Load - Read Writecpp-perf-bench: Stepanov Vectorstockfish: Total Timebuild-llvm: Time To Compilecpp-perf-bench: Atolbuild-php: Time To Compilemcperf: Setgraphics-magick: Noise-Gaussiangraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: Enhancedgraphics-magick: Swirlgraphics-magick: Rotategraphics-magick: HWB Color Spacemcperf: Addnginx: Static Web Page Servinghimeno: Poisson Pressure Solvercompress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19mcperf: Replacemcperf: Getaobench: 2048 x 2048 - Total Timec-ray: Total Time - 4K, 16 Rays Per Pixelt-test1: 1redis: LPOPredis: GETcpp-perf-bench: Stepanov Abstractioncpp-perf-bench: Ctypescimark2: Compositeredis: SETpovray: Trace Timemcperf: Appendmcperf: Prependredis: SADDbuild-imagemagick: Time To Compileopenssl: RSA 4096-bit Performancemcperf: Deletex265: H.265 1080p Video Encodingt-test1: 2encode-flac: WAV To FLACmkl-dnn: IP Batch 1D - f32cpp-perf-bench: Function Objectsx264: H.264 Video Encodingsvt-av1: 1080p 8-bit YUV To AV1 Video Encoderedis: LPUSHsvt-vp9: 1080p 8-bit YUV To VP9 Video Encodeencode-mp3: WAV To MP3svt-hevc: 1080p 8-bit YUV To HEVC Video Encodemafft: Multiple Sequence Alignmentsmallpt: Global Illumination Renderer; 128 Samplesbullet: Rayteststscp: AI Chess Performancectx-clock: Context Switch Timebullet: Convex Trimeshbullet: Prim Trimeshbullet: 136 Ragdollsbullet: 1000 Convexbullet: 1000 Stackbullet: 3000 Fallscimark2: Jacobi Successive Over-Relaxationscimark2: Dense LU Matrix Factorizationscimark2: Sparse Matrix Multiplyscimark2: Fast Fourier Transformscimark2: Monte Carlo7980XE2990WX GCC 8.3 GCC 9.1 Clang 8 GCC 8.3 GCC 9.1 Clang 89233461850223.8767030.255436061246583.284757058022658.6451.22776621691862492112272572647580349752327217.619.958272512689435.9855.3518.423054513276494033.1929.202730211487627.958401784314246133724.40469012500439.577.669.1119.0213.5312820.4318212463279.623142.506.202.2514667953701.000.842.283.934.043.802193625134707799588663381923524.7265850.255447591238684.334719077023858.6057.03771931701962512102262572647801749739326317.8310.028230712520035.0633.8218.312999947287146133.0128.00272521142888446884291242726120.2246791264647.549.1019.1013.5212720.4320478063289.373152.416.322.5814151703640.980.812.273.873.993.7421906240346377795511143241792323.7962240.245087331246875.404711611520258.9769.19768641591702251752042632327648350060242618.089.868458012762835.9367.0718.453026435294498531.7625.242555205081731.418339083389252271418.25455112607137.677.529.7915.6014.8812821.99208746130311.932832.442.8916530033661.291.073.025.075.574.5916486398326575471110573541592726.5467480.224735791633674.206687037321069.2056.18451642032182382312492452695170330464129425.7118.25516256941438.6417.9425.952680556260192428.2432.102405183166217.654580845945205543425.2158356943533.458.889.5470.9915.6214621.5215434051108.001772.793.832.3711162951501.010.862.384.034.373.8522155599321127073110223511470826.5166940.224628341623474.936693316869.0963.32458912042202412332502482724342829644131926.1419.17356837207339.1018.0526.742576300244563628.2333.87253718061573587535850208050019.3358285661233.658.959.5470.9915.4314619.1815488371148.042372.663.842.3511135891501.000.832.303.964.413.8422196255320727073213633441534927.4060560.224702191627972.937000621319069.2278.86348901831932082052212832404675829611136726.2218.58360326851540.5429.3226.392616490250659028.0131.662532180685517.803569635982209539918.3058355724033.958.758.658.1415.5514921.2515361151189.531792.622.4311911521501.030.862.514.064.683.96187065123288268723OpenBenchmarking.org

CppPerformanceBenchmarks

Test: Random Numbers

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Random NumbersClang 8GCC 8.3GCC 9.130060090012001500SE +/- 0.28, N = 3SE +/- 0.16, N = 3SE +/- 0.02, N = 3SE +/- 0.21, N = 3SE +/- 0.79, N = 3SE +/- 0.67, N = 313631057102211149238661. (CXX) g++ options: -O3 -march=native -std=c++11

CppPerformanceBenchmarks

Test: Math Library

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Math LibraryClang 8GCC 8.3GCC 9.180160240320400SE +/- 0.08, N = 3SE +/- 0.24, N = 3SE +/- 0.16, N = 3SE +/- 0.46, N = 3SE +/- 1.78, N = 3SE +/- 0.09, N = 33443543513243463381. (CXX) g++ options: -O3 -march=native -std=c++11

FFTW

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

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Float + SSE - Size: 2D FFT Size 4096Clang 8GCC 8.3GCC 9.14K8K12K16K20KSE +/- 71.88, N = 3SE +/- 161.04, N = 3SE +/- 24.34, N = 3SE +/- 58.61, N = 3SE +/- 41.36, N = 3SE +/- 123.96, N = 31534915927147081792318502192351. (CC) gcc options: -pthread -O3 -march=native -lm

VP9 libvpx Encoding

vpxenc VP9 1080p Video Encode

2990WX7980XEOpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.8.0vpxenc VP9 1080p Video EncodeClang 8GCC 8.3GCC 9.1612182430SE +/- 0.04, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.06, N = 3SE +/- 0.28, N = 3SE +/- 0.18, N = 327.4026.5426.5123.7923.8724.721. (CXX) g++ options: -m64 -lm -lpthread -O3 -march=native -fPIC -U_FORTIFY_SOURCE -std=c++11

FFTW

Build: Stock - Size: 2D FFT Size 4096

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 4096Clang 8GCC 8.3GCC 9.114002800420056007000SE +/- 14.75, N = 3SE +/- 7.62, N = 3SE +/- 10.36, N = 3SE +/- 34.57, N = 3SE +/- 101.31, N = 3SE +/- 46.81, N = 36056674866946224670365851. (CC) gcc options: -pthread -O3 -march=native -lm

AOM AV1

AV1 Video Encoding

2990WX7980XEOpenBenchmarking.orgFrames Per Second, More Is BetterAOM AV1 2019-02-11AV1 Video EncodingClang 8GCC 8.3GCC 9.10.05630.11260.16890.22520.2815SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.220.220.220.240.250.251. (CXX) g++ options: -O3 -march=native -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread

PostgreSQL pgbench

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

2990WX7980XEOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read OnlyClang 8GCC 8.3GCC 9.1120K240K360K480K600KSE +/- 1790.12, N = 3SE +/- 5552.19, N = 3SE +/- 2001.66, N = 3SE +/- 2049.13, N = 3SE +/- 928.33, N = 3SE +/- 913.86, N = 34702194735794628345087335436065447591. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

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

2990WX7980XEOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read WriteClang 8GCC 8.3GCC 9.13K6K9K12K15KSE +/- 40.72, N = 3SE +/- 159.33, N = 3SE +/- 134.86, N = 3SE +/- 102.32, N = 3SE +/- 71.17, N = 3SE +/- 107.98, N = 31627916336162341246812465123861. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

CppPerformanceBenchmarks

Test: Stepanov Vector

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov VectorClang 8GCC 8.3GCC 9.120406080100SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.12, N = 3SE +/- 0.10, N = 3SE +/- 0.06, N = 372.9374.2074.9375.4083.2884.331. (CXX) g++ options: -O3 -march=native -std=c++11

Stockfish

Total Time

2990WX7980XEOpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total TimeClang 8GCC 8.3GCC 9.115M30M45M60M75MSE +/- 327377.69, N = 3SE +/- 261886.86, N = 3SE +/- 461460.58, N = 3SE +/- 477709.19, N = 3SE +/- 177609.16, N = 3SE +/- 498259.68, N = 37000621366870373669331684711611547570580471907701. (CXX) g++ options: -m64 -lpthread -O3 -march=native -fno-exceptions -std=c++11 -pedantic -msse -msse3 -mpopcnt -flto

Timed LLVM Compilation

Time To Compile

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterTimed LLVM Compilation 6.0.1Time To CompileClang 8GCC 8.3GCC 9.150100150200250190210202226238

CppPerformanceBenchmarks

Test: Atol

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: AtolClang 8GCC 8.3GCC 9.11530456075SE +/- 0.12, N = 3SE +/- 0.56, N = 3SE +/- 0.20, N = 3SE +/- 0.03, N = 3SE +/- 0.10, N = 3SE +/- 0.01, N = 369.2269.2069.0958.9758.6458.601. (CXX) g++ options: -O3 -march=native -std=c++11

Timed PHP Compilation

Time To Compile

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 7.1.9Time To CompileClang 8GCC 8.3GCC 9.120406080100SE +/- 0.03, N = 3SE +/- 0.16, N = 3SE +/- 0.09, N = 3SE +/- 0.08, N = 3SE +/- 0.05, N = 3SE +/- 0.14, N = 378.8656.1863.3269.1951.2257.031. (CC) gcc options: -O3 -march=native -pedantic -ldl -lz -lm

Memcached mcperf

Method: Set

2990WX7980XEOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: SetClang 8GCC 8.3GCC 9.117K34K51K68K85KSE +/- 60.28, N = 3SE +/- 1442.28, N = 15SE +/- 1799.58, N = 15SE +/- 90.13, N = 3SE +/- 594.59, N = 3SE +/- 867.51, N = 33489045164458917686477662771931. (CC) gcc options: -O3 -march=native -lm -rdynamic

GraphicsMagick

Operation: Noise-Gaussian

2990WX7980XEOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: Noise-GaussianClang 8GCC 8.3GCC 9.14080120160200SE +/- 1.67, N = 3SE +/- 0.33, N = 31832032041591691701. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

2990WX7980XEOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SharpenClang 8GCC 8.3GCC 9.150100150200250SE +/- 0.58, N = 3SE +/- 0.58, N = 31932182201701861961. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

GraphicsMagick

Operation: Resizing

2990WX7980XEOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: ResizingClang 8GCC 8.3GCC 9.150100150200250SE +/- 2.52, N = 3SE +/- 0.58, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 0.67, N = 3SE +/- 1.53, N = 32082382412252492511. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

GraphicsMagick

Operation: Enhanced

2990WX7980XEOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: EnhancedClang 8GCC 8.3GCC 9.150100150200250SE +/- 0.33, N = 3SE +/- 0.88, N = 3SE +/- 0.33, N = 32052312331752112101. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

GraphicsMagick

Operation: Swirl

2990WX7980XEOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: SwirlClang 8GCC 8.3GCC 9.150100150200250SE +/- 0.88, N = 3SE +/- 0.33, N = 32212492502042272261. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

GraphicsMagick

Operation: Rotate

2990WX7980XEOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: RotateClang 8GCC 8.3GCC 9.160120180240300SE +/- 1.00, N = 3SE +/- 0.58, N = 3SE +/- 1.20, N = 32832452482632572571. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

GraphicsMagick

Operation: HWB Color Space

2990WX7980XEOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.30Operation: HWB Color SpaceClang 8GCC 8.3GCC 9.160120180240300SE +/- 0.88, N = 3SE +/- 0.33, N = 32402692722322642641. (CC) gcc options: -fopenmp -O3 -march=native -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -lpthread

Memcached mcperf

Method: Add

2990WX7980XEOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: AddClang 8GCC 8.3GCC 9.120K40K60K80K100KSE +/- 1620.95, N = 15SE +/- 2671.28, N = 15SE +/- 569.36, N = 3SE +/- 391.04, N = 3SE +/- 337.73, N = 3SE +/- 687.54, N = 34675851703434287648375803780171. (CC) gcc options: -O3 -march=native -lm -rdynamic

NGINX Benchmark

Static Web Page Serving

2990WX7980XEOpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.9.9Static Web Page ServingClang 8GCC 8.3GCC 9.111K22K33K44K55KSE +/- 436.75, N = 4SE +/- 61.79, N = 3SE +/- 413.90, N = 3SE +/- 251.20, N = 3SE +/- 41.76, N = 3SE +/- 309.56, N = 32961130464296445006049752497391. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native

Himeno Benchmark

Poisson Pressure Solver

2990WX7980XEOpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverClang 8GCC 8.3GCC 9.17001400210028003500SE +/- 1.83, N = 3SE +/- 2.10, N = 3SE +/- 0.99, N = 3SE +/- 5.54, N = 3SE +/- 8.04, N = 3SE +/- 4.35, N = 31367129413192426327232631. (CC) gcc options: -O3 -march=native -mavx2

XZ Compression

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

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterXZ Compression 5.2.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9Clang 8GCC 8.3GCC 9.1612182430SE +/- 0.12, N = 3SE +/- 0.30, N = 6SE +/- 0.34, N = 15SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.11, N = 326.2225.7126.1418.0817.6117.831. (CC) gcc options: -pthread -fvisibility=hidden -O3 -march=native

Zstd Compression

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

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19Clang 8GCC 8.3GCC 9.1510152025SE +/- 0.61, N = 12SE +/- 0.49, N = 12SE +/- 0.80, N = 12SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 318.5818.2519.179.869.9510.021. (CC) gcc options: -O3 -march=native -pthread -lz -llzma

Memcached mcperf

Method: Replace

2990WX7980XEOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: ReplaceClang 8GCC 8.3GCC 9.120K40K60K80K100KSE +/- 298.74, N = 3SE +/- 2677.79, N = 15SE +/- 149.39, N = 3SE +/- 452.06, N = 3SE +/- 313.55, N = 3SE +/- 168.91, N = 33603251625356838458082725823071. (CC) gcc options: -O3 -march=native -lm -rdynamic

Memcached mcperf

Method: Get

2990WX7980XEOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: GetClang 8GCC 8.3GCC 9.130K60K90K120K150KSE +/- 574.78, N = 15SE +/- 274.74, N = 3SE +/- 3134.41, N = 12SE +/- 585.06, N = 3SE +/- 1056.87, N = 3SE +/- 1704.49, N = 46851569414720731276281268941252001. (CC) gcc options: -O3 -march=native -lm -rdynamic

AOBench

Size: 2048 x 2048 - Total Time

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeClang 8GCC 8.3GCC 9.1918273645SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.09, N = 340.5438.6439.1035.9335.9835.061. (CC) gcc options: -lm -O3 -march=native

C-Ray

Total Time - 4K, 16 Rays Per Pixel

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelClang 8GCC 8.3GCC 9.11530456075SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.26, N = 3SE +/- 0.02, N = 329.3217.9418.0567.0755.3533.821. (CC) gcc options: -lm -lpthread -O3 -march=native

t-test1

Threads: 1

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 1Clang 8GCC 8.3GCC 9.1612182430SE +/- 0.05, N = 3SE +/- 0.15, N = 3SE +/- 0.23, N = 12SE +/- 0.10, N = 3SE +/- 0.11, N = 3SE +/- 0.08, N = 326.3925.9526.7418.4518.4218.311. (CC) gcc options: -pthread -O3 -march=native

Redis

Test: LPOP

2990WX7980XEOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPOPClang 8GCC 8.3GCC 9.1700K1400K2100K2800K3500KSE +/- 35892.40, N = 3SE +/- 34933.56, N = 4SE +/- 27813.89, N = 7SE +/- 43615.55, N = 15SE +/- 31258.17, N = 15SE +/- 68131.37, N = 122616490268055625763003026435305451329999471. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: GET

2990WX7980XEOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GETClang 8GCC 8.3GCC 9.1600K1200K1800K2400K3000KSE +/- 20122.74, N = 3SE +/- 4521.17, N = 3SE +/- 28068.34, N = 3SE +/- 52195.81, N = 15SE +/- 42873.09, N = 15SE +/- 42142.68, N = 152506590260192424456362944985276494028714611. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

CppPerformanceBenchmarks

Test: Stepanov Abstraction

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Stepanov AbstractionClang 8GCC 8.3GCC 9.1816243240SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.04, N = 328.0128.2428.2331.7633.1933.011. (CXX) g++ options: -O3 -march=native -std=c++11

CppPerformanceBenchmarks

Test: Ctype

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: CtypeClang 8GCC 8.3GCC 9.1816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 331.6632.1033.8725.2429.2028.001. (CXX) g++ options: -O3 -march=native -std=c++11

SciMark

Computational Test: Composite

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeClang 8GCC 8.3GCC 9.16001200180024003000SE +/- 1.63, N = 3SE +/- 8.56, N = 3SE +/- 2.91, N = 3SE +/- 4.47, N = 3SE +/- 1.75, N = 3SE +/- 2.10, N = 32532240525372555273027251. (CC) gcc options: -O3 -march=native -lm

Redis

Test: SET

2990WX7980XEOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SETClang 8GCC 8.3GCC 9.1500K1000K1500K2000K2500KSE +/- 22439.98, N = 5SE +/- 12155.82, N = 3SE +/- 22140.94, N = 5SE +/- 15504.64, N = 3SE +/- 36850.43, N = 15SE +/- 30595.80, N = 151806855183166218061572050817211487621142881. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

POV-Ray

Trace Time

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeClang 8GCC 8.3714212835SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 317.8017.6531.4127.951. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

Memcached mcperf

Method: Append

2990WX7980XEOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: AppendClang 8GCC 8.3GCC 9.120K40K60K80K100KSE +/- 160.70, N = 3SE +/- 488.33, N = 3SE +/- 113.51, N = 3SE +/- 459.53, N = 3SE +/- 576.19, N = 3SE +/- 1111.80, N = 33569645808358758339084017844681. (CC) gcc options: -O3 -march=native -lm -rdynamic

Memcached mcperf

Method: Prepend

2990WX7980XEOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: PrependClang 8GCC 8.3GCC 9.120K40K60K80K100KSE +/- 149.46, N = 3SE +/- 722.78, N = 3SE +/- 52.23, N = 3SE +/- 348.93, N = 3SE +/- 490.37, N = 3SE +/- 611.41, N = 33598245945358508338984314842911. (CC) gcc options: -O3 -march=native -lm -rdynamic

Redis

Test: SADD

2990WX7980XEOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADDClang 8GCC 8.3GCC 9.1500K1000K1500K2000K2500KSE +/- 21045.22, N = 3SE +/- 25645.48, N = 3SE +/- 7619.52, N = 3SE +/- 34969.21, N = 15SE +/- 19407.79, N = 3SE +/- 33103.69, N = 152095399205543420805002522714246133724272611. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Timed ImageMagick Compilation

Time To Compile

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.9.0Time To CompileClang 8GCC 8.3GCC 9.1612182430SE +/- 0.03, N = 3SE +/- 0.30, N = 3SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.08, N = 318.3025.2119.3318.2524.4020.22

OpenSSL

RSA 4096-bit Performance

2990WX7980XEOpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.1RSA 4096-bit PerformanceClang 8GCC 8.3GCC 9.113002600390052006500SE +/- 2.40, N = 3SE +/- 2.82, N = 3SE +/- 6.06, N = 3SE +/- 6.07, N = 3SE +/- 8.27, N = 3SE +/- 6.44, N = 35835583558284551469046791. (CC) gcc options: -pthread -m64 -O3 -march=native -lssl -lcrypto -ldl

Memcached mcperf

Method: Delete

2990WX7980XEOpenBenchmarking.orgOperations Per Second, More Is BetterMemcached mcperf 1.5.10Method: DeleteClang 8GCC 8.3GCC 9.130K60K90K120K150KSE +/- 769.23, N = 3SE +/- 614.71, N = 3SE +/- 383.07, N = 3SE +/- 1817.56, N = 3SE +/- 835.23, N = 3SE +/- 912.12, N = 35724069435566121260711250041264641. (CC) gcc options: -O3 -march=native -lm -rdynamic

x265

H.265 1080p Video Encoding

2990WX7980XEOpenBenchmarking.orgFrames Per Second, More Is Betterx265 3.0H.265 1080p Video EncodingClang 8GCC 8.3GCC 9.1918273645SE +/- 0.10, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 3SE +/- 0.20, N = 3SE +/- 0.26, N = 333.9533.4533.6537.6739.571. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma

t-test1

Threads: 2

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is Bettert-test1 2017-01-13Threads: 2Clang 8GCC 8.3GCC 9.13691215SE +/- 0.05, N = 3SE +/- 0.09, N = 8SE +/- 0.13, N = 3SE +/- 0.05, N = 3SE +/- 0.07, N = 15SE +/- 0.09, N = 38.758.888.957.527.667.541. (CC) gcc options: -pthread -O3 -march=native

FLAC Audio Encoding

WAV To FLAC

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLACClang 8GCC 8.3GCC 9.13691215SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 5SE +/- 0.03, N = 5SE +/- 0.01, N = 5SE +/- 0.01, N = 58.659.549.549.799.119.101. (CXX) g++ options: -O3 -march=native -logg -lm

MKL-DNN

Harness: IP Batch 1D - Data Type: f32

2990WX7980XEOpenBenchmarking.orgms, Fewer Is BetterMKL-DNN 2019-04-16Harness: IP Batch 1D - Data Type: f32Clang 8GCC 8.3GCC 9.11632486480SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 3SE +/- 0.18, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 38.1470.9970.9915.6019.0219.101. (CXX) g++ options: -O3 -march=native -std=c++11 -fPIC -pie -lmklml_intel -ldl

CppPerformanceBenchmarks

Test: Function Objects

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterCppPerformanceBenchmarks 9Test: Function ObjectsClang 8GCC 8.3GCC 9.148121620SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 315.5515.6215.4314.8813.5313.521. (CXX) g++ options: -O3 -march=native -std=c++11

x264

H.264 Video Encoding

2990WX7980XEOpenBenchmarking.orgFrames Per Second, More Is Betterx264 2018-09-25H.264 Video EncodingClang 8GCC 8.3GCC 9.1306090120150SE +/- 0.98, N = 3SE +/- 1.44, N = 9SE +/- 1.94, N = 3SE +/- 1.12, N = 15SE +/- 1.23, N = 12SE +/- 1.20, N = 101491461461281281271. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -march=native -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize

SVT-AV1

1080p 8-bit YUV To AV1 Video Encode

2990WX7980XEOpenBenchmarking.orgFrames Per Second, More Is BetterSVT-AV1 2019-03-071080p 8-bit YUV To AV1 Video EncodeClang 8GCC 8.3GCC 9.1510152025SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.26, N = 4SE +/- 0.09, N = 3SE +/- 0.03, N = 3SE +/- 0.07, N = 321.2521.5219.1821.9920.4320.431. (CXX) g++ options: -O3 -march=native -pie -lpthread -lm

Redis

Test: LPUSH

2990WX7980XEOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSHClang 8GCC 8.3GCC 9.1400K800K1200K1600K2000KSE +/- 3597.31, N = 3SE +/- 12298.56, N = 3SE +/- 6250.09, N = 3SE +/- 35977.91, N = 3SE +/- 27858.52, N = 3SE +/- 5049.22, N = 31536115154340515488372087461182124620478061. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

SVT-VP9

1080p 8-bit YUV To VP9 Video Encode

2990WX7980XEOpenBenchmarking.orgFrames Per Second, More Is BetterSVT-VP9 2019-02-171080p 8-bit YUV To VP9 Video EncodeClang 8GCC 8.3GCC 9.170140210280350SE +/- 1.79, N = 15SE +/- 1.23, N = 7SE +/- 0.41, N = 3SE +/- 3.29, N = 3SE +/- 4.63, N = 4SE +/- 4.13, N = 51181101143033273281. (CC) gcc options: -O3 -march=native -pie -rdynamic -lpthread -lrt -lm

LAME MP3 Encoding

WAV To MP3

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3Clang 8GCC 8.3GCC 9.13691215SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 39.538.008.0411.939.629.371. (CC) gcc options: -O3 -march=native -lm

SVT-HEVC

1080p 8-bit YUV To HEVC Video Encode

2990WX7980XEOpenBenchmarking.orgFrames Per Second, More Is BetterSVT-HEVC 2019-02-031080p 8-bit YUV To HEVC Video EncodeClang 8GCC 8.3GCC 9.170140210280350SE +/- 5.74, N = 15SE +/- 4.46, N = 15SE +/- 2.01, N = 3SE +/- 2.30, N = 3SE +/- 4.06, N = 3SE +/- 4.88, N = 31791772372833143151. (CC) gcc options: -O3 -march=native -pie -rdynamic -lpthread -lrt

Timed MAFFT Alignment

Multiple Sequence Alignment

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 7.392Multiple Sequence AlignmentClang 8GCC 8.3GCC 9.10.62781.25561.88342.51123.139SE +/- 0.05, N = 15SE +/- 0.04, N = 15SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 15SE +/- 0.02, N = 32.622.792.662.442.502.411. (CC) gcc options: -std=c99 -O3 -lm -lpthread

Smallpt

Global Illumination Renderer; 128 Samples

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 128 SamplesGCC 8.3GCC 9.1246810SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 33.833.846.206.321. (CXX) g++ options: -fopenmp -O3 -march=native

Bullet Physics Engine

Test: Raytests

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: RaytestsClang 8GCC 8.3GCC 9.10.65031.30061.95092.60123.2515SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 32.432.372.352.892.252.581. (CXX) g++ options: -O3 -march=native -rdynamic

TSCP

AI Chess Performance

2990WX7980XEOpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceClang 8GCC 8.3GCC 9.1400K800K1200K1600K2000KSE +/- 2644.03, N = 5SE +/- 1153.01, N = 5SE +/- 1350.53, N = 5SE +/- 1857.68, N = 5SE +/- 11981.82, N = 5SE +/- 2414.89, N = 51191152111629511135891653003146679514151701. (CC) gcc options: -O3 -march=native

ctx_clock

Context Switch Time

2990WX7980XEOpenBenchmarking.orgClocks, Fewer Is Betterctx_clockContext Switch TimeClang 8GCC 8.3GCC 9.180160240320400SE +/- 5.03, N = 31501501503663703641. (CC) gcc options: -O3 -march=native

Bullet Physics Engine

Test: Convex Trimesh

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex TrimeshClang 8GCC 8.3GCC 9.10.29030.58060.87091.16121.4515SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 31.031.011.001.291.000.981. (CXX) g++ options: -O3 -march=native -rdynamic

Bullet Physics Engine

Test: Prim Trimesh

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim TrimeshClang 8GCC 8.3GCC 9.10.24080.48160.72240.96321.204SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 30.860.860.831.070.840.811. (CXX) g++ options: -O3 -march=native -rdynamic

Bullet Physics Engine

Test: 136 Ragdolls

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 RagdollsClang 8GCC 8.3GCC 9.10.67951.3592.03852.7183.3975SE +/- 0.00, N = 3SE +/- 0.04, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 32.512.382.303.022.282.271. (CXX) g++ options: -O3 -march=native -rdynamic

Bullet Physics Engine

Test: 1000 Convex

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 ConvexClang 8GCC 8.3GCC 9.11.14082.28163.42244.56325.704SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 34.064.033.965.073.933.871. (CXX) g++ options: -O3 -march=native -rdynamic

Bullet Physics Engine

Test: 1000 Stack

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 StackClang 8GCC 8.3GCC 9.11.25332.50663.75995.01326.2665SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 34.684.374.415.574.043.991. (CXX) g++ options: -O3 -march=native -rdynamic

Bullet Physics Engine

Test: 3000 Fall

2990WX7980XEOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 FallClang 8GCC 8.3GCC 9.11.03282.06563.09844.13125.164SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.07, N = 33.963.853.844.593.803.741. (CXX) g++ options: -O3 -march=native -rdynamic

SciMark

Computational Test: Jacobi Successive Over-Relaxation

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationClang 8GCC 8.3GCC 9.15001000150020002500SE +/- 0.67, N = 3SE +/- 0.71, N = 3SE +/- 1.12, N = 3SE +/- 0.62, N = 3SE +/- 1.99, N = 3SE +/- 3.86, N = 31870221522191648219321901. (CC) gcc options: -O3 -march=native -lm

SciMark

Computational Test: Dense LU Matrix Factorization

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationClang 8GCC 8.3GCC 9.114002800420056007000SE +/- 17.74, N = 3SE +/- 31.53, N = 3SE +/- 6.11, N = 3SE +/- 13.53, N = 3SE +/- 7.31, N = 3SE +/- 0.88, N = 36512559962556398625162401. (CC) gcc options: -O3 -march=native -lm

SciMark

Computational Test: Sparse Matrix Multiply

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyClang 8GCC 8.3GCC 9.17001400210028003500SE +/- 11.40, N = 3SE +/- 11.29, N = 3SE +/- 8.64, N = 3SE +/- 9.63, N = 3SE +/- 7.86, N = 3SE +/- 3.06, N = 33288321132073265347034631. (CC) gcc options: -O3 -march=native -lm

SciMark

Computational Test: Fast Fourier Transform

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformClang 8GCC 8.3GCC 9.12004006008001000SE +/- 0.32, N = 3SE +/- 0.09, N = 3SE +/- 0.06, N = 3SE +/- 3.05, N = 3SE +/- 3.63, N = 3SE +/- 4.78, N = 32682702707547797771. (CC) gcc options: -O3 -march=native -lm

SciMark

Computational Test: Monte Carlo

2990WX7980XEOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloClang 8GCC 8.3GCC 9.12004006008001000SE +/- 0.13, N = 3SE +/- 0.12, N = 3SE +/- 0.08, N = 3SE +/- 0.28, N = 3SE +/- 1.33, N = 3SE +/- 0.28, N = 37237317327119589551. (CC) gcc options: -O3 -march=native -lm

Phoronix Test Suite v10.8.4