3900X + Polaris AMD Ryzen 9 3900X 12-Core testing with a ASUS TUF GAMING X570-PLUS (WI-FI) (2203 BIOS) and MSI AMD Radeon RX 470/480/570/570X/580/580X/590 8GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2101013-HA-3900XPOLA89&grs .
3900X + Polaris Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads) ASUS TUF GAMING X570-PLUS (WI-FI) (2203 BIOS) AMD Starship/Matisse 16GB Samsung SSD 970 EVO Plus 250GB MSI AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1366/2000MHz) AMD Ellesmere HDMI Audio LG Ultra HD Realtek RTL8111/8168/8411 + Intel-AC 9260 Ubuntu 20.04 5.9.0-050900rc6daily20200922-generic (x86_64) 20200921 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 21.0.0-devel (git-28a202f 2020-12-31 focal-oibaf-ppa) (LLVM 11.0.0) 1.2.145 GCC 9.3.0 ext4 1920x1080 5.10.4-051004-generic (x86_64) 5.11.0-rc1-phx (x86_64) 20201228 OpenBenchmarking.org 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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/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: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8701021 Graphics Details - GLAMOR Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected Python Details - RRR: Python 3.8.5
3900X + Polaris onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 1D - f32 - CPU pgbench: 1 - 1 - Read Only - Average Latency onednn: Recurrent Neural Network Inference - f32 - CPU pgbench: 100 - 50 - Read Write pgbench: 100 - 50 - Read Write - Average Latency pgbench: 1 - 1 - Read Only onednn: Recurrent Neural Network Training - f32 - CPU encode-wavpack: WAV To WavPack ncnn: CPU - blazeface pgbench: 100 - 1 - Read Only cryptsetup: Twofish-XTS 512b Decryption encode-ape: WAV To APE ncnn: Vulkan GPU - yolov4-tiny clomp: Static OMP Speedup cryptsetup: Twofish-XTS 256b Encryption ncnn: CPU - yolov4-tiny x264: H.264 Video Encoding pgbench: 100 - 1 - Read Only - Average Latency onednn: Convolution Batch Shapes Auto - f32 - CPU cryptsetup: Twofish-XTS 256b Decryption pgbench: 1 - 50 - Read Write - Average Latency pgbench: 1 - 50 - Read Write cryptsetup: AES-XTS 256b Decryption cryptsetup: AES-XTS 256b Encryption cryptsetup: AES-XTS 512b Encryption cryptsetup: AES-XTS 512b Decryption cryptsetup: Twofish-XTS 512b Encryption pgbench: 1 - 100 - Read Write pgbench: 1 - 100 - Read Write - Average Latency cryptsetup: Serpent-XTS 512b Decryption build-eigen: Time To Compile cryptsetup: Serpent-XTS 256b Encryption cryptsetup: Serpent-XTS 512b Encryption cryptsetup: Serpent-XTS 256b Decryption ncnn: CPU - googlenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 x265: Bosphorus 4K encode-opus: WAV To Opus Encode pgbench: 1 - 50 - Read Only ncnn: Vulkan GPU - efficientnet-b0 cryptsetup: PBKDF2-sha512 ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - mobilenet pgbench: 1 - 50 - Read Only - Average Latency cryptsetup: PBKDF2-whirlpool ncnn: Vulkan GPU - resnet50 vkmark: 1280 x 1024 ncnn: CPU-v2-v2 - mobilenet-v2 pgbench: 100 - 100 - Read Only - Average Latency ncnn: CPU - squeezenet_ssd pgbench: 100 - 50 - Read Only - Average Latency pgbench: 100 - 100 - Read Only onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU ncnn: CPU - resnet18 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: CPU - mnasnet kvazaar: Bosphorus 4K - Medium ncnn: CPU - efficientnet-b0 build2: Time To Compile kvazaar: Bosphorus 1080p - Very Fast ncnn: Vulkan GPU - alexnet kvazaar: Bosphorus 1080p - Ultra Fast ncnn: Vulkan GPU - mnasnet vkmark: 1920 x 1080 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - shufflenet-v2 pgbench: 100 - 50 - Read Only ncnn: CPU - regnety_400m pgbench: 1 - 100 - Read Only - Average Latency ncnn: Vulkan GPU - regnety_400m onednn: Deconvolution Batch shapes_1d - f32 - CPU pgbench: 1 - 1 - Read Write - Average Latency ncnn: Vulkan GPU - resnet18 ncnn: CPU - shufflenet-v2 pgbench: 1 - 100 - Read Only kvazaar: Bosphorus 4K - Ultra Fast pgbench: 1 - 1 - Read Write ncnn: CPU - resnet50 kvazaar: Bosphorus 1080p - Medium kvazaar: Bosphorus 4K - Very Fast ncnn: CPU-v3-v3 - mobilenet-v3 onednn: Deconvolution Batch shapes_3d - f32 - CPU x265: Bosphorus 1080p ncnn: CPU - vgg16 ncnn: CPU - alexnet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - blazeface unpack-firefox: firefox-84.0.source.tar.xz ncnn: CPU - mobilenet basis: UASTC Level 3 basis: UASTC Level 2 basis: UASTC Level 0 basis: ETC1S neatbench: openvino: Person Detection 0106 FP32 - CPU openvino: Person Detection 0106 FP32 - CPU openvino: Person Detection 0106 FP16 - CPU openvino: Person Detection 0106 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP32 - CPU openvino: Age Gender Recognition Retail 0013 FP32 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Face Detection 0106 FP32 - CPU openvino: Face Detection 0106 FP32 - CPU openvino: Face Detection 0106 FP16 - CPU openvino: Face Detection 0106 FP16 - CPU openvkl: vklBenchmarkVdbVolume openvkl: vklBenchmarkUnstructuredVolume openvkl: vklBenchmarkStructuredVolume openvkl: vklBenchmark oidn: Memorial onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU embree: Pathtracer ISPC - Crown embree: Pathtracer ISPC - Asian Dragon Obj embree: Pathtracer ISPC - Asian Dragon embree: Pathtracer - Crown embree: Pathtracer - Asian Dragon Obj embree: Pathtracer - Asian Dragon gegl: Tile Glass gegl: Reflect gegl: Wavelet Blur gegl: Crop gegl: Color Enhance gegl: Cartoon gegl: Antialias gegl: Scale gegl: Rotate 90 Degrees rsvg: SVG Files To PNG darktable: Server Rack - CPU-only darktable: Server Room - CPU-only darktable: Masskrug - CPU-only darktable: Boat - CPU-only hugin: Panorama Photo Assistant + Stitching Time montage: Mosaic of M17, K band, 1.5 deg x 1.5 deg dcraw: RAW To PPM Image Conversion gimp: auto-levels gimp: rotate gimp: resize gimp: unsharp-mask tjbench: rawtherapee: Total Benchmark Time webp: Quality 100, Lossless, Highest Compression webp: Quality 100, Lossless webp: Quality 100, Highest Compression webp: Quality 100 webp: Default libraw: Post-Processing Benchmark gmic: 3D Elevated Function In Rand Colors, 100 Times gmic: Plotting Isosurface Of A 3D Volume, 1000 Times gmic: 2D Function Plotting, 1000 Times inkscape: SVG Files To PNG graphics-magick: Swirl graphics-magick: Sharpen graphics-magick: Rotate graphics-magick: Resizing graphics-magick: Enhanced graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space encode-flac: WAV To FLAC encode-ogg: WAV To Ogg encode-mp3: WAV To MP3 avifenc: 10 avifenc: 8 avifenc: 2 avifenc: 0 rav1e: 1 rav1e: 5 rav1e: 6 rav1e: 10 libgav1: Chimera 1080p 10-bit libgav1: Chimera 1080p libgav1: Summer Nature 4K libgav1: Summer Nature 1080p svt-av1: Enc Mode 0 - 1080p svt-av1: Enc Mode 4 - 1080p svt-av1: Enc Mode 8 - 1080p aom-av1: Speed 0 Two-Pass aom-av1: Speed 4 Two-Pass aom-av1: Speed 6 Two-Pass aom-av1: Speed 6 Realtime aom-av1: Speed 8 Realtime dav1d: Chimera 1080p 10-bit dav1d: Chimera 1080p dav1d: Summer Nature 4K dav1d: Summer Nature 1080p vpxenc: Speed 0 vpxenc: Speed 5 ffmpeg: H.264 HD To NTSC DV kvazaar: Bosphorus 4K - Slow kvazaar: Bosphorus 1080p - Slow svt-hevc: 1080p 8-bit YUV To HEVC Video Encode svt-vp9: VMAF Optimized - Bosphorus 1080p svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p svt-vp9: Visual Quality Optimized - Bosphorus 1080p ocrmypdf: Processing 60 Page PDF Document tesseract-ocr: Time To OCR 7 Images indigobench: CPU - Bedroom indigobench: CPU - Supercar v-ray: CPU ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping smallpt: Global Illumination Renderer; 128 Samples luxcorerender: Rainbow Colors and Prism luxcorerender: DLSC aobench: 2048 x 2048 - Total Time radiance: SMP Parallel radiance: Serial appleseed: Material Tester appleseed: Disney Material appleseed: Emily tungsten: Volumetric Caustic tungsten: Non-Exponential tungsten: Water Caustic tungsten: Hair blender: Barbershop - CPU-Only blender: Pabellon Barcelona - CPU-Only blender: Fishy Cat - CPU-Only blender: Classroom - CPU-Only blender: BMW27 - CPU-Only yafaray: Total Time For Sample Scene rays1bench: Large Scene povray: Trace Time tachyon: Total Time c-ray: Total Time - 4K, 16 Rays Per Pixel ospray: San Miguel - Path Tracer ospray: San Miguel - SciVis ospray: NASA Streamlines - Path Tracer ospray: NASA Streamlines - SciVis ospray: XFrog Forest - Path Tracer ospray: XFrog Forest - SciVis ospray: Magnetic Reconnection - Path Tracer ospray: Magnetic Reconnection - SciVis onednn: Recurrent Neural Network Training - u8s8f32 - CPU pgbench: 100 - 100 - Read Write - Average Latency pgbench: 100 - 100 - Read Write pgbench: 100 - 1 - Read Write - Average Latency pgbench: 100 - 1 - Read Write Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 10.3172 4.78459 0.029 2304.60 9138 5.488 34776 3904.27 12.128 2.37 29761 420.7 11.099 27.08 32.2 428.8 26.53 135.58 0.033 22.3272 427.9 49.918 1002 2085.1 2081.4 1844.4 1844.4 429.4 957 104.551 723.7 71.658 736.8 740.4 723.7 16.34 5.39 19.08 7.107 420576 7.07 1737821 18.66 16.43 0.119 751194 27.75 6608 5.39 0.278 18.57 0.148 359412 0.867501 15.97 4.65 4.83 7.48 7.08 88.090 62.03 12.28 116.93 4.82 4942 16.22 6.30 337295 21.49 0.221 21.50 3.57564 1.098 15.92 6.32 453503 35.84 911 27.53 27.89 20.47 4.65 5.03296 60.27 59.16 12.28 59.56 2.32 17.546 16.47 9.235 10881 1.264 791 8.00465 4.30955 0.030 2097.96 8657 5.777 33818 3677.65 12.139 2.44 30241 434.7 11.206 27.12 32.1 435.4 26.05 131.47 0.033 21.7033 434.7 50.730 986 2109.8 2098.1 1865.0 1869.4 435.9 959 104.306 735.1 72.245 748.2 749.8 735.1 16.57 5.40 19.18 7.080 421604 7.05 1769325 18.76 16.57 0.119 763582 27.81 6664 5.40 0.280 18.61 0.149 356863 0.868645 16.18 4.66 4.86 7.46 7.12 89.062 62.24 12.21 117.47 4.82 4975 16.18 6.31 336573 21.54 0.221 21.49 3.54551 1.099 15.87 6.31 452199 36.12 910 27.33 27.82 20.54 4.68 5.05202 60.44 59.23 12.23 59.40 2.33 17.589 16.52 9.405 10657 1.513 669 8.00681 4.25293 0.027 2159.44 8422 5.941 36144 3673.92 11.948 2.33 31121 440.4 11.257 26.21 31.5 441.3 26.13 135.43 0.032 21.6515 440.6 49.258 1015 2148.4 2144.2 1899.1 1898.9 442.0 985 101.597 743.2 71.313 757.5 758.3 742.3 16.33 5.37 19.40 6.972 425848 7.01 1764323 18.69 16.37 0.117 763217 27.38 6576 5.38 0.276 18.76 0.147 361619 0.857362 15.98 4.66 4.82 7.45 7.07 88.924 62.71 12.19 118.17 4.79 4928 16.13 6.31 339648 21.45 0.219 21.49 3.55786 1.093 15.87 6.29 455761 36.06 915 27.34 27.89 20.51 4.67 5.04675 60.40 59.22 12.30 59.30 2.32 17.605 16.49 9.668 10373 1.562 644 8.01007 4.19200 0.027 2219.39 9052 5.540 36302 3734.56 12.457 2.31 31281 440.6 11.619 27.38 30.9 442.4 26.87 135.40 0.032 21.7438 441.1 49.224 1016 2135.1 2112.1 1896.0 1896.9 441.9 974 102.707 744.4 73.338 745.1 760.1 742.8 16.21 5.48 19.03 7.069 428685 7.14 1758791 18.98 16.65 0.117 758501 27.67 6563 5.46 0.278 18.83 0.147 360324 0.865668 15.99 4.71 4.80 7.39 7.04 89.081 62.45 12.32 117.25 4.84 4926 16.29 6.36 339732 21.34 0.220 21.68 3.55338 1.102 16.00 6.27 454815 36.07 908 27.54 27.68 20.39 4.67 5.06536 60.06 59.51 12.24 59.52 2.33 17.558 16.51 41.697 23.221 6.839 44.730 25.1 2863.61 2.05 2844.73 2.08 0.65 9041.53 0.65 9079.79 2161.79 2.76 2174.40 2.76 15836286.787879 1987918.4079916 65542933.791506 175.58 10.82 2388.68 2383.87 3988.91 2.02345 0.890048 1.92786 3.58178 4.24124 24.7319 14.8731 14.7346 16.5260 15.4994 15.3746 16.8105 29.749 30.445 61.616 8.382 56.631 89.402 37.64 5.823 38.444 24.317 0.187 3.855 4.588 11.813 45.743 70.715 39.848 12.039 11.343 7.407 15.090 222.076471 55.422 32.843 15.539 6.831 2.198 1.402 42.39 80.670 18.824 119.204 24.732 751 182 730 1379 292 355 1346 7.752 18.832 7.160 4.509 4.702 42.020 69.231 0.407 1.202 1.607 3.560 21.54 53.60 24.71 82.53 0.120 4.377 36.124 0.33 2.70 4.14 19.77 38.02 110.68 590.44 195.92 554.44 7.63 25.75 7.052 7.29 27.09 75.96 196.19 200.65 177.64 21.542 23.531 2.746 5.850 20547 660.199 7.179 2.60 2.42 32.315 179.453 552.166 162.035966 167.40638 271.240019 7.47658 5.86974 24.5054 18.2184 461.57 359.85 148.56 322.05 112.51 105.711 83.66 31.619 63.4140 43.336 1.45 18.87 5.43 27.03 1.83 3.50 200 12.82 4220.58 9.299 10781 1.518 663 OpenBenchmarking.org
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 3 6 9 12 15 SE +/- 0.00977, N = 3 SE +/- 0.01168, N = 3 SE +/- 0.03417, N = 3 SE +/- 0.00701, N = 3 10.31720 8.00465 8.00681 8.01007 MIN: 10.14 MIN: 7.84 MIN: 7.79 MIN: 7.83 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.0765 2.153 3.2295 4.306 5.3825 SE +/- 0.00691, N = 3 SE +/- 0.00839, N = 3 SE +/- 0.03458, N = 3 SE +/- 0.03067, N = 3 4.78459 4.30955 4.25293 4.19200 MIN: 4.54 MIN: 4.05 MIN: 3.98 MIN: 3.9 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Only - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.0068 0.0136 0.0204 0.0272 0.034 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.029 0.030 0.027 0.027 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 500 1000 1500 2000 2500 SE +/- 7.67, N = 3 SE +/- 25.25, N = 3 SE +/- 25.62, N = 6 SE +/- 17.85, N = 3 2304.60 2097.96 2159.44 2219.39 MIN: 2283.7 MIN: 2041.82 MIN: 2090.31 MIN: 2167.39 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2K 4K 6K 8K 10K SE +/- 127.86, N = 15 SE +/- 40.78, N = 3 SE +/- 137.31, N = 3 SE +/- 128.07, N = 15 9138 8657 8422 9052 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Write - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.3367 2.6734 4.0101 5.3468 6.6835 SE +/- 0.075, N = 15 SE +/- 0.027, N = 3 SE +/- 0.098, N = 3 SE +/- 0.078, N = 15 5.488 5.777 5.941 5.540 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Only Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 8K 16K 24K 32K 40K SE +/- 225.36, N = 3 SE +/- 294.74, N = 3 SE +/- 310.12, N = 3 SE +/- 281.42, N = 3 34776 33818 36144 36302 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 800 1600 2400 3200 4000 SE +/- 15.40, N = 3 SE +/- 13.58, N = 3 SE +/- 7.70, N = 3 SE +/- 2.61, N = 3 3904.27 3677.65 3673.92 3734.56 MIN: 3855.3 MIN: 3650.2 MIN: 3655.31 MIN: 3718.9 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
WavPack Audio Encoding WAV To WavPack OpenBenchmarking.org Seconds, Fewer Is Better WavPack Audio Encoding 5.3 WAV To WavPack Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 3 6 9 12 15 SE +/- 0.08, N = 5 SE +/- 0.14, N = 5 SE +/- 0.04, N = 5 SE +/- 0.08, N = 5 12.13 12.14 11.95 12.65 1. (CXX) g++ options: -rdynamic
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.549 1.098 1.647 2.196 2.745 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 2.37 2.44 2.33 2.31 MIN: 2.27 / MAX: 2.51 MIN: 2.3 / MAX: 2.54 MIN: 2.26 / MAX: 2.88 MIN: 2.27 / MAX: 2.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Only Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 7K 14K 21K 28K 35K SE +/- 159.76, N = 3 SE +/- 301.46, N = 3 SE +/- 148.88, N = 3 SE +/- 208.68, N = 3 29761 30241 31121 31281 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Cryptsetup Twofish-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Decryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 100 200 300 400 500 SE +/- 3.50, N = 2 SE +/- 7.96, N = 3 SE +/- 0.70, N = 2 SE +/- 1.61, N = 3 420.7 434.7 440.4 440.6
Monkey Audio Encoding WAV To APE OpenBenchmarking.org Seconds, Fewer Is Better Monkey Audio Encoding 3.99.6 WAV To APE Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 3 6 9 12 15 SE +/- 0.05, N = 5 SE +/- 0.10, N = 5 SE +/- 0.15, N = 5 SE +/- 0.08, N = 5 11.10 11.21 11.26 11.54 1. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 6 12 18 24 30 SE +/- 0.42, N = 3 SE +/- 0.40, N = 3 SE +/- 0.07, N = 3 SE +/- 0.45, N = 3 27.08 27.12 26.21 27.38 MIN: 26.06 / MAX: 36.14 MIN: 25.92 / MAX: 75.32 MIN: 25.86 / MAX: 34.86 MIN: 26.28 / MAX: 31.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 7 14 21 28 35 SE +/- 0.15, N = 3 SE +/- 0.28, N = 3 SE +/- 0.24, N = 3 SE +/- 0.39, N = 4 32.2 32.1 31.5 30.9 1. (CC) gcc options: -fopenmp -O3 -lm
Cryptsetup Twofish-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Encryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 100 200 300 400 500 SE +/- 7.51, N = 3 SE +/- 7.70, N = 3 SE +/- 0.61, N = 3 SE +/- 1.74, N = 3 428.8 435.4 441.3 442.4
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 6 12 18 24 30 SE +/- 0.43, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 SE +/- 0.47, N = 3 26.53 26.05 26.13 26.87 MIN: 25.91 / MAX: 32.22 MIN: 25.68 / MAX: 28.05 MIN: 25.91 / MAX: 35.78 MIN: 26.08 / MAX: 29.22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 30 60 90 120 150 SE +/- 1.50, N = 7 SE +/- 1.54, N = 3 SE +/- 1.94, N = 3 SE +/- 1.50, N = 6 135.58 131.47 135.43 133.73 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Only - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.0074 0.0148 0.0222 0.0296 0.037 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.033 0.033 0.032 0.032 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 22.33 21.70 21.65 21.74 MIN: 21.78 MIN: 21.1 MIN: 21.05 MIN: 21.15 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Cryptsetup Twofish-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Decryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 100 200 300 400 500 SE +/- 6.96, N = 3 SE +/- 8.09, N = 3 SE +/- 0.41, N = 3 SE +/- 1.60, N = 3 427.9 434.7 440.6 441.1
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.83, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 49.92 50.73 49.26 49.22 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Write Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 200 400 600 800 1000 SE +/- 1.26, N = 3 SE +/- 15.84, N = 3 SE +/- 0.27, N = 3 SE +/- 1.46, N = 3 1002 986 1015 1016 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Cryptsetup AES-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Decryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 500 1000 1500 2000 2500 SE +/- 35.59, N = 3 SE +/- 36.87, N = 3 SE +/- 4.89, N = 3 SE +/- 2.60, N = 2 2085.1 2109.8 2148.4 2135.1
Cryptsetup AES-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Encryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 500 1000 1500 2000 2500 SE +/- 37.92, N = 3 SE +/- 28.55, N = 3 SE +/- 0.92, N = 3 SE +/- 23.64, N = 3 2081.4 2098.1 2144.2 2112.1
Cryptsetup AES-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Encryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 400 800 1200 1600 2000 SE +/- 29.59, N = 3 SE +/- 31.30, N = 3 SE +/- 3.53, N = 3 SE +/- 7.52, N = 3 1844.4 1865.0 1899.1 1896.0
Cryptsetup AES-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Decryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 400 800 1200 1600 2000 SE +/- 29.78, N = 3 SE +/- 32.26, N = 3 SE +/- 3.96, N = 3 SE +/- 8.03, N = 3 1844.4 1869.4 1898.9 1896.9
Cryptsetup Twofish-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Encryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 100 200 300 400 500 SE +/- 6.94, N = 3 SE +/- 8.06, N = 3 SE +/- 0.42, N = 3 SE +/- 1.73, N = 3 429.4 435.9 442.0 441.9
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 200 400 600 800 1000 SE +/- 2.09, N = 3 SE +/- 0.97, N = 3 SE +/- 1.65, N = 3 SE +/- 3.74, N = 3 957 959 985 974 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Write - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 20 40 60 80 100 SE +/- 0.23, N = 3 SE +/- 0.11, N = 3 SE +/- 0.18, N = 3 SE +/- 0.39, N = 3 104.55 104.31 101.60 102.71 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Cryptsetup Serpent-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Decryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 160 320 480 640 800 SE +/- 11.06, N = 3 SE +/- 13.67, N = 3 SE +/- 0.52, N = 3 SE +/- 2.79, N = 3 723.7 735.1 743.2 744.4
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 16 32 48 64 80 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 SE +/- 0.49, N = 3 71.66 72.25 71.31 73.34
Cryptsetup Serpent-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Encryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 160 320 480 640 800 SE +/- 12.35, N = 3 SE +/- 13.16, N = 3 SE +/- 0.37, N = 3 SE +/- 10.29, N = 3 736.8 748.2 757.5 745.1
Cryptsetup Serpent-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Encryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 160 320 480 640 800 SE +/- 19.10, N = 2 SE +/- 13.85, N = 3 SE +/- 0.55, N = 3 SE +/- 2.71, N = 3 740.4 749.8 758.3 760.1
Cryptsetup Serpent-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Decryption Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 160 320 480 640 800 SE +/- 11.00, N = 3 SE +/- 13.99, N = 3 SE +/- 1.07, N = 3 SE +/- 1.36, N = 3 723.7 735.1 742.3 742.8
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.20, N = 3 SE +/- 0.04, N = 3 16.34 16.57 16.33 16.21 MIN: 15.95 / MAX: 20.77 MIN: 16 / MAX: 17.41 MIN: 15.81 / MAX: 18.11 MIN: 15.75 / MAX: 16.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.233 2.466 3.699 4.932 6.165 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.39 5.40 5.37 5.48 MIN: 5.25 / MAX: 6.72 MIN: 5.28 / MAX: 6.5 MIN: 5.26 / MAX: 6.45 MIN: 5.37 / MAX: 6.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
x265 Video Input: Bosphorus 4K OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 19.08 19.18 19.40 19.03 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2 4 6 8 10 SE +/- 0.074, N = 5 SE +/- 0.074, N = 5 SE +/- 0.034, N = 5 SE +/- 0.047, N = 5 7.107 7.080 6.972 7.055 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 90K 180K 270K 360K 450K SE +/- 1677.28, N = 3 SE +/- 833.77, N = 3 SE +/- 3021.99, N = 3 SE +/- 1552.64, N = 3 420576 421604 425848 428685 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 7.07 7.05 7.01 7.14 MIN: 6.96 / MAX: 7.6 MIN: 6.97 / MAX: 7.7 MIN: 6.94 / MAX: 7.09 MIN: 7.06 / MAX: 7.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup PBKDF2-sha512 OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-sha512 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 400K 800K 1200K 1600K 2000K SE +/- 26354.44, N = 3 SE +/- 8115.50, N = 3 SE +/- 5494.25, N = 3 SE +/- 19263.23, N = 3 1737821 1769325 1764323 1758791
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.04, N = 3 18.66 18.76 18.69 18.98 MIN: 18.29 / MAX: 30.89 MIN: 18.46 / MAX: 19.32 MIN: 18.25 / MAX: 19.2 MIN: 18.6 / MAX: 34.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mobilenet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.16, N = 3 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 16.43 16.57 16.37 16.65 MIN: 16.02 / MAX: 17.58 MIN: 16.09 / MAX: 27.26 MIN: 16.11 / MAX: 19.85 MIN: 16.33 / MAX: 17.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PostgreSQL pgbench Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 50 - Mode: Read Only - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.0268 0.0536 0.0804 0.1072 0.134 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 0.119 0.119 0.117 0.117 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Cryptsetup PBKDF2-whirlpool OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-whirlpool Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 160K 320K 480K 640K 800K SE +/- 4959.25, N = 3 SE +/- 4616.94, N = 3 SE +/- 4832.23, N = 3 SE +/- 6987.07, N = 3 751194 763582 763217 758501
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet50 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 7 14 21 28 35 SE +/- 0.20, N = 3 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 SE +/- 0.22, N = 3 27.75 27.81 27.38 27.67 MIN: 27.17 / MAX: 117.41 MIN: 27.2 / MAX: 55 MIN: 27.15 / MAX: 28.04 MIN: 27.24 / MAX: 31.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
VKMark Resolution: 1280 x 1024 OpenBenchmarking.org VKMark Score, More Is Better VKMark 2020-05-21 Resolution: 1280 x 1024 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1400 2800 4200 5600 7000 SE +/- 11.46, N = 3 SE +/- 7.31, N = 3 SE +/- 4.93, N = 3 SE +/- 1.67, N = 3 6608 6664 6576 6563 1. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.2285 2.457 3.6855 4.914 6.1425 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 5.39 5.40 5.38 5.46 MIN: 5.29 / MAX: 6.65 MIN: 5.28 / MAX: 7.47 MIN: 5.21 / MAX: 15.03 MIN: 5.36 / MAX: 6.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.063 0.126 0.189 0.252 0.315 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.000, N = 3 0.278 0.280 0.276 0.278 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 18.57 18.61 18.76 18.83 MIN: 18.14 / MAX: 19.41 MIN: 18.15 / MAX: 19.06 MIN: 18.36 / MAX: 20.33 MIN: 18.46 / MAX: 32.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.0335 0.067 0.1005 0.134 0.1675 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.148 0.149 0.147 0.147 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Only Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 80K 160K 240K 320K 400K SE +/- 341.85, N = 3 SE +/- 1059.83, N = 3 SE +/- 797.43, N = 3 SE +/- 497.89, N = 3 359412 356863 361619 360324 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.1954 0.3908 0.5862 0.7816 0.977 SE +/- 0.001024, N = 3 SE +/- 0.005917, N = 3 SE +/- 0.001376, N = 3 SE +/- 0.003522, N = 3 0.867501 0.868645 0.857362 0.865668 MIN: 0.84 MIN: 0.83 MIN: 0.83 MIN: 0.83 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 15.97 16.18 15.98 15.99 MIN: 15.79 / MAX: 19.67 MIN: 15.76 / MAX: 26.72 MIN: 15.72 / MAX: 16.45 MIN: 15.84 / MAX: 20.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.0598 2.1196 3.1794 4.2392 5.299 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.65 4.66 4.66 4.71 MIN: 4.6 / MAX: 5.85 MIN: 4.61 / MAX: 5.8 MIN: 4.59 / MAX: 5.72 MIN: 4.64 / MAX: 5.45 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.0935 2.187 3.2805 4.374 5.4675 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 4.83 4.86 4.82 4.80 MIN: 4.75 / MAX: 5.75 MIN: 4.75 / MAX: 5.99 MIN: 4.7 / MAX: 5.68 MIN: 4.74 / MAX: 5.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Kvazaar Video Input: Bosphorus 4K - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Medium Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 7.48 7.46 7.45 7.39 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 7.08 7.12 7.07 7.04 MIN: 6.96 / MAX: 7.5 MIN: 7.06 / MAX: 8.35 MIN: 6.93 / MAX: 16.48 MIN: 6.92 / MAX: 7.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.38, N = 3 SE +/- 0.23, N = 3 SE +/- 0.10, N = 3 88.09 89.06 88.92 89.08
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 14 28 42 56 70 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.00, N = 3 62.03 62.24 62.71 62.45 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: alexnet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 12.28 12.21 12.19 12.32 MIN: 12.06 / MAX: 12.64 MIN: 12.03 / MAX: 13.46 MIN: 12.03 / MAX: 14.9 MIN: 12.12 / MAX: 12.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 30 60 90 120 150 SE +/- 0.21, N = 3 SE +/- 0.33, N = 3 SE +/- 0.11, N = 3 SE +/- 0.23, N = 3 116.93 117.47 118.17 117.25 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mnasnet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.089 2.178 3.267 4.356 5.445 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 4.82 4.82 4.79 4.84 MIN: 4.74 / MAX: 5.95 MIN: 4.74 / MAX: 5.92 MIN: 4.73 / MAX: 5.93 MIN: 4.76 / MAX: 5.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
VKMark Resolution: 1920 x 1080 OpenBenchmarking.org VKMark Score, More Is Better VKMark 2020-05-21 Resolution: 1920 x 1080 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1100 2200 3300 4400 5500 SE +/- 2.33, N = 3 SE +/- 4.36, N = 3 SE +/- 1.00, N = 3 SE +/- 4.70, N = 3 4942 4975 4928 4926 1. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: googlenet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.07, N = 3 16.22 16.18 16.13 16.29 MIN: 15.77 / MAX: 17.11 MIN: 15.72 / MAX: 19.8 MIN: 15.76 / MAX: 17.05 MIN: 15.9 / MAX: 16.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 6.30 6.31 6.31 6.36 MIN: 6.24 / MAX: 7.4 MIN: 6.22 / MAX: 7.38 MIN: 6.18 / MAX: 7.34 MIN: 6.28 / MAX: 6.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PostgreSQL pgbench Scaling Factor: 100 - Clients: 50 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 50 - Mode: Read Only Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 70K 140K 210K 280K 350K SE +/- 894.55, N = 3 SE +/- 660.15, N = 3 SE +/- 1501.79, N = 3 SE +/- 1369.50, N = 3 337295 336573 339648 339732 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 5 10 15 20 25 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 21.49 21.54 21.45 21.34 MIN: 21.17 / MAX: 89.86 MIN: 21.23 / MAX: 22.28 MIN: 21.15 / MAX: 22.65 MIN: 21.12 / MAX: 22 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.0497 0.0994 0.1491 0.1988 0.2485 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 0.221 0.221 0.219 0.220 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 21.50 21.49 21.49 21.68 MIN: 21.29 / MAX: 22.87 MIN: 21.32 / MAX: 22.08 MIN: 21.25 / MAX: 24.16 MIN: 21.45 / MAX: 33.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.8045 1.609 2.4135 3.218 4.0225 SE +/- 0.01529, N = 3 SE +/- 0.00923, N = 3 SE +/- 0.00720, N = 3 SE +/- 0.01395, N = 3 3.57564 3.54551 3.55786 3.55338 MIN: 3.49 MIN: 3.46 MIN: 3.48 MIN: 3.47 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Write - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.248 0.496 0.744 0.992 1.24 SE +/- 0.000, N = 3 SE +/- 0.001, N = 3 SE +/- 0.002, N = 3 SE +/- 0.011, N = 3 1.098 1.099 1.093 1.102 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet18 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 15.92 15.87 15.87 16.00 MIN: 15.76 / MAX: 17.57 MIN: 15.74 / MAX: 16.44 MIN: 15.7 / MAX: 19.75 MIN: 15.86 / MAX: 19.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 6.32 6.31 6.29 6.27 MIN: 6.21 / MAX: 22.45 MIN: 6.22 / MAX: 7.07 MIN: 6.18 / MAX: 6.84 MIN: 6.18 / MAX: 7.86 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
PostgreSQL pgbench Scaling Factor: 1 - Clients: 100 - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 100 - Mode: Read Only Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 100K 200K 300K 400K 500K SE +/- 149.78, N = 3 SE +/- 761.26, N = 3 SE +/- 574.62, N = 3 SE +/- 1385.84, N = 3 453503 452199 455761 454815 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Kvazaar Video Input: Bosphorus 4K - Video Preset: Ultra Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 8 16 24 32 40 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 35.84 36.12 36.06 36.07 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
PostgreSQL pgbench Scaling Factor: 1 - Clients: 1 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 1 - Clients: 1 - Mode: Read Write Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 200 400 600 800 1000 SE +/- 0.37, N = 3 SE +/- 0.98, N = 3 SE +/- 1.38, N = 3 SE +/- 8.79, N = 3 911 910 915 908 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 6 12 18 24 30 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.11, N = 3 27.53 27.33 27.34 27.54 MIN: 27.11 / MAX: 28.7 MIN: 27.04 / MAX: 27.83 MIN: 27.14 / MAX: 30.97 MIN: 27.19 / MAX: 39.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Medium OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Medium Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 27.89 27.82 27.89 27.68 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 4K - Video Preset: Very Fast OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 20.47 20.54 20.51 20.39 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.053 2.106 3.159 4.212 5.265 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 4.65 4.68 4.67 4.67 MIN: 4.6 / MAX: 5.89 MIN: 4.6 / MAX: 5.83 MIN: 4.57 / MAX: 5.3 MIN: 4.6 / MAX: 5.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 1.1397 2.2794 3.4191 4.5588 5.6985 SE +/- 0.00318, N = 3 SE +/- 0.00045, N = 3 SE +/- 0.01033, N = 3 SE +/- 0.00652, N = 3 5.03296 5.05202 5.04675 5.06536 MIN: 4.97 MIN: 4.95 MIN: 4.97 MIN: 4.98 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 14 28 42 56 70 SE +/- 0.16, N = 3 SE +/- 0.16, N = 3 SE +/- 0.23, N = 3 SE +/- 0.03, N = 3 60.27 60.44 60.40 60.06 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 13 26 39 52 65 SE +/- 0.12, N = 3 SE +/- 0.24, N = 3 SE +/- 0.08, N = 3 SE +/- 0.10, N = 3 59.16 59.23 59.22 59.51 MIN: 58.33 / MAX: 92.19 MIN: 57.92 / MAX: 86.76 MIN: 58.43 / MAX: 60.85 MIN: 58.76 / MAX: 70.64 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 12.28 12.23 12.30 12.24 MIN: 12.11 / MAX: 14.19 MIN: 12.05 / MAX: 12.95 MIN: 12.1 / MAX: 12.66 MIN: 12.07 / MAX: 14.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: vgg16 Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 13 26 39 52 65 SE +/- 0.13, N = 3 SE +/- 0.11, N = 3 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 59.56 59.40 59.30 59.52 MIN: 58.63 / MAX: 83.96 MIN: 58.53 / MAX: 96.54 MIN: 58.5 / MAX: 63.18 MIN: 58.66 / MAX: 68.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: blazeface Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.5243 1.0486 1.5729 2.0972 2.6215 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.32 2.33 2.32 2.33 MIN: 2.29 / MAX: 2.43 MIN: 2.29 / MAX: 3.41 MIN: 2.29 / MAX: 2.41 MIN: 2.29 / MAX: 2.42 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Unpacking Firefox Extracting: firefox-84.0.source.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking Firefox 84.0 Extracting: firefox-84.0.source.tar.xz Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 4 8 12 16 20 SE +/- 0.10, N = 4 SE +/- 0.06, N = 4 SE +/- 0.02, N = 4 SE +/- 0.11, N = 4 17.55 17.59 17.61 17.56
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 16.47 16.52 16.49 16.51 MIN: 16.18 / MAX: 18.49 MIN: 16.15 / MAX: 18.17 MIN: 16.23 / MAX: 26.18 MIN: 16.25 / MAX: 20.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Basis Universal Settings: UASTC Level 3 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 RRR 10 20 30 40 50 SE +/- 0.05, N = 3 41.70 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Basis Universal Settings: UASTC Level 2 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 RRR 6 12 18 24 30 SE +/- 0.04, N = 3 23.22 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Basis Universal Settings: UASTC Level 0 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 0 RRR 2 4 6 8 10 SE +/- 0.062, N = 3 6.839 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Basis Universal Settings: ETC1S OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: ETC1S RRR 10 20 30 40 50 SE +/- 0.20, N = 3 44.73 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
NeatBench OpenBenchmarking.org FPS, More Is Better NeatBench 5 RRR 6 12 18 24 30 SE +/- 0.03, N = 3 25.1
OpenVINO Model: Person Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU RRR 600 1200 1800 2400 3000 SE +/- 18.15, N = 3 2863.61
OpenVINO Model: Person Detection 0106 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU RRR 0.4613 0.9226 1.3839 1.8452 2.3065 SE +/- 0.01, N = 3 2.05
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU RRR 600 1200 1800 2400 3000 SE +/- 7.71, N = 3 2844.73
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU RRR 0.468 0.936 1.404 1.872 2.34 SE +/- 0.01, N = 3 2.08
OpenVINO Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU RRR 0.1463 0.2926 0.4389 0.5852 0.7315 SE +/- 0.00, N = 3 0.65
OpenVINO Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP32 - Device: CPU RRR 2K 4K 6K 8K 10K SE +/- 20.22, N = 3 9041.53
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU RRR 0.1463 0.2926 0.4389 0.5852 0.7315 SE +/- 0.00, N = 3 0.65
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU RRR 2K 4K 6K 8K 10K SE +/- 28.29, N = 3 9079.79
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU RRR 500 1000 1500 2000 2500 SE +/- 2.70, N = 3 2161.79
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU RRR 0.621 1.242 1.863 2.484 3.105 SE +/- 0.00, N = 3 2.76
OpenVINO Model: Face Detection 0106 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU RRR 500 1000 1500 2000 2500 SE +/- 3.74, N = 3 2174.40
OpenVINO Model: Face Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU RRR 0.621 1.242 1.863 2.484 3.105 SE +/- 0.01, N = 3 2.76
OpenVKL Benchmark: vklBenchmarkVdbVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkVdbVolume RRR 3M 6M 9M 12M 15M SE +/- 112679.77, N = 3 15836286.79 MIN: 935966 / MAX: 67276224
OpenVKL Benchmark: vklBenchmarkUnstructuredVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkUnstructuredVolume RRR 400K 800K 1200K 1600K 2000K SE +/- 10860.54, N = 3 1987918.41 MIN: 28787 / MAX: 6602247
OpenVKL Benchmark: vklBenchmarkStructuredVolume OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmarkStructuredVolume RRR 14M 28M 42M 56M 70M SE +/- 736858.97, N = 7 65542933.79 MIN: 958636 / MAX: 594957960
OpenVKL Benchmark: vklBenchmark OpenBenchmarking.org Items / Sec, More Is Better OpenVKL 0.9 Benchmark: vklBenchmark RRR 40 80 120 160 200 SE +/- 0.05, N = 3 175.58 MIN: 1 / MAX: 628
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.2.0 Scene: Memorial RRR 3 6 9 12 15 SE +/- 0.01, N = 3 10.82
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU RRR 500 1000 1500 2000 2500 SE +/- 11.23, N = 3 2388.68 MIN: 2362.7 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU RRR 500 1000 1500 2000 2500 SE +/- 5.68, N = 3 2383.87 MIN: 2364.7 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU RRR 900 1800 2700 3600 4500 SE +/- 7.25, N = 3 3988.91 MIN: 3969.05 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU RRR 0.4553 0.9106 1.3659 1.8212 2.2765 SE +/- 0.00938, N = 3 2.02345 MIN: 1.95 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU RRR 0.2003 0.4006 0.6009 0.8012 1.0015 SE +/- 0.007086, N = 3 0.890048 MIN: 0.82 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU RRR 0.4338 0.8676 1.3014 1.7352 2.169 SE +/- 0.00409, N = 3 1.92786 MIN: 1.89 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU RRR 0.8059 1.6118 2.4177 3.2236 4.0295 SE +/- 0.00094, N = 3 3.58178 MIN: 3.48 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU RRR 0.9543 1.9086 2.8629 3.8172 4.7715 SE +/- 0.00633, N = 3 4.24124 MIN: 4.07 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU RRR 6 12 18 24 30 SE +/- 0.01, N = 3 24.73 MIN: 24.37 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer ISPC - Model: Crown RRR 4 8 12 16 20 SE +/- 0.03, N = 3 14.87 MIN: 14.7 / MAX: 15.17
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer ISPC - Model: Asian Dragon Obj RRR 4 8 12 16 20 SE +/- 0.05, N = 3 14.73 MIN: 14.21 / MAX: 15.01
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer ISPC - Model: Asian Dragon RRR 4 8 12 16 20 SE +/- 0.06, N = 3 16.53 MIN: 16.38 / MAX: 16.92
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Crown RRR 4 8 12 16 20 SE +/- 0.03, N = 3 15.50 MIN: 15.34 / MAX: 15.78
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Asian Dragon Obj RRR 4 8 12 16 20 SE +/- 0.02, N = 3 15.37 MIN: 15.25 / MAX: 15.62
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Asian Dragon RRR 4 8 12 16 20 SE +/- 0.06, N = 3 16.81 MIN: 16.62 / MAX: 17.18
GEGL Operation: Tile Glass OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Tile Glass RRR 7 14 21 28 35 SE +/- 0.06, N = 3 29.75
GEGL Operation: Reflect OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Reflect RRR 7 14 21 28 35 SE +/- 0.04, N = 3 30.45
GEGL Operation: Wavelet Blur OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Wavelet Blur RRR 14 28 42 56 70 SE +/- 0.11, N = 3 61.62
GEGL Operation: Crop OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Crop RRR 2 4 6 8 10 SE +/- 0.018, N = 3 8.382
GEGL Operation: Color Enhance OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Color Enhance RRR 13 26 39 52 65 SE +/- 0.02, N = 3 56.63
GEGL Operation: Cartoon OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Cartoon RRR 20 40 60 80 100 SE +/- 0.35, N = 3 89.40
GEGL Operation: Antialias OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Antialias RRR 9 18 27 36 45 SE +/- 0.17, N = 3 37.64
GEGL Operation: Scale OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Scale RRR 1.3102 2.6204 3.9306 5.2408 6.551 SE +/- 0.022, N = 3 5.823
GEGL Operation: Rotate 90 Degrees OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Rotate 90 Degrees RRR 9 18 27 36 45 SE +/- 0.17, N = 3 38.44
librsvg Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better librsvg Operation: SVG Files To PNG RRR 6 12 18 24 30 SE +/- 0.11, N = 3 24.32 1. rsvg-convert version 2.48.9
Darktable Test: Server Rack - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.0.1 Test: Server Rack - Acceleration: CPU-only RRR 0.0421 0.0842 0.1263 0.1684 0.2105 SE +/- 0.000, N = 3 0.187
Darktable Test: Server Room - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.0.1 Test: Server Room - Acceleration: CPU-only RRR 0.8674 1.7348 2.6022 3.4696 4.337 SE +/- 0.006, N = 3 3.855
Darktable Test: Masskrug - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.0.1 Test: Masskrug - Acceleration: CPU-only RRR 1.0323 2.0646 3.0969 4.1292 5.1615 SE +/- 0.013, N = 3 4.588
Darktable Test: Boat - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.0.1 Test: Boat - Acceleration: CPU-only RRR 3 6 9 12 15 SE +/- 0.00, N = 3 11.81
Hugin Panorama Photo Assistant + Stitching Time OpenBenchmarking.org Seconds, Fewer Is Better Hugin Panorama Photo Assistant + Stitching Time RRR 10 20 30 40 50 SE +/- 0.38, N = 3 45.74
Montage Astronomical Image Mosaic Engine Mosaic of M17, K band, 1.5 deg x 1.5 deg OpenBenchmarking.org Seconds, Fewer Is Better Montage Astronomical Image Mosaic Engine 6.0 Mosaic of M17, K band, 1.5 deg x 1.5 deg RRR 16 32 48 64 80 SE +/- 0.29, N = 3 70.72 1. (CC) gcc options: -std=gnu99 -lcfitsio -lm -O2
dcraw RAW To PPM Image Conversion OpenBenchmarking.org Seconds, Fewer Is Better dcraw RAW To PPM Image Conversion RRR 9 18 27 36 45 SE +/- 0.01, N = 3 39.85 1. (CC) gcc options: -lm
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: auto-levels RRR 3 6 9 12 15 SE +/- 0.05, N = 3 12.04
GIMP Test: rotate OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: rotate RRR 3 6 9 12 15 SE +/- 0.02, N = 3 11.34
GIMP Test: resize OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: resize RRR 2 4 6 8 10 SE +/- 0.010, N = 3 7.407
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: unsharp-mask RRR 4 8 12 16 20 SE +/- 0.10, N = 3 15.09
libjpeg-turbo tjbench OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 2.0.2 RRR 50 100 150 200 250 SE +/- 2.99, N = 4 222.08 1. (CC) gcc options: -O3 -rdynamic
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time RRR 12 24 36 48 60 SE +/- 0.07, N = 3 55.42 1. RawTherapee, version 5.8, command line.
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression RRR 8 16 24 32 40 SE +/- 0.31, N = 3 32.84 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless RRR 4 8 12 16 20 SE +/- 0.19, N = 3 15.54 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression RRR 2 4 6 8 10 SE +/- 0.033, N = 3 6.831 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 RRR 0.4946 0.9892 1.4838 1.9784 2.473 SE +/- 0.026, N = 3 2.198 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default RRR 0.3155 0.631 0.9465 1.262 1.5775 SE +/- 0.001, N = 3 1.402 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark RRR 10 20 30 40 50 SE +/- 0.10, N = 3 42.39 1. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
G'MIC Test: 3D Elevated Function In Random Colors, 100 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 3D Elevated Function In Random Colors, 100 Times RRR 20 40 60 80 100 SE +/- 1.18, N = 3 80.67 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: Plotting Isosurface Of A 3D Volume, 1000 Times RRR 5 10 15 20 25 SE +/- 0.29, N = 3 18.82 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
G'MIC Test: 2D Function Plotting, 1000 Times OpenBenchmarking.org Seconds, Fewer Is Better G'MIC Test: 2D Function Plotting, 1000 Times RRR 30 60 90 120 150 SE +/- 0.43, N = 3 119.20 1. Version 2.4.5, Copyright (c) 2008-2019, David Tschumperle.
Inkscape Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better Inkscape Operation: SVG Files To PNG RRR 6 12 18 24 30 SE +/- 0.21, N = 3 24.73 1. Inkscape 0.92.5 (2060ec1f9f, 2020-04-08)
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl RRR 160 320 480 640 800 751 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen RRR 40 80 120 160 200 SE +/- 0.67, N = 3 182 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate RRR 160 320 480 640 800 SE +/- 10.35, N = 3 730 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing RRR 300 600 900 1200 1500 SE +/- 1.73, N = 3 1379 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced RRR 60 120 180 240 300 SE +/- 0.33, N = 3 292 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian RRR 80 160 240 320 400 SE +/- 0.88, N = 3 355 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space RRR 300 600 900 1200 1500 SE +/- 4.37, N = 3 1346 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC RRR 2 4 6 8 10 SE +/- 0.032, N = 5 7.752 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
Ogg Audio Encoding WAV To Ogg OpenBenchmarking.org Seconds, Fewer Is Better Ogg Audio Encoding 1.3.4 WAV To Ogg RRR 5 10 15 20 25 SE +/- 0.13, N = 3 18.83 1. (CC) gcc options: -O2 -ffast-math -fsigned-char
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 RRR 2 4 6 8 10 SE +/- 0.114, N = 3 7.160 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 10 RRR 1.0145 2.029 3.0435 4.058 5.0725 SE +/- 0.017, N = 3 4.509 1. (CXX) g++ options: -O3 -fPIC
libavif avifenc Encoder Speed: 8 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 8 RRR 1.058 2.116 3.174 4.232 5.29 SE +/- 0.016, N = 3 4.702 1. (CXX) g++ options: -O3 -fPIC
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 2 RRR 10 20 30 40 50 SE +/- 0.11, N = 3 42.02 1. (CXX) g++ options: -O3 -fPIC
libavif avifenc Encoder Speed: 0 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 0 RRR 15 30 45 60 75 SE +/- 0.14, N = 3 69.23 1. (CXX) g++ options: -O3 -fPIC
rav1e Speed: 1 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 1 RRR 0.0916 0.1832 0.2748 0.3664 0.458 SE +/- 0.001, N = 3 0.407
rav1e Speed: 5 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 5 RRR 0.2705 0.541 0.8115 1.082 1.3525 SE +/- 0.003, N = 3 1.202
rav1e Speed: 6 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 6 RRR 0.3616 0.7232 1.0848 1.4464 1.808 SE +/- 0.001, N = 3 1.607
rav1e Speed: 10 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 10 RRR 0.801 1.602 2.403 3.204 4.005 SE +/- 0.004, N = 3 3.560
libgav1 Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Chimera 1080p 10-bit RRR 5 10 15 20 25 SE +/- 0.04, N = 3 21.54 1. (CXX) g++ options: -O3 -lpthread
libgav1 Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Chimera 1080p RRR 12 24 36 48 60 SE +/- 0.09, N = 3 53.60 1. (CXX) g++ options: -O3 -lpthread
libgav1 Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Summer Nature 4K RRR 6 12 18 24 30 SE +/- 0.02, N = 3 24.71 1. (CXX) g++ options: -O3 -lpthread
libgav1 Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Summer Nature 1080p RRR 20 40 60 80 100 SE +/- 0.06, N = 3 82.53 1. (CXX) g++ options: -O3 -lpthread
SVT-AV1 Encoder Mode: Enc Mode 0 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 0 - Input: 1080p RRR 0.027 0.054 0.081 0.108 0.135 SE +/- 0.000, N = 3 0.120 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
SVT-AV1 Encoder Mode: Enc Mode 4 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 4 - Input: 1080p RRR 0.9848 1.9696 2.9544 3.9392 4.924 SE +/- 0.007, N = 3 4.377 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
SVT-AV1 Encoder Mode: Enc Mode 8 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p RRR 8 16 24 32 40 SE +/- 0.21, N = 3 36.12 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
AOM AV1 Encoder Mode: Speed 0 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 0 Two-Pass RRR 0.0743 0.1486 0.2229 0.2972 0.3715 SE +/- 0.00, N = 3 0.33 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 4 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 4 Two-Pass RRR 0.6075 1.215 1.8225 2.43 3.0375 SE +/- 0.00, N = 3 2.70 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 6 Two-Pass OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Two-Pass RRR 0.9315 1.863 2.7945 3.726 4.6575 SE +/- 0.02, N = 3 4.14 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 6 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 6 Realtime RRR 5 10 15 20 25 SE +/- 0.11, N = 3 19.77 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
AOM AV1 Encoder Mode: Speed 8 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2.0 Encoder Mode: Speed 8 Realtime RRR 9 18 27 36 45 SE +/- 0.07, N = 3 38.02 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Chimera 1080p 10-bit RRR 20 40 60 80 100 SE +/- 0.05, N = 3 110.68 MIN: 74.02 / MAX: 234.47 1. (CC) gcc options: -pthread
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Chimera 1080p RRR 130 260 390 520 650 SE +/- 0.62, N = 3 590.44 MIN: 462.39 / MAX: 722.19 1. (CC) gcc options: -pthread
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Summer Nature 4K RRR 40 80 120 160 200 SE +/- 0.28, N = 3 195.92 MIN: 158.27 / MAX: 206.94 1. (CC) gcc options: -pthread
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Summer Nature 1080p RRR 120 240 360 480 600 SE +/- 0.59, N = 3 554.44 MIN: 432.24 / MAX: 598.74 1. (CC) gcc options: -pthread
VP9 libvpx Encoding Speed: Speed 0 OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 0 RRR 2 4 6 8 10 SE +/- 0.01, N = 3 7.63 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
VP9 libvpx Encoding Speed: Speed 5 OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 5 RRR 6 12 18 24 30 SE +/- 0.25, N = 3 25.75 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
FFmpeg H.264 HD To NTSC DV OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 4.0.2 H.264 HD To NTSC DV RRR 2 4 6 8 10 SE +/- 0.034, N = 3 7.052 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lasound -lSDL2 -lsndio -pthread -lva -lbz2 -llzma -lva-drm -lva-x11 -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT
Kvazaar Video Input: Bosphorus 4K - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Slow RRR 2 4 6 8 10 SE +/- 0.01, N = 3 7.29 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Kvazaar Video Input: Bosphorus 1080p - Video Preset: Slow OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Slow RRR 6 12 18 24 30 SE +/- 0.02, N = 3 27.09 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
SVT-HEVC 1080p 8-bit YUV To HEVC Video Encode OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.4.1 1080p 8-bit YUV To HEVC Video Encode RRR 20 40 60 80 100 SE +/- 0.10, N = 3 75.96 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p RRR 40 80 120 160 200 SE +/- 0.48, N = 3 196.19 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p RRR 40 80 120 160 200 SE +/- 0.44, N = 3 200.65 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p RRR 40 80 120 160 200 SE +/- 1.30, N = 3 177.64 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OCRMyPDF Processing 60 Page PDF Document OpenBenchmarking.org Seconds, Fewer Is Better OCRMyPDF 9.6.0+dfsg Processing 60 Page PDF Document RRR 5 10 15 20 25 SE +/- 0.14, N = 3 21.54
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.1.1 Time To OCR 7 Images RRR 6 12 18 24 30 SE +/- 0.18, N = 3 23.53
IndigoBench Acceleration: CPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Bedroom RRR 0.6179 1.2358 1.8537 2.4716 3.0895 SE +/- 0.002, N = 3 2.746
IndigoBench Acceleration: CPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Supercar RRR 1.3163 2.6326 3.9489 5.2652 6.5815 SE +/- 0.004, N = 3 5.850
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org Ksamples, More Is Better Chaos Group V-RAY 4.10.07 Mode: CPU RRR 4K 8K 12K 16K 20K SE +/- 38.94, N = 3 20547
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping RRR 140 280 420 560 700 SE +/- 0.82, N = 3 660.20 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
Smallpt Global Illumination Renderer; 128 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples RRR 2 4 6 8 10 SE +/- 0.006, N = 3 7.179 1. (CXX) g++ options: -fopenmp -O3
LuxCoreRender Scene: Rainbow Colors and Prism OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: Rainbow Colors and Prism RRR 0.585 1.17 1.755 2.34 2.925 SE +/- 0.01, N = 3 2.60 MIN: 2.58 / MAX: 2.64
LuxCoreRender Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.3 Scene: DLSC RRR 0.5445 1.089 1.6335 2.178 2.7225 SE +/- 0.01, N = 3 2.42 MIN: 2.36 / MAX: 2.52
AOBench Size: 2048 x 2048 - Total Time OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time RRR 8 16 24 32 40 SE +/- 0.10, N = 3 32.32 1. (CC) gcc options: -lm -O3
Radiance Benchmark Test: SMP Parallel OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: SMP Parallel RRR 40 80 120 160 200 179.45
Radiance Benchmark Test: Serial OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: Serial RRR 120 240 360 480 600 552.17
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester RRR 40 80 120 160 200 162.04
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material RRR 40 80 120 160 200 167.41
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily RRR 60 120 180 240 300 271.24
Tungsten Renderer Scene: Volumetric Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Volumetric Caustic RRR 2 4 6 8 10 SE +/- 0.01802, N = 3 7.47658 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl
Tungsten Renderer Scene: Non-Exponential OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential RRR 1.3207 2.6414 3.9621 5.2828 6.6035 SE +/- 0.00877, N = 3 5.86974 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl
Tungsten Renderer Scene: Water Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic RRR 6 12 18 24 30 SE +/- 0.05, N = 3 24.51 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl
Tungsten Renderer Scene: Hair OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair RRR 4 8 12 16 20 SE +/- 0.01, N = 3 18.22 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lGL -lGLU -lpthread -ldl
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: CPU-Only RRR 100 200 300 400 500 SE +/- 0.72, N = 3 461.57
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Pabellon Barcelona - Compute: CPU-Only RRR 80 160 240 320 400 SE +/- 1.16, N = 3 359.85
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: CPU-Only RRR 30 60 90 120 150 SE +/- 0.19, N = 3 148.56
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Classroom - Compute: CPU-Only RRR 70 140 210 280 350 SE +/- 0.22, N = 3 322.05
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: CPU-Only RRR 30 60 90 120 150 SE +/- 0.23, N = 3 112.51
YafaRay Total Time For Sample Scene OpenBenchmarking.org Seconds, Fewer Is Better YafaRay 3.4.1 Total Time For Sample Scene RRR 20 40 60 80 100 SE +/- 0.36, N = 3 105.71 1. (CXX) g++ options: -std=c++11 -O3 -ffast-math -rdynamic -ldl -lImath -lIlmImf -lIex -lHalf -lz -lIlmThread -lxml2 -lfreetype -lpthread
rays1bench Large Scene OpenBenchmarking.org mrays/s, More Is Better rays1bench 2020-01-09 Large Scene RRR 20 40 60 80 100 SE +/- 0.03, N = 3 83.66
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time RRR 7 14 21 28 35 SE +/- 0.03, N = 3 31.62 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time RRR 14 28 42 56 70 SE +/- 0.04, N = 3 63.41 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel RRR 10 20 30 40 50 SE +/- 0.00, N = 3 43.34 1. (CC) gcc options: -lm -lpthread -O3
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer RRR 0.3263 0.6526 0.9789 1.3052 1.6315 SE +/- 0.00, N = 3 1.45 MIN: 1.44 / MAX: 1.46
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis RRR 5 10 15 20 25 SE +/- 0.00, N = 12 18.87 MIN: 18.18 / MAX: 20
OSPray Demo: NASA Streamlines - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer RRR 1.2218 2.4436 3.6654 4.8872 6.109 SE +/- 0.00, N = 12 5.43 MIN: 5.21 / MAX: 5.52
OSPray Demo: NASA Streamlines - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis RRR 6 12 18 24 30 SE +/- 0.00, N = 12 27.03 MIN: 25.64 / MAX: 27.78
OSPray Demo: XFrog Forest - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer RRR 0.4118 0.8236 1.2354 1.6472 2.059 SE +/- 0.00, N = 6 1.83 MIN: 1.81 / MAX: 1.85
OSPray Demo: XFrog Forest - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis RRR 0.7875 1.575 2.3625 3.15 3.9375 SE +/- 0.00, N = 9 3.50 MIN: 3.46 / MAX: 3.55
OSPray Demo: Magnetic Reconnection - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: Path Tracer RRR 40 80 120 160 200 200 MIN: 166.67 / MAX: 250
OSPray Demo: Magnetic Reconnection - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis RRR 3 6 9 12 15 SE +/- 0.00, N = 15 12.82 MIN: 12.5 / MAX: 12.99
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU RRR 900 1800 2700 3600 4500 SE +/- 240.52, N = 15 4220.58 MIN: 3937.12 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 3 6 9 12 15 SE +/- 0.165, N = 15 SE +/- 0.103, N = 15 SE +/- 0.121, N = 15 SE +/- 0.105, N = 15 9.235 9.405 9.668 9.299 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 100 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 100 - Mode: Read Write Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 2K 4K 6K 8K 10K SE +/- 182.18, N = 15 SE +/- 112.91, N = 15 SE +/- 126.98, N = 15 SE +/- 122.81, N = 15 10881 10657 10373 10781 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency OpenBenchmarking.org ms, Fewer Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Write - Average Latency Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 0.3515 0.703 1.0545 1.406 1.7575 SE +/- 0.002, N = 3 SE +/- 0.045, N = 15 SE +/- 0.034, N = 12 SE +/- 0.034, N = 15 1.264 1.513 1.562 1.518 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
PostgreSQL pgbench Scaling Factor: 100 - Clients: 1 - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 13.0 Scaling Factor: 100 - Clients: 1 - Mode: Read Write Linux 5.9 Linux 5.10.4 Linux 5.11-rc1 RRR 200 400 600 800 1000 SE +/- 1.05, N = 3 SE +/- 18.86, N = 15 SE +/- 14.85, N = 12 SE +/- 14.17, N = 15 791 669 644 663 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -ldl -lm
Phoronix Test Suite v10.8.4