6800K May Intel Core i7-6800K testing with a MSI X99A WORKSTATION (MS-7A54) v1.0 (1.10 BIOS) and Zotac NVIDIA NV137 2GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2105106-IB-6800KMAY414&grs .
6800K May Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution 1 2 3 Intel Core i7-6800K @ 3.80GHz (6 Cores / 12 Threads) MSI X99A WORKSTATION (MS-7A54) v1.0 (1.10 BIOS) Intel Xeon E7 v4/Xeon 16GB 120GB TOSHIBA TR150 Zotac NVIDIA NV137 2GB Realtek ALC1150 G237HL Intel I218-LM + Intel I210 Ubuntu 20.10 5.8.0-41-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 nouveau 4.3 Mesa 20.2.1 GCC 10.2.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-10-JvwpWM/gcc-10-10.2.0/debian/tmp-gcn/usr,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Processor Details - Scaling Governor: intel_cpufreq ondemand - CPU Microcode: 0xb000038 Python Details - Python 3.8.6 Security Details - itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + 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 generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Mitigation of Clear buffers; SMT vulnerable
6800K May vosk: liquid-dsp: 8 - 256 - 57 onednn: IP Shapes 3D - u8s8f32 - CPU gnuradio: Five Back to Back FIR Filters incompact3d: input.i3d 129 Cells Per Direction incompact3d: input.i3d 193 Cells Per Direction svt-vp9: VMAF Optimized - Bosphorus 1080p mrbayes: Primate Phylogeny Analysis viennacl: CPU BLAS - sDOT gnuradio: IIR Filter svt-hevc: 7 - Bosphorus 1080p jpegxl: JPEG - 8 jpegxl: JPEG - 5 mnn: resnet-v2-50 onednn: Deconvolution Batch shapes_3d - f32 - CPU embree: Pathtracer - Asian Dragon Obj stockfish: Total Time viennacl: CPU BLAS - dDOT embree: Pathtracer ISPC - Asian Dragon Obj gnuradio: FIR Filter jpegxl-decode: All luaradio: FM Deemphasis Filter compress-zstd: 19, Long Mode - Compression Speed gnuradio: Signal Source (Cosine) viennacl: CPU BLAS - sAXPY compress-zstd: 8 - Compression Speed gmpbench: Total Time compress-zstd: 3 - Compression Speed build-linux-kernel: Time To Compile chia-vdf: Square Assembly Optimized avifenc: 10 mnn: inception-v3 jpegxl: PNG - 8 srslte: OFDM_Test viennacl: CPU BLAS - dGEMV-T viennacl: CPU BLAS - dGEMV-N liquid-dsp: 2 - 256 - 57 draco: Church Facade jpegxl-decode: 1 srslte: PHY_DL_Test embree: Pathtracer - Crown stream: Add toktx: UASTC 3 avifenc: 10, Lossless stream: Scale liquid-dsp: 4 - 256 - 57 build-mesa: Time To Compile basis: UASTC Level 0 onednn: IP Shapes 3D - f32 - CPU compress-zstd: 8 - Decompression Speed compress-zstd: 19 - Compression Speed qmcpack: simple-H2O openscad: Retro Car luaradio: Five Back to Back FIR Filters toktx: UASTC 3 + Zstd Compression 19 viennacl: CPU BLAS - sCOPY jpegxl: PNG - 5 jpegxl: JPEG - 7 cp2k: Fayalite-FIST tjbench: Decompression Throughput aom-av1: Speed 8 Realtime - Bosphorus 1080p viennacl: CPU BLAS - dAXPY liquid-dsp: 1 - 256 - 57 stream: Copy xmrig: Monero - 1M onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU compress-zstd: 3, Long Mode - Decompression Speed onednn: Recurrent Neural Network Training - u8s8f32 - CPU gnuradio: FM Deemphasis Filter compress-zstd: 19 - Decompression Speed stream: Triad srslte: PHY_DL_Test luaradio: Complex Phase compress-zstd: 3, Long Mode - Compression Speed embree: Pathtracer - Asian Dragon compress-zstd: 19, Long Mode - Decompression Speed helsing: 12 digit avifenc: 0 astcenc: Medium onednn: IP Shapes 1D - u8s8f32 - CPU openscad: Mini-ITX Case liquid-dsp: 12 - 256 - 57 pjsip: OPTIONS, Stateless sysbench: RAM / Memory onednn: IP Shapes 1D - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU svt-vp9: Visual Quality Optimized - Bosphorus 1080p embree: Pathtracer ISPC - Crown basis: UASTC Level 3 avifenc: 6, Lossless basis: ETC1S openscad: Leonardo Phone Case Slim toktx: Zstd Compression 9 aom-av1: Speed 6 Realtime - Bosphorus 1080p dav1d: Chimera 1080p svt-hevc: 10 - Bosphorus 1080p onednn: Recurrent Neural Network Inference - u8s8f32 - CPU luaradio: Hilbert Transform onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU compress-zstd: 8, Long Mode - Compression Speed build-wasmer: Time To Compile aom-av1: Speed 8 Realtime - Bosphorus 4K blender: BMW27 - CPU-Only viennacl: CPU BLAS - dCOPY avifenc: 2 aom-av1: Speed 9 Realtime - Bosphorus 1080p aom-av1: Speed 6 Realtime - Bosphorus 4K blender: Fishy Cat - CPU-Only libgav1: Chimera 1080p onednn: Recurrent Neural Network Training - f32 - CPU blender: Classroom - CPU-Only aom-av1: Speed 6 Two-Pass - Bosphorus 1080p onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU openscad: Projector Mount Swivel hmmer: Pfam Database Search avifenc: 6 openscad: Pistol aom-av1: Speed 6 Two-Pass - Bosphorus 4K onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU libgav1: Chimera 1080p 10-bit embree: Pathtracer ISPC - Asian Dragon onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU dav1d: Chimera 1080p 10-bit basis: UASTC Level 2 aom-av1: Speed 4 Two-Pass - Bosphorus 1080p build-llvm: Unix Makefiles onednn: Deconvolution Batch shapes_1d - f32 - CPU gnuradio: Hilbert Transform build-erlang: Time To Compile compress-zstd: 3 - Decompression Speed xmrig: Wownero - 1M pjsip: OPTIONS, Stateful dav1d: Summer Nature 4K gromacs: water_GMX50_bare jpegxl: PNG - 7 aom-av1: Speed 9 Realtime - Bosphorus 4K helsing: 14 digit toktx: Zstd Compression 19 build-llvm: Ninja pjsip: INVITE compress-zstd: 8, Long Mode - Decompression Speed onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU dav1d: Summer Nature 1080p build-nodejs: Time To Compile libgav1: Summer Nature 1080p onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU chia-vdf: Square Plain C++ libgav1: Summer Nature 4K astcenc: Exhaustive draco: Lion astcenc: Thorough sysbench: CPU svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p toktx: UASTC 4 + Zstd Compression 19 svt-hevc: 1 - Bosphorus 1080p aom-av1: Speed 0 Two-Pass - Bosphorus 1080p aom-av1: Speed 4 Two-Pass - Bosphorus 4K aom-av1: Speed 0 Two-Pass - Bosphorus 4K mnn: mobilenet-v1-1.0 mnn: MobileNetV2_224 mnn: SqueezeNetV1.0 viennacl: CPU BLAS - dGEMM-TT viennacl: CPU BLAS - dGEMM-TN viennacl: CPU BLAS - dGEMM-NT viennacl: CPU BLAS - dGEMM-NN securemark: SecureMark-TLS 1 2 3 25.697 255830000 3.36519 504.8 41.1415367 156.713745 89.33 173.544 18 436 55.68 19.5 43 59.04 16.0755 7.106 13973741 23.1 8.0582 532.9 129.91 365.6 21.3 2194.1 29.2 317.2 4608.3 1739.9 176.899 150500 5.133 74.299 0.59 79500000 24.3 24.6 98947000 9048 29.17 78.5 6.4186 29342.3 23.051 8.545 27218.3 188270000 100.103 10.899 9.84608 2996.4 26.7 55.883 24.251 651.6 29.179 19.9 39.88 42.45 1347.639 171.679919 77.27 33.6 52021000 43325.4 2565.9 16.9558 9.70189 3161.7 11018.3 593 2810.6 29294 197 481.3 673.2 7.5488 2783.8 10.27 122.957 8.0446 9.09941 58.362 284670000 48893 16736.89 12.7942 7328.24 75.25 7.2156 113.168 111.766 35.089 23.438 3.412 13.38 369.44 121.24 7353.4 82.9 7382.83 336.2 165.544 24.26 285.35 22.6 63.797 92.81 7.4 401.68 112.23 11040.2 856.95 10.89 17.1722 129.726 151.69 21.756 139.345 3.52 10.7622 35.5 8.8669 7.11325 87.27 59.031 3.8 1394.792 19.4447 335.3 169.146 2988.7 3445.7 6406 104.3 0.566 5.77 34.84 918.416 21.532 1368.459 3779 3215.6 10.3818 332.31 888.501 135.37 11062.7 119000 39.91 198.6593 6335 25.9384 10354.19 95.25 655.567 3.84 0.21 1.87 0.07 7.042 6.371 12.364 20.9 19.5 20 20.2 205983 23.408 277256667 3.57796 490.9 43.4190303 149.263896 92.51 174.592 17.4 449.8 57.43 20.10 41.92 57.332 15.6669 6.9095 13605923 23.5 7.8579 519.7 128.81 366.4 20.8 2176.4 28.6 317.8 4608 1773.5 173.552 153300 5.227 73.524 0.59 80466667 24.4 24.8 98514333 9045 29.63 77.3 6.3377 29554.4 23.220 8.603 27311.6 190735000 98.819 10.923 9.90494 3031.7 26.7 55.279 24.442 654.7 28.904 19.9 40.26 42.30 1335.09 171.397632 76.87 33.9 52412000 43524.3 2580.7 16.8938 9.78194 3135.9 11106.7 595.3 2802.3 29324.2 195.5 482.7 669.8 7.5463 2766.1 10.304 123.708 8.0747 9.03875 58.322 286536667 49132 16779.82 12.7342 7369.73 75.16 7.1725 113.846 112.325 35.228 23.357 3.412 13.42 371.37 121.87 7368.77 82.8 7367.46 337.5 164.766 24.15 286.64 22.5 63.954 92.42 7.38 400.78 111.79 11061.1 858.13 10.87 17.1720 129.572 151.321 21.716 139.800 3.53 10.7842 35.40 8.8919 7.11114 87.13 59.076 3.81 1397.413 19.4434 334.6 168.784 2982.2 3438.5 6419 104.38 0.565 5.76 34.83 918.952 21.526 1370.702 3775 3216.1 10.3787 332.59 889.312 135.33 11053.1 118900 39.94 198.6162 6333 25.9345 10352.60 95.30 655.439 3.84 0.21 1.87 0.07 7.058 6.203 12.127 18.9 21.3 19.6 20.7 206085 23.327 269162667 3.56832 478.0 42.5190188 150.013595 92.74 180.163 17.7 448.9 57.37 19.76 41.74 57.526 15.6227 7.0486 13737688 23.7 7.9602 525.1 126.70 357.4 21.1 2226.4 29.1 323.6 4519.2 1755.8 174.277 153233 5.173 73.004 0.60 80833333 24.0 24.4 97365167 9189 29.40 78 6.4339 29759.5 23.374 8.663 27580.0 190431667 98.898 11.040 9.96725 3031.6 26.4 55.582 24.181 658.6 28.877 20.1 39.89 42.05 1341.451 170.100454 76.56 33.7 52477667 43699.5 2587.9 17.0378 9.76810 3159.3 11089.2 597.7 2788.7 29521.1 196.8 479.1 668.3 7.6012 2785.3 10.234 123.797 8.0995 9.05168 58.713 286083333 49207 16673.45 12.7154 7372.41 74.80 7.1957 113.366 112.435 35.023 23.491 3.394 13.35 369.97 121.55 7333.18 82.5 7347.50 337.8 165.459 24.21 285.71 22.6 64.068 92.46 7.37 400.10 112.18 11082.8 860.12 10.85 17.2335 130.000 151.195 21.787 139.503 3.53 10.7538 35.42 8.8853 7.09340 87.03 59.189 3.80 1398.367 19.3952 335.4 169.186 2983.7 3443.9 6414 104.17 0.566 5.76 34.89 919.967 21.496 1370.148 3781 3211.5 10.3930 332.73 889.461 135.24 11060.2 118933 39.94 198.5244 6331 25.9505 10358.79 95.25 655.462 3.84 0.21 1.87 0.07 7.867 6.039 11.519 19.6 21.5 19.1 19.6 199607 OpenBenchmarking.org
VOSK Speech Recognition Toolkit OpenBenchmarking.org Seconds, Fewer Is Better VOSK Speech Recognition Toolkit 0.3.21 1 2 3 6 12 18 24 30 SE +/- 0.21, N = 15 SE +/- 0.20, N = 15 25.70 23.41 23.33
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 1 2 3 60M 120M 180M 240M 300M SE +/- 2271668.50, N = 3 SE +/- 2636553.03, N = 15 255830000 277256667 269162667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 1 2 3 0.805 1.61 2.415 3.22 4.025 SE +/- 0.02094, N = 3 SE +/- 0.01805, N = 3 3.36519 3.57796 3.56832 MIN: 3.1 MIN: 3.12 MIN: 3.05 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
GNU Radio Test: Five Back to Back FIR Filters OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Five Back to Back FIR Filters 1 2 3 110 220 330 440 550 SE +/- 6.36, N = 9 SE +/- 4.01, N = 3 504.8 490.9 478.0 1. 3.8.1.0
Xcompact3d Incompact3d Input: input.i3d 129 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction 1 2 3 10 20 30 40 50 SE +/- 0.29, N = 15 SE +/- 0.35, N = 9 41.14 43.42 42.52 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz
Xcompact3d Incompact3d Input: input.i3d 193 Cells Per Direction OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction 1 2 3 30 60 90 120 150 SE +/- 0.63, N = 3 SE +/- 0.64, N = 3 156.71 149.26 150.01 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi -lopen-rte -lopen-pal -lhwloc -ldl -levent -levent_pthreads -lutil -lm -lrt -lz
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p 1 2 3 20 40 60 80 100 SE +/- 0.97, N = 5 SE +/- 0.97, N = 5 89.33 92.51 92.74 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis 1 2 3 40 80 120 160 200 SE +/- 1.69, N = 3 SE +/- 1.97, N = 5 173.54 174.59 180.16 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
ViennaCL Test: CPU BLAS - sDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sDOT 1 2 3 4 8 12 16 20 SE +/- 0.55, N = 3 SE +/- 0.17, N = 12 18.0 17.4 17.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
GNU Radio Test: IIR Filter OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: IIR Filter 1 2 3 100 200 300 400 500 SE +/- 1.40, N = 9 SE +/- 2.30, N = 3 436.0 449.8 448.9 1. 3.8.1.0
SVT-HEVC Tuning: 7 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p 1 2 3 13 26 39 52 65 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 55.68 57.43 57.37 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
JPEG XL Input: JPEG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL 0.3.3 Input: JPEG - Encode Speed: 8 1 2 3 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 19.50 20.10 19.76 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
JPEG XL Input: JPEG - Encode Speed: 5 OpenBenchmarking.org MP/s, More Is Better JPEG XL 0.3.3 Input: JPEG - Encode Speed: 5 1 2 3 10 20 30 40 50 SE +/- 0.25, N = 3 SE +/- 0.14, N = 3 43.00 41.92 41.74 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: resnet-v2-50 1 2 3 13 26 39 52 65 SE +/- 0.31, N = 9 SE +/- 0.82, N = 3 59.04 57.33 57.53 MIN: 47.53 / MAX: 248.6 MIN: 42.93 / MAX: 183.34 MIN: 43.37 / MAX: 182.6 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 1 2 3 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.09, N = 3 16.08 15.67 15.62 MIN: 11.92 MIN: 11.93 MIN: 11.89 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon Obj 1 2 3 2 4 6 8 10 SE +/- 0.0326, N = 3 SE +/- 0.0278, N = 3 7.1060 6.9095 7.0486 MIN: 7.08 / MAX: 7.17 MIN: 6.79 / MAX: 7.12 MIN: 6.93 / MAX: 7.17
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time 1 2 3 3M 6M 9M 12M 15M SE +/- 72340.52, N = 3 SE +/- 62832.49, N = 3 13973741 13605923 13737688 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
ViennaCL Test: CPU BLAS - dDOT OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dDOT 1 2 3 6 12 18 24 30 SE +/- 0.50, N = 3 SE +/- 0.18, N = 12 23.1 23.5 23.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 1 2 3 2 4 6 8 10 SE +/- 0.0092, N = 3 SE +/- 0.0144, N = 3 8.0582 7.8579 7.9602 MIN: 8.02 / MAX: 8.14 MIN: 7.79 / MAX: 8 MIN: 7.9 / MAX: 8.09
GNU Radio Test: FIR Filter OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FIR Filter 1 2 3 120 240 360 480 600 SE +/- 5.14, N = 9 SE +/- 2.59, N = 3 532.9 519.7 525.1 1. 3.8.1.0
JPEG XL Decoding CPU Threads: All OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding 0.3.3 CPU Threads: All 1 2 3 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 129.91 128.81 126.70
LuaRadio Test: FM Deemphasis Filter OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: FM Deemphasis Filter 1 2 3 80 160 240 320 400 SE +/- 0.27, N = 3 SE +/- 11.52, N = 3 365.6 366.4 357.4
Zstd Compression Compression Level: 19, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Compression Speed 1 2 3 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 21.3 20.8 21.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
GNU Radio Test: Signal Source (Cosine) OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Signal Source (Cosine) 1 2 3 500 1000 1500 2000 2500 SE +/- 20.50, N = 9 SE +/- 13.74, N = 3 2194.1 2176.4 2226.4 1. 3.8.1.0
ViennaCL Test: CPU BLAS - sAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY 1 2 3 7 14 21 28 35 SE +/- 0.20, N = 3 SE +/- 0.11, N = 12 29.2 28.6 29.1 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
Zstd Compression Compression Level: 8 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8 - Compression Speed 1 2 3 70 140 210 280 350 SE +/- 1.37, N = 3 SE +/- 0.90, N = 3 317.2 317.8 323.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
GNU GMP GMPbench Total Time OpenBenchmarking.org GMPbench Score, More Is Better GNU GMP GMPbench 6.2.1 Total Time 1 2 3 1000 2000 3000 4000 5000 4608.3 4608.0 4519.2 1. (CC) gcc options: -O3 -fomit-frame-pointer -lm
Zstd Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3 - Compression Speed 1 2 3 400 800 1200 1600 2000 SE +/- 9.22, N = 3 SE +/- 9.91, N = 3 1739.9 1773.5 1755.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.10.20 Time To Compile 1 2 3 40 80 120 160 200 SE +/- 1.19, N = 3 SE +/- 1.62, N = 3 176.90 173.55 174.28
Chia Blockchain VDF Test: Square Assembly Optimized OpenBenchmarking.org IPS, More Is Better Chia Blockchain VDF 1.0.1 Test: Square Assembly Optimized 1 2 3 30K 60K 90K 120K 150K SE +/- 1001.67, N = 3 SE +/- 1328.32, N = 3 150500 153300 153233 1. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10 1 2 3 1.1761 2.3522 3.5283 4.7044 5.8805 SE +/- 0.051, N = 3 SE +/- 0.006, N = 3 5.133 5.227 5.173 1. (CXX) g++ options: -O3 -fPIC -lm
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: inception-v3 1 2 3 16 32 48 64 80 SE +/- 0.45, N = 9 SE +/- 0.90, N = 3 74.30 73.52 73.00 MIN: 63.07 / MAX: 247.5 MIN: 57.58 / MAX: 234.51 MIN: 56.13 / MAX: 217.15 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
JPEG XL Input: PNG - Encode Speed: 8 OpenBenchmarking.org MP/s, More Is Better JPEG XL 0.3.3 Input: PNG - Encode Speed: 8 1 2 3 0.135 0.27 0.405 0.54 0.675 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.59 0.59 0.60 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
srsLTE Test: OFDM_Test OpenBenchmarking.org Samples / Second, More Is Better srsLTE 20.10.1 Test: OFDM_Test 1 2 3 20M 40M 60M 80M 100M SE +/- 633333.33, N = 3 SE +/- 384418.75, N = 3 79500000 80466667 80833333 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
ViennaCL Test: CPU BLAS - dGEMV-T OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T 1 2 3 6 12 18 24 30 SE +/- 0.26, N = 3 SE +/- 0.15, N = 10 24.3 24.4 24.0 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMV-N OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N 1 2 3 6 12 18 24 30 SE +/- 0.29, N = 3 SE +/- 0.10, N = 12 24.6 24.8 24.4 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
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 1 2 3 20M 40M 60M 80M 100M SE +/- 471745.81, N = 3 SE +/- 1085656.09, N = 12 98947000 98514333 97365167 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Google Draco Model: Church Facade OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Church Facade 1 2 3 2K 4K 6K 8K 10K SE +/- 7.51, N = 3 SE +/- 112.19, N = 15 9048 9045 9189 1. (CXX) g++ options: -O3
JPEG XL Decoding CPU Threads: 1 OpenBenchmarking.org MP/s, More Is Better JPEG XL Decoding 0.3.3 CPU Threads: 1 1 2 3 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 29.17 29.63 29.40
srsLTE Test: PHY_DL_Test OpenBenchmarking.org UE Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test 1 2 3 20 40 60 80 100 SE +/- 0.24, N = 3 78.5 77.3 78.0 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Crown 1 2 3 2 4 6 8 10 SE +/- 0.0011, N = 3 SE +/- 0.0158, N = 3 6.4186 6.3377 6.4339 MIN: 6.38 / MAX: 6.5 MIN: 6.28 / MAX: 6.47 MIN: 6.37 / MAX: 6.54
Stream Type: Add OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add 1 2 3 6K 12K 18K 24K 30K SE +/- 15.91, N = 5 SE +/- 12.57, N = 5 29342.3 29554.4 29759.5 1. (CC) gcc options: -O3 -march=native -fopenmp
KTX-Software toktx Settings: UASTC 3 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 1 2 3 6 12 18 24 30 SE +/- 0.12, N = 3 SE +/- 0.28, N = 3 23.05 23.22 23.37
libavif avifenc Encoder Speed: 10, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10, Lossless 1 2 3 2 4 6 8 10 SE +/- 0.030, N = 3 SE +/- 0.010, N = 3 8.545 8.603 8.663 1. (CXX) g++ options: -O3 -fPIC -lm
Stream Type: Scale OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale 1 2 3 6K 12K 18K 24K 30K SE +/- 41.98, N = 5 SE +/- 6.54, N = 5 27218.3 27311.6 27580.0 1. (CC) gcc options: -O3 -march=native -fopenmp
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 1 2 3 40M 80M 120M 160M 200M SE +/- 1897283.58, N = 6 SE +/- 1876216.79, N = 6 188270000 190735000 190431667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Timed Mesa Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Mesa Compilation 21.0 Time To Compile 1 2 3 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.09, N = 3 100.10 98.82 98.90
Basis Universal Settings: UASTC Level 0 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 0 1 2 3 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.11, N = 14 10.90 10.92 11.04 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.04476, N = 3 SE +/- 0.04181, N = 3 9.84608 9.90494 9.96725 MIN: 8.59 MIN: 8.69 MIN: 8.68 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Zstd Compression Compression Level: 8 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8 - Decompression Speed 1 2 3 700 1400 2100 2800 3500 SE +/- 1.79, N = 3 SE +/- 1.06, N = 3 2996.4 3031.7 3031.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
Zstd Compression Compression Level: 19 - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Compression Speed 1 2 3 6 12 18 24 30 SE +/- 0.29, N = 3 SE +/- 0.27, N = 3 26.7 26.7 26.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
QMCPACK Input: simple-H2O OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.11 Input: simple-H2O 1 2 3 13 26 39 52 65 SE +/- 0.21, N = 3 SE +/- 0.69, N = 3 55.88 55.28 55.58 1. (CXX) g++ options: -fopenmp -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -fomit-frame-pointer -ffast-math -pthread -lm
OpenSCAD Render: Retro Car OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Retro Car 1 2 3 6 12 18 24 30 SE +/- 0.20, N = 14 SE +/- 0.01, N = 3 24.25 24.44 24.18 1. OpenSCAD version 2019.05
LuaRadio Test: Five Back to Back FIR Filters OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Five Back to Back FIR Filters 1 2 3 140 280 420 560 700 SE +/- 4.23, N = 3 SE +/- 0.20, N = 3 651.6 654.7 658.6
KTX-Software toktx Settings: UASTC 3 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 + Zstd Compression 19 1 2 3 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 29.18 28.90 28.88
ViennaCL Test: CPU BLAS - sCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY 1 2 3 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.14, N = 12 19.9 19.9 20.1 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
JPEG XL Input: PNG - Encode Speed: 5 OpenBenchmarking.org MP/s, More Is Better JPEG XL 0.3.3 Input: PNG - Encode Speed: 5 1 2 3 9 18 27 36 45 SE +/- 0.20, N = 3 SE +/- 0.07, N = 3 39.88 40.26 39.89 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
JPEG XL Input: JPEG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL 0.3.3 Input: JPEG - Encode Speed: 7 1 2 3 10 20 30 40 50 SE +/- 0.44, N = 3 SE +/- 0.16, N = 3 42.45 42.30 42.05 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
CP2K Molecular Dynamics Input: Fayalite-FIST OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 8.1 Input: Fayalite-FIST 1 2 3 300 600 900 1200 1500 1347.64 1335.09 1341.45
libjpeg-turbo tjbench Test: Decompression Throughput OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 2.1.0 Test: Decompression Throughput 1 2 3 40 80 120 160 200 SE +/- 0.61, N = 3 SE +/- 0.71, N = 3 171.68 171.40 170.10 1. (CC) gcc options: -O3 -rdynamic
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p 1 2 3 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 0.30, N = 3 77.27 76.87 76.56 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
ViennaCL Test: CPU BLAS - dAXPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dAXPY 1 2 3 8 16 24 32 40 SE +/- 0.35, N = 3 SE +/- 0.12, N = 12 33.6 33.9 33.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
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 1 2 3 11M 22M 33M 44M 55M SE +/- 44508.43, N = 3 SE +/- 13678.86, N = 3 52021000 52412000 52477667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
Stream Type: Copy OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy 1 2 3 9K 18K 27K 36K 45K SE +/- 41.44, N = 5 SE +/- 128.05, N = 5 43325.4 43524.3 43699.5 1. (CC) gcc options: -O3 -march=native -fopenmp
Xmrig Variant: Monero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M 1 2 3 600 1200 1800 2400 3000 SE +/- 3.21, N = 3 SE +/- 4.53, N = 3 2565.9 2580.7 2587.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 1 2 3 4 8 12 16 20 SE +/- 0.13, N = 3 SE +/- 0.07, N = 3 16.96 16.89 17.04 MIN: 14.02 MIN: 13.96 MIN: 13.85 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.03538, N = 3 SE +/- 0.03293, N = 3 9.70189 9.78194 9.76810 MIN: 4.61 MIN: 4.62 MIN: 4.62 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Zstd Compression Compression Level: 3, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3, Long Mode - Decompression Speed 1 2 3 700 1400 2100 2800 3500 SE +/- 19.54, N = 3 SE +/- 1.14, N = 3 3161.7 3135.9 3159.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 1 2 3 2K 4K 6K 8K 10K SE +/- 27.42, N = 3 SE +/- 20.98, N = 3 11018.3 11106.7 11089.2 MIN: 10752.6 MIN: 10805 MIN: 10779.6 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
GNU Radio Test: FM Deemphasis Filter OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FM Deemphasis Filter 1 2 3 130 260 390 520 650 SE +/- 4.77, N = 9 SE +/- 8.03, N = 3 593.0 595.3 597.7 1. 3.8.1.0
Zstd Compression Compression Level: 19 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Decompression Speed 1 2 3 600 1200 1800 2400 3000 SE +/- 3.02, N = 3 SE +/- 10.31, N = 3 2810.6 2802.3 2788.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Stream Type: Triad OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad 1 2 3 6K 12K 18K 24K 30K SE +/- 4.27, N = 5 SE +/- 12.68, N = 5 29294.0 29324.2 29521.1 1. (CC) gcc options: -O3 -march=native -fopenmp
srsLTE Test: PHY_DL_Test OpenBenchmarking.org eNb Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test 1 2 3 40 80 120 160 200 SE +/- 1.19, N = 3 SE +/- 0.27, N = 3 197.0 195.5 196.8 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lmbedcrypto -lconfig++ -lsctp -lbladeRF -lm -lfftw3f
LuaRadio Test: Complex Phase OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Complex Phase 1 2 3 100 200 300 400 500 SE +/- 0.93, N = 3 SE +/- 2.75, N = 3 481.3 482.7 479.1
Zstd Compression Compression Level: 3, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3, Long Mode - Compression Speed 1 2 3 150 300 450 600 750 SE +/- 3.37, N = 3 SE +/- 5.03, N = 3 673.2 669.8 668.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer - Model: Asian Dragon 1 2 3 2 4 6 8 10 SE +/- 0.0542, N = 3 SE +/- 0.0353, N = 3 7.5488 7.5463 7.6012 MIN: 7.51 / MAX: 7.62 MIN: 7.46 / MAX: 7.75 MIN: 7.51 / MAX: 7.76
Zstd Compression Compression Level: 19, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Decompression Speed 1 2 3 600 1200 1800 2400 3000 SE +/- 17.80, N = 3 SE +/- 0.75, N = 3 2783.8 2766.1 2785.3 1. (CC) gcc options: -O3 -pthread -lz -llzma
Helsing Digit Range: 12 digit OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 12 digit 1 2 3 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 10.27 10.30 10.23 1. (CC) gcc options: -O2 -pthread
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 0 1 2 3 30 60 90 120 150 SE +/- 0.51, N = 3 SE +/- 0.22, N = 3 122.96 123.71 123.80 1. (CXX) g++ options: -O3 -fPIC -lm
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.4 Preset: Medium 1 2 3 2 4 6 8 10 SE +/- 0.0129, N = 3 SE +/- 0.0322, N = 3 8.0446 8.0747 8.0995 1. (CXX) g++ options: -O3 -flto -pthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.02692, N = 3 SE +/- 0.03152, N = 3 9.09941 9.03875 9.05168 MIN: 3.91 MIN: 3.85 MIN: 3.92 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenSCAD Render: Mini-ITX Case OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Mini-ITX Case 1 2 3 13 26 39 52 65 SE +/- 0.09, N = 3 SE +/- 0.50, N = 3 58.36 58.32 58.71 1. OpenSCAD version 2019.05
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 1 2 3 60M 120M 180M 240M 300M SE +/- 112150.69, N = 3 SE +/- 163333.33, N = 3 284670000 286536667 286083333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
PJSIP Method: OPTIONS, Stateless OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateless 1 2 3 11K 22K 33K 44K 55K SE +/- 96.85, N = 3 SE +/- 35.35, N = 3 48893 49132 49207 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
Sysbench Test: RAM / Memory OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory 1 2 3 4K 8K 12K 16K 20K SE +/- 47.60, N = 3 SE +/- 92.41, N = 3 16736.89 16779.82 16673.45 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 12.79 12.73 12.72 MIN: 8.26 MIN: 6.1 MIN: 7.47 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 1 2 3 1600 3200 4800 6400 8000 SE +/- 9.15, N = 3 SE +/- 4.84, N = 3 7328.24 7369.73 7372.41 MIN: 7044.31 MIN: 7085.09 MIN: 7094.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p 1 2 3 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.23, N = 3 75.25 75.16 74.80 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Crown 1 2 3 2 4 6 8 10 SE +/- 0.0186, N = 3 SE +/- 0.0160, N = 3 7.2156 7.1725 7.1957 MIN: 7.17 / MAX: 7.32 MIN: 7.09 / MAX: 7.31 MIN: 7.12 / MAX: 7.32
Basis Universal Settings: UASTC Level 3 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 3 1 2 3 30 60 90 120 150 SE +/- 0.60, N = 3 SE +/- 0.12, N = 3 113.17 113.85 113.37 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
libavif avifenc Encoder Speed: 6, Lossless OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6, Lossless 1 2 3 30 60 90 120 150 SE +/- 0.28, N = 3 SE +/- 0.51, N = 3 111.77 112.33 112.44 1. (CXX) g++ options: -O3 -fPIC -lm
Basis Universal Settings: ETC1S OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: ETC1S 1 2 3 8 16 24 32 40 SE +/- 0.19, N = 3 SE +/- 0.09, N = 3 35.09 35.23 35.02 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenSCAD Render: Leonardo Phone Case Slim OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Leonardo Phone Case Slim 1 2 3 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 23.44 23.36 23.49 1. OpenSCAD version 2019.05
KTX-Software toktx Settings: Zstd Compression 9 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: Zstd Compression 9 1 2 3 0.7677 1.5354 2.3031 3.0708 3.8385 SE +/- 0.006, N = 3 SE +/- 0.005, N = 3 3.412 3.412 3.394
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p 1 2 3 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 13.38 13.42 13.35 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Chimera 1080p 1 2 3 80 160 240 320 400 SE +/- 0.08, N = 3 SE +/- 0.78, N = 3 369.44 371.37 369.97 MIN: 273.31 / MAX: 554.87 MIN: 273.86 / MAX: 598.69 MIN: 272.55 / MAX: 578.08 1. (CC) gcc options: -pthread -lm
SVT-HEVC Tuning: 10 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p 1 2 3 30 60 90 120 150 SE +/- 0.24, N = 3 SE +/- 0.29, N = 3 121.24 121.87 121.55 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 1 2 3 1600 3200 4800 6400 8000 SE +/- 11.77, N = 3 SE +/- 10.21, N = 3 7353.40 7368.77 7333.18 MIN: 7100.35 MIN: 7106.81 MIN: 7032.31 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
LuaRadio Test: Hilbert Transform OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Hilbert Transform 1 2 3 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.38, N = 3 82.9 82.8 82.5
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 1 2 3 1600 3200 4800 6400 8000 SE +/- 8.78, N = 3 SE +/- 6.08, N = 3 7382.83 7367.46 7347.50 MIN: 7128.16 MIN: 7086.46 MIN: 7067.91 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Zstd Compression Compression Level: 8, Long Mode - Compression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8, Long Mode - Compression Speed 1 2 3 70 140 210 280 350 SE +/- 1.06, N = 3 SE +/- 0.55, N = 3 336.2 337.5 337.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 1.0.2 Time To Compile 1 2 3 40 80 120 160 200 SE +/- 0.63, N = 3 SE +/- 1.08, N = 3 165.54 164.77 165.46 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
AOM AV1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K 1 2 3 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 24.26 24.15 24.21 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: BMW27 - Compute: CPU-Only 1 2 3 60 120 180 240 300 SE +/- 0.16, N = 3 SE +/- 0.07, N = 3 285.35 286.64 285.71
ViennaCL Test: CPU BLAS - dCOPY OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dCOPY 1 2 3 5 10 15 20 25 SE +/- 0.15, N = 3 SE +/- 0.07, N = 12 22.6 22.5 22.6 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 2 1 2 3 14 28 42 56 70 SE +/- 0.31, N = 3 SE +/- 0.04, N = 3 63.80 63.95 64.07 1. (CXX) g++ options: -O3 -fPIC -lm
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p 1 2 3 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.09, N = 3 92.81 92.42 92.46 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K 1 2 3 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 7.40 7.38 7.37 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Fishy Cat - Compute: CPU-Only 1 2 3 90 180 270 360 450 SE +/- 0.27, N = 3 SE +/- 0.22, N = 3 401.68 400.78 400.10
libgav1 Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Chimera 1080p 1 2 3 30 60 90 120 150 SE +/- 0.31, N = 3 SE +/- 0.35, N = 3 112.23 111.79 112.18 1. (CXX) g++ options: -O3 -lpthread -lrt
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 1 2 3 2K 4K 6K 8K 10K SE +/- 13.40, N = 3 SE +/- 10.08, N = 3 11040.2 11061.1 11082.8 MIN: 10813.1 MIN: 10800.2 MIN: 10778.5 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.92 Blend File: Classroom - Compute: CPU-Only 1 2 3 200 400 600 800 1000 SE +/- 0.62, N = 3 SE +/- 1.77, N = 3 856.95 858.13 860.12
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p 1 2 3 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 10.89 10.87 10.85 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 1 2 3 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 17.17 17.17 17.23 MIN: 12.97 MIN: 13.2 MIN: 12.69 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenSCAD Render: Projector Mount Swivel OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Projector Mount Swivel 1 2 3 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.54, N = 3 129.73 129.57 130.00 1. OpenSCAD version 2019.05
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.2 Pfam Database Search 1 2 3 30 60 90 120 150 SE +/- 0.11, N = 3 SE +/- 0.10, N = 3 151.69 151.32 151.20 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm -lmpi
libavif avifenc Encoder Speed: 6 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6 1 2 3 5 10 15 20 25 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 21.76 21.72 21.79 1. (CXX) g++ options: -O3 -fPIC -lm
OpenSCAD Render: Pistol OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Pistol 1 2 3 30 60 90 120 150 SE +/- 0.29, N = 3 SE +/- 0.20, N = 3 139.35 139.80 139.50 1. OpenSCAD version 2019.05
AOM AV1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K 1 2 3 0.7943 1.5886 2.3829 3.1772 3.9715 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.52 3.53 3.53 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 10.76 10.78 10.75 MIN: 8.2 MIN: 8.22 MIN: 8.21 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
libgav1 Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Chimera 1080p 10-bit 1 2 3 8 16 24 32 40 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 35.50 35.40 35.42 1. (CXX) g++ options: -O3 -lpthread -lrt
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.13 Binary: Pathtracer ISPC - Model: Asian Dragon 1 2 3 2 4 6 8 10 SE +/- 0.0200, N = 3 SE +/- 0.0342, N = 3 8.8669 8.8919 8.8853 MIN: 8.83 / MAX: 8.95 MIN: 8.83 / MAX: 9.03 MIN: 8.78 / MAX: 9.04
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 1 2 3 2 4 6 8 10 SE +/- 0.01221, N = 3 SE +/- 0.02595, N = 3 7.11325 7.11114 7.09340 MIN: 3.36 MIN: 3.38 MIN: 3.38 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Chimera 1080p 10-bit 1 2 3 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 87.27 87.13 87.03 MIN: 57.49 / MAX: 206.69 MIN: 57.31 / MAX: 206.69 MIN: 57.18 / MAX: 209.79 1. (CC) gcc options: -pthread -lm
Basis Universal Settings: UASTC Level 2 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 2 1 2 3 13 26 39 52 65 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 59.03 59.08 59.19 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p 1 2 3 0.8573 1.7146 2.5719 3.4292 4.2865 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 3.80 3.81 3.80 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Timed LLVM Compilation Build System: Unix Makefiles OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Unix Makefiles 1 2 3 300 600 900 1200 1500 SE +/- 5.10, N = 3 SE +/- 1.12, N = 3 1394.79 1397.41 1398.37
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 1 2 3 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 19.44 19.44 19.40 MIN: 9.35 MIN: 8.16 MIN: 8.12 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
GNU Radio Test: Hilbert Transform OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Hilbert Transform 1 2 3 70 140 210 280 350 SE +/- 1.51, N = 9 SE +/- 1.35, N = 3 335.3 334.6 335.4 1. 3.8.1.0
Timed Erlang/OTP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Erlang/OTP Compilation 23.2 Time To Compile 1 2 3 40 80 120 160 200 SE +/- 0.21, N = 3 SE +/- 0.21, N = 3 169.15 168.78 169.19
Zstd Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3 - Decompression Speed 1 2 3 600 1200 1800 2400 3000 SE +/- 0.78, N = 3 SE +/- 2.22, N = 3 2988.7 2982.2 2983.7 1. (CC) gcc options: -O3 -pthread -lz -llzma
Xmrig Variant: Wownero - Hash Count: 1M OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M 1 2 3 700 1400 2100 2800 3500 SE +/- 13.36, N = 3 SE +/- 3.71, N = 3 3445.7 3438.5 3443.9 1. (CXX) g++ options: -fexceptions -fno-rtti -maes -O3 -Ofast -static-libgcc -static-libstdc++ -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
PJSIP Method: OPTIONS, Stateful OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: OPTIONS, Stateful 1 2 3 1400 2800 4200 5600 7000 SE +/- 4.04, N = 3 SE +/- 0.88, N = 3 6406 6419 6414 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Summer Nature 4K 1 2 3 20 40 60 80 100 SE +/- 0.16, N = 3 SE +/- 0.15, N = 3 104.30 104.38 104.17 MIN: 98.53 / MAX: 116.86 MIN: 98.48 / MAX: 117.64 MIN: 98.31 / MAX: 117.28 1. (CC) gcc options: -pthread -lm
GROMACS Input: water_GMX50_bare OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2021 Input: water_GMX50_bare 1 2 3 0.1274 0.2548 0.3822 0.5096 0.637 SE +/- 0.006, N = 3 SE +/- 0.007, N = 4 0.566 0.565 0.566 1. (CXX) g++ options: -O3 -pthread
JPEG XL Input: PNG - Encode Speed: 7 OpenBenchmarking.org MP/s, More Is Better JPEG XL 0.3.3 Input: PNG - Encode Speed: 7 1 2 3 1.2983 2.5966 3.8949 5.1932 6.4915 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.77 5.76 5.76 1. (CXX) g++ options: -funwind-tables -O3 -O2 -pthread -fPIE -pie -ldl
AOM AV1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K 1 2 3 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 34.84 34.83 34.89 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Helsing Digit Range: 14 digit OpenBenchmarking.org Seconds, Fewer Is Better Helsing 1.0-beta Digit Range: 14 digit 1 2 3 200 400 600 800 1000 SE +/- 0.54, N = 3 SE +/- 0.13, N = 3 918.42 918.95 919.97 1. (CC) gcc options: -O2 -pthread
KTX-Software toktx Settings: Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: Zstd Compression 19 1 2 3 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 21.53 21.53 21.50
Timed LLVM Compilation Build System: Ninja OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 12.0 Build System: Ninja 1 2 3 300 600 900 1200 1500 SE +/- 1.68, N = 3 SE +/- 0.07, N = 3 1368.46 1370.70 1370.15
PJSIP Method: INVITE OpenBenchmarking.org Responses Per Second, More Is Better PJSIP 2.11 Method: INVITE 1 2 3 800 1600 2400 3200 4000 SE +/- 1.20, N = 3 SE +/- 3.28, N = 3 3779 3775 3781 1. (CC) gcc options: -lSDL2 -lavformat -lavcodec -lswscale -lavutil -lstdc++ -lssl -lcrypto -luuid -lm -lrt -lpthread -lasound -O2
Zstd Compression Compression Level: 8, Long Mode - Decompression Speed OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8, Long Mode - Decompression Speed 1 2 3 700 1400 2100 2800 3500 SE +/- 2.82, N = 3 SE +/- 4.71, N = 3 3215.6 3216.1 3211.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 10.38 10.38 10.39 MIN: 5.16 MIN: 5.14 MIN: 5.15 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Summer Nature 1080p 1 2 3 70 140 210 280 350 SE +/- 0.62, N = 3 SE +/- 1.02, N = 3 332.31 332.59 332.73 MIN: 294.32 / MAX: 361.09 MIN: 290.31 / MAX: 364.3 MIN: 281.58 / MAX: 363.48 1. (CC) gcc options: -pthread -lm
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 15.11 Time To Compile 1 2 3 200 400 600 800 1000 SE +/- 0.14, N = 3 SE +/- 0.33, N = 3 888.50 889.31 889.46
libgav1 Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Summer Nature 1080p 1 2 3 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.54, N = 3 135.37 135.33 135.24 1. (CXX) g++ options: -O3 -lpthread -lrt
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 1 2 3 2K 4K 6K 8K 10K SE +/- 16.13, N = 3 SE +/- 10.66, N = 3 11062.7 11053.1 11060.2 MIN: 10779.5 MIN: 10763.5 MIN: 10798.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Chia Blockchain VDF Test: Square Plain C++ OpenBenchmarking.org IPS, More Is Better Chia Blockchain VDF 1.0.1 Test: Square Plain C++ 1 2 3 30K 60K 90K 120K 150K SE +/- 57.74, N = 3 SE +/- 33.33, N = 3 119000 118900 118933 1. (CXX) g++ options: -flto -no-pie -lgmpxx -lgmp -lboost_system -pthread
libgav1 Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better libgav1 0.16.3 Video Input: Summer Nature 4K 1 2 3 9 18 27 36 45 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 39.91 39.94 39.94 1. (CXX) g++ options: -O3 -lpthread -lrt
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.4 Preset: Exhaustive 1 2 3 40 80 120 160 200 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 198.66 198.62 198.52 1. (CXX) g++ options: -O3 -flto -pthread
Google Draco Model: Lion OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.4.1 Model: Lion 1 2 3 1400 2800 4200 5600 7000 SE +/- 15.84, N = 3 SE +/- 8.84, N = 3 6335 6333 6331 1. (CXX) g++ options: -O3
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.4 Preset: Thorough 1 2 3 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 25.94 25.93 25.95 1. (CXX) g++ options: -O3 -flto -pthread
Sysbench Test: CPU OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU 1 2 3 2K 4K 6K 8K 10K SE +/- 2.89, N = 3 SE +/- 2.02, N = 3 10354.19 10352.60 10358.79 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p 1 2 3 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.22, N = 3 95.25 95.30 95.25 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
KTX-Software toktx Settings: UASTC 4 + Zstd Compression 19 OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 4 + Zstd Compression 19 1 2 3 140 280 420 560 700 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 655.57 655.44 655.46
SVT-HEVC Tuning: 1 - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p 1 2 3 0.864 1.728 2.592 3.456 4.32 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.84 3.84 3.84 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p 1 2 3 0.0473 0.0946 0.1419 0.1892 0.2365 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.21 0.21 0.21 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K 1 2 3 0.4208 0.8416 1.2624 1.6832 2.104 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.87 1.87 1.87 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.1 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K 1 2 3 0.0158 0.0316 0.0474 0.0632 0.079 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.07 0.07 0.07 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: mobilenet-v1-1.0 1 2 3 2 4 6 8 10 SE +/- 0.054, N = 9 SE +/- 0.799, N = 3 7.042 7.058 7.867 MIN: 6.48 / MAX: 25.93 MIN: 4.84 / MAX: 31.92 MIN: 4.68 / MAX: 31.89 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: MobileNetV2_224 1 2 3 2 4 6 8 10 SE +/- 0.130, N = 9 SE +/- 0.012, N = 3 6.371 6.203 6.039 MIN: 3.99 / MAX: 30.98 MIN: 3.99 / MAX: 30.96 MIN: 5.58 / MAX: 23.61 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: SqueezeNetV1.0 1 2 3 3 6 9 12 15 SE +/- 0.35, N = 9 SE +/- 0.14, N = 3 12.36 12.13 11.52 MIN: 7.66 / MAX: 47.8 MIN: 7.02 / MAX: 50.71 MIN: 8.33 / MAX: 53.25 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
ViennaCL Test: CPU BLAS - dGEMM-TT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT 1 2 3 5 10 15 20 25 SE +/- 0.49, N = 3 SE +/- 0.38, N = 12 20.9 18.9 19.6 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-TN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN 1 2 3 5 10 15 20 25 SE +/- 1.18, N = 3 SE +/- 0.42, N = 11 19.5 21.3 21.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-NT OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT 1 2 3 5 10 15 20 25 SE +/- 0.46, N = 3 SE +/- 0.39, N = 11 20.0 19.6 19.1 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
ViennaCL Test: CPU BLAS - dGEMM-NN OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN 1 2 3 5 10 15 20 25 SE +/- 0.70, N = 3 SE +/- 0.40, N = 10 20.2 20.7 19.6 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
SecureMark Benchmark: SecureMark-TLS OpenBenchmarking.org marks, More Is Better SecureMark 1.0.4 Benchmark: SecureMark-TLS 1 2 3 40K 80K 120K 160K 200K SE +/- 181.65, N = 3 SE +/- 5046.21, N = 9 205983 206085 199607 1. (CC) gcc options: -pedantic -O3
Phoronix Test Suite v10.8.4