GCC and Clang compiler benchmarks by Michael Larabel for year end 2023 future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2312240-PTS-COMPILER73 GCC Clang Compiler Benchmarks Zen 4 Threadripper - Phoronix Test Suite GCC Clang Compiler Benchmarks Zen 4 Threadripper GCC and Clang compiler benchmarks by Michael Larabel for year end 2023 future article.
HTML result view exported from: https://openbenchmarking.org/result/2312240-PTS-COMPILER73&export=pdf&grs&sor .
GCC Clang Compiler Benchmarks Zen 4 Threadripper Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec AMD Ryzen Threadripper PRO 7995WX 96-Cores @ 6.44GHz (96 Cores / 192 Threads) HP 8B24 (U65 Ver. 01.01.04 BIOS) AMD Device 14a4 128GB 2 x 1024GB SAMSUNG MZVL21T0HCLR-00BH1 NVIDIA RTX A4000 16GB NVIDIA GA104 HD Audio ASUS VP28U Realtek RTL8111/8168/8411 Ubuntu 23.10 6.5.0-14-generic (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 NVIDIA 535.129.03 4.6.0 OpenCL 3.0 CUDA 12.2.147 GCC 13.2.0 ext4 3840x2160 Clang 17.0.2 Clang 18.0.0 GCC 14.0.0 20231224 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Environment Details - CXXFLAGS="-O3 -march=native" CFLAGS="-O3 -march=native" Compiler Details - GCC 13.2: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-gcn/usr --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-build-config=bootstrap-lto-lean --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v - GCC 14 23 Dec: --disable-multilib --enable-checking=release --enable-languages=c,c++ Processor Details - Scaling Governor: amd-pstate-epp performance (EPP: performance) - CPU Microcode: 0xa108105 OpenCL Details - GPU Compute Cores: 6144 Python Details - Python 3.11.6 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
GCC Clang Compiler Benchmarks Zen 4 Threadripper smhasher: SHA3-256 openssl: ChaCha20-Poly1305 openssl: ChaCha20 graphics-magick: HWB Color Space c-ray: Total Time - 4K, 16 Rays Per Pixel graphics-magick: Swirl graphics-magick: Noise-Gaussian lczero: Eigen smhasher: FarmHash32 x86_64 AVX liquid-dsp: 1 - 256 - 512 webp: Quality 100, Highest Compression graphics-magick: Enhanced tscp: AI Chess Performance minibude: OpenMP - BM2 minibude: OpenMP - BM2 john-the-ripper: WPA PSK cryptopp: Unkeyed Algorithms liquid-dsp: 128 - 256 - 32 coremark: CoreMark Size 666 - Iterations Per Second liquid-dsp: 192 - 256 - 32 liquid-dsp: 1 - 256 - 32 astcenc: Medium simdjson: LargeRand stargate: 96000 - 1024 stargate: 96000 - 512 stargate: 44100 - 512 stargate: 192000 - 1024 stargate: 192000 - 512 stargate: 44100 - 1024 liquid-dsp: 128 - 256 - 512 securemark: SecureMark-TLS simdjson: DistinctUserID blosc: blosclz shuffle - 256MB simdjson: Kostya openjpeg: NASA Curiosity Panorama M34 quantlib: Single-Threaded encode-flac: WAV To FLAC kvazaar: Bosphorus 4K - Slow encode-mp3: WAV To MP3 smhasher: FarmHash128 redis: GET - 500 kvazaar: Bosphorus 4K - Medium pgbench: 100 - 1000 - Read Only quantlib: Multi-Threaded pgbench: 100 - 1000 - Read Only - Average Latency blosc: blosclz noshuffle - 256MB simdjson: PartialTweets avifenc: 6, Lossless uvg266: Bosphorus 4K - Very Fast graphics-magick: Sharpen compress-lz4: 9 - Compression Speed x265: Bosphorus 4K john-the-ripper: MD5 blosc: blosclz bitshuffle - 256MB vvenc: Bosphorus 4K - Faster webp: Default cryptopp: Keyed Algorithms encode-opus: WAV To Opus Encode svt-av1: Preset 8 - Bosphorus 4K gpaw: Carbon Nanotube john-the-ripper: bcrypt kvazaar: Bosphorus 4K - Super Fast openvino: Person Vehicle Bike Detection FP16 - CPU gromacs: MPI CPU - water_GMX50_bare openvino: Person Vehicle Bike Detection FP16 - CPU svt-vp9: Visual Quality Optimized - Bosphorus 4K uvg266: Bosphorus 4K - Super Fast openssl: SHA256 kvazaar: Bosphorus 4K - Very Fast john-the-ripper: Blowfish webp: Quality 100, Lossless vvenc: Bosphorus 4K - Fast openvino: Handwritten English Recognition FP16-INT8 - CPU uvg266: Bosphorus 4K - Slow openvino: Handwritten English Recognition FP16-INT8 - CPU avifenc: 0 avifenc: 2 mrbayes: Primate Phylogeny Analysis compress-zstd: 12 - Decompression Speed uvg266: Bosphorus 4K - Medium povray: Trace Time graphics-magick: Rotate svt-av1: Preset 12 - Bosphorus 4K uvg266: Bosphorus 4K - Ultra Fast webp: Quality 100 compress-zstd: 19 - Decompression Speed memcached: 1:10 avifenc: 6 svt-av1: Preset 4 - Bosphorus 4K openssl: SHA512 compress-zstd: 12 - Compression Speed liquid-dsp: 192 - 256 - 512 smhasher: MeowHash x86_64 AES-NI simdjson: TopTweet svt-av1: Preset 13 - Bosphorus 4K lammps: 20k Atoms xmrig: KawPow - 1M openvino: Face Detection Retail FP16-INT8 - CPU compress-lz4: 9 - Decompression Speed openvino: Face Detection Retail FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU astcenc: Thorough openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU xmrig: GhostRider - 1M openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openssl: RSA4096 webp: Quality 100, Lossless, Highest Compression compress-zstd: 19, Long Mode - Decompression Speed memcached: 1:100 compress-zstd: 19 - Compression Speed astcenc: Exhaustive openssl: AES-256-GCM smhasher: t1ha0_aes_avx2 x86_64 kvazaar: Bosphorus 4K - Ultra Fast xmrig: CryptoNight-Femto UPX2 - 1M compress-zstd: 19, Long Mode - Compression Speed xmrig: Monero - 1M xmrig: CryptoNight-Heavy - 1M openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openssl: AES-128-GCM petsc: Streams openssl: RSA4096 openvino: Weld Porosity Detection FP16-INT8 - CPU xmrig: Wownero - 1M openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU redis: SET - 500 svt-vp9: PSNR/SSIM Optimized - Bosphorus 4K smhasher: MeowHash x86_64 AES-NI smhasher: t1ha0_aes_avx2 x86_64 smhasher: FarmHash32 x86_64 AVX smhasher: FarmHash128 smhasher: SHA3-256 GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec 290.65 361301039787 512442016473 1069 4.950 2600 817 671 51654.97 17781400 4.51 1638 2216345 4581.390 183.256 613307 539.172205 4228033333 3955168.745941 5518300000 48601000 426.4857 1.70 5.601831 5.131378 7.403037 3.657915 3.258674 7.987047 1293233333 392447 8.67 8137.1 5.45 82008 4151.0 12.231 42.44 4.747 29054.81 4484373.8 43.54 3780387 308069.5 0.265 7804.7 9.01 4.176 67.31 1038 67.01 39.38 14526667 7649.3 16.492 25.65 848.073852 20.031 94.710 37.890 173913 89.12 5480.25 11.203 8.75 199.54 69.54 128629387223 86.89 173760 2.04 9.038 40.45 30.82 2372.40 49.184 26.596 113.106 2212.9 34.05 6.050 690 212.001 71.37 15.24 1895.8 5921751.45 2.116 9.589 43028797080 416.1 1496100000 68597.56 9.72 208.824 42.448 56883.5 18002.34 17018.5 5.32 0.62 69.8358 25.45 1883.57 13592.0 141.26 339.37 1541833.5 0.79 1795.5 7695223.15 24.9 7.2724 819163695240 131074.98 94.70 56592.8 11.7 56279.6 56361.0 93.18 514.54 113554.50 487.79 98.10 946233938740 183886.9500 50251.7 9.7 71242.7 8.03 5964.98 9919.18 3079293.25 224.12 34.258 15.635 20.189 35.544 1353.924 459.02 229128259903 335909931727 751 6.848 1987 623 816 40846.89 21974667 5.60 1479 2458869 5376.447 215.058 511546 450.462765 5040300000 3332695.383619 6543933333 56815750 499.3909 1.59 6.474312 5.922697 8.527328 4.204693 3.738894 9.124527 1447966667 442902 9.73 8125.5 5.25 75630 4578.8 11.123 46.65 5.209 26974.45 4242865.92 47.38 3570369 329638.6 0.280 7735.7 9.64 3.917 70.81 985 65.18 40.43 15165000 7628.0 15.577 27.08 873.133433 19.128 99.212 37.616 182570 92.52 5230.49 10.816 9.16 190.79 71.84 124526197107 89.69 180170 1.98 8.747 39.38 32.01 2436.02 47.787 25.652 109.116 2151.0 35.23 5.868 685 208.924 73.25 15.73 1856.6 6092998.10 2.087 9.872 43131468240 414.4 1495833333 67078.43 9.59 208.707 42.367 57018.3 17698.62 17310.2 5.41 0.63 70.0092 25.82 1856.67 13628.9 142.62 336.16 1538339.5 0.79 1774.3 7774340.30 25.0 7.2323 816930832563 132159.77 94.29 56300.8 11.8 55888.6 56105.9 93.05 515.15 112991.73 490.20 97.62 944090667870 183268.5282 50097.7 9.67 71216.1 8.05 5952.83 9912.53 2829400.83 232.28 34.108 15.251 22.559 25.128 812.789 463.94 228903633260 335886221587 747 6.896 1966 623 857 41578.48 22239000 5.39 1457 2708002 5572.326 222.893 518594 533.227225 4994600000 3642203.842569 6541433333 56732000 482.3822 1.46 6.371475 5.827354 8.415251 4.122784 3.703294 9.030747 1469833333 420687 9.72 7795.9 4.87 74343 11.143 45.54 5.074 26494.22 4649256.8 46.76 3511928 0.285 7496.2 9.51 4.053 71.76 977 69.19 41.05 15399667 7454.2 26.81 894.485900 19.287 94.444 36.403 181400 92.02 5271.52 10.695 9.09 194.92 72.62 129800447513 89.00 181091 1.96 38.94 31.58 2463.91 47.369 25.619 109.583 2173.3 34.66 5.848 675 205.933 73.72 15.37 1866.6 6108890.58 2.149 9.667 43912408803 405.5 1528766667 67945.38 9.51 204.328 41.658 56651.0 17696.86 17044.4 5.41 0.63 68.8980 25.80 1857.83 13438.4 143.24 334.69 1552460.9 0.79 1776.6 7679397.09 24.7 7.1900 811977109867 130792.83 94.59 56023.0 11.8 55839.5 55924.5 93.71 511.63 113505.56 489.66 97.72 944539664203 183176.5581 50206.9 9.67 71240.6 8.05 5951.95 9909.42 3090972.67 235.76 34.756 15.565 22.072 25.247 817.895 287.86 364041629243 513536630053 1048 4.912 2446 807 50400.25 17950067 4.48 1331 2246260 4789.291 191.572 616447 4262500000 3955659.291168 5587766667 48068000 5.951828 5.388126 7.530593 3.955202 3.479722 8.111928 1301200000 406282 7258.5 82985 4504.6 11.846 43.43 4.819 28278.49 4589226.3 44.32 3593163 331562.3 0.278 7291.9 4.106 67.98 1003 66.32 38.70 14730000 7218.1 16.345 26.07 20.152 96.129 38.230 177062 88.23 199.29 69.71 125384626833 86.05 175544 2.01 9.102 31.60 48.048 26.165 110.558 2136.2 34.91 667 205.098 71.62 15.65 1837.3 5956401.51 2.142 9.717 42698789480 411.4 1491466667 68248.31 205.982 57660.1 17246.0 13625.2 1532147.3 0.78 1773.2 7735938.66 24.7 821035343690 132218.26 93.72 56155.2 11.8 55867.9 56126.3 948573686080 50065.0 71393.6 3175906.7 218.02 34.175 15.433 19.860 35.681 1356.534 OpenBenchmarking.org
SMHasher Hash: SHA3-256 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: SHA3-256 Clang 18 23 Dec Clang 17.0.2 GCC 13.2 GCC 14 23 Dec 100 200 300 400 500 SE +/- 3.98, N = 3 SE +/- 4.14, N = 7 SE +/- 3.50, N = 4 SE +/- 2.29, N = 3 463.94 459.02 290.65 287.86 -flto=thin -flto=thin -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects 1. (CXX) g++ options: -O3 -march=native
OpenSSL Algorithm: ChaCha20-Poly1305 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: ChaCha20-Poly1305 GCC 14 23 Dec GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 80000M 160000M 240000M 320000M 400000M SE +/- 38965461.92, N = 3 SE +/- 138801171.04, N = 3 SE +/- 74912722.41, N = 3 SE +/- 143870310.16, N = 3 364041629243 361301039787 229128259903 228903633260 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenSSL Algorithm: ChaCha20 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: ChaCha20 GCC 14 23 Dec GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 110000M 220000M 330000M 440000M 550000M SE +/- 289414516.97, N = 3 SE +/- 264097935.23, N = 3 SE +/- 201482071.29, N = 3 SE +/- 195079194.35, N = 3 513536630053 512442016473 335909931727 335886221587 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 200 400 600 800 1000 SE +/- 5.24, N = 3 SE +/- 5.13, N = 3 SE +/- 3.18, N = 3 SE +/- 0.58, N = 3 1069 1048 751 747 1. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel GCC 14 23 Dec GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 2 4 6 8 10 SE +/- 0.029, N = 3 SE +/- 0.029, N = 3 SE +/- 0.068, N = 3 SE +/- 0.067, N = 3 4.912 4.950 6.848 6.896 1. (CC) gcc options: -lm -lpthread -O3 -march=native
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 600 1200 1800 2400 3000 SE +/- 3.93, N = 3 SE +/- 0.88, N = 3 SE +/- 1.33, N = 3 SE +/- 2.89, N = 3 2600 2446 1987 1966 1. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian GCC 13.2 GCC 14 23 Dec Clang 18 23 Dec Clang 17.0.2 200 400 600 800 1000 SE +/- 4.33, N = 3 SE +/- 5.04, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 817 807 623 623 1. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.30 Backend: Eigen Clang 18 23 Dec Clang 17.0.2 GCC 13.2 200 400 600 800 1000 SE +/- 7.84, N = 3 SE +/- 11.58, N = 9 SE +/- 6.34, N = 9 857 816 671 1. (CXX) g++ options: -flto -O3 -march=native -pthread
SMHasher Hash: FarmHash32 x86_64 AVX OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX GCC 13.2 GCC 14 23 Dec Clang 18 23 Dec Clang 17.0.2 11K 22K 33K 44K 55K SE +/- 264.89, N = 3 SE +/- 531.14, N = 3 SE +/- 372.44, N = 3 SE +/- 439.18, N = 3 51654.97 50400.25 41578.48 40846.89 -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects -flto=thin -flto=thin 1. (CXX) g++ options: -O3 -march=native
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 512 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 5M 10M 15M 20M 25M SE +/- 100374.30, N = 3 SE +/- 88706.13, N = 3 SE +/- 235451.13, N = 15 SE +/- 127219.34, N = 15 22239000 21974667 17950067 17781400 1. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Highest Compression Clang 17.0.2 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec 1.26 2.52 3.78 5.04 6.3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 5.60 5.39 4.51 4.48 -lpng16 -ljpeg -ltiff -lpng16 -ljpeg -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec 400 800 1200 1600 2000 SE +/- 4.04, N = 3 SE +/- 1.53, N = 3 SE +/- 2.65, N = 3 SE +/- 5.84, N = 3 1638 1479 1457 1331 1. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 600K 1200K 1800K 2400K 3000K SE +/- 9910.25, N = 5 SE +/- 4909.07, N = 5 SE +/- 3431.38, N = 5 SE +/- 21601.14, N = 5 2708002 2458869 2246260 2216345 1. (CC) gcc options: -O3 -march=native
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org GFInst/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 1200 2400 3600 4800 6000 SE +/- 24.10, N = 3 SE +/- 62.02, N = 3 SE +/- 52.09, N = 5 SE +/- 51.09, N = 3 5572.33 5376.45 4789.29 4581.39 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
miniBUDE Implementation: OpenMP - Input Deck: BM2 OpenBenchmarking.org Billion Interactions/s, More Is Better miniBUDE 20210901 Implementation: OpenMP - Input Deck: BM2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 50 100 150 200 250 SE +/- 0.96, N = 3 SE +/- 2.48, N = 3 SE +/- 2.08, N = 5 SE +/- 2.04, N = 3 222.89 215.06 191.57 183.26 1. (CC) gcc options: -std=c99 -Ofast -ffast-math -fopenmp -march=native -lm
John The Ripper Test: WPA PSK OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: WPA PSK GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec Clang 17.0.2 130K 260K 390K 520K 650K SE +/- 3178.61, N = 3 SE +/- 2497.30, N = 3 SE +/- 5465.43, N = 3 SE +/- 4559.35, N = 3 616447 613307 518594 511546 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Crypto++ Test: Unkeyed Algorithms OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.8 Test: Unkeyed Algorithms GCC 13.2 Clang 18 23 Dec Clang 17.0.2 120 240 360 480 600 SE +/- 0.95, N = 3 SE +/- 2.74, N = 3 SE +/- 0.49, N = 3 539.17 533.23 450.46 -fno-devirtualize 1. (CXX) g++ options: -g2 -fPIC -pthread -pipe -O3 -march=native
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 32 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 1100M 2200M 3300M 4400M 5500M SE +/- 38722904.51, N = 3 SE +/- 37430513.40, N = 3 SE +/- 43594839.14, N = 3 SE +/- 12640191.63, N = 3 5040300000 4994600000 4262500000 4228033333 1. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec Clang 17.0.2 800K 1600K 2400K 3200K 4000K SE +/- 38604.00, N = 3 SE +/- 27949.92, N = 3 SE +/- 34986.71, N = 3 SE +/- 19620.88, N = 3 3955659.29 3955168.75 3642203.84 3332695.38 1. (CC) gcc options: -O2 -O3 -march=native -lrt" -lrt
Liquid-DSP Threads: 192 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 192 - Buffer Length: 256 - Filter Length: 32 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 1400M 2800M 4200M 5600M 7000M SE +/- 23899256.15, N = 3 SE +/- 42403157.64, N = 3 SE +/- 36511383.31, N = 3 SE +/- 32255852.18, N = 3 6543933333 6541433333 5587766667 5518300000 1. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 32 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 1 - Buffer Length: 256 - Filter Length: 32 Clang 17.0.2 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec 12M 24M 36M 48M 60M SE +/- 705129.82, N = 4 SE +/- 61098.28, N = 3 SE +/- 13747.73, N = 3 SE +/- 134747.91, N = 3 56815750 56732000 48601000 48068000 1. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
ASTC Encoder Preset: Medium OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Clang 17.0.2 Clang 18 23 Dec GCC 13.2 110 220 330 440 550 SE +/- 0.56, N = 3 SE +/- 1.39, N = 3 SE +/- 0.80, N = 3 499.39 482.38 426.49 1. (CXX) g++ options: -O3 -march=native -flto -pthread
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: LargeRandom GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 0.3825 0.765 1.1475 1.53 1.9125 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.70 1.59 1.46 1. (CXX) g++ options: -O3 -march=native
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 1024 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 2 4 6 8 10 SE +/- 0.004464, N = 3 SE +/- 0.009480, N = 3 SE +/- 0.007988, N = 3 SE +/- 0.009825, N = 3 6.474312 6.371475 5.951828 5.601831 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 96000 - Buffer Size: 512 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 1.3326 2.6652 3.9978 5.3304 6.663 SE +/- 0.004937, N = 3 SE +/- 0.003453, N = 3 SE +/- 0.012082, N = 3 SE +/- 0.011976, N = 3 5.922697 5.827354 5.388126 5.131378 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 512 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 2 4 6 8 10 SE +/- 0.051637, N = 3 SE +/- 0.038112, N = 3 SE +/- 0.023956, N = 3 SE +/- 0.067600, N = 3 8.527328 8.415251 7.530593 7.403037 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 1024 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 0.9461 1.8922 2.8383 3.7844 4.7305 SE +/- 0.018365, N = 3 SE +/- 0.020650, N = 3 SE +/- 0.006090, N = 3 SE +/- 0.008117, N = 3 4.204693 4.122784 3.955202 3.657915 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 192000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 192000 - Buffer Size: 512 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 0.8413 1.6826 2.5239 3.3652 4.2065 SE +/- 0.004927, N = 3 SE +/- 0.002560, N = 3 SE +/- 0.001538, N = 3 SE +/- 0.007583, N = 3 3.738894 3.703294 3.479722 3.258674 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Stargate Digital Audio Workstation Sample Rate: 44100 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 22.11.5 Sample Rate: 44100 - Buffer Size: 1024 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 3 6 9 12 15 SE +/- 0.009153, N = 3 SE +/- 0.018602, N = 3 SE +/- 0.013114, N = 3 SE +/- 0.011137, N = 3 9.124527 9.030747 8.111928 7.987047 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Liquid-DSP Threads: 128 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 128 - Buffer Length: 256 - Filter Length: 512 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 300M 600M 900M 1200M 1500M SE +/- 3295114.23, N = 3 SE +/- 5446813.54, N = 3 SE +/- 1882374.39, N = 3 SE +/- 3447865.68, N = 3 1469833333 1447966667 1301200000 1293233333 1. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 90K 180K 270K 360K 450K SE +/- 3387.50, N = 3 SE +/- 3191.95, N = 3 SE +/- 996.80, N = 3 SE +/- 25.96, N = 3 442902 420687 406282 392447 1. (CC) gcc options: -pedantic -O3
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: DistinctUserID Clang 17.0.2 Clang 18 23 Dec GCC 13.2 3 6 9 12 15 SE +/- 0.09, N = 7 SE +/- 0.08, N = 15 SE +/- 0.03, N = 3 9.73 9.72 8.67 1. (CXX) g++ options: -O3 -march=native
C-Blosc Test: blosclz shuffle - Buffer Size: 256MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz shuffle - Buffer Size: 256MB GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec 2K 4K 6K 8K 10K SE +/- 15.55, N = 3 SE +/- 23.87, N = 3 SE +/- 34.63, N = 3 SE +/- 37.76, N = 3 8137.1 8125.5 7795.9 7258.5 -std=gnu99 -lrt -ldl -lm -march=native -march=native -std=gnu99 -ldl -lrt -lm 1. (CC) gcc options: -O3
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: Kostya GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 1.2263 2.4526 3.6789 4.9052 6.1315 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 5.45 5.25 4.87 1. (CXX) g++ options: -O3 -march=native
OpenJPEG Encode: NASA Curiosity Panorama M34 OpenBenchmarking.org ms, Fewer Is Better OpenJPEG 2.4 Encode: NASA Curiosity Panorama M34 Clang 18 23 Dec Clang 17.0.2 GCC 13.2 GCC 14 23 Dec 20K 40K 60K 80K 100K SE +/- 627.99, N = 3 SE +/- 34.27, N = 3 SE +/- 357.19, N = 3 SE +/- 1022.49, N = 4 74343 75630 82008 82985 1. (CXX) g++ options: -O3 -march=native -rdynamic
QuantLib Configuration: Single-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Single-Threaded Clang 17.0.2 GCC 14 23 Dec GCC 13.2 1000 2000 3000 4000 5000 SE +/- 40.89, N = 3 SE +/- 30.04, N = 3 SE +/- 33.97, N = 3 4578.8 4504.6 4151.0 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.4 WAV To FLAC Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 3 6 9 12 15 SE +/- 0.02, N = 5 SE +/- 0.05, N = 5 SE +/- 0.06, N = 5 SE +/- 0.04, N = 5 11.12 11.14 11.85 12.23 1. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Slow Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 11 22 33 44 55 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.16, N = 3 SE +/- 0.46, N = 3 46.65 45.54 43.43 42.44 -lpthread -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 GCC 13.2 GCC 14 23 Dec Clang 18 23 Dec Clang 17.0.2 1.172 2.344 3.516 4.688 5.86 SE +/- 0.051, N = 3 SE +/- 0.059, N = 3 SE +/- 0.047, N = 3 SE +/- 0.022, N = 3 4.747 4.819 5.074 5.209 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr 1. (CC) gcc options: -O3 -pipe -march=native -lncurses -lm
SMHasher Hash: FarmHash128 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: FarmHash128 GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 6K 12K 18K 24K 30K SE +/- 187.58, N = 15 SE +/- 311.86, N = 3 SE +/- 227.32, N = 3 SE +/- 100.64, N = 3 29054.81 28278.49 26974.45 26494.22 -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects -flto=thin -flto=thin 1. (CXX) g++ options: -O3 -march=native
Redis Test: GET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: GET - Parallel Connections: 500 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 Clang 17.0.2 1000K 2000K 3000K 4000K 5000K SE +/- 27204.42, N = 3 SE +/- 33944.52, N = 15 SE +/- 47771.21, N = 4 SE +/- 37859.85, N = 15 4649256.80 4589226.30 4484373.80 4242865.92 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Medium Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 11 22 33 44 55 SE +/- 0.23, N = 3 SE +/- 0.22, N = 3 SE +/- 0.11, N = 3 SE +/- 0.21, N = 3 47.38 46.76 44.32 43.54 -lpthread -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 800K 1600K 2400K 3200K 4000K SE +/- 14867.69, N = 3 SE +/- 7434.99, N = 3 SE +/- 34138.17, N = 3 SE +/- 23217.69, N = 3 3780387 3593163 3570369 3511928 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lm
QuantLib Configuration: Multi-Threaded OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.32 Configuration: Multi-Threaded GCC 14 23 Dec Clang 17.0.2 GCC 13.2 70K 140K 210K 280K 350K SE +/- 1487.52, N = 3 SE +/- 1401.25, N = 3 SE +/- 819.02, N = 3 331562.3 329638.6 308069.5 1. (CXX) g++ options: -O3 -march=native -fPIE -pie
PostgreSQL Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL 16 Scaling Factor: 100 - Clients: 1000 - Mode: Read Only - Average Latency GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 0.0641 0.1282 0.1923 0.2564 0.3205 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.003, N = 3 SE +/- 0.002, N = 3 0.265 0.278 0.280 0.285 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -march=native -lpgcommon -lpgport -lpq -lm
C-Blosc Test: blosclz noshuffle - Buffer Size: 256MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz noshuffle - Buffer Size: 256MB GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec 2K 4K 6K 8K 10K SE +/- 17.86, N = 3 SE +/- 10.30, N = 3 SE +/- 0.87, N = 3 SE +/- 3.92, N = 3 7804.7 7735.7 7496.2 7291.9 -std=gnu99 -lrt -ldl -lm -march=native -march=native -std=gnu99 -ldl -lrt -lm 1. (CC) gcc options: -O3
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: PartialTweets Clang 17.0.2 Clang 18 23 Dec GCC 13.2 3 6 9 12 15 SE +/- 0.12, N = 15 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 9.64 9.51 9.01 1. (CXX) g++ options: -O3 -march=native
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6, Lossless Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 0.9396 1.8792 2.8188 3.7584 4.698 SE +/- 0.004, N = 3 SE +/- 0.027, N = 3 SE +/- 0.014, N = 3 SE +/- 0.004, N = 3 3.917 4.053 4.106 4.176 1. (CXX) g++ options: -O3 -fPIC -march=native -lm
uvg266 Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Very Fast Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 16 32 48 64 80 SE +/- 0.19, N = 3 SE +/- 0.12, N = 3 SE +/- 0.27, N = 3 SE +/- 0.11, N = 3 71.76 70.81 67.98 67.31 1. (CXX) g++ options: -O3 -march=native
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 200 400 600 800 1000 SE +/- 1.73, N = 3 SE +/- 0.67, N = 3 SE +/- 2.00, N = 3 SE +/- 4.10, N = 3 1038 1003 985 977 1. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec Clang 17.0.2 15 30 45 60 75 SE +/- 0.58, N = 3 SE +/- 0.67, N = 5 SE +/- 0.69, N = 3 SE +/- 0.89, N = 3 69.19 67.01 66.32 65.18 1. (CC) gcc options: -O3
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Clang 18 23 Dec Clang 17.0.2 GCC 13.2 GCC 14 23 Dec 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.29, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 41.05 40.43 39.38 38.70 1. (CXX) g++ options: -O3 -march=native -rdynamic -lpthread -lrt -ldl -lnuma
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: MD5 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 3M 6M 9M 12M 15M SE +/- 133559.39, N = 3 SE +/- 114054.08, N = 3 SE +/- 75020.00, N = 3 SE +/- 43498.40, N = 3 15399667 15165000 14730000 14526667 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
C-Blosc Test: blosclz bitshuffle - Buffer Size: 256MB OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.11 Test: blosclz bitshuffle - Buffer Size: 256MB GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec 1600 3200 4800 6400 8000 SE +/- 30.09, N = 3 SE +/- 30.25, N = 3 SE +/- 15.49, N = 3 SE +/- 20.20, N = 3 7649.3 7628.0 7454.2 7218.1 -std=gnu99 -lrt -ldl -lm -march=native -march=native -std=gnu99 -ldl -lrt -lm 1. (CC) gcc options: -O3
VVenC Video Input: Bosphorus 4K - Video Preset: Faster OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Faster GCC 13.2 GCC 14 23 Dec Clang 17.0.2 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 16.49 16.35 15.58 -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects -flto=thin 1. (CXX) g++ options: -O3 -march=native
WebP Image Encode Encode Settings: Default OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Default Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 27.08 26.81 26.07 25.65 -lpng16 -ljpeg -ltiff -lpng16 -ljpeg -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
Crypto++ Test: Keyed Algorithms OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.8 Test: Keyed Algorithms Clang 18 23 Dec Clang 17.0.2 GCC 13.2 200 400 600 800 1000 SE +/- 0.92, N = 3 SE +/- 0.30, N = 3 SE +/- 1.20, N = 3 894.49 873.13 848.07 -fno-devirtualize 1. (CXX) g++ options: -g2 -fPIC -pthread -pipe -O3 -march=native
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.4 WAV To Opus Encode Clang 17.0.2 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec 5 10 15 20 25 SE +/- 0.10, N = 5 SE +/- 0.07, N = 5 SE +/- 0.13, N = 5 SE +/- 0.01, N = 5 19.13 19.29 20.03 20.15 1. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 8 - Input: Bosphorus 4K Clang 17.0.2 GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec 20 40 60 80 100 SE +/- 0.81, N = 3 SE +/- 1.18, N = 3 SE +/- 0.65, N = 15 SE +/- 1.06, N = 4 99.21 96.13 94.71 94.44 1. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 23.6 Input: Carbon Nanotube Clang 18 23 Dec Clang 17.0.2 GCC 13.2 GCC 14 23 Dec 9 18 27 36 45 SE +/- 0.07, N = 3 SE +/- 0.20, N = 3 SE +/- 0.52, N = 3 SE +/- 0.27, N = 3 36.40 37.62 37.89 38.23 1. (CC) gcc options: -shared -fwrapv -O2 -O3 -march=native -lxc -lblas -lmpi
John The Ripper Test: bcrypt OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: bcrypt Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 40K 80K 120K 160K 200K SE +/- 2054.27, N = 3 SE +/- 1771.90, N = 6 SE +/- 2123.51, N = 4 SE +/- 798.06, N = 3 182570 181400 177062 173913 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
Kvazaar Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Super Fast Clang 17.0.2 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec 20 40 60 80 100 SE +/- 0.65, N = 3 SE +/- 0.58, N = 3 SE +/- 0.68, N = 3 SE +/- 0.29, N = 3 92.52 92.02 89.12 88.23 -lpthread -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU GCC 13.2 Clang 18 23 Dec Clang 17.0.2 1200 2400 3600 4800 6000 SE +/- 61.07, N = 4 SE +/- 37.06, N = 3 SE +/- 37.89, N = 3 5480.25 5271.52 5230.49 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
GROMACS Implementation: MPI CPU - Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2023 Implementation: MPI CPU - Input: water_GMX50_bare GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 11.20 10.82 10.70 1. (CXX) g++ options: -O3 -march=native
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU GCC 13.2 Clang 18 23 Dec Clang 17.0.2 3 6 9 12 15 SE +/- 0.10, N = 4 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 8.75 9.09 9.16 -fno-strict-overflow -fwrapv - MIN: 5.37 / MAX: 26.49 MIN: 5.51 / MAX: 25.76 MIN: 5.67 / MAX: 27.63 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 4K GCC 13.2 GCC 14 23 Dec Clang 18 23 Dec Clang 17.0.2 40 80 120 160 200 SE +/- 2.26, N = 15 SE +/- 2.39, N = 4 SE +/- 1.78, N = 15 SE +/- 1.99, N = 3 199.54 199.29 194.92 190.79 1. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
uvg266 Video Input: Bosphorus 4K - Video Preset: Super Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Super Fast Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 16 32 48 64 80 SE +/- 0.29, N = 3 SE +/- 0.25, N = 3 SE +/- 0.45, N = 3 SE +/- 0.14, N = 3 72.62 71.84 69.71 69.54 1. (CXX) g++ options: -O3 -march=native
OpenSSL Algorithm: SHA256 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: SHA256 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec Clang 17.0.2 30000M 60000M 90000M 120000M 150000M SE +/- 366849309.72, N = 3 SE +/- 321788378.42, N = 3 SE +/- 271320016.95, N = 3 SE +/- 323275121.51, N = 3 129800447513 128629387223 125384626833 124526197107 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Very Fast Clang 17.0.2 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec 20 40 60 80 100 SE +/- 0.37, N = 3 SE +/- 0.40, N = 3 SE +/- 1.06, N = 3 SE +/- 0.65, N = 3 89.69 89.00 86.89 86.05 -lpthread -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 2023.03.14 Test: Blowfish Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 40K 80K 120K 160K 200K SE +/- 1422.62, N = 3 SE +/- 1555.73, N = 3 SE +/- 258.75, N = 3 SE +/- 164.19, N = 3 181091 180170 175544 173760 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -lm -lrt -lz -ldl -lcrypt -lbz2
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 0.459 0.918 1.377 1.836 2.295 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.04 2.01 1.98 1.96 -lpng16 -ljpeg -ltiff -lpng16 -ljpeg -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
VVenC Video Input: Bosphorus 4K - Video Preset: Fast OpenBenchmarking.org Frames Per Second, More Is Better VVenC 1.9 Video Input: Bosphorus 4K - Video Preset: Fast GCC 14 23 Dec GCC 13.2 Clang 17.0.2 3 6 9 12 15 SE +/- 0.019, N = 3 SE +/- 0.090, N = 3 SE +/- 0.023, N = 3 9.102 9.038 8.747 -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects -flto=thin 1. (CXX) g++ options: -O3 -march=native
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU Clang 18 23 Dec Clang 17.0.2 GCC 13.2 9 18 27 36 45 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 SE +/- 0.43, N = 5 38.94 39.38 40.45 MIN: 26.83 / MAX: 59.8 MIN: 24.17 / MAX: 80.88 -fno-strict-overflow -fwrapv - MIN: 20.38 / MAX: 57.81 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
uvg266 Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Slow Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec GCC 13.2 7 14 21 28 35 SE +/- 0.20, N = 3 SE +/- 0.18, N = 3 SE +/- 0.17, N = 3 SE +/- 0.08, N = 3 32.01 31.60 31.58 30.82 1. (CXX) g++ options: -O3 -march=native
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU Clang 18 23 Dec Clang 17.0.2 GCC 13.2 500 1000 1500 2000 2500 SE +/- 13.82, N = 3 SE +/- 2.50, N = 3 SE +/- 24.51, N = 5 2463.91 2436.02 2372.40 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 0 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 11 22 33 44 55 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.42, N = 3 SE +/- 0.28, N = 3 47.37 47.79 48.05 49.18 1. (CXX) g++ options: -O3 -fPIC -march=native -lm
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.15, N = 3 SE +/- 0.23, N = 3 SE +/- 0.23, N = 3 25.62 25.65 26.17 26.60 1. (CXX) g++ options: -O3 -fPIC -march=native -lm
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec GCC 13.2 30 60 90 120 150 SE +/- 0.58, N = 3 SE +/- 0.68, N = 3 SE +/- 0.79, N = 3 SE +/- 1.70, N = 15 109.12 109.58 110.56 113.11 -mabm -mabm 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mavx512f -mavx512cd -mavx512vl -mavx512bw -mavx512dq -mavx512ifma -mavx512vbmi -mrdrnd -mbmi -mbmi2 -madx -O3 -std=c99 -pedantic -march=native -lm -lreadline
Zstd Compression Compression Level: 12 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Decompression Speed GCC 13.2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec 500 1000 1500 2000 2500 SE +/- 26.26, N = 3 SE +/- 30.79, N = 3 SE +/- 29.73, N = 3 SE +/- 10.68, N = 3 2212.9 2173.3 2151.0 2136.2 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
uvg266 Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Medium Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec GCC 13.2 8 16 24 32 40 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.18, N = 3 35.23 34.91 34.66 34.05 1. (CXX) g++ options: -O3 -march=native
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Clang 18 23 Dec Clang 17.0.2 GCC 13.2 2 4 6 8 10 SE +/- 0.061, N = 3 SE +/- 0.033, N = 3 SE +/- 0.037, N = 3 5.848 5.868 6.050 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec 150 300 450 600 750 SE +/- 0.67, N = 3 SE +/- 1.73, N = 3 SE +/- 2.33, N = 3 SE +/- 1.20, N = 3 690 685 675 667 1. (CC) gcc options: -fopenmp -O3 -march=native -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lzstd -lm -lpthread
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 12 - Input: Bosphorus 4K GCC 13.2 Clang 17.0.2 Clang 18 23 Dec GCC 14 23 Dec 50 100 150 200 250 SE +/- 0.51, N = 3 SE +/- 1.47, N = 13 SE +/- 1.52, N = 3 SE +/- 1.12, N = 3 212.00 208.92 205.93 205.10 1. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
uvg266 Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better uvg266 0.4.1 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 16 32 48 64 80 SE +/- 0.24, N = 3 SE +/- 0.27, N = 3 SE +/- 0.15, N = 3 SE +/- 0.51, N = 3 73.72 73.25 71.62 71.37 1. (CXX) g++ options: -O3 -march=native
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100 Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec GCC 13.2 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.12, N = 3 15.73 15.65 15.37 15.24 -lpng16 -ljpeg -ltiff -lpng16 -ljpeg -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Decompression Speed GCC 13.2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec 400 800 1200 1600 2000 SE +/- 2.12, N = 3 SE +/- 5.93, N = 3 SE +/- 14.06, N = 3 SE +/- 18.21, N = 3 1895.8 1866.6 1856.6 1837.3 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Memcached Set To Get Ratio: 1:10 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:10 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec GCC 13.2 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 27110.93, N = 3 SE +/- 18523.18, N = 3 SE +/- 50152.31, N = 3 SE +/- 44027.28, N = 3 6108890.58 6092998.10 5956401.51 5921751.45 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 1.0 Encoder Speed: 6 Clang 17.0.2 GCC 13.2 GCC 14 23 Dec Clang 18 23 Dec 0.4835 0.967 1.4505 1.934 2.4175 SE +/- 0.002, N = 3 SE +/- 0.004, N = 3 SE +/- 0.005, N = 3 SE +/- 0.006, N = 3 2.087 2.116 2.142 2.149 1. (CXX) g++ options: -O3 -fPIC -march=native -lm
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 4 - Input: Bosphorus 4K Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec GCC 13.2 3 6 9 12 15 SE +/- 0.063, N = 3 SE +/- 0.096, N = 5 SE +/- 0.065, N = 3 SE +/- 0.076, N = 3 9.872 9.717 9.667 9.589 1. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
OpenSSL Algorithm: SHA512 OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: SHA512 Clang 18 23 Dec Clang 17.0.2 GCC 13.2 GCC 14 23 Dec 9000M 18000M 27000M 36000M 45000M SE +/- 11847693.41, N = 3 SE +/- 29437974.38, N = 3 SE +/- 55003825.70, N = 3 SE +/- 7258386.62, N = 3 43912408803 43131468240 43028797080 42698789480 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
Zstd Compression Compression Level: 12 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 12 - Compression Speed GCC 13.2 Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec 90 180 270 360 450 SE +/- 4.45, N = 3 SE +/- 2.30, N = 3 SE +/- 3.96, N = 3 SE +/- 4.56, N = 3 416.1 414.4 411.4 405.5 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Liquid-DSP Threads: 192 - Buffer Length: 256 - Filter Length: 512 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 1.6 Threads: 192 - Buffer Length: 256 - Filter Length: 512 Clang 18 23 Dec GCC 13.2 Clang 17.0.2 GCC 14 23 Dec 300M 600M 900M 1200M 1500M SE +/- 4115148.17, N = 3 SE +/- 5921430.01, N = 3 SE +/- 4870432.33, N = 3 SE +/- 7348998.42, N = 3 1528766667 1496100000 1495833333 1491466667 1. (CC) gcc options: -O3 -march=native -pthread -lm -lc -lliquid
SMHasher Hash: MeowHash x86_64 AES-NI OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI GCC 13.2 GCC 14 23 Dec Clang 18 23 Dec Clang 17.0.2 15K 30K 45K 60K 75K SE +/- 715.67, N = 3 SE +/- 626.56, N = 6 SE +/- 980.00, N = 3 SE +/- 966.63, N = 3 68597.56 68248.31 67945.38 67078.43 -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects -flto=thin -flto=thin 1. (CXX) g++ options: -O3 -march=native
simdjson Throughput Test: TopTweet OpenBenchmarking.org GB/s, More Is Better simdjson 2.0 Throughput Test: TopTweet GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.10, N = 3 SE +/- 0.09, N = 6 9.72 9.59 9.51 1. (CXX) g++ options: -O3 -march=native
SVT-AV1 Encoder Mode: Preset 13 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.8 Encoder Mode: Preset 13 - Input: Bosphorus 4K GCC 13.2 Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec 50 100 150 200 250 SE +/- 0.96, N = 3 SE +/- 0.72, N = 3 SE +/- 1.82, N = 15 SE +/- 2.03, N = 3 208.82 208.71 205.98 204.33 1. (CXX) g++ options: -O3 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 23Jun2022 Model: 20k Atoms GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 10 20 30 40 50 SE +/- 0.20, N = 3 SE +/- 0.22, N = 3 SE +/- 0.23, N = 3 42.45 42.37 41.66 1. (CXX) g++ options: -O3 -march=native -lm -ldl
Xmrig Variant: KawPow - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: KawPow - Hash Count: 1M GCC 14 23 Dec Clang 17.0.2 GCC 13.2 Clang 18 23 Dec 12K 24K 36K 48K 60K SE +/- 668.49, N = 3 SE +/- 640.77, N = 3 SE +/- 417.45, N = 3 SE +/- 529.15, N = 3 57660.1 57018.3 56883.5 56651.0 -static-libgcc -static-libstdc++ -funroll-loops -static-libgcc -static-libstdc++ -funroll-loops 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 4K 8K 12K 16K 20K SE +/- 35.94, N = 3 SE +/- 14.36, N = 3 SE +/- 15.90, N = 3 18002.34 17698.62 17696.86 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec GCC 13.2 4K 8K 12K 16K 20K SE +/- 45.07, N = 3 SE +/- 98.79, N = 3 SE +/- 42.11, N = 3 SE +/- 22.99, N = 5 17310.2 17246.0 17044.4 17018.5 1. (CC) gcc options: -O3
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 1.2173 2.4346 3.6519 4.8692 6.0865 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.32 5.41 5.41 -fno-strict-overflow -fwrapv - MIN: 3.18 / MAX: 23.99 MIN: 2.92 / MAX: 24.06 MIN: 3.22 / MAX: 23.18 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 0.1418 0.2836 0.4254 0.5672 0.709 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 0.62 0.63 0.63 -fno-strict-overflow -fwrapv - MIN: 0.2 / MAX: 20.88 MIN: 0.18 / MAX: 18.68 MIN: 0.21 / MAX: 18.55 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
ASTC Encoder Preset: Thorough OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Clang 17.0.2 GCC 13.2 Clang 18 23 Dec 16 32 48 64 80 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 70.01 69.84 68.90 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU GCC 13.2 Clang 18 23 Dec Clang 17.0.2 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.16, N = 3 SE +/- 0.13, N = 3 25.45 25.80 25.82 -fno-strict-overflow -fwrapv - MIN: 13.56 / MAX: 47.82 MIN: 13.56 / MAX: 46.4 MIN: 12.71 / MAX: 45.92 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU GCC 13.2 Clang 18 23 Dec Clang 17.0.2 400 800 1200 1600 2000 SE +/- 4.24, N = 3 SE +/- 11.87, N = 3 SE +/- 9.44, N = 3 1883.57 1857.83 1856.67 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
Xmrig Variant: GhostRider - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: GhostRider - Hash Count: 1M Clang 17.0.2 GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec 3K 6K 9K 12K 15K SE +/- 36.45, N = 3 SE +/- 11.65, N = 3 SE +/- 43.77, N = 3 SE +/- 17.51, N = 3 13628.9 13625.2 13592.0 13438.4 -funroll-loops -static-libgcc -static-libstdc++ -static-libgcc -static-libstdc++ -funroll-loops 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 30 60 90 120 150 SE +/- 0.40, N = 3 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 141.26 142.62 143.24 -fno-strict-overflow -fwrapv - MIN: 43.59 / MAX: 209.89 MIN: 60.05 / MAX: 210.86 MIN: 53.57 / MAX: 210.54 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 70 140 210 280 350 SE +/- 1.01, N = 3 SE +/- 0.30, N = 3 SE +/- 0.04, N = 3 339.37 336.16 334.69 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 Clang 18 23 Dec GCC 13.2 Clang 17.0.2 GCC 14 23 Dec 300K 600K 900K 1200K 1500K SE +/- 595.23, N = 3 SE +/- 1093.03, N = 3 SE +/- 3224.17, N = 3 SE +/- 4067.66, N = 3 1552460.9 1541833.5 1538339.5 1532147.3 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org MP/s, More Is Better WebP Image Encode 1.2.4 Encode Settings: Quality 100, Lossless, Highest Compression Clang 18 23 Dec Clang 17.0.2 GCC 13.2 GCC 14 23 Dec 0.1778 0.3556 0.5334 0.7112 0.889 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.79 0.79 0.79 0.78 -lpng16 -ljpeg -ltiff -lpng16 -ljpeg -ltiff 1. (CC) gcc options: -fvisibility=hidden -O3 -march=native -lm
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Decompression Speed GCC 13.2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec 400 800 1200 1600 2000 SE +/- 19.09, N = 3 SE +/- 21.26, N = 3 SE +/- 23.70, N = 3 SE +/- 21.40, N = 3 1795.5 1776.6 1774.3 1773.2 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Memcached Set To Get Ratio: 1:100 OpenBenchmarking.org Ops/sec, More Is Better Memcached 1.6.19 Set To Get Ratio: 1:100 Clang 17.0.2 GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec 1.7M 3.4M 5.1M 6.8M 8.5M SE +/- 54728.52, N = 3 SE +/- 44302.45, N = 3 SE +/- 9027.10, N = 3 SE +/- 7633.51, N = 3 7774340.30 7735938.66 7695223.15 7679397.09 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19 - Compression Speed Clang 17.0.2 GCC 13.2 GCC 14 23 Dec Clang 18 23 Dec 6 12 18 24 30 SE +/- 0.12, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 25.0 24.9 24.7 24.7 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 2 4 6 8 10 SE +/- 0.0327, N = 3 SE +/- 0.0190, N = 3 SE +/- 0.0210, N = 3 7.2724 7.2323 7.1900 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenSSL Algorithm: AES-256-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: AES-256-GCM GCC 14 23 Dec GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 200000M 400000M 600000M 800000M 1000000M SE +/- 458494386.59, N = 3 SE +/- 617348183.36, N = 3 SE +/- 367647705.83, N = 3 SE +/- 745364268.21, N = 3 821035343690 819163695240 816930832563 811977109867 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
SMHasher Hash: t1ha0_aes_avx2 x86_64 OpenBenchmarking.org MiB/sec, More Is Better SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 GCC 14 23 Dec Clang 17.0.2 GCC 13.2 Clang 18 23 Dec 30K 60K 90K 120K 150K SE +/- 1656.41, N = 3 SE +/- 1814.82, N = 3 SE +/- 759.57, N = 3 SE +/- 954.34, N = 3 132218.26 132159.77 131074.98 130792.83 -flto=auto -fno-fat-lto-objects -flto=thin -flto=auto -fno-fat-lto-objects -flto=thin 1. (CXX) g++ options: -O3 -march=native
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.2 Video Input: Bosphorus 4K - Video Preset: Ultra Fast GCC 13.2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec 20 40 60 80 100 SE +/- 0.61, N = 3 SE +/- 0.18, N = 3 SE +/- 0.35, N = 3 SE +/- 0.73, N = 3 94.70 94.59 94.29 93.72 -lpthread -lpthread 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O3 -march=native -lm -lrt
Xmrig Variant: CryptoNight-Femto UPX2 - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Femto UPX2 - Hash Count: 1M GCC 13.2 Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec 12K 24K 36K 48K 60K SE +/- 150.17, N = 3 SE +/- 155.80, N = 3 SE +/- 136.66, N = 3 SE +/- 216.50, N = 3 56592.8 56300.8 56155.2 56023.0 -static-libgcc -static-libstdc++ -funroll-loops -static-libgcc -static-libstdc++ -funroll-loops 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.4 Compression Level: 19, Long Mode - Compression Speed GCC 14 23 Dec Clang 18 23 Dec Clang 17.0.2 GCC 13.2 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 11.8 11.8 11.8 11.7 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -O3 -march=native -pthread -lz -llzma
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Monero - Hash Count: 1M GCC 13.2 Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec 12K 24K 36K 48K 60K SE +/- 228.27, N = 3 SE +/- 154.69, N = 3 SE +/- 234.92, N = 3 SE +/- 215.49, N = 3 56279.6 55888.6 55867.9 55839.5 -static-libgcc -static-libstdc++ -funroll-loops -static-libgcc -static-libstdc++ -funroll-loops 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
Xmrig Variant: CryptoNight-Heavy - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: CryptoNight-Heavy - Hash Count: 1M GCC 13.2 GCC 14 23 Dec Clang 17.0.2 Clang 18 23 Dec 12K 24K 36K 48K 60K SE +/- 147.72, N = 3 SE +/- 185.10, N = 3 SE +/- 146.78, N = 3 SE +/- 91.23, N = 3 56361.0 56126.3 56105.9 55924.5 -static-libgcc -static-libstdc++ -static-libgcc -static-libstdc++ -funroll-loops -funroll-loops 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Clang 17.0.2 GCC 13.2 Clang 18 23 Dec 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.08, N = 3 SE +/- 0.33, N = 3 93.05 93.18 93.71 MIN: 43.63 / MAX: 147.75 -fno-strict-overflow -fwrapv - MIN: 45.56 / MAX: 146.45 MIN: 39.51 / MAX: 151.45 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Clang 17.0.2 GCC 13.2 Clang 18 23 Dec 110 220 330 440 550 SE +/- 0.40, N = 3 SE +/- 0.42, N = 3 SE +/- 1.83, N = 3 515.15 514.54 511.63 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU GCC 13.2 Clang 18 23 Dec Clang 17.0.2 20K 40K 60K 80K 100K SE +/- 733.05, N = 3 SE +/- 50.71, N = 3 SE +/- 567.66, N = 3 113554.50 113505.56 112991.73 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU GCC 13.2 Clang 18 23 Dec Clang 17.0.2 110 220 330 440 550 SE +/- 0.75, N = 3 SE +/- 0.22, N = 3 SE +/- 0.30, N = 3 487.79 489.66 490.20 -fno-strict-overflow -fwrapv - MIN: 394.16 / MAX: 515.77 MIN: 381.31 / MAX: 514.98 MIN: 249.93 / MAX: 516.28 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU GCC 13.2 Clang 18 23 Dec Clang 17.0.2 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 98.10 97.72 97.62 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenSSL Algorithm: AES-128-GCM OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.1 Algorithm: AES-128-GCM GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec Clang 17.0.2 200000M 400000M 600000M 800000M 1000000M SE +/- 227590943.13, N = 3 SE +/- 926361343.56, N = 3 SE +/- 712012274.52, N = 3 SE +/- 1012640703.78, N = 3 948573686080 946233938740 944539664203 944090667870 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
PETSc Test: Streams OpenBenchmarking.org MB/s, More Is Better PETSc 3.19 Test: Streams GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 40K 80K 120K 160K 200K SE +/- 272.88, N = 3 SE +/- 138.55, N = 3 SE +/- 20.67, N = 3 183886.95 183268.53 183176.56 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -fPIC -O3 -O2 -lpthread -lpciaccess -lm
OpenSSL Algorithm: RSA4096 OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.1 Algorithm: RSA4096 GCC 13.2 Clang 18 23 Dec Clang 17.0.2 GCC 14 23 Dec 11K 22K 33K 44K 55K SE +/- 84.27, N = 3 SE +/- 80.27, N = 3 SE +/- 91.28, N = 3 SE +/- 103.69, N = 3 50251.7 50206.9 50097.7 50065.0 -Qunused-arguments -Qunused-arguments 1. (CC) gcc options: -pthread -m64 -O3 -march=native -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Clang 17.0.2 Clang 18 23 Dec GCC 13.2 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 9.67 9.67 9.70 MIN: 4.96 / MAX: 29.01 MIN: 5.1 / MAX: 28.3 -fno-strict-overflow -fwrapv - MIN: 4.82 / MAX: 28.19 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.21 Variant: Wownero - Hash Count: 1M GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec Clang 17.0.2 15K 30K 45K 60K 75K SE +/- 161.46, N = 3 SE +/- 161.43, N = 3 SE +/- 267.90, N = 3 SE +/- 205.42, N = 3 71393.6 71242.7 71240.6 71216.1 -static-libgcc -static-libstdc++ -static-libgcc -static-libstdc++ -funroll-loops -funroll-loops 1. (CXX) g++ options: -O3 -march=native -fexceptions -fno-rtti -maes -Ofast -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 8.03 8.05 8.05 -fno-strict-overflow -fwrapv - MIN: 4.11 / MAX: 25.57 MIN: 4.4 / MAX: 25.17 MIN: 4.56 / MAX: 25.34 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 1300 2600 3900 5200 6500 SE +/- 20.52, N = 3 SE +/- 28.17, N = 3 SE +/- 23.74, N = 3 5964.98 5952.83 5951.95 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU GCC 13.2 Clang 17.0.2 Clang 18 23 Dec 2K 4K 6K 8K 10K SE +/- 32.34, N = 3 SE +/- 35.14, N = 3 SE +/- 27.69, N = 3 9919.18 9912.53 9909.42 -fno-strict-overflow -fwrapv 1. (CXX) g++ options: -fPIC -O3 -march=native -fsigned-char -ffunction-sections -fdata-sections -shared -ldl
Redis Test: SET - Parallel Connections: 500 OpenBenchmarking.org Requests Per Second, More Is Better Redis 7.0.4 Test: SET - Parallel Connections: 500 GCC 14 23 Dec Clang 18 23 Dec GCC 13.2 Clang 17.0.2 700K 1400K 2100K 2800K 3500K SE +/- 22198.55, N = 3 SE +/- 21571.11, N = 3 SE +/- 53058.07, N = 15 SE +/- 37397.13, N = 15 3175906.70 3090972.67 3079293.25 2829400.83 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -march=native
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 4K Clang 18 23 Dec Clang 17.0.2 GCC 13.2 GCC 14 23 Dec 50 100 150 200 250 SE +/- 1.77, N = 3 SE +/- 0.19, N = 3 SE +/- 8.63, N = 12 SE +/- 0.67, N = 3 235.76 232.28 224.12 218.02 1. (CC) gcc options: -O3 -fcommon -march=native -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SMHasher Hash: MeowHash x86_64 AES-NI OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: MeowHash x86_64 AES-NI Clang 17.0.2 GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec 8 16 24 32 40 SE +/- 0.40, N = 3 SE +/- 0.24, N = 6 SE +/- 0.24, N = 3 SE +/- 0.45, N = 3 34.11 34.18 34.26 34.76 -flto=thin -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects -flto=thin 1. (CXX) g++ options: -O3 -march=native
SMHasher Hash: t1ha0_aes_avx2 x86_64 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: t1ha0_aes_avx2 x86_64 Clang 17.0.2 GCC 14 23 Dec Clang 18 23 Dec GCC 13.2 4 8 12 16 20 SE +/- 0.15, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 15.25 15.43 15.57 15.64 -flto=thin -flto=auto -fno-fat-lto-objects -flto=thin -flto=auto -fno-fat-lto-objects 1. (CXX) g++ options: -O3 -march=native
SMHasher Hash: FarmHash32 x86_64 AVX OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: FarmHash32 x86_64 AVX GCC 14 23 Dec GCC 13.2 Clang 18 23 Dec Clang 17.0.2 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.03, N = 3 SE +/- 0.21, N = 3 SE +/- 0.09, N = 3 19.86 20.19 22.07 22.56 -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects -flto=thin -flto=thin 1. (CXX) g++ options: -O3 -march=native
SMHasher Hash: FarmHash128 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: FarmHash128 Clang 17.0.2 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 SE +/- 0.17, N = 15 SE +/- 0.12, N = 3 25.13 25.25 35.54 35.68 -flto=thin -flto=thin -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects 1. (CXX) g++ options: -O3 -march=native
SMHasher Hash: SHA3-256 OpenBenchmarking.org cycles/hash, Fewer Is Better SMHasher 2022-08-22 Hash: SHA3-256 Clang 17.0.2 Clang 18 23 Dec GCC 13.2 GCC 14 23 Dec 300 600 900 1200 1500 SE +/- 7.46, N = 7 SE +/- 8.35, N = 3 SE +/- 14.31, N = 4 SE +/- 8.88, N = 3 812.79 817.90 1353.92 1356.53 -flto=thin -flto=thin -flto=auto -fno-fat-lto-objects -flto=auto -fno-fat-lto-objects 1. (CXX) g++ options: -O3 -march=native
Phoronix Test Suite v10.8.4