Fedora Linux -fno-omit-frame-pointer Performance Impact AMD Ryzen 5 5500U testing Tuxedo laptop on Fedora 36 looking at performance cost of "-fno-omit-frame-pointer" as part of CFLAGS/CXXFLAGS. Benchmarks by Michael Larabel.
HTML result view exported from: https://openbenchmarking.org/result/2206274-NE-FEDORACFL13&sro&grr .
Fedora Linux -fno-omit-frame-pointer Performance Impact Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution -O2 -O2 -fno-omit-frame-pointer AMD Ryzen 5 5500U @ 4.06GHz (6 Cores / 12 Threads) NB01 NL5xNU (1.07.11RTR1 BIOS) AMD Renoir/Cezanne 16GB Samsung SSD 970 EVO Plus 500GB AMD Lucienne 512MB (1800/400MHz) AMD Renoir Radeon HD Audio Realtek RTL8111/8168/8411 + Intel Wi-Fi 6 AX200 Fedora Linux 36 5.18.6-200.fc36.x86_64 (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.1.2 (LLVM 14.0.0 DRM 3.46) GCC 12.1.1 20220507 btrfs 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Environment Details - -O2: CXXFLAGS=-O2 DEBUGINFOD_URLS=https://debuginfod.fedoraproject.org/ CFLAGS=-O2 - -O2 -fno-omit-frame-pointer: CXXFLAGS="-O2 -fno-omit-frame-pointer" DEBUGINFOD_URLS=https://debuginfod.fedoraproject.org/ CFLAGS="-O2 -fno-omit-frame-pointer" Compiler Details - --build=x86_64-redhat-linux --disable-libunwind-exceptions --enable-__cxa_atexit --enable-bootstrap --enable-cet --enable-checking=release --enable-gnu-indirect-function --enable-gnu-unique-object --enable-initfini-array --enable-languages=c,c++,fortran,objc,obj-c++,ada,go,d,lto --enable-libstdcxx-backtrace --enable-link-serialization=1 --enable-multilib --enable-offload-defaulted --enable-offload-targets=nvptx-none --enable-plugin --enable-shared --enable-threads=posix --mandir=/usr/share/man --with-arch_32=i686 --with-build-config=bootstrap-lto --with-gcc-major-version-only --with-linker-hash-style=gnu --with-tune=generic --without-cuda-driver Disk Details - NONE / compress=zstd:1,relatime,rw,seclabel,space_cache=v2,ssd,subvol=/home,subvolid=256 / Block Size: 4096 Processor Details - Scaling Governor: amd-pstate schedutil (Boost: Enabled) - CPU Microcode: 0x8608103 Graphics Details - -O2: BAR1 / Visible vRAM Size: 512 MB - -O2 -fno-omit-frame-pointer: BAR1 / Visible vRAM Size: 512 MB - vBIOS Version: 113-LUCIENNE-016 Python Details - Python 3.10.5 Security Details - SELinux + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Fedora Linux -fno-omit-frame-pointer Performance Impact svt-hevc: 1 - Bosphorus 4K astcenc: Exhaustive mt-dgemm: Sustained Floating-Point Rate ngspice: C7552 c-ray: Total Time - 4K, 16 Rays Per Pixel gcrypt: x264: Bosphorus 4K svt-av1: Preset 4 - Bosphorus 4K kripke: stargate: 96000 - 512 stargate: 96000 - 1024 ngspice: C2670 mrbayes: Primate Phylogeny Analysis daphne: OpenMP - Points2Image svt-vp9: VMAF Optimized - Bosphorus 4K stargate: 480000 - 512 stargate: 44100 - 512 stargate: 480000 - 1024 stargate: 44100 - 1024 onednn: Recurrent Neural Network Training - f32 - CPU sysbench: CPU compress-lz4: 3 - Decompression Speed compress-lz4: 3 - Compression Speed povray: Trace Time sqlite-speedtest: Timed Time - Size 1,000 compress-zstd: 19, Long Mode - Decompression Speed compress-zstd: 19, Long Mode - Compression Speed compress-zstd: 19 - Decompression Speed compress-zstd: 19 - Compression Speed cryptopp: Unkeyed Algorithms pjsip: INVITE pjsip: OPTIONS, Stateful ddnet: 1920 x 1080 - Fullscreen - OpenGL 3.3 - Default - Multeasymap graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Noise-Gaussian graphics-magick: Swirl liquid-dsp: 4 - 256 - 57 graphics-magick: Resizing graphics-magick: Rotate himeno: Poisson Pressure Solver postmark: Disk Transaction Performance svt-av1: Preset 8 - Bosphorus 4K botan: AES-256 - Decrypt botan: AES-256 compress-zstd: 8, Long Mode - Decompression Speed compress-zstd: 8, Long Mode - Compression Speed espeak: Text-To-Speech Synthesis compress-zstd: 3 - Compression Speed compress-zstd: 3, Long Mode - Decompression Speed compress-zstd: 3, Long Mode - Compression Speed aobench: 2048 x 2048 - Total Time botan: ChaCha20Poly1305 - Decrypt botan: ChaCha20Poly1305 botan: Blowfish - Decrypt botan: Blowfish botan: Twofish - Decrypt botan: Twofish compress-lz4: 1 - Decompression Speed compress-lz4: 1 - Compression Speed botan: CAST-256 - Decrypt botan: CAST-256 botan: KASUMI - Decrypt botan: KASUMI svt-hevc: 7 - Bosphorus 4K daphne: OpenMP - NDT Mapping encode-flac: WAV To FLAC redis: SET svt-vp9: Visual Quality Optimized - Bosphorus 4K scimark2: Composite redis: GET sysbench: RAM / Memory onednn: Deconvolution Batch shapes_1d - f32 - CPU svt-vp9: PSNR/SSIM Optimized - Bosphorus 4K encode-wavpack: WAV To WavPack liquid-dsp: 2 - 256 - 57 daphne: OpenMP - Euclidean Cluster liquid-dsp: 1 - 256 - 57 liquid-dsp: 8 - 256 - 57 liquid-dsp: 12 - 256 - 57 astcenc: Thorough svt-av1: Preset 10 - Bosphorus 4K svt-hevc: 10 - Bosphorus 4K pjsip: OPTIONS, Stateless onednn: IP Shapes 1D - f32 - CPU encode-opus: WAV To Opus Encode svt-av1: Preset 12 - Bosphorus 4K encode-mp3: WAV To MP3 yquake2: Software CPU Color Light - On - On - 1920 x 1080 yquake2: Software CPU - On - On - 1920 x 1080 onednn: Convolution Batch Shapes Auto - f32 - CPU astcenc: Medium onednn: Deconvolution Batch shapes_3d - f32 - CPU yquake2: OpenGL 3.x - On - On - 1920 x 1080 yquake2: OpenGL ES 3.x - On - On - 1920 x 1080 scimark2: Jacobi Successive Over-Relaxation scimark2: Dense LU Matrix Factorization scimark2: Sparse Matrix Multiply scimark2: Fast Fourier Transform scimark2: Monte Carlo -O2 -O2 -fno-omit-frame-pointer 0.97 139.6550 0.788976 288.793 244.918 215.370 14.35 0.987 20822210 1.113083 1.175738 139.663 131.731 18321.878984164 28.86 1.534235 1.526909 1.559068 1.580043 6153.02 12696.34 7842.4 54.39 81.030 83.240 2770.1 16.9 2669.8 19.5 383.588997 2690 4356 557.98 83 131 169 335 233046667 598 606 4425.831157 5282 13.354 5348.250 5435.968 3488.2 145.3 30.017 1391.3 3396.4 335.5 37.159 756.317 762.163 429.884 417.773 343.041 345.587 8190.6 7273.84 91.210 92.598 83.532 86.885 20.21 664.26 15.925 1709750.00 23.15 1581.17 2317168.00 10939.82 11.4215 30.82 12.338 127233333 1108.24 63592333 310600000 322190000 14.7127 38.311 40.84 157897 9.18063 7.711 57.252 9.027 78.6 84.2 22.0844 5.5136 11.8017 647.7 658.9 1968.87 2285.03 2701.34 208.27 742.34 0.96 151.7993 0.643800 290.722 245.279 219.476 14.17 0.970 20654480 1.109181 1.139809 139.889 132.660 18292.204158398 28.35 1.500155 1.528819 1.513763 1.548565 6417.22 12498.56 7789.7 54.10 86.371 84.694 2757.3 16.9 2661.1 19.3 368.997383 2655 4301 552.68 82 129 166 330 206968000 600 606 4242.328104 5102 13.059 754.641 754.615 3496.8 143.3 30.376 1364.0 3414.3 322.2 37.581 400.685 402.122 280.332 276.979 249.432 251.443 8171.2 7223.79 82.044 82.040 74.335 78.038 19.93 655.77 17.372 344012.95 22.30 1524.29 363907.59 2526.02 12.2529 30.13 12.486 123466667 1095.49 61948667 300993333 309426667 15.0202 37.400 40.51 142790 9.09057 7.782 56.148 9.113 78.5 84.1 21.9364 5.7500 12.3610 623.8 641.9 1945.40 2126.45 2603.66 210.73 735.22 OpenBenchmarking.org
SVT-HEVC Tuning: 1 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 0.2183 0.4366 0.6549 0.8732 1.0915 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.97 0.96 1. (CC) gcc options: -O2 -fPIE -fPIC -O3 -pie -rdynamic -lpthread -lrt
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Exhaustive -O2 -O2 -fno-omit-frame-pointer 30 60 90 120 150 SE +/- 0.37, N = 3 SE +/- 1.44, N = 12 139.66 151.80 1. (CXX) g++ options: -O2 -O3 -flto -pthread
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate -O2 -O2 -fno-omit-frame-pointer 0.1775 0.355 0.5325 0.71 0.8875 SE +/- 0.008876, N = 3 SE +/- 0.001837, N = 3 0.788976 0.643800 1. (CC) gcc options: -O3 -march=native -fopenmp -O2
Ngspice Circuit: C7552 OpenBenchmarking.org Seconds, Fewer Is Better Ngspice 34 Circuit: C7552 -O2 -O2 -fno-omit-frame-pointer 60 120 180 240 300 SE +/- 1.35, N = 3 SE +/- 0.32, N = 3 288.79 290.72 1. (CC) gcc options: -O2 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE
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 -O2 -O2 -fno-omit-frame-pointer 50 100 150 200 250 SE +/- 0.29, N = 3 SE +/- 0.47, N = 3 244.92 245.28 1. (CC) gcc options: -lm -lpthread -O3 -O2
Gcrypt Library OpenBenchmarking.org Seconds, Fewer Is Better Gcrypt Library 1.9 -O2 -O2 -fno-omit-frame-pointer 50 100 150 200 250 SE +/- 0.81, N = 3 SE +/- 0.28, N = 3 215.37 219.48 1. (CC) gcc options: -O2 -fvisibility=hidden
x264 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x264 2022-02-22 Video Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 4 8 12 16 20 SE +/- 0.10, N = 12 SE +/- 0.10, N = 13 14.35 14.17 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -flto
SVT-AV1 Encoder Mode: Preset 4 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 4 - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 0.2221 0.4442 0.6663 0.8884 1.1105 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.987 0.970 1. (CXX) g++ options: -O2 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Kripke OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 -O2 -O2 -fno-omit-frame-pointer 4M 8M 12M 16M 20M SE +/- 29023.91, N = 3 SE +/- 42502.90, N = 3 20822210 20654480 1. (CXX) g++ options: -O2 -O3 -fopenmp
Stargate Digital Audio Workstation Sample Rate: 96000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 96000 - Buffer Size: 512 -O2 -O2 -fno-omit-frame-pointer 0.2504 0.5008 0.7512 1.0016 1.252 SE +/- 0.002150, N = 3 SE +/- 0.003576, N = 3 1.113083 1.109181 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: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 96000 - Buffer Size: 1024 -O2 -O2 -fno-omit-frame-pointer 0.2645 0.529 0.7935 1.058 1.3225 SE +/- 0.001752, N = 3 SE +/- 0.003041, N = 3 1.175738 1.139809 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
Ngspice Circuit: C2670 OpenBenchmarking.org Seconds, Fewer Is Better Ngspice 34 Circuit: C2670 -O2 -O2 -fno-omit-frame-pointer 30 60 90 120 150 SE +/- 0.39, N = 3 SE +/- 0.33, N = 3 139.66 139.89 1. (CC) gcc options: -O2 -fopenmp -lm -lstdc++ -lfftw3 -lXaw -lXmu -lXt -lXext -lX11 -lSM -lICE
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis -O2 -O2 -fno-omit-frame-pointer 30 60 90 120 150 SE +/- 0.49, N = 3 SE +/- 0.47, N = 3 131.73 132.66 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 -O2 -lm
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 -O2 -O2 -fno-omit-frame-pointer 4K 8K 12K 16K 20K SE +/- 100.97, N = 3 SE +/- 150.13, N = 3 18321.88 18292.20 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 7 14 21 28 35 SE +/- 0.28, N = 15 SE +/- 0.27, N = 15 28.86 28.35 1. (CC) gcc options: -O3 -fcommon -O2 -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Stargate Digital Audio Workstation Sample Rate: 480000 - Buffer Size: 512 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 480000 - Buffer Size: 512 -O2 -O2 -fno-omit-frame-pointer 0.3452 0.6904 1.0356 1.3808 1.726 SE +/- 0.002863, N = 3 SE +/- 0.002213, N = 3 1.534235 1.500155 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 21.10.9 Sample Rate: 44100 - Buffer Size: 512 -O2 -O2 -fno-omit-frame-pointer 0.344 0.688 1.032 1.376 1.72 SE +/- 0.004298, N = 3 SE +/- 0.006686, N = 3 1.526909 1.528819 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: 480000 - Buffer Size: 1024 OpenBenchmarking.org Render Ratio, More Is Better Stargate Digital Audio Workstation 21.10.9 Sample Rate: 480000 - Buffer Size: 1024 -O2 -O2 -fno-omit-frame-pointer 0.3508 0.7016 1.0524 1.4032 1.754 SE +/- 0.002546, N = 3 SE +/- 0.001433, N = 3 1.559068 1.513763 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 21.10.9 Sample Rate: 44100 - Buffer Size: 1024 -O2 -O2 -fno-omit-frame-pointer 0.3555 0.711 1.0665 1.422 1.7775 SE +/- 0.003221, N = 3 SE +/- 0.001721, N = 3 1.580043 1.548565 1. (CXX) g++ options: -lpthread -lsndfile -lm -O3 -march=native -ffast-math -funroll-loops -fstrength-reduce -fstrict-aliasing -finline-functions
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU -O2 -O2 -fno-omit-frame-pointer 1400 2800 4200 5600 7000 SE +/- 71.79, N = 3 SE +/- 80.48, N = 3 6153.02 6417.22 MIN: 5992.59 MIN: 6223.32 1. (CXX) g++ options: -O3 -march=native -O2 -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
Sysbench Test: CPU OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU -O2 -O2 -fno-omit-frame-pointer 3K 6K 9K 12K 15K SE +/- 0.52, N = 3 SE +/- 0.42, N = 3 12696.34 12498.56 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed -O2 -O2 -fno-omit-frame-pointer 2K 4K 6K 8K 10K SE +/- 8.06, N = 5 SE +/- 32.72, N = 4 7842.4 7789.7 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed -O2 -O2 -fno-omit-frame-pointer 12 24 36 48 60 SE +/- 0.59, N = 5 SE +/- 0.61, N = 4 54.39 54.10 1. (CC) gcc options: -O3
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.22, N = 3 SE +/- 0.98, N = 3 81.03 86.37 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -O2 -R/usr/lib -lXpm -lSM -lICE -lX11 -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.54, N = 3 83.24 84.69 1. (CC) gcc options: -O2 -lz
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed -O2 -O2 -fno-omit-frame-pointer 600 1200 1800 2400 3000 SE +/- 4.34, N = 3 SE +/- 5.52, N = 3 2770.1 2757.3 1. (CC) gcc options: -O2 -pthread -lz
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed -O2 -O2 -fno-omit-frame-pointer 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 16.9 16.9 1. (CC) gcc options: -O2 -pthread -lz
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Decompression Speed -O2 -O2 -fno-omit-frame-pointer 600 1200 1800 2400 3000 SE +/- 4.14, N = 3 SE +/- 1.15, N = 3 2669.8 2661.1 1. (CC) gcc options: -O2 -pthread -lz
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed -O2 -O2 -fno-omit-frame-pointer 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 19.5 19.3 1. (CC) gcc options: -O2 -pthread -lz
Crypto++ Test: Unkeyed Algorithms OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Unkeyed Algorithms -O2 -O2 -fno-omit-frame-pointer 80 160 240 320 400 SE +/- 0.09, N = 3 SE +/- 0.28, N = 3 383.59 369.00 1. (CXX) g++ options: -O2 -fPIC -pthread -pipe
PJSIP Method: INVITE OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: INVITE -O2 -O2 -fno-omit-frame-pointer 600 1200 1800 2400 3000 SE +/- 11.05, N = 3 SE +/- 5.90, N = 3 2690 2655 1. (CC) gcc options: -pthread -lSDL2 -lstdc++ -lopus -lssl -lcrypto -lm -lrt -lpthread -lasound -O2
PJSIP Method: OPTIONS, Stateful OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateful -O2 -O2 -fno-omit-frame-pointer 900 1800 2700 3600 4500 SE +/- 3.53, N = 3 SE +/- 7.00, N = 3 4356 4301 1. (CC) gcc options: -pthread -lSDL2 -lstdc++ -lopus -lssl -lcrypto -lm -lrt -lpthread -lasound -O2
DDraceNetwork Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap - Total Frame Time OpenBenchmarking.org Milliseconds, Fewer Is Better DDraceNetwork 15.8.1 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap - Total Frame Time -O2 -O2 -fno-omit-frame-pointer 3 6 9 12 15 Min: 1.19 / Avg: 1.81 / Max: 8.65 Min: 1.3 / Avg: 1.82 / Max: 8.74 1. (CXX) g++ options: -O2 -O3 -lrt -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
DDraceNetwork Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 15.8.1 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap -O2 -O2 -fno-omit-frame-pointer 120 240 360 480 600 SE +/- 1.79, N = 3 SE +/- 4.00, N = 3 557.98 552.68 1. (CXX) g++ options: -O2 -O3 -lrt -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 83 82 1. (CC) gcc options: -fopenmp -O2 -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced -O2 -O2 -fno-omit-frame-pointer 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 131 129 1. (CC) gcc options: -fopenmp -O2 -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian -O2 -O2 -fno-omit-frame-pointer 40 80 120 160 200 SE +/- 1.45, N = 3 SE +/- 0.33, N = 3 169 166 1. (CC) gcc options: -fopenmp -O2 -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl -O2 -O2 -fno-omit-frame-pointer 70 140 210 280 350 SE +/- 2.33, N = 3 SE +/- 0.88, N = 3 335 330 1. (CC) gcc options: -fopenmp -O2 -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
Liquid-DSP Threads: 4 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 4 - Buffer Length: 256 - Filter Length: 57 -O2 -O2 -fno-omit-frame-pointer 50M 100M 150M 200M 250M SE +/- 1699650.29, N = 3 SE +/- 3103085.28, N = 15 233046667 206968000 1. (CC) gcc options: -O3 -O2 -pthread -lm -lc -lliquid
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing -O2 -O2 -fno-omit-frame-pointer 130 260 390 520 650 SE +/- 1.86, N = 3 SE +/- 2.40, N = 3 598 600 1. (CC) gcc options: -fopenmp -O2 -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate -O2 -O2 -fno-omit-frame-pointer 130 260 390 520 650 SE +/- 0.33, N = 3 SE +/- 2.31, N = 3 606 606 1. (CC) gcc options: -fopenmp -O2 -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lpthread
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver -O2 -O2 -fno-omit-frame-pointer 900 1800 2700 3600 4500 SE +/- 47.90, N = 3 SE +/- 33.04, N = 3 4425.83 4242.33 1. (CC) gcc options: -O3 -O2 -mavx2
PostMark Disk Transaction Performance OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance -O2 -O2 -fno-omit-frame-pointer 1100 2200 3300 4400 5500 SE +/- 37.00, N = 3 SE +/- 0.00, N = 3 5282 5102 1. (CC) gcc options: -O3 -O2
SVT-AV1 Encoder Mode: Preset 8 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 8 - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 3 6 9 12 15 SE +/- 0.15, N = 3 SE +/- 0.19, N = 3 13.35 13.06 1. (CXX) g++ options: -O2 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
Botan Test: AES-256 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 - Decrypt -O2 -O2 -fno-omit-frame-pointer 1100 2200 3300 4400 5500 SE +/- 3.66, N = 3 SE +/- 0.15, N = 3 5348.25 754.64 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: AES-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 -O2 -O2 -fno-omit-frame-pointer 1200 2400 3600 4800 6000 SE +/- 6.09, N = 3 SE +/- 0.06, N = 3 5435.97 754.62 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Decompression Speed -O2 -O2 -fno-omit-frame-pointer 700 1400 2100 2800 3500 SE +/- 5.43, N = 3 SE +/- 2.19, N = 3 3488.2 3496.8 1. (CC) gcc options: -O2 -pthread -lz
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 8, Long Mode - Compression Speed -O2 -O2 -fno-omit-frame-pointer 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.29, N = 3 145.3 143.3 1. (CC) gcc options: -O2 -pthread -lz
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis -O2 -O2 -fno-omit-frame-pointer 7 14 21 28 35 SE +/- 0.07, N = 4 SE +/- 0.14, N = 4 30.02 30.38 1. (CC) gcc options: -O2 -std=c99 -lpthread -lm
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3 - Compression Speed -O2 -O2 -fno-omit-frame-pointer 300 600 900 1200 1500 SE +/- 11.98, N = 3 SE +/- 6.27, N = 3 1391.3 1364.0 1. (CC) gcc options: -O2 -pthread -lz
Zstd Compression Compression Level: 3, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3, Long Mode - Decompression Speed -O2 -O2 -fno-omit-frame-pointer 700 1400 2100 2800 3500 SE +/- 5.81, N = 3 SE +/- 6.77, N = 3 3396.4 3414.3 1. (CC) gcc options: -O2 -pthread -lz
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 3, Long Mode - Compression Speed -O2 -O2 -fno-omit-frame-pointer 70 140 210 280 350 SE +/- 0.19, N = 3 SE +/- 0.40, N = 3 335.5 322.2 1. (CC) gcc options: -O2 -pthread -lz
AOBench Size: 2048 x 2048 - Total Time OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time -O2 -O2 -fno-omit-frame-pointer 9 18 27 36 45 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 37.16 37.58 1. (CC) gcc options: -lm -O3 -O2
Botan Test: ChaCha20Poly1305 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 - Decrypt -O2 -O2 -fno-omit-frame-pointer 160 320 480 640 800 SE +/- 0.49, N = 3 SE +/- 0.17, N = 3 756.32 400.69 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: ChaCha20Poly1305 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 -O2 -O2 -fno-omit-frame-pointer 160 320 480 640 800 SE +/- 0.41, N = 3 SE +/- 0.35, N = 3 762.16 402.12 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Blowfish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish - Decrypt -O2 -O2 -fno-omit-frame-pointer 90 180 270 360 450 SE +/- 0.12, N = 3 SE +/- 0.45, N = 3 429.88 280.33 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Blowfish OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish -O2 -O2 -fno-omit-frame-pointer 90 180 270 360 450 SE +/- 0.19, N = 3 SE +/- 0.05, N = 3 417.77 276.98 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Twofish - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish - Decrypt -O2 -O2 -fno-omit-frame-pointer 70 140 210 280 350 SE +/- 0.12, N = 3 SE +/- 0.23, N = 3 343.04 249.43 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: Twofish OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish -O2 -O2 -fno-omit-frame-pointer 80 160 240 320 400 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 345.59 251.44 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
LZ4 Compression Compression Level: 1 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Decompression Speed -O2 -O2 -fno-omit-frame-pointer 2K 4K 6K 8K 10K SE +/- 44.10, N = 3 SE +/- 28.42, N = 3 8190.6 8171.2 1. (CC) gcc options: -O3
LZ4 Compression Compression Level: 1 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Compression Speed -O2 -O2 -fno-omit-frame-pointer 1600 3200 4800 6400 8000 SE +/- 20.57, N = 3 SE +/- 31.80, N = 3 7273.84 7223.79 1. (CC) gcc options: -O3
Botan Test: CAST-256 - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: CAST-256 - Decrypt -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.60, N = 3 SE +/- 0.03, N = 3 91.21 82.04 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: CAST-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: CAST-256 -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 92.60 82.04 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: KASUMI - Decrypt OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI - Decrypt -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 83.53 74.34 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Botan Test: KASUMI OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 86.89 78.04 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
SVT-HEVC Tuning: 7 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 20.21 19.93 1. (CC) gcc options: -O2 -fPIE -fPIC -O3 -pie -rdynamic -lpthread -lrt
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 -O2 -O2 -fno-omit-frame-pointer 140 280 420 560 700 SE +/- 2.10, N = 3 SE +/- 1.23, N = 3 664.26 655.77 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.3 WAV To FLAC -O2 -O2 -fno-omit-frame-pointer 4 8 12 16 20 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 15.93 17.37 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET -O2 -O2 -fno-omit-frame-pointer 400K 800K 1200K 1600K 2000K SE +/- 14263.08, N = 3 SE +/- 3363.41, N = 3 1709750.00 344012.95 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -O2
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 -O2 -O2 -fno-omit-frame-pointer 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 23.15 22.30 1. (CC) gcc options: -O3 -fcommon -O2 -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite -O2 -O2 -fno-omit-frame-pointer 300 600 900 1200 1500 SE +/- 1.80, N = 3 SE +/- 4.45, N = 3 1581.17 1524.29 1. (CC) gcc options: -O2 -lm
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: GET -O2 -O2 -fno-omit-frame-pointer 500K 1000K 1500K 2000K 2500K SE +/- 2206.51, N = 3 SE +/- 4094.53, N = 3 2317168.00 363907.59 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3 -O2
Sysbench Test: RAM / Memory OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory -O2 -O2 -fno-omit-frame-pointer 2K 4K 6K 8K 10K SE +/- 3.48, N = 3 SE +/- 6.05, N = 3 10939.82 2526.02 1. (CC) gcc options: -O2 -funroll-loops -rdynamic -ldl -laio -lm
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU -O2 -O2 -fno-omit-frame-pointer 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 11.42 12.25 MIN: 9.2 MIN: 9.87 1. (CXX) g++ options: -O3 -march=native -O2 -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
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 -O2 -O2 -fno-omit-frame-pointer 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 30.82 30.13 1. (CC) gcc options: -O3 -fcommon -O2 -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
WavPack Audio Encoding WAV To WavPack OpenBenchmarking.org Seconds, Fewer Is Better WavPack Audio Encoding 5.3 WAV To WavPack -O2 -O2 -fno-omit-frame-pointer 3 6 9 12 15 SE +/- 0.00, N = 5 SE +/- 0.00, N = 5 12.34 12.49 1. (CXX) g++ options: -O2 -rdynamic
Liquid-DSP Threads: 2 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 2 - Buffer Length: 256 - Filter Length: 57 -O2 -O2 -fno-omit-frame-pointer 30M 60M 90M 120M 150M SE +/- 69602.04, N = 3 SE +/- 55477.72, N = 3 127233333 123466667 1. (CC) gcc options: -O3 -O2 -pthread -lm -lc -lliquid
Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Euclidean Cluster OpenBenchmarking.org Test Cases Per Minute, More Is Better Darmstadt Automotive Parallel Heterogeneous Suite Backend: OpenMP - Kernel: Euclidean Cluster -O2 -O2 -fno-omit-frame-pointer 200 400 600 800 1000 SE +/- 3.93, N = 3 SE +/- 3.50, N = 3 1108.24 1095.49 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp
Liquid-DSP Threads: 1 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 1 - Buffer Length: 256 - Filter Length: 57 -O2 -O2 -fno-omit-frame-pointer 14M 28M 42M 56M 70M SE +/- 28759.54, N = 3 SE +/- 90152.34, N = 3 63592333 61948667 1. (CC) gcc options: -O3 -O2 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 8 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 8 - Buffer Length: 256 - Filter Length: 57 -O2 -O2 -fno-omit-frame-pointer 70M 140M 210M 280M 350M SE +/- 1804355.84, N = 3 SE +/- 1704741.75, N = 3 310600000 300993333 1. (CC) gcc options: -O3 -O2 -pthread -lm -lc -lliquid
Liquid-DSP Threads: 12 - Buffer Length: 256 - Filter Length: 57 OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 12 - Buffer Length: 256 - Filter Length: 57 -O2 -O2 -fno-omit-frame-pointer 70M 140M 210M 280M 350M SE +/- 1362363.14, N = 3 SE +/- 1500092.59, N = 3 322190000 309426667 1. (CC) gcc options: -O3 -O2 -pthread -lm -lc -lliquid
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Thorough -O2 -O2 -fno-omit-frame-pointer 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 14.71 15.02 1. (CXX) g++ options: -O2 -O3 -flto -pthread
SVT-AV1 Encoder Mode: Preset 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 10 - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.07, N = 3 38.31 37.40 1. (CXX) g++ options: -O2 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
SVT-HEVC Tuning: 10 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 40.84 40.51 1. (CC) gcc options: -O2 -fPIE -fPIC -O3 -pie -rdynamic -lpthread -lrt
PJSIP Method: OPTIONS, Stateless OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless -O2 -O2 -fno-omit-frame-pointer 30K 60K 90K 120K 150K SE +/- 1238.78, N = 3 SE +/- 1031.85, N = 3 157897 142790 1. (CC) gcc options: -pthread -lSDL2 -lstdc++ -lopus -lssl -lcrypto -lm -lrt -lpthread -lasound -O2
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU -O2 -O2 -fno-omit-frame-pointer 3 6 9 12 15 SE +/- 0.00524, N = 3 SE +/- 0.02613, N = 3 9.18063 9.09057 MIN: 8.9 MIN: 8.77 1. (CXX) g++ options: -O3 -march=native -O2 -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode -O2 -O2 -fno-omit-frame-pointer 2 4 6 8 10 SE +/- 0.014, N = 5 SE +/- 0.011, N = 5 7.711 7.782 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
SVT-AV1 Encoder Mode: Preset 12 - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.0 Encoder Mode: Preset 12 - Input: Bosphorus 4K -O2 -O2 -fno-omit-frame-pointer 13 26 39 52 65 SE +/- 0.23, N = 3 SE +/- 0.17, N = 3 57.25 56.15 1. (CXX) g++ options: -O2 -march=native -mno-avx -mavx2 -mavx512f -mavx512bw -mavx512dq -pie
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 -O2 -O2 -fno-omit-frame-pointer 3 6 9 12 15 SE +/- 0.003, N = 3 SE +/- 0.006, N = 3 9.027 9.113 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -O2 -lm
yquake2 Renderer: Software CPU Color Light - AF: On - MSAA: On - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: Software CPU Color Light - AF: On - MSAA: On - Resolution: 1920 x 1080 -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.28, N = 3 78.6 78.5 1. (CC) gcc options: -shared -lm -ldl -rdynamic -pthread -lSDL2 -O2 -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
yquake2 Renderer: Software CPU - AF: On - MSAA: On - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: Software CPU - AF: On - MSAA: On - Resolution: 1920 x 1080 -O2 -O2 -fno-omit-frame-pointer 20 40 60 80 100 SE +/- 0.23, N = 3 SE +/- 0.15, N = 3 84.2 84.1 1. (CC) gcc options: -shared -lm -ldl -rdynamic -pthread -lSDL2 -O2 -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU -O2 -O2 -fno-omit-frame-pointer 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 22.08 21.94 MIN: 21.67 MIN: 21.56 1. (CXX) g++ options: -O3 -march=native -O2 -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 3.2 Preset: Medium -O2 -O2 -fno-omit-frame-pointer 1.2938 2.5876 3.8814 5.1752 6.469 SE +/- 0.0046, N = 3 SE +/- 0.0079, N = 3 5.5136 5.7500 1. (CXX) g++ options: -O2 -O3 -flto -pthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.6 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU -O2 -O2 -fno-omit-frame-pointer 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 11.80 12.36 MIN: 10.47 MIN: 10.44 1. (CXX) g++ options: -O3 -march=native -O2 -fopenmp -msse4.1 -fPIC -std=c++11 -pie -ldl -lpthread
yquake2 Renderer: OpenGL 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: OpenGL 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080 -O2 -O2 -fno-omit-frame-pointer 140 280 420 560 700 SE +/- 6.31, N = 3 SE +/- 6.69, N = 5 647.7 623.8 1. (CC) gcc options: -shared -lm -ldl -rdynamic -pthread -lSDL2 -O2 -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
yquake2 Renderer: OpenGL ES 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 8.10 Renderer: OpenGL ES 3.x - AF: On - MSAA: On - Resolution: 1920 x 1080 -O2 -O2 -fno-omit-frame-pointer 140 280 420 560 700 SE +/- 5.52, N = 3 SE +/- 7.67, N = 4 658.9 641.9 1. (CC) gcc options: -shared -lm -ldl -rdynamic -pthread -lSDL2 -O2 -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation -O2 -O2 -fno-omit-frame-pointer 400 800 1200 1600 2000 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 1968.87 1945.40 1. (CC) gcc options: -O2 -lm
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization -O2 -O2 -fno-omit-frame-pointer 500 1000 1500 2000 2500 SE +/- 2.53, N = 3 SE +/- 8.42, N = 3 2285.03 2126.45 1. (CC) gcc options: -O2 -lm
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply -O2 -O2 -fno-omit-frame-pointer 600 1200 1800 2400 3000 SE +/- 7.92, N = 3 SE +/- 13.11, N = 3 2701.34 2603.66 1. (CC) gcc options: -O2 -lm
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform -O2 -O2 -fno-omit-frame-pointer 50 100 150 200 250 SE +/- 1.18, N = 3 SE +/- 0.91, N = 3 208.27 210.73 1. (CC) gcc options: -O2 -lm
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo -O2 -O2 -fno-omit-frame-pointer 160 320 480 640 800 SE +/- 0.71, N = 3 SE +/- 0.03, N = 3 742.34 735.22 1. (CC) gcc options: -O2 -lm
Phoronix Test Suite v10.8.5