Apple M1 Compilers

Apple M1 compiler testing for a future article.

HTML result view exported from: https://openbenchmarking.org/result/2204107-NE-APPLEM1CO68&rdt&grs.

Apple M1 CompilersProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerOpenGLCompilerFile-SystemScreen ResolutionGCC 11.2.0Clang 13.0.1Apple M1 @ 2.06GHz (4 Cores / 8 Threads)Apple Mac mini (M1 2020)8GB251GB APPLE SSD AP0256Q + 2 x 0GB APPLE SSD AP0256QllvmpipeBroadcom NetXtreme BCM57762 PCIe + Broadcom BRCM4378 + Broadcom Device 5f69Arch Linux ARM5.17.0-rc7-asahi-next-20220310-5-2-ARCH (aarch64)KDE Plasma 5.24.4X Server 1.21.1.34.5 Mesa 22.0.1 (LLVM 13.0.1 128 bits)GCC 11.2.0 + Clang 13.0.1ext41920x1080Clang 13.0.1OpenBenchmarking.orgEnvironment Details- CXXFLAGS="-O3 -flto" CFLAGS="-O3 -flto"Compiler Details- GCC 11.2.0: --build=aarch64-unknown-linux-gnu --disable-libssp --disable-libstdcxx-pch --disable-multilib --disable-werror --enable-__cxa_atexit --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-default-ssp --enable-fix-cortex-a53-835769 --enable-fix-cortex-a53-843419 --enable-gnu-indirect-function --enable-gnu-unique-object --enable-languages=c,c++,fortran,go,lto,objc,obj-c++,d --enable-lto --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-unknown-linux-gnu --mandir=/usr/share/man --with-arch=armv8-a --with-isl --with-linker-hash-style=gnu Disk Details- MQ-DEADLINE / relatime,rw / Block Size: 4096Processor Details- Scaling Governor: apple-cpufreq schedutilPython Details- Python 3.10.4Security Details- itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Not affected + srbds: Not affected + tsx_async_abort: Not affected

Apple M1 Compilersncnn: CPU - resnet50ncnn: CPU - alexnetncnn: CPU - resnet18ncnn: CPU - vgg16ncnn: CPU - mnasnetncnn: CPU - efficientnet-b0ncnn: CPU-v2-v2 - mobilenet-v2ncnn: CPU-v3-v3 - mobilenet-v3ncnn: CPU - yolov4-tinyncnn: CPU - googlenetstress-ng: Vector Mathncnn: CPU - shufflenet-v2cryptopp: Unkeyed Algorithmsncnn: CPU - mobilenetncnn: CPU - squeezenet_ssdncnn: CPU - regnety_400mc-ray: Total Time - 4K, 16 Rays Per Pixelcryptopp: Keyed Algorithmsstress-ng: Memory Copyingliquid-dsp: 4 - 256 - 57liquid-dsp: 2 - 256 - 57liquid-dsp: 1 - 256 - 57liquid-dsp: 8 - 256 - 57stress-ng: Matrix Mathaobench: 2048 x 2048 - Total Timecoremark: CoreMark Size 666 - Iterations Per Secondencode-flac: WAV To FLACcryptopp: All Algorithmspovray: Trace Timeavifenc: 2encode-wavpack: WAV To WavPackencode-mp3: WAV To MP3cryptopp: Integer + Elliptic Curve Public Key Algorithmshimeno: Poisson Pressure Solvercompress-zstd: 3, Long Mode - Compression Speedavifenc: 0openssl: SHA256espeak: Text-To-Speech Synthesisavifenc: 6, Losslessavifenc: 6tjbench: Decompression Throughputcompress-zstd: 19 - Decompression Speedcompress-lz4: 9 - Decompression Speedcompress-lz4: 3 - Decompression Speedopenjpeg: NASA Curiosity Panorama M34compress-zstd: 3 - Decompression Speedcompress-zstd: 19, Long Mode - Decompression Speedcompress-zstd: 3, Long Mode - Decompression Speedcompress-zstd: 8 - Compression Speedavifenc: 10, Losslesscompress-zstd: 8, Long Mode - Decompression Speedcompress-zstd: 8 - Decompression Speedsqlite-speedtest: Timed Time - Size 1,000lczero: Eigencompress-zstd: 19 - Compression Speedcompress-lz4: 9 - Compression Speedstress-ng: IO_uringprimesieve: 1e12 Prime Number Generationxmrig: Monero - 1Mcompress-zstd: 8, Long Mode - Compression Speedcompress-lz4: 3 - Compression Speeddraco: Church Facadeopenssl: RSA4096compress-zstd: 3 - Compression Speedcompress-lz4: 1 - Decompression Speedstress-ng: Cryptodraco: Lionstress-ng: Socket Activityxmrig: Wownero - 1Mcompress-lz4: 1 - Compression Speedopenssl: RSA4096compress-zstd: 19, Long Mode - Compression SpeedGCC 11.2.0Clang 13.0.117.1611.817.3133.782.524.182.612.3417.2013.3223954.102.17539.28182714.4014.265.8864.437508.8364482763.25115230000576110002877866715112000023588.9627.458179896.59941170.648954.95611372.017143.44217.2057.2391766.9858807577.316534240.0287.397805969105022.28915.65314.094206.1773503546.217478.517490.9538903850.23765.44221.1721.56.0704416.34016.451.372126322.748.94144281.6729.1182247.2693.051.9956491408.53341.227018.51511.7537474331.712798.221909.4599370.518.846.7931.6618.1880.445.869.515.844.8232.7725.1141899.943.76338.40836922.2120.158.0887.824374.8961753741.17151820000758986673789733319651000030254.2133.402148361.36244059.074823.15353262.416161.61219.3208.1241875.5235207158.970486253.7303.550847452735023.42914.92913.516197.9452253684.316863.316877.4520243977.73887.34356.6699.65.8874553.44141.052.900129723.249.89147040.9829.6262209.7703.451.3257221391.43301.126736.41527.1737724313.482804.821875.5499445.418.8OpenBenchmarking.org

NCNN

Target: CPU - Model: resnet50

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet50GCC 11.2.0Clang 13.0.11122334455SE +/- 0.08, N = 3SE +/- 0.01, N = 317.1646.79-lgomp -lpthread - MIN: 15.54 / MAX: 27.86MIN: 46.7 / MAX: 46.91. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: alexnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: alexnetGCC 11.2.0Clang 13.0.1714212835SE +/- 0.10, N = 3SE +/- 0.00, N = 311.8131.66-lgomp -lpthread - MIN: 9.48 / MAX: 21.58MIN: 31.62 / MAX: 33.421. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: resnet18

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: resnet18GCC 11.2.0Clang 13.0.148121620SE +/- 0.04, N = 3SE +/- 0.01, N = 37.3118.18-lgomp -lpthread - MIN: 6.17 / MAX: 16.92MIN: 18.14 / MAX: 18.231. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: vgg16

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: vgg16GCC 11.2.0Clang 13.0.120406080100SE +/- 0.14, N = 3SE +/- 0.01, N = 333.7880.44-lgomp -lpthread - MIN: 30.68 / MAX: 45.72MIN: 80.22 / MAX: 80.951. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: mnasnet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mnasnetGCC 11.2.0Clang 13.0.11.31852.6373.95555.2746.5925SE +/- 0.01, N = 3SE +/- 0.01, N = 22.525.86-lgomp -lpthread - MIN: 2.48 / MAX: 2.84MIN: 5.84 / MAX: 5.871. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: efficientnet-b0

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: efficientnet-b0GCC 11.2.0Clang 13.0.13691215SE +/- 0.02, N = 3SE +/- 0.00, N = 34.189.51-lgomp -lpthread - MIN: 4.13 / MAX: 8.1MIN: 9.47 / MAX: 9.671. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU-v2-v2 - Model: mobilenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v2-v2 - Model: mobilenet-v2GCC 11.2.0Clang 13.0.11.3142.6283.9425.2566.57SE +/- 0.05, N = 3SE +/- 0.01, N = 32.615.84-lgomp -lpthread - MIN: 2.48 / MAX: 12.2MIN: 5.81 / MAX: 5.871. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU-v3-v3 - Model: mobilenet-v3

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU-v3-v3 - Model: mobilenet-v3GCC 11.2.0Clang 13.0.11.08452.1693.25354.3385.4225SE +/- 0.01, N = 3SE +/- 0.01, N = 32.344.82-lgomp -lpthread - MIN: 2.32 / MAX: 2.49MIN: 4.8 / MAX: 4.851. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: yolov4-tiny

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: yolov4-tinyGCC 11.2.0Clang 13.0.1816243240SE +/- 0.07, N = 3SE +/- 0.00, N = 317.2032.77-lgomp -lpthread - MIN: 14.01 / MAX: 27.33MIN: 32.68 / MAX: 32.881. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: googlenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: googlenetGCC 11.2.0Clang 13.0.1612182430SE +/- 0.10, N = 3SE +/- 0.01, N = 313.3225.11-lgomp -lpthread - MIN: 9.14 / MAX: 21.97MIN: 25.07 / MAX: 25.161. (CXX) g++ options: -O3 -flto -rdynamic

Stress-NG

Test: Vector Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Vector MathGCC 11.2.0Clang 13.0.19K18K27K36K45KSE +/- 195.44, N = 15SE +/- 2.19, N = 323954.1041899.941. (CC) gcc options: -O3 -flto -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -pthread -lkmod -lc -latomic

NCNN

Target: CPU - Model: shufflenet-v2

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: shufflenet-v2GCC 11.2.0Clang 13.0.10.8461.6922.5383.3844.23SE +/- 0.01, N = 3SE +/- 0.00, N = 32.173.76-lgomp -lpthread - MIN: 2.15 / MAX: 2.48MAX: 3.851. (CXX) g++ options: -O3 -flto -rdynamic

Crypto++

Test: Unkeyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Unkeyed AlgorithmsGCC 11.2.0Clang 13.0.1120240360480600SE +/- 0.04, N = 3SE +/- 0.01, N = 3539.28338.411. (CXX) g++ options: -O3 -flto -fPIC -pthread -pipe

NCNN

Target: CPU - Model: mobilenet

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: mobilenetGCC 11.2.0Clang 13.0.1510152025SE +/- 0.17, N = 3SE +/- 0.01, N = 314.4022.21-lgomp -lpthread - MIN: 9.21 / MAX: 25.2MIN: 22.15 / MAX: 22.251. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: squeezenet_ssd

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: squeezenet_ssdGCC 11.2.0Clang 13.0.1510152025SE +/- 0.17, N = 3SE +/- 0.00, N = 314.2620.15-lgomp -lpthread - MIN: 9.6 / MAX: 28.57MIN: 20.08 / MAX: 20.211. (CXX) g++ options: -O3 -flto -rdynamic

NCNN

Target: CPU - Model: regnety_400m

OpenBenchmarking.orgms, Fewer Is BetterNCNN 20210720Target: CPU - Model: regnety_400mGCC 11.2.0Clang 13.0.1246810SE +/- 0.03, N = 3SE +/- 0.00, N = 35.888.08-lgomp -lpthread - MIN: 5.78 / MAX: 8.62MIN: 8.05 / MAX: 8.151. (CXX) g++ options: -O3 -flto -rdynamic

C-Ray

Total Time - 4K, 16 Rays Per Pixel

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time - 4K, 16 Rays Per PixelGCC 11.2.0Clang 13.0.120406080100SE +/- 0.04, N = 3SE +/- 0.05, N = 364.4487.821. (CC) gcc options: -lm -lpthread -O3 -flto

Crypto++

Test: Keyed Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Keyed AlgorithmsGCC 11.2.0Clang 13.0.1110220330440550SE +/- 0.07, N = 3SE +/- 1.08, N = 3508.84374.901. (CXX) g++ options: -O3 -flto -fPIC -pthread -pipe

Stress-NG

Test: Memory Copying

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Memory CopyingGCC 11.2.0Clang 13.0.18001600240032004000SE +/- 6.71, N = 3SE +/- 15.21, N = 32763.253741.171. (CC) gcc options: -O3 -flto -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -pthread -lkmod -lc -latomic

Liquid-DSP

Threads: 4 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 4 - Buffer Length: 256 - Filter Length: 57GCC 11.2.0Clang 13.0.130M60M90M120M150MSE +/- 0.00, N = 3SE +/- 0.00, N = 31152300001518200001. (CC) gcc options: -O3 -flto -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 2 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 2 - Buffer Length: 256 - Filter Length: 57GCC 11.2.0Clang 13.0.116M32M48M64M80MSE +/- 2081.67, N = 3SE +/- 1763.83, N = 357611000758986671. (CC) gcc options: -O3 -flto -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 1 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 1 - Buffer Length: 256 - Filter Length: 57GCC 11.2.0Clang 13.0.18M16M24M32M40MSE +/- 3527.67, N = 3SE +/- 2905.93, N = 328778667378973331. (CC) gcc options: -O3 -flto -pthread -lm -lc -lliquid

Liquid-DSP

Threads: 8 - Buffer Length: 256 - Filter Length: 57

OpenBenchmarking.orgsamples/s, More Is BetterLiquid-DSP 2021.01.31Threads: 8 - Buffer Length: 256 - Filter Length: 57GCC 11.2.0Clang 13.0.140M80M120M160M200MSE +/- 0.00, N = 3SE +/- 0.00, N = 31511200001965100001. (CC) gcc options: -O3 -flto -pthread -lm -lc -lliquid

Stress-NG

Test: Matrix Math

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Matrix MathGCC 11.2.0Clang 13.0.16K12K18K24K30KSE +/- 332.61, N = 3SE +/- 0.69, N = 323588.9630254.211. (CC) gcc options: -O3 -flto -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -pthread -lkmod -lc -latomic

AOBench

Size: 2048 x 2048 - Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total TimeGCC 11.2.0Clang 13.0.1816243240SE +/- 0.03, N = 3SE +/- 0.01, N = 327.4633.401. (CC) gcc options: -lm -O3 -flto

Coremark

CoreMark Size 666 - Iterations Per Second

OpenBenchmarking.orgIterations/Sec, More Is BetterCoremark 1.0CoreMark Size 666 - Iterations Per SecondGCC 11.2.0Clang 13.0.140K80K120K160K200KSE +/- 59.94, N = 3SE +/- 146.27, N = 3179896.60148361.361. (CC) gcc options: -O2 -O3 -flto -lrt" -lrt

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.3WAV To FLACGCC 11.2.0Clang 13.0.11632486480SE +/- 0.01, N = 5SE +/- 0.01, N = 570.6559.07-fvisibility=hidden1. (CXX) g++ options: -O3 -flto -logg -lm

Crypto++

Test: All Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: All AlgorithmsGCC 11.2.0Clang 13.0.12004006008001000SE +/- 0.23, N = 3SE +/- 0.17, N = 3954.96823.151. (CXX) g++ options: -O3 -flto -fPIC -pthread -pipe

POV-Ray

Trace Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.7.0.7Trace TimeGCC 11.2.0Clang 13.0.11632486480SE +/- 0.85, N = 4SE +/- 0.64, N = 572.0262.42-R/usr/lib1. (CXX) g++ options: -pipe -O3 -ffast-math -flto -lSDL -lpthread -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system

libavif avifenc

Encoder Speed: 2

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 2GCC 11.2.0Clang 13.0.14080120160200SE +/- 0.32, N = 3SE +/- 0.72, N = 3143.44161.611. (CXX) g++ options: -O3 -fPIC -flto -lm

WavPack Audio Encoding

WAV To WavPack

OpenBenchmarking.orgSeconds, Fewer Is BetterWavPack Audio Encoding 5.3WAV To WavPackGCC 11.2.0Clang 13.0.1510152025SE +/- 0.00, N = 5SE +/- 0.00, N = 517.2119.321. (CXX) g++ options: -O3 -flto -rdynamic

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3GCC 11.2.0Clang 13.0.1246810SE +/- 0.011, N = 3SE +/- 0.005, N = 37.2398.124-pipe1. (CC) gcc options: -O3 -flto -lncurses -lm

Crypto++

Test: Integer + Elliptic Curve Public Key Algorithms

OpenBenchmarking.orgMiB/second, More Is BetterCrypto++ 8.2Test: Integer + Elliptic Curve Public Key AlgorithmsGCC 11.2.0Clang 13.0.1400800120016002000SE +/- 0.67, N = 3SE +/- 1.78, N = 31766.991875.521. (CXX) g++ options: -O3 -flto -fPIC -pthread -pipe

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure SolverGCC 11.2.0Clang 13.0.116003200480064008000SE +/- 2.64, N = 3SE +/- 3.44, N = 37577.327158.971. (CC) gcc options: -O3 -flto

Zstd Compression

Compression Level: 3, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Compression SpeedGCC 11.2.0Clang 13.0.160120180240300SE +/- 2.00, N = 15SE +/- 3.51, N = 3240.0253.71. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

libavif avifenc

Encoder Speed: 0

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 0GCC 11.2.0Clang 13.0.170140210280350SE +/- 0.92, N = 3SE +/- 0.16, N = 3287.40303.551. (CXX) g++ options: -O3 -fPIC -flto -lm

OpenSSL

Algorithm: SHA256

OpenBenchmarking.orgbyte/s, More Is BetterOpenSSL 3.0Algorithm: SHA256GCC 11.2.0Clang 13.0.12000M4000M6000M8000M10000MSE +/- 12283962.01, N = 3SE +/- 3887401.32, N = 380596910508474527350-Qunused-arguments1. (CC) gcc options: -pthread -O3 -flto -lssl -lcrypto -ldl

eSpeak-NG Speech Engine

Text-To-Speech Synthesis

OpenBenchmarking.orgSeconds, Fewer Is BettereSpeak-NG Speech Engine 20200907Text-To-Speech SynthesisGCC 11.2.0Clang 13.0.1612182430SE +/- 0.03, N = 4SE +/- 0.03, N = 422.2923.431. (CC) gcc options: -O3 -flto -std=c99 -lpthread -lm

libavif avifenc

Encoder Speed: 6, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6, LosslessGCC 11.2.0Clang 13.0.148121620SE +/- 0.18, N = 3SE +/- 0.21, N = 315.6514.931. (CXX) g++ options: -O3 -fPIC -flto -lm

libavif avifenc

Encoder Speed: 6

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 6GCC 11.2.0Clang 13.0.148121620SE +/- 0.14, N = 6SE +/- 0.15, N = 514.0913.521. (CXX) g++ options: -O3 -fPIC -flto -lm

libjpeg-turbo tjbench

Test: Decompression Throughput

OpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 2.1.0Test: Decompression ThroughputGCC 11.2.0Clang 13.0.150100150200250SE +/- 0.03, N = 3SE +/- 2.27, N = 3206.18197.95-lm1. (CC) gcc options: -O3 -flto -rdynamic

Zstd Compression

Compression Level: 19 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Decompression SpeedGCC 11.2.0Clang 13.0.18001600240032004000SE +/- 0.15, N = 3SE +/- 1.62, N = 33546.23684.31. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

LZ4 Compression

Compression Level: 9 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Decompression SpeedGCC 11.2.0Clang 13.0.14K8K12K16K20KSE +/- 1.03, N = 3SE +/- 3.18, N = 317478.516863.31. (CC) gcc options: -O3

LZ4 Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Decompression SpeedGCC 11.2.0Clang 13.0.14K8K12K16K20KSE +/- 0.40, N = 3SE +/- 3.46, N = 317490.916877.41. (CC) gcc options: -O3

OpenJPEG

Encode: NASA Curiosity Panorama M34

OpenBenchmarking.orgms, Fewer Is BetterOpenJPEG 2.4Encode: NASA Curiosity Panorama M34GCC 11.2.0Clang 13.0.112K24K36K48K60KSE +/- 92.73, N = 3SE +/- 161.48, N = 353890520241. (CXX) g++ options: -O3 -flto -rdynamic

Zstd Compression

Compression Level: 3 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Decompression SpeedGCC 11.2.0Clang 13.0.19001800270036004500SE +/- 0.87, N = 3SE +/- 0.75, N = 33850.23977.71. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

Zstd Compression

Compression Level: 19, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Decompression SpeedGCC 11.2.0Clang 13.0.18001600240032004000SE +/- 0.92, N = 3SE +/- 0.69, N = 43765.43887.31. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

Zstd Compression

Compression Level: 3, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3, Long Mode - Decompression SpeedGCC 11.2.0Clang 13.0.19001800270036004500SE +/- 0.25, N = 15SE +/- 0.40, N = 34221.14356.61. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

Zstd Compression

Compression Level: 8 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Compression SpeedGCC 11.2.0Clang 13.0.1160320480640800SE +/- 3.70, N = 3SE +/- 4.97, N = 3721.5699.61. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

libavif avifenc

Encoder Speed: 10, Lossless

OpenBenchmarking.orgSeconds, Fewer Is Betterlibavif avifenc 0.10Encoder Speed: 10, LosslessGCC 11.2.0Clang 13.0.1246810SE +/- 0.049, N = 3SE +/- 0.047, N = 36.0705.8871. (CXX) g++ options: -O3 -fPIC -flto -lm

Zstd Compression

Compression Level: 8, Long Mode - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Decompression SpeedGCC 11.2.0Clang 13.0.110002000300040005000SE +/- 1.55, N = 3SE +/- 3.13, N = 34416.34553.41. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

Zstd Compression

Compression Level: 8 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8 - Decompression SpeedGCC 11.2.0Clang 13.0.19001800270036004500SE +/- 1.95, N = 3SE +/- 3.02, N = 34016.44141.01. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

SQLite Speedtest

Timed Time - Size 1,000

OpenBenchmarking.orgSeconds, Fewer Is BetterSQLite Speedtest 3.30Timed Time - Size 1,000GCC 11.2.0Clang 13.0.11224364860SE +/- 0.04, N = 3SE +/- 0.07, N = 351.3752.901. (CC) gcc options: -O3 -flto -lz

LeelaChessZero

Backend: Eigen

OpenBenchmarking.orgNodes Per Second, More Is BetterLeelaChessZero 0.28Backend: EigenGCC 11.2.0Clang 13.0.130060090012001500SE +/- 10.69, N = 3SE +/- 18.26, N = 3126312971. (CXX) g++ options: -flto -O3 -pthread

Zstd Compression

Compression Level: 19 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19 - Compression SpeedGCC 11.2.0Clang 13.0.1612182430SE +/- 0.07, N = 3SE +/- 0.17, N = 322.723.21. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

LZ4 Compression

Compression Level: 9 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 9 - Compression SpeedGCC 11.2.0Clang 13.0.11122334455SE +/- 0.09, N = 3SE +/- 0.12, N = 348.9449.891. (CC) gcc options: -O3

Stress-NG

Test: IO_uring

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: IO_uringGCC 11.2.0Clang 13.0.130K60K90K120K150KSE +/- 28.54, N = 3SE +/- 271.95, N = 3144281.67147040.981. (CC) gcc options: -O3 -flto -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -pthread -lkmod -lc -latomic

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 7.71e12 Prime Number GenerationGCC 11.2.0Clang 13.0.1714212835SE +/- 0.01, N = 3SE +/- 0.03, N = 329.1229.631. (CXX) g++ options: -O3 -flto

Xmrig

Variant: Monero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Monero - Hash Count: 1MGCC 11.2.0Clang 13.0.15001000150020002500SE +/- 9.05, N = 3SE +/- 7.70, N = 32247.22209.7-static-libgcc -static-libstdc++-funroll-loops1. (CXX) g++ options: -O3 -flto -fexceptions -fno-rtti -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

Zstd Compression

Compression Level: 8, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 8, Long Mode - Compression SpeedGCC 11.2.0Clang 13.0.1150300450600750SE +/- 2.35, N = 3SE +/- 2.38, N = 3693.0703.41. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

LZ4 Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 3 - Compression SpeedGCC 11.2.0Clang 13.0.11224364860SE +/- 0.05, N = 3SE +/- 0.09, N = 351.9951.321. (CC) gcc options: -O3

Google Draco

Model: Church Facade

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: Church FacadeGCC 11.2.0Clang 13.0.112002400360048006000SE +/- 7.21, N = 3SE +/- 3.79, N = 3564957221. (CXX) g++ options: -O3 -flto

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgsign/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096GCC 11.2.0Clang 13.0.130060090012001500SE +/- 0.78, N = 3SE +/- 0.15, N = 31408.51391.4-Qunused-arguments1. (CC) gcc options: -pthread -O3 -flto -lssl -lcrypto -ldl

Zstd Compression

Compression Level: 3 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 3 - Compression SpeedGCC 11.2.0Clang 13.0.17001400210028003500SE +/- 6.19, N = 3SE +/- 39.46, N = 33341.23301.11. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

LZ4 Compression

Compression Level: 1 - Decompression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Decompression SpeedGCC 11.2.0Clang 13.0.16K12K18K24K30KSE +/- 1.47, N = 3SE +/- 8.86, N = 327018.526736.41. (CC) gcc options: -O3

Stress-NG

Test: Crypto

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: CryptoGCC 11.2.0Clang 13.0.130060090012001500SE +/- 16.47, N = 3SE +/- 0.94, N = 31511.751527.171. (CC) gcc options: -O3 -flto -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -pthread -lkmod -lc -latomic

Google Draco

Model: Lion

OpenBenchmarking.orgms, Fewer Is BetterGoogle Draco 1.5.0Model: LionGCC 11.2.0Clang 13.0.18001600240032004000SE +/- 2.73, N = 3SE +/- 0.58, N = 3374737721. (CXX) g++ options: -O3 -flto

Stress-NG

Test: Socket Activity

OpenBenchmarking.orgBogo Ops/s, More Is BetterStress-NG 0.13.02Test: Socket ActivityGCC 11.2.0Clang 13.0.19001800270036004500SE +/- 4.58, N = 3SE +/- 13.20, N = 34331.714313.481. (CC) gcc options: -O3 -flto -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -pthread -lkmod -lc -latomic

Xmrig

Variant: Wownero - Hash Count: 1M

OpenBenchmarking.orgH/s, More Is BetterXmrig 6.12.1Variant: Wownero - Hash Count: 1MGCC 11.2.0Clang 13.0.16001200180024003000SE +/- 1.83, N = 3SE +/- 1.95, N = 32798.22804.8-static-libgcc -static-libstdc++-funroll-loops1. (CXX) g++ options: -O3 -flto -fexceptions -fno-rtti -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc

LZ4 Compression

Compression Level: 1 - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterLZ4 Compression 1.9.3Compression Level: 1 - Compression SpeedGCC 11.2.0Clang 13.0.15K10K15K20K25KSE +/- 5.50, N = 3SE +/- 3.05, N = 321909.4521875.541. (CC) gcc options: -O3

OpenSSL

Algorithm: RSA4096

OpenBenchmarking.orgverify/s, More Is BetterOpenSSL 3.0Algorithm: RSA4096GCC 11.2.0Clang 13.0.120K40K60K80K100KSE +/- 18.59, N = 3SE +/- 16.80, N = 399370.599445.4-Qunused-arguments1. (CC) gcc options: -pthread -O3 -flto -lssl -lcrypto -ldl

Zstd Compression

Compression Level: 19, Long Mode - Compression Speed

OpenBenchmarking.orgMB/s, More Is BetterZstd Compression 1.5.0Compression Level: 19, Long Mode - Compression SpeedGCC 11.2.0Clang 13.0.1510152025SE +/- 0.13, N = 3SE +/- 0.21, N = 418.818.81. (CC) gcc options: -O3 -flto -pthread -lz -llzma -llz4

Phoronix Test Suite v10.8.5