Tests for a future article.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2012152-HA-GCCZNVER322 GCC Znver3 Compiler Optimization Levels - Phoronix Test Suite GCC Znver3 Compiler Optimization Levels Tests for a future article.
HTML result view exported from: https://openbenchmarking.org/result/2012152-HA-GCCZNVER322&grs&rdt .
GCC Znver3 Compiler Optimization Levels Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS) AMD Starship/Matisse 16GB 2000GB Corsair Force MP600 AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz) AMD Navi 10 HDMI Audio ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.10.0-051000rc6daily20201205-generic (x86_64) 20201204 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 21.0.0-devel (git-1a53572 2020-12-09 focal-oibaf-ppa) (LLVM 11.0.0) 1.2.145 GCC 11.0.0 20201213 ext4 3840x2160 OpenBenchmarking.org Environment Details - -O3 -march=znver3: CXXFLAGS="-O3 -march=znver3" CFLAGS="-O3 -march=znver3" - -O3 -march=znver2: CXXFLAGS="-O3 -march=znver2" CFLAGS="-O3 -march=znver2" - -O3 -march=x86-64: CXXFLAGS="-O3 -march=x86-64" CFLAGS="-O3 -march=x86-64" - -O3 -maech=znver3 -flto: CXXFLAGS="-O3 -march=znver3 -flto" CFLAGS="-O3 -march=znver3 -flto" - -Ofast -march=znver3 -flto: CXXFLAGS="-Ofast -march=znver3 -flto" CFLAGS="-Ofast -march=znver3 -flto" - -O2 -march=znver3 -flto: CXXFLAGS="-O2 -march=znver3 -flto" CFLAGS="-O2 -march=znver3 -flto" Compiler Details - --disable-multilib --enable-checking=release Disk Details - -O3 -march=znver3: NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009 Python Details - -O3 -march=znver3: Python 2.7.18 + Python 3.8.5 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
GCC Znver3 Compiler Optimization Levels build-imagemagick: Time To Compile scimark2: Dense LU Matrix Factorization scimark2: Monte Carlo scimark2: Jacobi Successive Over-Relaxation c-ray: Total Time - 4K, 16 Rays Per Pixel mrbayes: Primate Phylogeny Analysis graphics-magick: Sharpen libraw: Post-Processing Benchmark scimark2: Composite scimark2: Sparse Matrix Multiply bullet: 1000 Convex dav1d: Chimera 1080p 10-bit bullet: Convex Trimesh cpp-perf-bench: Math Library bullet: Prim Trimesh fftw: Stock - 1D FFT Size 4096 bullet: 136 Ragdolls bullet: 3000 Fall bullet: 1000 Stack graphics-magick: Enhanced graphics-magick: Resizing fftw: Stock - 2D FFT Size 4096 encode-mp3: WAV To MP3 aobench: 2048 x 2048 - Total Time cpp-perf-bench: Function Objects graphics-magick: Rotate scimark2: Fast Fourier Transform mt-dgemm: Sustained Floating-Point Rate graphics-magick: Noise-Gaussian bullet: Raytests sqlite-speedtest: Timed Time - Size 1,000 hmmer: Pfam Database Search kvazaar: Bosphorus 1080p - Ultra Fast hint: FLOAT smallpt: Global Illumination Renderer; 128 Samples graphics-magick: Swirl kvazaar: Bosphorus 1080p - Very Fast tscp: AI Chess Performance coremark: CoreMark Size 666 - Iterations Per Second kvazaar: Bosphorus 4K - Ultra Fast kvazaar: Bosphorus 4K - Very Fast aom-av1: Speed 8 Realtime nginx: Static Web Page Serving aom-av1: Speed 4 Realtime webp: Quality 100 kvazaar: Bosphorus 1080p - Slow graphics-magick: HWB Color Space kvazaar: Bosphorus 4K - Medium kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 1080p - Medium aom-av1: Speed 5 Two-Pass daphne: OpenMP - NDT Mapping cpp-perf-bench: Atol mafft: Multiple Sequence Alignment - LSU RNA build-php: Time To Compile compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 daphne: OpenMP - Points2Image dav1d: Chimera 1080p svt-vp9: Visual Quality Optimized - Bosphorus 1080p svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p dav1d: Summer Nature 1080p cpp-perf-bench: Stepanov Vector x264: H.264 Video Encoding x265: Bosphorus 4K x265: Bosphorus 1080p dav1d: Summer Nature 4K svt-av1: Enc Mode 8 - 1080p svt-av1: Enc Mode 4 - 1080p build-mplayer: Time To Compile compress-zstd: 3 compress-7zip: Compress Speed Test apache: Static Web Page Serving build-ffmpeg: Time To Compile tachyon: Total Time compress-zstd: 19 openssl: RSA 4096-bit Performance build-apache: Time To Compile aircrack-ng: cpp-perf-bench: Stepanov Abstraction cpp-perf-bench: Ctype rnnoise: encode-flac: WAV To FLAC himeno: Poisson Pressure Solver vpxenc: Speed 5 vpxenc: Speed 0 crafty: Elapsed Time fftw: Float + SSE - 2D FFT Size 4096 fftw: Float + SSE - 1D FFT Size 4096 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 18.859 10128.76 883.30 3043.46 25.254 76.317 361 73.83 3958.17 4779.43 2.672805 261.39 0.731618 222.245 0.656643 13702 1.710504 2.651887 3.265452 432 2135 9314.1 5.445 25.065 11.198 1064 467.20 7.307093 441 1.663293 40.643 85.020 200.12 530415720.66861 4.673 1196 111.50 2055431 716026.620271 54.73 30.31 62.33 51446.92 2.64 1.648 44.91 1115 11.74 11.58 46.42 4.69 971.31 35.813 7.115 36.676 23.603 30333.660297739 879.20 230.15 239.32 914.92 42.380 199.02 27.54 89.13 240.24 60.383 7.014 19.798 5066.0 95844 46267.92 30.871 49.4827 44.2 4849.5 15.138 75202.344 18.864 40.081 16.563 6.534 4918.506823 39.78 10.03 11396837 32774 69819 19.370 12537.23 867.28 2972.33 25.251 75.697 377 75.26 4407.32 5128.66 3.197418 260.36 0.876382 220.550 0.786183 14096 2.041453 3.164171 3.890664 444 1907 8927.1 5.673 25.016 11.464 919 531.10 7.512189 434 1.785458 41.912 84.791 199.35 535659290.50880 4.677 1139 111.54 2010350 721620.067510 54.75 30.34 62.28 48905.01 2.53 1.684 44.97 1064 11.72 11.59 46.38 4.79 964.72 35.332 7.324 36.753 23.415 30133.174304110 893.72 223.97 234.58 932.67 41.717 200.66 27.81 88.80 241.87 59.944 6.956 19.598 5028.1 95715 46212.92 30.811 49.2891 44.2 4857.9 15.189 75330.448 20.635 40.712 14.070 6.616 5341.802444 39.66 10.75 11460428 30461 71917 19.000 9747.10 897.30 2473.84 31.364 77.074 225 63.90 3660.74 4634.54 3.627370 187.65 0.930682 223.874 0.815518 12436 2.184048 3.331015 4.077866 382 1721 8169.2 5.787 29.991 11.328 987 550.92 6.484557 426 1.792863 41.948 85.596 198.84 536140751.38618 5.068 1094 111.77 2035599 717480.237613 54.43 30.48 60.07 51463.87 2.62 1.726 45.75 1067 11.86 11.69 46.74 4.84 931.03 36.377 7.399 35.348 23.173 29933.960506534 903.91 224.11 235.02 921.07 42.383 202.78 27.63 88.92 243.36 59.840 6.960 19.817 5042.5 95316 45996.80 30.711 49.5027 44.3 4847.3 15.177 75091.643 19.848 41.935 14.523 6.441 4972.634733 33.71 9.44 11161599 63.476 8601.61 1625.41 2552.11 25.480 73.919 370 73.73 3855.30 4016.10 2.625405 0.708918 219.480 0.640668 15584 1.771787 2.69281 3.319278 445 1906 10125 5.789 25.848 11.473 948 460.20 7.696089 430 1.632244 41.305 84.119 203.89 525844746.56770 4.656 1156 116.07 2082271 736850.433639 56.12 31.44 62.52 51640.99 2.63 1.636 46.30 1110 12.03 11.88 47.32 4.90 971.45 35.329 7.286 24.093 29966.049994027 224.25 235.83 41.579 27.75 89.08 60.224 6.972 5043.1 95172 49.4275 44.2 4836.6 75160.065 18.884 39.867 13.860 6.606 5235.075565 12020364 31709 64468 66.843 9843.10 1893.64 2998.47 27.342 45.274 328 75.23 4101.89 5235.17 2.629167 0.708037 217.509 0.640757 12149.0 1.769900 2.692827 3.316208 449 1901 8755.9 5.282 24.505 11.259 961 539.06 7.758952 504 1.627688 41.127 76.943 220.99 483531659.13924 4.602 1201 121.74 2187546 728279.792211 58.69 32.40 63.76 49006.08 2.66 1.660 47.25 1119 12.27 12.12 48.54 4.81 969.91 36.784 7.341 23.710 29964.692392405 228.43 237.74 41.827 27.32 88.21 59.761 6.934 5030.2 95872 49.5398 44.2 4839.5 75105.172 18.550 40.206 6.233 4974.883078 12258866 31754 63882 50.407 5574.17 891.29 1577.67 46.419 79.513 377 49.32 2924.23 6037.39 2.573982 0.69347 283.694 0.627687 15232 1.737217 2.632108 3.255847 476 1854 9718.2 6.473 27.363 13.449 888 540.63 7.345638 445 1.594243 45.485 84.929 201.85 533589946.00456 4.607 1153 113.41 2153845 681281.706242 54.91 30.76 62.08 51831.76 2.67 1.648 45.68 1111 11.84 11.68 47.04 4.87 970.46 35.385 7.365 23.336 29486.004018584 225.36 236.33 42.033 27.48 87.71 59.679 6.957 5045.8 95588 49.5202 44.1 4852.6 75257.164 25.795 48.606 15.654 6.186 5357.653937 11650472 31717 72763 OpenBenchmarking.org
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 15 30 45 60 75 SE +/- 0.07, N = 3 SE +/- 0.18, N = 15 SE +/- 0.03, N = 3 SE +/- 0.32, N = 3 SE +/- 0.30, N = 3 SE +/- 0.34, N = 3 18.86 19.37 19.00 63.48 66.84 50.41
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 3K 6K 9K 12K 15K SE +/- 581.61, N = 3 SE +/- 14.88, N = 3 SE +/- 36.04, N = 3 SE +/- 1258.08, N = 3 SE +/- 85.21, N = 3 SE +/- 41.97, N = 3 10128.76 12537.23 9747.10 8601.61 9843.10 5574.17 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 400 800 1200 1600 2000 SE +/- 7.40, N = 3 SE +/- 2.47, N = 3 SE +/- 1.74, N = 3 SE +/- 249.49, N = 3 SE +/- 19.53, N = 3 SE +/- 7.74, N = 3 883.30 867.28 897.30 1625.41 1893.64 891.29 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 700 1400 2100 2800 3500 SE +/- 34.33, N = 3 SE +/- 14.93, N = 3 SE +/- 10.49, N = 3 SE +/- 398.20, N = 3 SE +/- 27.35, N = 3 SE +/- 18.54, N = 3 3043.46 2972.33 2473.84 2552.11 2998.47 1577.67 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm
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 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 11 22 33 44 55 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 25.25 25.25 31.36 25.48 27.34 46.42 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm -lpthread -O3
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 20 40 60 80 100 SE +/- 0.72, N = 9 SE +/- 0.64, N = 15 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.29, N = 3 SE +/- 0.19, N = 3 76.32 75.70 77.07 73.92 45.27 79.51 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 80 160 240 320 400 SE +/- 2.33, N = 3 SE +/- 1.20, N = 3 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 1.20, N = 3 361 377 225 370 328 377 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 20 40 60 80 100 SE +/- 1.48, N = 15 SE +/- 0.59, N = 3 SE +/- 0.24, N = 3 SE +/- 0.89, N = 3 SE +/- 0.56, N = 3 SE +/- 0.36, N = 3 73.83 75.26 63.90 73.73 75.23 49.32 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -fopenmp -ljpeg -lz -lm
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 900 1800 2700 3600 4500 SE +/- 35.50, N = 15 SE +/- 11.01, N = 3 SE +/- 12.53, N = 3 SE +/- 130.68, N = 12 SE +/- 33.94, N = 3 SE +/- 25.20, N = 3 3958.17 4407.32 3660.74 3855.30 4101.89 2924.23 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1300 2600 3900 5200 6500 SE +/- 18.73, N = 3 SE +/- 19.91, N = 3 SE +/- 14.37, N = 3 SE +/- 594.21, N = 3 SE +/- 33.83, N = 3 SE +/- 52.45, N = 3 4779.43 5128.66 4634.54 4016.10 5235.17 6037.39 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm
Bullet Physics Engine Test: 1000 Convex OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Convex -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.8162 1.6324 2.4486 3.2648 4.081 SE +/- 0.004286, N = 3 SE +/- 0.604893, N = 3 SE +/- 0.648498, N = 3 SE +/- 0.006441, N = 3 SE +/- 0.006861, N = 3 SE +/- 0.026939, N = 3 2.672805 3.197418 3.627370 2.625405 2.629167 2.573982 -march=znver3 -lglut -lGL -lGLU -march=znver2 -lglut -lGL -lGLU -march=x86-64 -lglut -lGL -lGLU -march=znver3 -flto -Ofast -march=znver3 -flto -lglut -lGL -lGLU -O2 -march=znver3 -flto -lglut -lGL -lGLU 1. (CXX) g++ options: -O3 -rdynamic
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Chimera 1080p 10-bit -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 60 120 180 240 300 SE +/- 0.57, N = 3 SE +/- 1.53, N = 3 SE +/- 0.69, N = 3 261.39 260.36 187.65 -march=znver3 - MIN: 173.03 / MAX: 490.65 -march=znver2 - MIN: 173.47 / MAX: 476.91 -march=x86-64 - MIN: 122.85 / MAX: 373.39 1. (CC) gcc options: -O3 -pthread
Bullet Physics Engine Test: Convex Trimesh OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Convex Trimesh -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.2094 0.4188 0.6282 0.8376 1.047 SE +/- 0.000878, N = 3 SE +/- 0.167457, N = 3 SE +/- 0.168559, N = 3 SE +/- 0.001768, N = 3 SE +/- 0.002714, N = 3 SE +/- 0.007502, N = 3 0.731618 0.876382 0.930682 0.708918 0.708037 0.693470 -march=znver3 -lglut -lGL -lGLU -march=znver2 -lglut -lGL -lGLU -march=x86-64 -lglut -lGL -lGLU -march=znver3 -flto -Ofast -march=znver3 -flto -lglut -lGL -lGLU -O2 -march=znver3 -flto -lglut -lGL -lGLU 1. (CXX) g++ options: -O3 -rdynamic
CppPerformanceBenchmarks Test: Math Library OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Math Library -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 60 120 180 240 300 SE +/- 0.77, N = 3 SE +/- 1.88, N = 3 SE +/- 2.74, N = 3 SE +/- 1.97, N = 3 SE +/- 2.13, N = 3 SE +/- 26.60, N = 9 222.25 220.55 223.87 219.48 217.51 283.69 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11
Bullet Physics Engine Test: Prim Trimesh OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Prim Trimesh -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.1835 0.367 0.5505 0.734 0.9175 SE +/- 0.001134, N = 3 SE +/- 0.149603, N = 3 SE +/- 0.146828, N = 3 SE +/- 0.001284, N = 3 SE +/- 0.002855, N = 3 SE +/- 0.006380, N = 3 0.656643 0.786183 0.815518 0.640668 0.640757 0.627687 -march=znver3 -lglut -lGL -lGLU -march=znver2 -lglut -lGL -lGLU -march=x86-64 -lglut -lGL -lGLU -march=znver3 -flto -Ofast -march=znver3 -flto -lglut -lGL -lGLU -O2 -march=znver3 -flto -lglut -lGL -lGLU 1. (CXX) g++ options: -O3 -rdynamic
FFTW Build: Stock - Size: 1D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 3K 6K 9K 12K 15K SE +/- 54.77, N = 3 SE +/- 75.72, N = 3 SE +/- 80.35, N = 3 SE +/- 105.64, N = 3 SE +/- 564.61, N = 15 SE +/- 16.50, N = 3 13702.0 14096.0 12436.0 15584.0 12149.0 15232.0 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -lm
Bullet Physics Engine Test: 136 Ragdolls OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 136 Ragdolls -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.4914 0.9828 1.4742 1.9656 2.457 SE +/- 0.003623, N = 3 SE +/- 0.384993, N = 3 SE +/- 0.385000, N = 3 SE +/- 0.002552, N = 3 SE +/- 0.004039, N = 3 SE +/- 0.024499, N = 3 1.710504 2.041453 2.184048 1.771787 1.769900 1.737217 -march=znver3 -lglut -lGL -lGLU -march=znver2 -lglut -lGL -lGLU -march=x86-64 -lglut -lGL -lGLU -march=znver3 -flto -Ofast -march=znver3 -flto -lglut -lGL -lGLU -O2 -march=znver3 -flto -lglut -lGL -lGLU 1. (CXX) g++ options: -O3 -rdynamic
Bullet Physics Engine Test: 3000 Fall OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 3000 Fall -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.7495 1.499 2.2485 2.998 3.7475 SE +/- 0.004533, N = 3 SE +/- 0.599476, N = 3 SE +/- 0.590113, N = 3 SE +/- 0.005845, N = 3 SE +/- 0.009048, N = 3 SE +/- 0.027956, N = 3 2.651887 3.164171 3.331015 2.692810 2.692827 2.632108 -march=znver3 -lglut -lGL -lGLU -march=znver2 -lglut -lGL -lGLU -march=x86-64 -lglut -lGL -lGLU -march=znver3 -flto -Ofast -march=znver3 -flto -lglut -lGL -lGLU -O2 -march=znver3 -flto -lglut -lGL -lGLU 1. (CXX) g++ options: -O3 -rdynamic
Bullet Physics Engine Test: 1000 Stack OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Stack -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.9175 1.835 2.7525 3.67 4.5875 SE +/- 0.005866, N = 3 SE +/- 0.728617, N = 3 SE +/- 0.721313, N = 3 SE +/- 0.006493, N = 3 SE +/- 0.007476, N = 3 SE +/- 0.032238, N = 3 3.265452 3.890664 4.077866 3.319278 3.316208 3.255847 -march=znver3 -lglut -lGL -lGLU -march=znver2 -lglut -lGL -lGLU -march=x86-64 -lglut -lGL -lGLU -march=znver3 -flto -Ofast -march=znver3 -flto -lglut -lGL -lGLU -O2 -march=znver3 -flto -lglut -lGL -lGLU 1. (CXX) g++ options: -O3 -rdynamic
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 100 200 300 400 500 SE +/- 5.29, N = 3 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 0.88, N = 3 SE +/- 0.33, N = 3 432 444 382 445 449 476 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 500 1000 1500 2000 2500 SE +/- 8.37, N = 3 SE +/- 1.20, N = 3 SE +/- 14.34, N = 3 SE +/- 1.76, N = 3 SE +/- 1.15, N = 3 2135 1907 1721 1906 1901 1854 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
FFTW Build: Stock - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 2K 4K 6K 8K 10K SE +/- 18.57, N = 3 SE +/- 15.97, N = 3 SE +/- 312.57, N = 12 SE +/- 25.21, N = 3 SE +/- 86.92, N = 3 SE +/- 96.35, N = 3 9314.1 8927.1 8169.2 10125.0 8755.9 9718.2 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 2 4 6 8 10 SE +/- 0.016, N = 3 SE +/- 0.239, N = 15 SE +/- 0.023, N = 3 SE +/- 0.319, N = 15 SE +/- 0.022, N = 3 SE +/- 0.033, N = 3 5.445 5.673 5.787 5.789 5.282 6.473 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm
AOBench Size: 2048 x 2048 - Total Time OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 7 14 21 28 35 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 1.25, N = 15 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.23, N = 3 25.07 25.02 29.99 25.85 24.51 27.36 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm -O3
CppPerformanceBenchmarks Test: Function Objects OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Function Objects -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 3 6 9 12 15 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 SE +/- 0.93, N = 15 11.20 11.46 11.33 11.47 11.26 13.45 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 200 400 600 800 1000 SE +/- 5.70, N = 3 SE +/- 27.55, N = 15 SE +/- 8.62, N = 3 SE +/- 2.65, N = 3 SE +/- 7.88, N = 3 SE +/- 37.25, N = 15 1064 919 987 948 961 888 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 120 240 360 480 600 SE +/- 4.02, N = 3 SE +/- 2.93, N = 3 SE +/- 1.10, N = 3 SE +/- 71.30, N = 3 SE +/- 4.57, N = 3 SE +/- 5.61, N = 3 467.20 531.10 550.92 460.20 539.06 540.63 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lm
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 2 4 6 8 10 SE +/- 0.086169, N = 3 SE +/- 0.069362, N = 3 SE +/- 0.050043, N = 15 SE +/- 0.089342, N = 6 SE +/- 0.087025, N = 3 SE +/- 0.071987, N = 3 7.307093 7.512189 6.484557 7.696089 7.758952 7.345638 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -O3 -march=native -fopenmp
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 110 220 330 440 550 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 4.91, N = 12 SE +/- 1.53, N = 3 SE +/- 1.53, N = 3 SE +/- 1.45, N = 3 441 434 426 430 504 445 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Bullet Physics Engine Test: Raytests OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Raytests -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.4034 0.8068 1.2102 1.6136 2.017 SE +/- 0.002327, N = 3 SE +/- 0.101438, N = 15 SE +/- 0.075833, N = 15 SE +/- 0.002589, N = 3 SE +/- 0.004567, N = 3 SE +/- 0.014472, N = 3 1.663293 1.785458 1.792863 1.632244 1.627688 1.594243 -march=znver3 -lglut -lGL -lGLU -march=znver2 -lglut -lGL -lGLU -march=x86-64 -lglut -lGL -lGLU -march=znver3 -flto -Ofast -march=znver3 -flto -lglut -lGL -lGLU -O2 -march=znver3 -flto -lglut -lGL -lGLU 1. (CXX) g++ options: -O3 -rdynamic
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 10 20 30 40 50 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 SE +/- 0.35, N = 3 SE +/- 0.51, N = 3 SE +/- 2.71, N = 15 40.64 41.91 41.95 41.31 41.13 45.49 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -ldl -lz -lpthread
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.09, N = 3 85.02 84.79 85.60 84.12 76.94 84.93 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -lhmmer -leasel -lm
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 50 100 150 200 250 SE +/- 0.25, N = 3 SE +/- 0.35, N = 3 SE +/- 0.89, N = 3 SE +/- 0.63, N = 3 SE +/- 0.20, N = 3 SE +/- 0.55, N = 3 200.12 199.35 198.84 203.89 220.99 201.85 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Hierarchical INTegration Test: FLOAT OpenBenchmarking.org QUIPs, More Is Better Hierarchical INTegration 1.0 Test: FLOAT -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 110M 220M 330M 440M 550M SE +/- 5853530.73, N = 3 SE +/- 5929051.95, N = 3 SE +/- 4969986.40, N = 3 SE +/- 794515.24, N = 3 SE +/- 31530973.95, N = 9 SE +/- 4842392.51, N = 3 530415720.67 535659290.51 536140751.39 525844746.57 483531659.14 533589946.00 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -O3 -march=native -lm
Smallpt Global Illumination Renderer; 128 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1.1403 2.2806 3.4209 4.5612 5.7015 SE +/- 0.025, N = 3 SE +/- 0.016, N = 3 SE +/- 0.018, N = 3 SE +/- 0.012, N = 3 SE +/- 0.005, N = 3 SE +/- 0.009, N = 3 4.673 4.677 5.068 4.656 4.602 4.607 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -fopenmp -O3
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 300 600 900 1200 1500 SE +/- 4.36, N = 3 SE +/- 4.18, N = 3 SE +/- 2.85, N = 3 SE +/- 2.96, N = 3 SE +/- 2.40, N = 3 SE +/- 2.60, N = 3 1196 1139 1094 1156 1201 1153 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 30 60 90 120 150 SE +/- 0.17, N = 3 SE +/- 0.15, N = 3 SE +/- 0.30, N = 3 SE +/- 0.16, N = 3 SE +/- 0.24, N = 3 SE +/- 0.14, N = 3 111.50 111.54 111.77 116.07 121.74 113.41 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 500K 1000K 1500K 2000K 2500K SE +/- 12293.02, N = 5 SE +/- 47716.25, N = 25 SE +/- 10113.82, N = 5 SE +/- 49215.47, N = 25 SE +/- 9982.18, N = 5 SE +/- 19185.63, N = 5 2055431 2010350 2035599 2082271 2187546 2153845 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -O3 -march=native
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 160K 320K 480K 640K 800K SE +/- 449.85, N = 3 SE +/- 1896.73, N = 3 SE +/- 371.91, N = 3 SE +/- 1257.49, N = 3 SE +/- 1316.80, N = 3 SE +/- 5589.70, N = 3 716026.62 721620.07 717480.24 736850.43 728279.79 681281.71 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -march=znver3 -flto 1. (CC) gcc options: -O2 -lrt" -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 13 26 39 52 65 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.11, N = 3 SE +/- 0.13, N = 3 SE +/- 0.10, N = 3 SE +/- 0.31, N = 3 54.73 54.75 54.43 56.12 58.69 54.91 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 8 16 24 32 40 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 30.31 30.34 30.48 31.44 32.40 30.76 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
AOM AV1 Encoder Mode: Speed 8 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 8 Realtime -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 14 28 42 56 70 SE +/- 0.65, N = 3 SE +/- 0.23, N = 3 SE +/- 0.99, N = 15 SE +/- 0.59, N = 9 SE +/- 0.25, N = 3 SE +/- 0.79, N = 3 62.33 62.28 60.07 62.52 63.76 62.08 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 11K 22K 33K 44K 55K SE +/- 101.68, N = 3 SE +/- 1677.08, N = 12 SE +/- 186.11, N = 3 SE +/- 95.73, N = 3 SE +/- 1017.37, N = 15 SE +/- 77.42, N = 3 51446.92 48905.01 51463.87 51640.99 49006.08 51831.76 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
AOM AV1 Encoder Mode: Speed 4 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Realtime -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.6008 1.2016 1.8024 2.4032 3.004 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 7 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 2.64 2.53 2.62 2.63 2.66 2.67 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 0.3884 0.7768 1.1652 1.5536 1.942 SE +/- 0.017, N = 3 SE +/- 0.002, N = 3 SE +/- 0.006, N = 3 SE +/- 0.013, N = 3 SE +/- 0.004, N = 3 SE +/- 0.014, N = 3 1.648 1.684 1.726 1.636 1.660 1.648 -O3 -march=znver3 -ltiff -O3 -march=znver2 -ltiff -O3 -march=x86-64 -ltiff -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fvisibility=hidden -pthread -lm -ljpeg -lpng16
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Slow -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 11 22 33 44 55 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 44.91 44.97 45.75 46.30 47.25 45.68 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 200 400 600 800 1000 SE +/- 4.41, N = 3 SE +/- 1.53, N = 3 SE +/- 3.00, N = 3 SE +/- 1.45, N = 3 SE +/- 8.84, N = 3 SE +/- 2.65, N = 3 1115 1064 1067 1110 1119 1111 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Medium -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 11.74 11.72 11.86 12.03 12.27 11.84 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Slow -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 11.58 11.59 11.69 11.88 12.12 11.68 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Medium -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 11 22 33 44 55 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 46.42 46.38 46.74 47.32 48.54 47.04 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -lpthread -lm -lrt
AOM AV1 Encoder Mode: Speed 5 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 5 Two-Pass -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1.1025 2.205 3.3075 4.41 5.5125 SE +/- 0.07, N = 15 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 12 SE +/- 0.05, N = 3 4.69 4.79 4.84 4.90 4.81 4.87 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: NDT Mapping OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: NDT Mapping -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 200 400 600 800 1000 SE +/- 2.43, N = 3 SE +/- 0.72, N = 3 SE +/- 3.82, N = 3 SE +/- 2.69, N = 3 SE +/- 3.18, N = 3 SE +/- 2.71, N = 3 971.31 964.72 931.03 971.45 969.91 970.46 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
CppPerformanceBenchmarks Test: Atol OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Atol -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 8 16 24 32 40 SE +/- 0.38, N = 3 SE +/- 0.49, N = 3 SE +/- 0.37, N = 3 SE +/- 0.35, N = 3 SE +/- 1.55, N = 15 SE +/- 0.39, N = 3 35.81 35.33 36.38 35.33 36.78 35.39 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11
Timed MAFFT Alignment Multiple Sequence Alignment - LSU RNA OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 2 4 6 8 10 SE +/- 0.068, N = 3 SE +/- 0.117, N = 3 SE +/- 0.101, N = 3 SE +/- 0.086, N = 3 SE +/- 0.096, N = 4 SE +/- 0.062, N = 15 7.115 7.324 7.399 7.286 7.341 7.365 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.4.2 Time To Compile -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 8 16 24 32 40 SE +/- 0.50, N = 4 SE +/- 0.49, N = 5 SE +/- 0.07, N = 3 36.68 36.75 35.35
XZ Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.28, N = 3 SE +/- 0.17, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 SE +/- 0.24, N = 3 23.60 23.42 23.17 24.09 23.71 23.34 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -fvisibility=hidden
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Points2Image OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Points2Image -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 6K 12K 18K 24K 30K SE +/- 132.80, N = 3 SE +/- 334.66, N = 15 SE +/- 382.84, N = 3 SE +/- 432.33, N = 14 SE +/- 241.17, N = 15 SE +/- 474.52, N = 3 30333.66 30133.17 29933.96 29966.05 29964.69 29486.00 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Chimera 1080p -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 200 400 600 800 1000 SE +/- 2.44, N = 3 SE +/- 2.12, N = 3 SE +/- 1.99, N = 3 879.20 893.72 903.91 -march=znver3 - MIN: 689.9 / MAX: 1074.02 -march=znver2 - MIN: 699.85 / MAX: 1086.55 -march=x86-64 - MIN: 707.97 / MAX: 1105.39 1. (CC) gcc options: -O3 -pthread
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 50 100 150 200 250 SE +/- 0.72, N = 3 SE +/- 0.63, N = 3 SE +/- 0.95, N = 3 SE +/- 0.12, N = 3 SE +/- 0.74, N = 3 SE +/- 1.47, N = 3 230.15 223.97 224.11 224.25 228.43 225.36 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 50 100 150 200 250 SE +/- 3.14, N = 4 SE +/- 1.99, N = 12 SE +/- 2.28, N = 12 SE +/- 2.07, N = 12 SE +/- 2.03, N = 13 SE +/- 2.16, N = 12 239.32 234.58 235.02 235.83 237.74 236.33 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Summer Nature 1080p -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 200 400 600 800 1000 SE +/- 6.51, N = 3 SE +/- 1.62, N = 3 SE +/- 10.42, N = 3 914.92 932.67 921.07 -march=znver3 - MIN: 671.69 / MAX: 1004.13 -march=znver2 - MIN: 678.72 / MAX: 1016.6 -march=x86-64 - MIN: 615.39 / MAX: 1021.01 1. (CC) gcc options: -O3 -pthread
CppPerformanceBenchmarks Test: Stepanov Vector OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Vector -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 10 20 30 40 50 SE +/- 0.15, N = 3 SE +/- 0.46, N = 3 SE +/- 0.45, N = 3 SE +/- 0.25, N = 3 SE +/- 0.45, N = 3 SE +/- 0.40, N = 3 42.38 41.72 42.38 41.58 41.83 42.03 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 40 80 120 160 200 SE +/- 2.81, N = 4 SE +/- 1.66, N = 15 SE +/- 1.58, N = 15 199.02 200.66 202.78 -march=znver3 -march=znver2 -march=x86-64 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 27.54 27.81 27.63 27.75 27.32 27.48 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 20 40 60 80 100 SE +/- 0.11, N = 3 SE +/- 0.30, N = 3 SE +/- 0.36, N = 3 SE +/- 0.18, N = 3 SE +/- 0.25, N = 3 SE +/- 0.33, N = 3 89.13 88.80 88.92 89.08 88.21 87.71 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Summer Nature 4K -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 50 100 150 200 250 SE +/- 2.87, N = 3 SE +/- 0.26, N = 3 SE +/- 0.92, N = 3 240.24 241.87 243.36 -march=znver3 - MIN: 152.32 / MAX: 251.91 -march=znver2 - MIN: 177.93 / MAX: 250.43 -march=x86-64 - MIN: 175.57 / MAX: 254.29 1. (CC) gcc options: -O3 -pthread
SVT-AV1 Encoder Mode: Enc Mode 8 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 14 28 42 56 70 SE +/- 0.64, N = 3 SE +/- 0.11, N = 3 SE +/- 0.14, N = 3 SE +/- 0.22, N = 3 SE +/- 0.04, N = 3 SE +/- 0.46, N = 3 60.38 59.94 59.84 60.22 59.76 59.68 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
SVT-AV1 Encoder Mode: Enc Mode 4 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 2 4 6 8 10 SE +/- 0.033, N = 3 SE +/- 0.038, N = 3 SE +/- 0.018, N = 3 SE +/- 0.010, N = 3 SE +/- 0.057, N = 3 SE +/- 0.055, N = 3 7.014 6.956 6.960 6.972 6.934 6.957 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
Timed MPlayer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.4 Time To Compile -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 5 10 15 20 25 SE +/- 0.22, N = 6 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 19.80 19.60 19.82
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1100 2200 3300 4400 5500 SE +/- 12.00, N = 3 SE +/- 7.47, N = 3 SE +/- 40.40, N = 3 SE +/- 11.65, N = 3 SE +/- 7.82, N = 3 SE +/- 31.10, N = 3 5066.0 5028.1 5042.5 5043.1 5030.2 5045.8 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -lz -llzma
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 20K 40K 60K 80K 100K SE +/- 286.46, N = 3 SE +/- 115.21, N = 3 SE +/- 378.23, N = 3 SE +/- 384.90, N = 3 SE +/- 132.15, N = 3 SE +/- 249.42, N = 3 95844 95715 95316 95172 95872 95588 1. (CXX) g++ options: -pipe -lpthread
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 10K 20K 30K 40K 50K SE +/- 521.28, N = 3 SE +/- 362.23, N = 3 SE +/- 201.19, N = 3 46267.92 46212.92 45996.80 -march=znver3 -march=znver2 -march=x86-64 1. (CC) gcc options: -shared -fPIC -pthread -O3
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 7 14 21 28 35 SE +/- 0.13, N = 3 SE +/- 0.28, N = 13 SE +/- 0.10, N = 3 30.87 30.81 30.71
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 11 22 33 44 55 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.06, N = 3 49.48 49.29 49.50 49.43 49.54 49.52 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 10 20 30 40 50 SE +/- 0.10, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 44.2 44.2 44.3 44.2 44.2 44.1 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -lz -llzma
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1000 2000 3000 4000 5000 SE +/- 3.15, N = 3 SE +/- 7.55, N = 3 SE +/- 7.21, N = 3 SE +/- 8.42, N = 3 SE +/- 2.72, N = 3 SE +/- 3.01, N = 3 4849.5 4857.9 4847.3 4836.6 4839.5 4852.6 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -m64 -lssl -lcrypto -ldl
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 4 8 12 16 20 SE +/- 0.20, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 15.14 15.19 15.18
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.5.2 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 16K 32K 48K 64K 80K SE +/- 57.69, N = 3 SE +/- 19.16, N = 3 SE +/- 83.30, N = 3 SE +/- 20.34, N = 3 SE +/- 44.68, N = 3 SE +/- 96.05, N = 3 75202.34 75330.45 75091.64 75160.07 75105.17 75257.16 1. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -fcommon -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
CppPerformanceBenchmarks Test: Stepanov Abstraction OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Abstraction -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 6 12 18 24 30 SE +/- 0.20, N = 3 SE +/- 1.21, N = 15 SE +/- 0.88, N = 15 SE +/- 0.08, N = 3 SE +/- 0.11, N = 3 SE +/- 1.80, N = 15 18.86 20.64 19.85 18.88 18.55 25.80 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11
CppPerformanceBenchmarks Test: Ctype OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Ctype -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 11 22 33 44 55 SE +/- 0.18, N = 3 SE +/- 1.66, N = 15 SE +/- 2.39, N = 15 SE +/- 0.32, N = 15 SE +/- 0.37, N = 3 SE +/- 3.45, N = 15 40.08 40.71 41.94 39.87 40.21 48.61 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -O3 -std=c++11
RNNoise OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -O2 -march=znver3 -flto 4 8 12 16 20 SE +/- 1.10, N = 15 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 3 SE +/- 0.65, N = 15 16.56 14.07 14.52 13.86 15.65 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pedantic -fvisibility=hidden
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 2 4 6 8 10 SE +/- 0.131, N = 25 SE +/- 0.175, N = 25 SE +/- 0.166, N = 25 SE +/- 0.232, N = 25 SE +/- 0.047, N = 5 SE +/- 0.043, N = 5 6.534 6.616 6.441 6.606 6.233 6.186 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1100 2200 3300 4400 5500 SE +/- 247.48, N = 12 SE +/- 26.98, N = 3 SE +/- 199.91, N = 15 SE +/- 179.16, N = 12 SE +/- 307.73, N = 12 SE +/- 203.31, N = 12 4918.51 5341.80 4972.63 5235.08 4974.88 5357.65 -march=znver3 -march=znver2 -march=x86-64 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -O3 -mavx2
VP9 libvpx Encoding Speed: Speed 5 OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 5 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.29, N = 3 SE +/- 1.60, N = 14 39.78 39.66 33.71 -march=znver3 -march=znver2 -march=x86-64 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
VP9 libvpx Encoding Speed: Speed 0 OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 0 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 3 6 9 12 15 SE +/- 0.29, N = 14 SE +/- 0.09, N = 3 SE +/- 0.41, N = 15 10.03 10.75 9.44 -march=znver3 -march=znver2 -march=x86-64 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time -O3 -march=znver3 -O3 -march=znver2 -O3 -march=x86-64 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 3M 6M 9M 12M 15M SE +/- 376923.05, N = 12 SE +/- 425288.16, N = 15 SE +/- 505442.39, N = 15 SE +/- 25650.81, N = 3 SE +/- 110552.33, N = 3 SE +/- 388230.44, N = 12 11396837 11460428 11161599 12020364 12258866 11650472 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 -O3 -march=znver3 -O3 -march=znver2 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 7K 14K 21K 28K 35K SE +/- 428.13, N = 3 SE +/- 945.33, N = 9 SE +/- 261.90, N = 3 SE +/- 225.04, N = 3 SE +/- 342.00, N = 7 32774 30461 31709 31754 31717 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 -O3 -march=znver3 -O3 -march=znver2 -O3 -maech=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 16K 32K 48K 64K 80K SE +/- 842.00, N = 3 SE +/- 675.82, N = 3 SE +/- 3728.41, N = 12 SE +/- 3515.17, N = 15 SE +/- 1067.12, N = 3 69819 71917 64468 63882 72763 -O3 -march=znver3 -O3 -march=znver2 -O3 -march=znver3 -flto -Ofast -march=znver3 -flto -O2 -march=znver3 -flto 1. (CC) gcc options: -pthread -lm
Phoronix Test Suite v10.8.4