Ryzen 7 1700 + RX 480 AMD Ryzen 7 1700 Eight-Core testing with a MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS) and AMD Radeon RX 470/480/570/570X/580/580X/590 8GB on Ubuntu 20.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012315-HA-RYZEN717043&grs .
Ryzen 7 1700 + RX 480 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Default Kernel Linux 5.10.4 Linux 5.11-rc1 AMD Ryzen 7 1700 Eight-Core @ 3.00GHz (8 Cores / 16 Threads) MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS) AMD 17h 16GB 120GB Samsung SSD 840 AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1266/2000MHz) AMD Ellesmere HDMI Audio VA2431 Realtek RTL8111/8168/8411 Ubuntu 20.10 5.8.0-33-generic (x86_64) GNOME Shell 3.38.1 X Server 1.20.9 amdgpu 19.1.0 4.6 Mesa 20.2.1 (LLVM 11.0.0) 1.2.131 GCC 10.2.0 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++,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 Disk Details - MQ-DEADLINE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Default Kernel: Scaling Governor: acpi-cpufreq ondemand (Boost: Enabled) - CPU Microcode: 0x8001137 - Linux 5.10.4: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001137 - Linux 5.11-rc1: Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x8001137 Graphics Details - GLAMOR Java Details - OpenJDK Runtime Environment (build 11.0.9.1+1-Ubuntu-0ubuntu1.20.10) Python Details - Python 3.8.6 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: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ryzen 7 1700 + RX 480 redis: LPOP pyperformance: python_startup onednn: IP Shapes 3D - f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU ncnn: CPU - resnet50 ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - googlenet ncnn: CPU - googlenet ncnn: CPU - resnet18 hmmer: Pfam Database Search ncnn: CPU - mobilenet ncnn: CPU - yolov4-tiny ncnn: Vulkan GPU - mobilenet clomp: Static OMP Speedup ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - squeezenet_ssd ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - squeezenet_ssd deepspeech: CPU ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - blazeface polyhedron: tfft2 ncnn: Vulkan GPU - efficientnet-b0 ncnn: CPU - vgg16 redis: GET ncnn: Vulkan GPU - vgg16 tensorflow-lite: NASNet Mobile onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU ncnn: CPU - regnety_400m ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 webp: Quality 100, Lossless, Highest Compression ncnn: Vulkan GPU - shufflenet-v2 tensorflow-lite: Inception ResNet V2 tensorflow-lite: Inception V4 ncnn: Vulkan GPU - regnety_400m cryptsetup: Twofish-XTS 256b Decryption cryptsetup: Serpent-XTS 256b Decryption tensorflow-lite: Mobilenet Quant cryptsetup: Twofish-XTS 512b Encryption onednn: Deconvolution Batch shapes_1d - f32 - CPU cryptsetup: Serpent-XTS 512b Decryption tensorflow-lite: Mobilenet Float cryptsetup: Twofish-XTS 512b Decryption webp: Quality 100, Lossless mnn: inception-v3 webp: Quality 100 cryptsetup: Serpent-XTS 512b Encryption pyperformance: pathlib gimp: resize build-eigen: Time To Compile cryptsetup: Twofish-XTS 256b Encryption cryptsetup: AES-XTS 512b Encryption cryptsetup: PBKDF2-whirlpool cryptsetup: Serpent-XTS 256b Encryption redis: SET cryptsetup: AES-XTS 256b Decryption cryptsetup: AES-XTS 512b Decryption rnnoise: mnn: SqueezeNetV1.0 encode-opus: WAV To Opus Encode pyperformance: json_loads cryptsetup: AES-XTS 256b Encryption byte: Dhrystone 2 encode-mp3: WAV To MP3 compress-lz4: 9 - Compression Speed encode-wavpack: WAV To WavPack glmark2: 1280 x 1024 polyhedron: mdbx tnn: CPU - SqueezeNet v1.1 polyhedron: ac polyhedron: fatigue2 pyperformance: chaos phpbench: PHP Benchmark Suite mnn: MobileNetV2_224 encode-ape: WAV To APE polyhedron: induct2 onednn: IP Shapes 3D - u8s8f32 - CPU polyhedron: protein polyhedron: doduc webp: Default polyhedron: mp_prop_design pyperformance: raytrace pyperformance: float polyhedron: air pyperformance: crypto_pyaes pyperformance: regex_compile compress-lz4: 3 - Compression Speed polyhedron: test_fpu2 simdjson: Kostya pyperformance: nbody sqlite-speedtest: Timed Time - Size 1,000 encode-flac: WAV To FLAC webp: Quality 100, Highest Compression onednn: Convolution Batch Shapes Auto - f32 - CPU hint: FLOAT polyhedron: aermod ncnn: Vulkan GPU - alexnet cryptsetup: PBKDF2-sha512 pyperformance: pickle_pure_python polyhedron: rnflow redis: SADD pyperformance: go basis: UASTC Level 0 ncnn: CPU - alexnet darktable: Server Rack - CPU-only glmark2: 1920 x 1080 pyperformance: django_template mnn: resnet-v2-50 numpy: ffte: N=256, 3D Complex FFT Routine onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU tensorflow-lite: SqueezeNet avifenc: 8 tnn: CPU - MobileNet v2 simdjson: LargeRand onednn: Recurrent Neural Network Inference - u8s8f32 - CPU node-web-tooling: basis: ETC1S gimp: auto-levels onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU compress-lz4: 1 - Decompression Speed onednn: Recurrent Neural Network Training - u8s8f32 - CPU darktable: Masskrug - CPU-only darktable: Server Room - CPU-only avifenc: 10 avifenc: 0 mnn: mobilenet-v1-1.0 compress-lz4: 1 - Compression Speed astcenc: Fast pyperformance: 2to3 onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: IP Shapes 1D - f32 - CPU espeak: Text-To-Speech Synthesis mafft: Multiple Sequence Alignment - LSU RNA polyhedron: gas_dyn2 stockfish: Total Time vkmark: 1280 x 1024 rsvg: SVG Files To PNG unpack-linux: linux-4.15.tar.xz yquake2: Software CPU - 1920 x 1080 appleseed: Disney Material vkmark: 1920 x 1080 ai-benchmark: Device Training Score compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 darktable: Boat - CPU-only vkfft: sunflow: Global Illumination + Image Synthesis gromacs: Water Benchmark unpack-firefox: firefox-84.0.source.tar.xz asmfish: 1024 Hash Memory, 26 Depth wireguard: avifenc: 2 yquake2: OpenGL 1.x - 1920 x 1080 onednn: IP Shapes 1D - u8s8f32 - CPU embree: Pathtracer ISPC - Asian Dragon onednn: Deconvolution Batch shapes_3d - f32 - CPU ai-benchmark: Device AI Score gimp: unsharp-mask build-ffmpeg: Time To Compile polyhedron: channel2 compress-zstd: 19 blender: BMW27 - CPU-Only basis: UASTC Level 2 rawtherapee: Total Benchmark Time gimp: rotate rav1e: 1 polyhedron: linpk rav1e: 5 indigobench: CPU - Bedroom yquake2: OpenGL 3.x - 1920 x 1080 astcenc: Thorough embree: Pathtracer - Asian Dragon astcenc: Exhaustive coremark: CoreMark Size 666 - Iterations Per Second redis: LPUSH astcenc: Medium basis: UASTC Level 2 + RDO Post-Processing rav1e: 10 indigobench: CPU - Supercar appleseed: Material Tester blender: Fishy Cat - CPU-Only build-linux-kernel: Time To Compile build-llvm: Time To Compile embree: Pathtracer - Crown ai-benchmark: Device Inference Score compress-lz4: 9 - Decompression Speed compress-zstd: 3 embree: Pathtracer ISPC - Crown basis: UASTC Level 3 embree: Pathtracer - Asian Dragon Obj onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU appleseed: Emily compress-lz4: 3 - Decompression Speed embree: Pathtracer ISPC - Asian Dragon Obj build2: Time To Compile rav1e: 6 polyhedron: capacita simdjson: DistinctUserID simdjson: PartialTweets ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - resnet18 ncnn: CPU - blazeface onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU lammps: Rhodopsin Protein Default Kernel Linux 5.10.4 Linux 5.11-rc1 2014169.29 12.2 11.5673 5.33146 58.38 59.31 31.60 31.77 25.46 151.893 38.47 49.92 38.45 7.8 10.09 11.62 11.91 37.31 11.59 10.85 15.55 37.15 94.00238 10.56 3.85 25.09 15.23 85.70 1863679.11 85.39 223426 6.60753 23.8283 33.49 9.59 50.890 11.00 3299807 3649700 32.86 331.7 320.6 177091 333.3 11.3777 321.6 169941 334.4 24.464 77.143 2.831 326.1 25.0 10.750 117.955 333.2 1356.0 550533 325.1 1363650.75 1531.1 1359.7 24.180 12.690 9.542 37.4 1521.6 33310090.4 10.370 36.03 16.208 6038 5.88 308.495 7.74 63.32 160 475137 6.965 17.208 25.16 2.94203 17.02 9.34 1.774 74.87 714 164 1.78 154 233 36.94 37.1 0.36 170 83.928 11.594 9.478 22.7874 282568835.29886 7.58 17.09 1300115 697 16.77 1540737.67 353 10.451 16.96 0.218 4432 80.9 71.661 246.26 29782.882133956 4749.06 251499 7.048 324.268 0.33 4737.79 7.24 64.563 16.032 9027.63 4742.11 8129.2 9028.50 6.745 5.210 6.622 131.138 13.624 7192.29 7.72 461 9002.53 9.34927 38.908 14.564 61.73 13361457 6184 34.317 7.403 85.4 322.771845 4664 667 47.565 13.747 10274 1.581 0.524 26.471 19306833 300.19 76.654 631.8 7.03197 7.9759 17.0012 1248 19.016 85.708 59.51 22.5 237.53 43.977 78.652 15.407 0.256 4.81 0.765 1.335 944.3 36.95 8.3970 303.53 267555.232946 1065654.10 6.11 867.808 2.349 2.828 287.576718 329.39 131.315 1057.630 7.3312 581 7828.5 2849.0 6.7689 82.388 7.8014 13.3370 539.955062 7835.5 7.2063 232.986 1.022 16.18 0.46 0.45 50.06 26.05 3.61 14.7823 4.311 1075736.66 20.7 8.81062 4.24151 46.37 47.21 26.28 25.83 20.97 128.726 32.21 41.80 32.79 9.3 8.50 10.14 10.09 31.61 9.82 9.22 13.24 31.80 109.72930 9.06 3.46 29.02 13.28 74.43 1611434.08 74.53 208952 5.78248 20.9864 29.37 8.45 44.854 9.71 3174873 3512430 29.49 367.1 354.9 170472 369.9 12.6415 356.7 163162 368.2 22.496 69.866 2.575 359.3 22.8 11.832 109.471 364.8 1485.4 603098 356.4 1243969.70 1668.2 1488.7 22.113 11.659 8.721 34.3 1658.9 35909522.3 9.490 39.19 14.870 6542 5.42 282.839 7.1 58.15 151 517024 6.402 15.839 23.15 2.87865 15.65 8.61 1.639 68.88 661 151 1.66 143 215 40.01 34.24 0.39 159 77.517 10.710 8.872 21.0535 305670769.36287 7.09 15.81 1403727 651 15.65 1429878.04 336 9.860 15.78 0.233 4722 75.9 67.179 262.15 31684.744460084 4488.10 244504 6.700 305.642 0.35 4482.27 7.67 60.998 16.903 8564.54 4497.06 8560.1 8575.95 6.392 4.940 6.312 126.027 12.956 7525.63 7.35 444 8588.64 9.80460 40.272 14.599 59.15 13559816 6350 35.652 7.131 88.2 316.758583 4732 689 46.205 13.322 9972 1.537 0.539 25.744 19840743 308.467 74.657 641.4 6.85975 8.1739 17.3787 1277 19.193 83.806 58.21 22.9 232.46 43.092 77.082 15.284 0.261 4.73 0.779 1.354 960.5 36.58 8.5188 300.62 270279.686207 1049901.52 6.05 855.355 2.316 2.867 291.466605 325.24 129.825 1044.459 7.3497 588 7895.5 2838.6 6.7934 81.475 7.8722 13.2398 535.01413 7899.3 7.2702 231.005 1.020 16.24 0.46 0.45 42.46 20.92 3.38 14.3114 4.720 1114626.25 20.7 8.61372 4.16855 46.40 47.65 25.27 26.29 21.96 127.071 32.63 43.19 32.20 9.1 8.60 9.81 10.31 31.76 9.86 9.35 13.51 31.73 108.33302 9.05 3.30 29.22 13.09 74.00 1727854.75 74.67 239203 5.87713 20.8695 29.60 8.69 45.159 10.04 3580783 3947703 29.35 369.8 357.3 189637 370.6 12.4213 355.3 180798 369.3 22.156 69.898 2.568 358 22.7 11.833 107.161 366.2 1488.7 603787 356.5 1297244.29 1678.3 1485.4 22.092 11.596 8.827 34.2 1663.4 36408424.2 9.496 39.36 14.853 6587 5.39 282.815 7.1 58.15 147 513740 6.429 15.819 23.13 2.70498 15.65 8.59 1.632 68.93 657 151 1.64 142 215 40.03 34.31 0.39 157 78.387 10.930 8.756 21.0906 305438957.41609 7.01 15.86 1404973 646 15.55 1465965.54 328 9.717 15.87 0.234 4755 75.5 66.976 262.75 31043.725914144 4470.71 259645 6.639 310.422 0.35 4468.08 7.62 60.951 16.981 8540.48 4486.34 8592.3 8545.33 6.397 4.959 6.284 124.542 12.939 7572.23 7.42 439 8583.12 9.49354 38.419 15.251 59.08 13897759 6426 34.998 7.160 88.6 311.487833 4827 685 46.085 13.343 9967 1.582 0.535 25.986 19661267 308.380 75.056 625.3 6.92207 8.1022 17.4095 1269 19.452 83.883 58.21 23.0 236.57 43.277 78.290 15.101 0.259 4.72 0.774 1.359 947.3 37.2 8.3775 305.64 271886.254101 1053853.02 6.14 857.228 2.347 2.843 289.579019 326.50 129.677 1050.445 7.4224 584 7920.9 2872.0 6.8458 81.620 7.8824 13.2091 536.842668 7906.8 7.2554 231.535 1.028 16.2 0.46 0.45 41.05 19.90 3.47 14.4510 4.762 OpenBenchmarking.org
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: LPOP Default Kernel Linux 5.10.4 Linux 5.11-rc1 400K 800K 1200K 1600K 2000K SE +/- 30740.73, N = 12 SE +/- 2684.98, N = 3 SE +/- 5120.03, N = 3 2014169.29 1075736.66 1114626.25 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
PyPerformance Benchmark: python_startup OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: python_startup Default Kernel Linux 5.10.4 Linux 5.11-rc1 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 12.2 20.7 20.7
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.03621, N = 3 SE +/- 0.02920, N = 3 SE +/- 0.01700, N = 3 11.56730 8.81062 8.61372 MIN: 10.87 MIN: 8.51 MIN: 8.27 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1.1996 2.3992 3.5988 4.7984 5.998 SE +/- 0.00649, N = 3 SE +/- 0.00670, N = 3 SE +/- 0.00397, N = 3 5.33146 4.24151 4.16855 MIN: 4.84 MIN: 4.14 MIN: 4.06 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 Default Kernel Linux 5.10.4 Linux 5.11-rc1 13 26 39 52 65 SE +/- 0.59, N = 3 SE +/- 0.32, N = 15 SE +/- 0.09, N = 3 58.38 46.37 46.40 MIN: 48.11 / MAX: 109.51 MIN: 45.13 / MAX: 83.86 MIN: 46.13 / MAX: 46.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet50 Default Kernel Linux 5.10.4 Linux 5.11-rc1 13 26 39 52 65 SE +/- 0.58, N = 3 SE +/- 1.01, N = 3 SE +/- 1.19, N = 3 59.31 47.21 47.65 MIN: 48.12 / MAX: 109.05 MIN: 45.3 / MAX: 81.34 MIN: 46.22 / MAX: 82.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: googlenet Default Kernel Linux 5.10.4 Linux 5.11-rc1 7 14 21 28 35 SE +/- 0.32, N = 3 SE +/- 0.11, N = 3 SE +/- 0.76, N = 3 31.60 26.28 25.27 MIN: 24.42 / MAX: 69.85 MIN: 25.18 / MAX: 37.2 MIN: 22.73 / MAX: 45.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet Default Kernel Linux 5.10.4 Linux 5.11-rc1 7 14 21 28 35 SE +/- 0.18, N = 3 SE +/- 0.32, N = 15 SE +/- 0.11, N = 3 31.77 25.83 26.29 MIN: 23.25 / MAX: 69.93 MIN: 22.76 / MAX: 58.24 MIN: 23.04 / MAX: 29.98 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.22, N = 3 SE +/- 0.28, N = 15 SE +/- 0.20, N = 3 25.46 20.97 21.96 MIN: 19.81 / MAX: 59.82 MIN: 18.91 / MAX: 67.27 MIN: 19.15 / MAX: 54.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 3.3.1 Pfam Database Search Default Kernel Linux 5.10.4 Linux 5.11-rc1 30 60 90 120 150 SE +/- 0.27, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 151.89 128.73 127.07 1. (CC) gcc options: -O3 -pthread -lhmmer -leasel -lm
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.44, N = 3 SE +/- 0.29, N = 15 SE +/- 0.27, N = 3 38.47 32.21 32.63 MIN: 33.17 / MAX: 75.32 MIN: 30.06 / MAX: 44.1 MIN: 31.52 / MAX: 114.19 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny Default Kernel Linux 5.10.4 Linux 5.11-rc1 11 22 33 44 55 SE +/- 0.08, N = 3 SE +/- 0.49, N = 15 SE +/- 0.01, N = 3 49.92 41.80 43.19 MIN: 41.04 / MAX: 67.32 MIN: 36.06 / MAX: 63.79 MIN: 41.97 / MAX: 48.03 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.19, N = 3 SE +/- 0.20, N = 3 38.45 32.79 32.20 MIN: 33.4 / MAX: 77.43 MIN: 30.27 / MAX: 45.97 MIN: 30.63 / MAX: 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.09, N = 4 SE +/- 0.11, N = 15 SE +/- 0.12, N = 3 7.8 9.3 9.1 1. (CC) gcc options: -fopenmp -O3 -lm
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.20, N = 3 SE +/- 0.03, N = 15 SE +/- 0.09, N = 3 10.09 8.50 8.60 MIN: 8.08 / MAX: 57.72 MIN: 8.19 / MAX: 20.56 MIN: 8.28 / MAX: 22.71 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.19, N = 3 SE +/- 0.21, N = 3 SE +/- 0.04, N = 3 11.62 10.14 9.81 MIN: 9.25 / MAX: 43.5 MIN: 9.38 / MAX: 12.94 MIN: 9.63 / MAX: 13.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.15, N = 3 SE +/- 0.11, N = 15 SE +/- 0.21, N = 3 11.91 10.09 10.31 MIN: 9.52 / MAX: 44.02 MIN: 9.47 / MAX: 59.9 MIN: 9.57 / MAX: 22.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 37.31 31.61 31.76 MIN: 32.73 / MAX: 94.67 MIN: 30.89 / MAX: 38.84 MIN: 30.84 / MAX: 39.08 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.14, N = 3 SE +/- 0.03, N = 15 SE +/- 0.05, N = 3 11.59 9.82 9.86 MIN: 9.62 / MAX: 57.85 MIN: 9.61 / MAX: 11.52 MIN: 9.73 / MAX: 10.13 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.27, N = 3 SE +/- 0.07, N = 15 SE +/- 0.16, N = 3 10.85 9.22 9.35 MIN: 8.7 / MAX: 50.23 MIN: 8.76 / MAX: 13.65 MIN: 9.12 / MAX: 10.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.25, N = 3 SE +/- 0.11, N = 15 SE +/- 0.29, N = 3 15.55 13.24 13.51 MIN: 12.82 / MAX: 44.91 MIN: 12.68 / MAX: 56.97 MIN: 13.14 / MAX: 14.47 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.35, N = 3 SE +/- 0.14, N = 15 SE +/- 0.04, N = 3 37.15 31.80 31.73 MIN: 32.74 / MAX: 88.45 MIN: 30.81 / MAX: 42.83 MIN: 30.96 / MAX: 37.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
DeepSpeech Acceleration: CPU OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.16, N = 3 SE +/- 0.78, N = 15 SE +/- 0.94, N = 8 94.00 109.73 108.33
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mnasnet Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.25, N = 3 SE +/- 0.12, N = 3 SE +/- 0.13, N = 3 10.56 9.06 9.05 MIN: 8.6 / MAX: 49.35 MIN: 8.8 / MAX: 9.55 MIN: 8.77 / MAX: 32.06 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.8663 1.7326 2.5989 3.4652 4.3315 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 3.85 3.46 3.30 MIN: 3.16 / MAX: 16.49 MIN: 3.33 / MAX: 7.35 MIN: 3.22 / MAX: 3.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Polyhedron Fortran Benchmarks Benchmark: tfft2 OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: tfft2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 7 14 21 28 35 25.09 29.02 29.22
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.10, N = 3 15.23 13.28 13.09 MIN: 12.91 / MAX: 49.97 MIN: 13.12 / MAX: 14.99 MIN: 12.94 / MAX: 14.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.20, N = 3 SE +/- 0.16, N = 15 SE +/- 0.12, N = 3 85.70 74.43 74.00 MIN: 76.58 / MAX: 109.13 MIN: 73.09 / MAX: 107.82 MIN: 73.3 / MAX: 82.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: GET Default Kernel Linux 5.10.4 Linux 5.11-rc1 400K 800K 1200K 1600K 2000K SE +/- 22737.24, N = 15 SE +/- 11369.12, N = 3 SE +/- 16571.48, N = 3 1863679.11 1611434.08 1727854.75 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: vgg16 Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.36, N = 3 SE +/- 0.33, N = 3 85.39 74.53 74.67 MIN: 76.96 / MAX: 108.88 MIN: 73.33 / MAX: 84.41 MIN: 73.34 / MAX: 83.99 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Default Kernel Linux 5.10.4 Linux 5.11-rc1 50K 100K 150K 200K 250K SE +/- 1532.37, N = 3 SE +/- 207.90, N = 3 SE +/- 1205.42, N = 3 223426 208952 239203
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.07065, N = 5 SE +/- 0.05897, N = 15 SE +/- 0.01520, N = 3 6.60753 5.78248 5.87713 MIN: 5.69 MIN: 5.23 MIN: 5.59 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 23.83 20.99 20.87 MIN: 22.68 MIN: 20.72 MIN: 20.57 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m Default Kernel Linux 5.10.4 Linux 5.11-rc1 8 16 24 32 40 SE +/- 0.53, N = 3 SE +/- 0.09, N = 15 SE +/- 0.06, N = 3 33.49 29.37 29.60 MIN: 30.17 / MAX: 68.43 MIN: 28.47 / MAX: 73.28 MIN: 29.39 / MAX: 40.11 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 9.59 8.45 8.69 MIN: 8.1 / MAX: 72.56 MIN: 8.09 / MAX: 10.09 MIN: 8.29 / MAX: 26.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 11 22 33 44 55 SE +/- 0.27, N = 3 SE +/- 0.02, N = 3 SE +/- 0.15, N = 3 50.89 44.85 45.16 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.30, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 11.00 9.71 10.04 MIN: 9.52 / MAX: 47.8 MIN: 9.51 / MAX: 10.13 MIN: 9.81 / MAX: 10.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TensorFlow Lite Model: Inception ResNet V2 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception ResNet V2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 800K 1600K 2400K 3200K 4000K SE +/- 1161.41, N = 3 SE +/- 713.33, N = 3 SE +/- 2970.22, N = 3 3299807 3174873 3580783
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Default Kernel Linux 5.10.4 Linux 5.11-rc1 800K 1600K 2400K 3200K 4000K SE +/- 2124.36, N = 3 SE +/- 2619.34, N = 3 SE +/- 912.82, N = 3 3649700 3512430 3947703
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m Default Kernel Linux 5.10.4 Linux 5.11-rc1 8 16 24 32 40 SE +/- 0.30, N = 3 SE +/- 0.25, N = 3 SE +/- 0.32, N = 3 32.86 29.49 29.35 MIN: 30.37 / MAX: 71.09 MIN: 28.88 / MAX: 31.63 MIN: 28.95 / MAX: 100.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup Twofish-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Decryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 1.40, N = 3 SE +/- 1.64, N = 3 SE +/- 0.24, N = 3 331.7 367.1 369.8
Cryptsetup Serpent-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Decryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 2.23, N = 3 SE +/- 1.70, N = 3 SE +/- 1.32, N = 3 320.6 354.9 357.3
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Default Kernel Linux 5.10.4 Linux 5.11-rc1 40K 80K 120K 160K 200K SE +/- 75.51, N = 3 SE +/- 30.12, N = 3 SE +/- 424.39, N = 3 177091 170472 189637
Cryptsetup Twofish-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Encryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 1.79, N = 3 SE +/- 1.00, N = 3 SE +/- 0.25, N = 3 333.3 369.9 370.6
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.12, N = 15 SE +/- 0.16, N = 15 11.38 12.64 12.42 MIN: 10.79 MIN: 11.31 MIN: 11.07 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Cryptsetup Serpent-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Decryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 2.22, N = 3 SE +/- 0.91, N = 3 SE +/- 1.71, N = 3 321.6 356.7 355.3
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Default Kernel Linux 5.10.4 Linux 5.11-rc1 40K 80K 120K 160K 200K SE +/- 82.73, N = 3 SE +/- 89.09, N = 3 SE +/- 51.97, N = 3 169941 163162 180798
Cryptsetup Twofish-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 512b Decryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 1.69, N = 3 SE +/- 0.35, N = 3 SE +/- 0.61, N = 3 334.4 368.2 369.3
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.26, N = 3 SE +/- 0.10, N = 3 SE +/- 0.19, N = 3 24.46 22.50 22.16 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.46, N = 3 SE +/- 0.35, N = 3 SE +/- 0.07, N = 3 77.14 69.87 69.90 MIN: 69.93 / MAX: 103.83 MIN: 68.99 / MAX: 81.83 MIN: 69.61 / MAX: 94.45 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
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.637 1.274 1.911 2.548 3.185 SE +/- 0.034, N = 3 SE +/- 0.009, N = 3 SE +/- 0.006, N = 3 2.831 2.575 2.568 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16
Cryptsetup Serpent-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 512b Encryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 2.94, N = 3 SE +/- 1.57, N = 3 SE +/- 2.00, N = 2 326.1 359.3 358.0
PyPerformance Benchmark: pathlib OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pathlib Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 25.0 22.8 22.7
GIMP Test: resize OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: resize Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 10.75 11.83 11.83
Timed Eigen Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Eigen Compilation 3.3.9 Time To Compile Default Kernel Linux 5.10.4 Linux 5.11-rc1 30 60 90 120 150 SE +/- 0.40, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 117.96 109.47 107.16
Cryptsetup Twofish-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Twofish-XTS 256b Encryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 1.62, N = 3 SE +/- 5.33, N = 3 SE +/- 4.26, N = 3 333.2 364.8 366.2
Cryptsetup AES-XTS 512b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Encryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 300 600 900 1200 1500 SE +/- 11.60, N = 3 SE +/- 3.09, N = 3 SE +/- 0.68, N = 3 1356.0 1485.4 1488.7
Cryptsetup PBKDF2-whirlpool OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-whirlpool Default Kernel Linux 5.10.4 Linux 5.11-rc1 130K 260K 390K 520K 650K SE +/- 1020.69, N = 3 SE +/- 1406.03, N = 3 SE +/- 613.12, N = 3 550533 603098 603787
Cryptsetup Serpent-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup Serpent-XTS 256b Encryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 1.68, N = 3 SE +/- 2.62, N = 3 SE +/- 4.86, N = 3 325.1 356.4 356.5
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SET Default Kernel Linux 5.10.4 Linux 5.11-rc1 300K 600K 900K 1200K 1500K SE +/- 16871.12, N = 4 SE +/- 8535.72, N = 15 SE +/- 2028.99, N = 3 1363650.75 1243969.70 1297244.29 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Cryptsetup AES-XTS 256b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Decryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 400 800 1200 1600 2000 SE +/- 7.30, N = 3 SE +/- 1.07, N = 3 SE +/- 1.79, N = 3 1531.1 1668.2 1678.3
Cryptsetup AES-XTS 512b Decryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 512b Decryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 300 600 900 1200 1500 SE +/- 9.75, N = 3 SE +/- 2.77, N = 3 SE +/- 3.76, N = 3 1359.7 1488.7 1485.4
RNNoise OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.17, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 24.18 22.11 22.09 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 12.69 11.66 11.60 MIN: 11.22 / MAX: 25.7 MIN: 11.43 / MAX: 23.12 MIN: 11.41 / MAX: 23.49 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
Opus Codec Encoding WAV To Opus Encode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.037, N = 5 SE +/- 0.015, N = 5 SE +/- 0.063, N = 12 9.542 8.721 8.827 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
PyPerformance Benchmark: json_loads OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: json_loads Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 37.4 34.3 34.2
Cryptsetup AES-XTS 256b Encryption OpenBenchmarking.org MiB/s, More Is Better Cryptsetup AES-XTS 256b Encryption Default Kernel Linux 5.10.4 Linux 5.11-rc1 400 800 1200 1600 2000 SE +/- 2.80, N = 3 SE +/- 12.75, N = 3 SE +/- 9.69, N = 3 1521.6 1658.9 1663.4
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 8M 16M 24M 32M 40M SE +/- 91702.31, N = 3 SE +/- 207274.15, N = 3 SE +/- 77245.63, N = 3 33310090.4 35909522.3 36408424.2
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.054, N = 3 SE +/- 0.005, N = 3 SE +/- 0.014, N = 3 10.370 9.490 9.496 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
LZ4 Compression Compression Level: 9 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.41, N = 3 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 36.03 39.19 39.36 1. (CC) gcc options: -O3
WavPack Audio Encoding WAV To WavPack OpenBenchmarking.org Seconds, Fewer Is Better WavPack Audio Encoding 5.3 WAV To WavPack Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.10, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 16.21 14.87 14.85 1. (CXX) g++ options: -rdynamic
GLmark2 Resolution: 1280 x 1024 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1280 x 1024 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1400 2800 4200 5600 7000 6038 6542 6587
Polyhedron Fortran Benchmarks Benchmark: mdbx OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: mdbx Default Kernel Linux 5.10.4 Linux 5.11-rc1 1.323 2.646 3.969 5.292 6.615 5.88 5.42 5.39
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 Default Kernel Linux 5.10.4 Linux 5.11-rc1 70 140 210 280 350 SE +/- 1.02, N = 3 SE +/- 0.18, N = 3 SE +/- 0.09, N = 3 308.50 282.84 282.82 MIN: 297.18 / MAX: 319.3 MIN: 281.31 / MAX: 287.35 MIN: 281.29 / MAX: 287.16 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
Polyhedron Fortran Benchmarks Benchmark: ac OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: ac Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 7.74 7.10 7.10
Polyhedron Fortran Benchmarks Benchmark: fatigue2 OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: fatigue2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 14 28 42 56 70 63.32 58.15 58.15
PyPerformance Benchmark: chaos OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: chaos Default Kernel Linux 5.10.4 Linux 5.11-rc1 40 80 120 160 200 SE +/- 0.67, N = 3 SE +/- 0.33, N = 3 160 151 147
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Default Kernel Linux 5.10.4 Linux 5.11-rc1 110K 220K 330K 440K 550K SE +/- 1118.13, N = 3 SE +/- 700.71, N = 3 SE +/- 1896.86, N = 3 475137 517024 513740
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.024, N = 3 SE +/- 0.054, N = 3 SE +/- 0.017, N = 3 6.965 6.402 6.429 MIN: 6.27 / MAX: 22.38 MIN: 6.26 / MAX: 15.65 MIN: 6.35 / MAX: 8.72 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
Monkey Audio Encoding WAV To APE OpenBenchmarking.org Seconds, Fewer Is Better Monkey Audio Encoding 3.99.6 WAV To APE Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.07, N = 5 SE +/- 0.04, N = 5 SE +/- 0.02, N = 5 17.21 15.84 15.82 1. (CXX) g++ options: -O3 -pedantic -rdynamic -lrt
Polyhedron Fortran Benchmarks Benchmark: induct2 OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: induct2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 25.16 23.15 23.13
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.662 1.324 1.986 2.648 3.31 SE +/- 0.01399, N = 3 SE +/- 0.02712, N = 3 SE +/- 0.03607, N = 3 2.94203 2.87865 2.70498 MIN: 2.51 MIN: 2.53 MIN: 2.43 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Polyhedron Fortran Benchmarks Benchmark: protein OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: protein Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 17.02 15.65 15.65
Polyhedron Fortran Benchmarks Benchmark: doduc OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: doduc Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 9.34 8.61 8.59
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.3992 0.7984 1.1976 1.5968 1.996 SE +/- 0.008, N = 3 SE +/- 0.011, N = 3 SE +/- 0.001, N = 3 1.774 1.639 1.632 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16
Polyhedron Fortran Benchmarks Benchmark: mp_prop_design OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: mp_prop_design Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 74.87 68.88 68.93
PyPerformance Benchmark: raytrace OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: raytrace Default Kernel Linux 5.10.4 Linux 5.11-rc1 150 300 450 600 750 SE +/- 1.20, N = 3 SE +/- 1.73, N = 3 714 661 657
PyPerformance Benchmark: float OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Default Kernel Linux 5.10.4 Linux 5.11-rc1 40 80 120 160 200 164 151 151
Polyhedron Fortran Benchmarks Benchmark: air OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: air Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.4005 0.801 1.2015 1.602 2.0025 1.78 1.66 1.64
PyPerformance Benchmark: crypto_pyaes OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: crypto_pyaes Default Kernel Linux 5.10.4 Linux 5.11-rc1 30 60 90 120 150 SE +/- 0.33, N = 3 154 143 142
PyPerformance Benchmark: regex_compile OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: regex_compile Default Kernel Linux 5.10.4 Linux 5.11-rc1 50 100 150 200 250 SE +/- 0.33, N = 3 233 215 215
LZ4 Compression Compression Level: 3 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.26, N = 3 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 36.94 40.01 40.03 1. (CC) gcc options: -O3
Polyhedron Fortran Benchmarks Benchmark: test_fpu2 OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: test_fpu2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 37.10 34.24 34.31
simdjson Throughput Test: Kostya OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: Kostya Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.0878 0.1756 0.2634 0.3512 0.439 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.36 0.39 0.39 1. (CXX) g++ options: -O3 -pthread
PyPerformance Benchmark: nbody OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: nbody Default Kernel Linux 5.10.4 Linux 5.11-rc1 40 80 120 160 200 SE +/- 0.67, N = 3 SE +/- 0.67, N = 3 170 159 157
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.66, N = 3 SE +/- 0.20, N = 3 SE +/- 0.35, N = 3 83.93 77.52 78.39 1. (CC) gcc options: -O2 -ldl -lz -lpthread
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.06, N = 5 SE +/- 0.03, N = 5 SE +/- 0.08, N = 5 11.59 10.71 10.93 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.033, N = 3 SE +/- 0.094, N = 5 SE +/- 0.008, N = 3 9.478 8.872 8.756 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 22.79 21.05 21.09 MIN: 21.5 MIN: 20.7 MIN: 20.58 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Hierarchical INTegration Test: FLOAT OpenBenchmarking.org QUIPs, More Is Better Hierarchical INTegration 1.0 Test: FLOAT Default Kernel Linux 5.10.4 Linux 5.11-rc1 70M 140M 210M 280M 350M SE +/- 1313862.73, N = 3 SE +/- 80446.54, N = 3 SE +/- 262122.57, N = 3 282568835.30 305670769.36 305438957.42 1. (CC) gcc options: -O3 -march=native -lm
Polyhedron Fortran Benchmarks Benchmark: aermod OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: aermod Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 7.58 7.09 7.01
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: alexnet Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 17.09 15.81 15.86 MIN: 15.85 / MAX: 45.86 MIN: 15.64 / MAX: 24.91 MIN: 15.71 / MAX: 16.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Cryptsetup PBKDF2-sha512 OpenBenchmarking.org Iterations Per Second, More Is Better Cryptsetup PBKDF2-sha512 Default Kernel Linux 5.10.4 Linux 5.11-rc1 300K 600K 900K 1200K 1500K SE +/- 12175.94, N = 3 SE +/- 2865.42, N = 3 SE +/- 1659.14, N = 3 1300115 1403727 1404973
PyPerformance Benchmark: pickle_pure_python OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: pickle_pure_python Default Kernel Linux 5.10.4 Linux 5.11-rc1 150 300 450 600 750 SE +/- 0.67, N = 3 697 651 646
Polyhedron Fortran Benchmarks Benchmark: rnflow OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: rnflow Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 16.77 15.65 15.55
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: SADD Default Kernel Linux 5.10.4 Linux 5.11-rc1 300K 600K 900K 1200K 1500K SE +/- 21666.11, N = 3 SE +/- 19698.88, N = 3 SE +/- 11716.13, N = 3 1540737.67 1429878.04 1465965.54 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
PyPerformance Benchmark: go OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: go Default Kernel Linux 5.10.4 Linux 5.11-rc1 80 160 240 320 400 SE +/- 0.33, N = 3 353 336 328
Basis Universal Settings: UASTC Level 0 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 0 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.048, N = 3 SE +/- 0.010, N = 3 SE +/- 0.040, N = 3 10.451 9.860 9.717 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.01, N = 15 SE +/- 0.03, N = 3 16.96 15.78 15.87 MIN: 15.86 / MAX: 33.88 MIN: 15.63 / MAX: 27.03 MIN: 15.7 / MAX: 18.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Darktable Test: Server Rack - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Server Rack - Acceleration: CPU-only Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.0527 0.1054 0.1581 0.2108 0.2635 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 SE +/- 0.001, N = 3 0.218 0.233 0.234
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1920 x 1080 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1000 2000 3000 4000 5000 4432 4722 4755
PyPerformance Benchmark: django_template OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: django_template Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.35, N = 3 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 80.9 75.9 75.5
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 Default Kernel Linux 5.10.4 Linux 5.11-rc1 16 32 48 64 80 SE +/- 0.91, N = 3 SE +/- 0.30, N = 3 SE +/- 0.14, N = 3 71.66 67.18 66.98 MIN: 63.38 / MAX: 108.99 MIN: 66.68 / MAX: 78.44 MIN: 66.5 / MAX: 78.24 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
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark Default Kernel Linux 5.10.4 Linux 5.11-rc1 60 120 180 240 300 SE +/- 2.11, N = 3 SE +/- 0.10, N = 3 SE +/- 0.21, N = 3 246.26 262.15 262.75
FFTE N=256, 3D Complex FFT Routine OpenBenchmarking.org MFLOPS, More Is Better FFTE 7.0 N=256, 3D Complex FFT Routine Default Kernel Linux 5.10.4 Linux 5.11-rc1 7K 14K 21K 28K 35K SE +/- 35.57, N = 3 SE +/- 40.89, N = 3 SE +/- 1.43, N = 3 29782.88 31684.74 31043.73 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1000 2000 3000 4000 5000 SE +/- 2.03, N = 3 SE +/- 5.53, N = 3 SE +/- 9.99, N = 3 4749.06 4488.10 4470.71 MIN: 4699.81 MIN: 4464.06 MIN: 4441.33 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Default Kernel Linux 5.10.4 Linux 5.11-rc1 60K 120K 180K 240K 300K SE +/- 272.99, N = 3 SE +/- 290.99, N = 3 SE +/- 354.62, N = 3 251499 244504 259645
libavif avifenc Encoder Speed: 8 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 8 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.031, N = 3 SE +/- 0.018, N = 3 SE +/- 0.006, N = 3 7.048 6.700 6.639 1. (CXX) g++ options: -O3 -fPIC
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: MobileNet v2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 70 140 210 280 350 SE +/- 0.50, N = 3 SE +/- 0.20, N = 3 SE +/- 0.45, N = 3 324.27 305.64 310.42 MIN: 310.87 / MAX: 349.12 MIN: 291.26 / MAX: 314.5 MIN: 290.92 / MAX: 337.97 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
simdjson Throughput Test: LargeRandom OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: LargeRandom Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.0788 0.1576 0.2364 0.3152 0.394 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.33 0.35 0.35 1. (CXX) g++ options: -O3 -pthread
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1000 2000 3000 4000 5000 SE +/- 8.86, N = 3 SE +/- 5.62, N = 3 SE +/- 13.33, N = 3 4737.79 4482.27 4468.08 MIN: 4680.34 MIN: 4460.82 MIN: 4427.82 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Node.js V8 Web Tooling Benchmark OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 7.24 7.67 7.62 1. Nodejs
v12.18.2
Basis Universal Settings: ETC1S OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: ETC1S Default Kernel Linux 5.10.4 Linux 5.11-rc1 14 28 42 56 70 SE +/- 0.35, N = 3 SE +/- 0.24, N = 3 SE +/- 0.22, N = 3 64.56 61.00 60.95 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: auto-levels Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 16.03 16.90 16.98
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2K 4K 6K 8K 10K SE +/- 9.60, N = 3 SE +/- 14.45, N = 3 SE +/- 17.59, N = 3 9027.63 8564.54 8540.48 MIN: 8975.45 MIN: 8529.89 MIN: 8490.77 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1000 2000 3000 4000 5000 SE +/- 20.61, N = 3 SE +/- 7.62, N = 3 SE +/- 8.44, N = 3 4742.11 4497.06 4486.34 MIN: 4659.09 MIN: 4465.18 MIN: 4457.53 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
LZ4 Compression Compression Level: 1 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Decompression Speed Default Kernel Linux 5.10.4 Linux 5.11-rc1 2K 4K 6K 8K 10K SE +/- 55.92, N = 3 SE +/- 9.29, N = 3 SE +/- 40.00, N = 3 8129.2 8560.1 8592.3 1. (CC) gcc options: -O3
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2K 4K 6K 8K 10K SE +/- 23.24, N = 3 SE +/- 15.87, N = 3 SE +/- 17.36, N = 3 9028.50 8575.95 8545.33 MIN: 8965.57 MIN: 8526.04 MIN: 8489.41 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Darktable Test: Masskrug - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Masskrug - Acceleration: CPU-only Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.017, N = 3 SE +/- 0.004, N = 3 SE +/- 0.006, N = 3 6.745 6.392 6.397
Darktable Test: Server Room - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Server Room - Acceleration: CPU-only Default Kernel Linux 5.10.4 Linux 5.11-rc1 1.1723 2.3446 3.5169 4.6892 5.8615 SE +/- 0.017, N = 3 SE +/- 0.006, N = 3 SE +/- 0.006, N = 3 5.210 4.940 4.959
libavif avifenc Encoder Speed: 10 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 10 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.026, N = 3 SE +/- 0.017, N = 3 SE +/- 0.005, N = 3 6.622 6.312 6.284 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 30 60 90 120 150 SE +/- 1.72, N = 3 SE +/- 0.38, N = 3 SE +/- 0.15, N = 3 131.14 126.03 124.54 1. (CXX) g++ options: -O3 -fPIC
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.14, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 13.62 12.96 12.94 MIN: 12.87 / MAX: 26.35 MIN: 12.85 / MAX: 22.3 MIN: 12.76 / MAX: 24.47 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
LZ4 Compression Compression Level: 1 - Compression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Compression Speed Default Kernel Linux 5.10.4 Linux 5.11-rc1 1600 3200 4800 6400 8000 SE +/- 73.87, N = 3 SE +/- 92.18, N = 3 SE +/- 46.06, N = 3 7192.29 7525.63 7572.23 1. (CC) gcc options: -O3
ASTC Encoder Preset: Fast OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.06, N = 8 7.72 7.35 7.42 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
PyPerformance Benchmark: 2to3 OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: 2to3 Default Kernel Linux 5.10.4 Linux 5.11-rc1 100 200 300 400 500 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 461 444 439
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2K 4K 6K 8K 10K SE +/- 4.57, N = 3 SE +/- 9.21, N = 3 SE +/- 10.93, N = 3 9002.53 8588.64 8583.12 MIN: 8960.78 MIN: 8557.28 MIN: 8546.55 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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.06535, N = 3 SE +/- 0.12964, N = 3 SE +/- 0.04049, N = 3 9.34927 9.80460 9.49354 MIN: 8.51 MIN: 9.16 MIN: 9 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.24, N = 16 SE +/- 0.54, N = 20 SE +/- 0.38, N = 4 38.91 40.27 38.42 1. (CC) gcc options: -O2 -std=c99
Timed MAFFT Alignment Multiple Sequence Alignment - LSU RNA OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 14.56 14.60 15.25 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
Polyhedron Fortran Benchmarks Benchmark: gas_dyn2 OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: gas_dyn2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 14 28 42 56 70 61.73 59.15 59.08
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 12 Total Time Default Kernel Linux 5.10.4 Linux 5.11-rc1 3M 6M 9M 12M 15M SE +/- 170465.83, N = 3 SE +/- 168497.64, N = 3 SE +/- 38144.94, N = 3 13361457 13559816 13897759 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
VKMark Resolution: 1280 x 1024 OpenBenchmarking.org VKMark Score, More Is Better VKMark 2020-05-21 Resolution: 1280 x 1024 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1400 2800 4200 5600 7000 SE +/- 3.28, N = 3 SE +/- 13.48, N = 3 SE +/- 8.41, N = 3 6184 6350 6426 1. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF
librsvg Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better librsvg Operation: SVG Files To PNG Default Kernel Linux 5.10.4 Linux 5.11-rc1 8 16 24 32 40 SE +/- 0.15, N = 3 SE +/- 0.31, N = 3 SE +/- 0.03, N = 3 34.32 35.65 35.00 1. rsvg-convert version 2.50.1
Unpacking The Linux Kernel linux-4.15.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel linux-4.15.tar.xz Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.047, N = 4 SE +/- 0.040, N = 20 SE +/- 0.037, N = 4 7.403 7.131 7.160
yquake2 Renderer: Software CPU - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: Software CPU - Resolution: 1920 x 1080 Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.52, N = 3 SE +/- 0.27, N = 3 SE +/- 0.29, N = 3 85.4 88.2 88.6 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material Default Kernel Linux 5.10.4 Linux 5.11-rc1 70 140 210 280 350 322.77 316.76 311.49
VKMark Resolution: 1920 x 1080 OpenBenchmarking.org VKMark Score, More Is Better VKMark 2020-05-21 Resolution: 1920 x 1080 Default Kernel Linux 5.10.4 Linux 5.11-rc1 1000 2000 3000 4000 5000 SE +/- 4.93, N = 3 SE +/- 3.71, N = 3 SE +/- 3.61, N = 3 4664 4732 4827 1. (CXX) g++ options: -pthread -ldl -pipe -std=c++14 -MD -MQ -MF
AI Benchmark Alpha Device Training Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Training Score Default Kernel Linux 5.10.4 Linux 5.11-rc1 150 300 450 600 750 667 689 685
XZ Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 Default Kernel Linux 5.10.4 Linux 5.11-rc1 11 22 33 44 55 SE +/- 0.30, N = 3 SE +/- 0.08, N = 3 SE +/- 0.12, N = 3 47.57 46.21 46.09 1. (CC) gcc options: -pthread -fvisibility=hidden -O2
Darktable Test: Boat - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 3.2.1 Test: Boat - Acceleration: CPU-only Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 13.75 13.32 13.34
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 1.1.1 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2K 4K 6K 8K 10K SE +/- 23.03, N = 3 SE +/- 67.59, N = 3 SE +/- 46.59, N = 3 10274 9972 9967 1. (CXX) g++ options: -O3 -pthread
Sunflow Rendering System Global Illumination + Image Synthesis OpenBenchmarking.org Seconds, Fewer Is Better Sunflow Rendering System 0.07.2 Global Illumination + Image Synthesis Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.356 0.712 1.068 1.424 1.78 SE +/- 0.014, N = 8 SE +/- 0.013, N = 3 SE +/- 0.022, N = 3 1.581 1.537 1.582 MIN: 1.38 / MAX: 2.33 MIN: 1.4 / MAX: 2.36 MIN: 1.4 / MAX: 2.3
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.3 Water Benchmark Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.1213 0.2426 0.3639 0.4852 0.6065 SE +/- 0.005, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.524 0.539 0.535 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.22, N = 8 SE +/- 0.14, N = 20 SE +/- 0.16, N = 20 26.47 25.74 25.99
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Default Kernel Linux 5.10.4 Linux 5.11-rc1 4M 8M 12M 16M 20M SE +/- 237774.54, N = 3 SE +/- 76230.74, N = 3 SE +/- 97740.42, N = 3 19306833 19840743 19661267
WireGuard + Linux Networking Stack Stress Test OpenBenchmarking.org Seconds, Fewer Is Better WireGuard + Linux Networking Stack Stress Test Default Kernel Linux 5.10.4 Linux 5.11-rc1 70 140 210 280 350 SE +/- 1.15, N = 3 SE +/- 3.52, N = 3 SE +/- 0.88, N = 3 300.19 308.47 308.38
libavif avifenc Encoder Speed: 2 OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.7.3 Encoder Speed: 2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.50, N = 3 SE +/- 0.18, N = 3 76.65 74.66 75.06 1. (CXX) g++ options: -O3 -fPIC
yquake2 Renderer: OpenGL 1.x - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 1.x - Resolution: 1920 x 1080 Default Kernel Linux 5.10.4 Linux 5.11-rc1 140 280 420 560 700 SE +/- 3.40, N = 3 SE +/- 8.16, N = 3 SE +/- 7.06, N = 3 631.8 641.4 625.3 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.00187, N = 3 SE +/- 0.03024, N = 3 SE +/- 0.04602, N = 3 7.03197 6.85975 6.92207 MIN: 6.48 MIN: 6.65 MIN: 6.7 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.0448, N = 3 SE +/- 0.0788, N = 3 SE +/- 0.0259, N = 3 7.9759 8.1739 8.1022 MIN: 7.86 / MAX: 8.15 MIN: 8.02 / MAX: 8.44 MIN: 8.03 / MAX: 8.26
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 17.00 17.38 17.41 MIN: 16.89 MIN: 17.2 MIN: 17.33 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
AI Benchmark Alpha Device AI Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device AI Score Default Kernel Linux 5.10.4 Linux 5.11-rc1 300 600 900 1200 1500 1248 1277 1269
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: unsharp-mask Default Kernel Linux 5.10.4 Linux 5.11-rc1 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 19.02 19.19 19.45
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.17, N = 3 85.71 83.81 83.88
Polyhedron Fortran Benchmarks Benchmark: channel2 OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: channel2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 13 26 39 52 65 59.51 58.21 58.21
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 22.5 22.9 23.0 1. (CC) gcc options: -O3 -pthread -lz
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: CPU-Only Default Kernel Linux 5.10.4 Linux 5.11-rc1 50 100 150 200 250 SE +/- 2.78, N = 4 SE +/- 0.81, N = 3 SE +/- 1.16, N = 3 237.53 232.46 236.57
Basis Universal Settings: UASTC Level 2 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 Default Kernel Linux 5.10.4 Linux 5.11-rc1 10 20 30 40 50 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 43.98 43.09 43.28 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 78.65 77.08 78.29 1. RawTherapee, version 5.8, command line.
GIMP Test: rotate OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.18 Test: rotate Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 15.41 15.28 15.10
rav1e Speed: 1 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 1 Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.0587 0.1174 0.1761 0.2348 0.2935 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 SE +/- 0.001, N = 3 0.256 0.261 0.259
Polyhedron Fortran Benchmarks Benchmark: linpk OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: linpk Default Kernel Linux 5.10.4 Linux 5.11-rc1 1.0823 2.1646 3.2469 4.3292 5.4115 4.81 4.73 4.72
rav1e Speed: 5 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 5 Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.1753 0.3506 0.5259 0.7012 0.8765 SE +/- 0.001, N = 3 SE +/- 0.005, N = 3 SE +/- 0.001, N = 3 0.765 0.779 0.774
IndigoBench Acceleration: CPU - Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Bedroom Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.3058 0.6116 0.9174 1.2232 1.529 SE +/- 0.001, N = 3 SE +/- 0.003, N = 3 SE +/- 0.001, N = 3 1.335 1.354 1.359
yquake2 Renderer: OpenGL 3.x - Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 3.x - Resolution: 1920 x 1080 Default Kernel Linux 5.10.4 Linux 5.11-rc1 200 400 600 800 1000 SE +/- 7.08, N = 3 SE +/- 2.23, N = 3 SE +/- 9.60, N = 3 944.3 960.5 947.3 1. (CC) gcc options: -lm -ldl -rdynamic -shared -lSDL2 -O2 -pipe -fomit-frame-pointer -std=gnu99 -fno-strict-aliasing -fwrapv -fvisibility=hidden -MMD -mfpmath=sse -fPIC
ASTC Encoder Preset: Thorough OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough Default Kernel Linux 5.10.4 Linux 5.11-rc1 9 18 27 36 45 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 36.95 36.58 37.20 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Asian Dragon Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.0725, N = 3 SE +/- 0.0500, N = 3 SE +/- 0.0404, N = 3 8.3970 8.5188 8.3775 MIN: 8.23 / MAX: 8.61 MIN: 8.4 / MAX: 8.7 MIN: 8.3 / MAX: 8.55
ASTC Encoder Preset: Exhaustive OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive Default Kernel Linux 5.10.4 Linux 5.11-rc1 70 140 210 280 350 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 303.53 300.62 305.64 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Default Kernel Linux 5.10.4 Linux 5.11-rc1 60K 120K 180K 240K 300K SE +/- 1434.22, N = 3 SE +/- 872.17, N = 3 SE +/- 802.31, N = 3 267555.23 270279.69 271886.25 1. (CC) gcc options: -O2 -lrt" -lrt
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 6.0.9 Test: LPUSH Default Kernel Linux 5.10.4 Linux 5.11-rc1 200K 400K 600K 800K 1000K SE +/- 9875.40, N = 15 SE +/- 14750.43, N = 3 SE +/- 11649.30, N = 3 1065654.10 1049901.52 1053853.02 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
ASTC Encoder Preset: Medium OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 6.11 6.05 6.14 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Basis Universal Settings: UASTC Level 2 + RDO Post-Processing OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 + RDO Post-Processing Default Kernel Linux 5.10.4 Linux 5.11-rc1 200 400 600 800 1000 SE +/- 0.27, N = 3 SE +/- 0.82, N = 3 SE +/- 1.15, N = 3 867.81 855.36 857.23 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
rav1e Speed: 10 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 10 Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.5285 1.057 1.5855 2.114 2.6425 SE +/- 0.007, N = 3 SE +/- 0.002, N = 3 SE +/- 0.019, N = 3 2.349 2.316 2.347
IndigoBench Acceleration: CPU - Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Supercar Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.6451 1.2902 1.9353 2.5804 3.2255 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 SE +/- 0.028, N = 3 2.828 2.867 2.843
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester Default Kernel Linux 5.10.4 Linux 5.11-rc1 60 120 180 240 300 287.58 291.47 289.58
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: CPU-Only Default Kernel Linux 5.10.4 Linux 5.11-rc1 70 140 210 280 350 SE +/- 0.28, N = 3 SE +/- 0.38, N = 3 SE +/- 0.76, N = 3 329.39 325.24 326.50
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Default Kernel Linux 5.10.4 Linux 5.11-rc1 30 60 90 120 150 SE +/- 0.91, N = 3 SE +/- 0.92, N = 3 SE +/- 0.86, N = 3 131.32 129.83 129.68
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 10.0 Time To Compile Default Kernel Linux 5.10.4 Linux 5.11-rc1 200 400 600 800 1000 SE +/- 0.68, N = 3 SE +/- 0.83, N = 3 SE +/- 3.21, N = 3 1057.63 1044.46 1050.45
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Crown Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.0587, N = 3 SE +/- 0.0471, N = 3 SE +/- 0.0326, N = 3 7.3312 7.3497 7.4224 MIN: 7.18 / MAX: 7.52 MIN: 7.23 / MAX: 7.53 MIN: 7.34 / MAX: 7.57
AI Benchmark Alpha Device Inference Score OpenBenchmarking.org Score, More Is Better AI Benchmark Alpha 0.1.2 Device Inference Score Default Kernel Linux 5.10.4 Linux 5.11-rc1 130 260 390 520 650 581 588 584
LZ4 Compression Compression Level: 9 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Decompression Speed Default Kernel Linux 5.10.4 Linux 5.11-rc1 2K 4K 6K 8K 10K SE +/- 8.31, N = 3 SE +/- 8.68, N = 3 SE +/- 13.60, N = 3 7828.5 7895.5 7920.9 1. (CC) gcc options: -O3
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 Default Kernel Linux 5.10.4 Linux 5.11-rc1 600 1200 1800 2400 3000 SE +/- 14.17, N = 3 SE +/- 7.47, N = 3 SE +/- 6.18, N = 3 2849.0 2838.6 2872.0 1. (CC) gcc options: -O3 -pthread -lz
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer ISPC - Model: Crown Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.0323, N = 3 SE +/- 0.0390, N = 3 SE +/- 0.0114, N = 3 6.7689 6.7934 6.8458 MIN: 6.67 / MAX: 6.9 MIN: 6.68 / MAX: 6.95 MIN: 6.79 / MAX: 6.96
Basis Universal Settings: UASTC Level 3 OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 Default Kernel Linux 5.10.4 Linux 5.11-rc1 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 82.39 81.48 81.62 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.0127, N = 3 SE +/- 0.0234, N = 3 SE +/- 0.0090, N = 3 7.8014 7.8722 7.8824 MIN: 7.74 / MAX: 7.91 MIN: 7.8 / MAX: 7.98 MIN: 7.84 / MAX: 7.97
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 13.34 13.24 13.21 MIN: 12.96 MIN: 12.87 MIN: 12.85 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily Default Kernel Linux 5.10.4 Linux 5.11-rc1 120 240 360 480 600 539.96 535.01 536.84
LZ4 Compression Compression Level: 3 - Decompression Speed OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed Default Kernel Linux 5.10.4 Linux 5.11-rc1 2K 4K 6K 8K 10K SE +/- 5.10, N = 3 SE +/- 14.26, N = 3 SE +/- 16.93, N = 3 7835.5 7899.3 7906.8 1. (CC) gcc options: -O3
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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 2 4 6 8 10 SE +/- 0.0139, N = 3 SE +/- 0.0051, N = 3 SE +/- 0.0109, N = 3 7.2063 7.2702 7.2554 MIN: 7.15 / MAX: 7.3 MIN: 7.24 / MAX: 7.35 MIN: 7.21 / MAX: 7.32
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile Default Kernel Linux 5.10.4 Linux 5.11-rc1 50 100 150 200 250 SE +/- 1.02, N = 3 SE +/- 1.49, N = 3 SE +/- 0.84, N = 3 232.99 231.01 231.54
rav1e Speed: 6 OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.4 Alpha Speed: 6 Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.2313 0.4626 0.6939 0.9252 1.1565 SE +/- 0.001, N = 3 SE +/- 0.004, N = 3 SE +/- 0.003, N = 3 1.022 1.020 1.028
Polyhedron Fortran Benchmarks Benchmark: capacita OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: capacita Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 16.18 16.24 16.20
simdjson Throughput Test: DistinctUserID OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: DistinctUserID Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.1035 0.207 0.3105 0.414 0.5175 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.46 0.46 0.46 1. (CXX) g++ options: -O3 -pthread
simdjson Throughput Test: PartialTweets OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: PartialTweets Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.1013 0.2026 0.3039 0.4052 0.5065 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.45 0.45 0.45 1. (CXX) g++ options: -O3 -pthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny Default Kernel Linux 5.10.4 Linux 5.11-rc1 11 22 33 44 55 SE +/- 0.25, N = 3 SE +/- 0.51, N = 3 SE +/- 1.73, N = 3 50.06 42.46 41.05 MIN: 40.36 / MAX: 77.16 MIN: 36.31 / MAX: 45.38 MIN: 36.21 / MAX: 43.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet18 Default Kernel Linux 5.10.4 Linux 5.11-rc1 6 12 18 24 30 SE +/- 0.42, N = 3 SE +/- 0.83, N = 3 SE +/- 0.86, N = 3 26.05 20.92 19.90 MIN: 20.5 / MAX: 71.2 MIN: 19.02 / MAX: 53.8 MIN: 18.96 / MAX: 22.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface Default Kernel Linux 5.10.4 Linux 5.11-rc1 0.8123 1.6246 2.4369 3.2492 4.0615 SE +/- 0.14, N = 3 SE +/- 0.03, N = 15 SE +/- 0.04, N = 3 3.61 3.38 3.47 MIN: 3.17 / MAX: 16.8 MIN: 3.16 / MAX: 4.51 MIN: 3.37 / MAX: 4.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -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 Default Kernel Linux 5.10.4 Linux 5.11-rc1 4 8 12 16 20 SE +/- 0.41, N = 15 SE +/- 0.30, N = 15 SE +/- 0.33, N = 15 14.78 14.31 14.45 MIN: 12.9 MIN: 13 MIN: 12.95 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 29Oct2020 Model: Rhodopsin Protein Default Kernel Linux 5.10.4 Linux 5.11-rc1 1.0715 2.143 3.2145 4.286 5.3575 SE +/- 0.098, N = 15 SE +/- 0.014, N = 3 SE +/- 0.012, N = 3 4.311 4.720 4.762 1. (CXX) g++ options: -O3 -pthread -lm
Phoronix Test Suite v10.8.4