Linux 5.10 Ryzen 7 3800XT AMD Ryzen 7 3800XT 8-Core testing with a ASRock X570 Pro4 (P3.00 BIOS) and Sapphire 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/2010245-FI-LINUX510R37&sor&grs .
Linux 5.10 Ryzen 7 3800XT Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Linux 5.9.1 Linux 5.10 Git 23 Oct AMD Ryzen 7 3800XT 8-Core @ 3.90GHz (8 Cores / 16 Threads) ASRock X570 Pro4 (P3.00 BIOS) AMD Starship/Matisse 16GB 500GB CT500P2SSD8 Sapphire AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1560/2100MHz) AMD Ellesmere HDMI Audio G237HL Intel I211 Ubuntu 20.04 5.9.1-050901-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 20.0.4 (LLVM 9.0.1) 1.2.128 GCC 9.3.0 ext4 1920x1080 5.9.0-050900daily20201023-generic (x86_64) 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 Disk Details - Linux 5.9.1: NONE / errors=remount-ro,relatime,rw - Linux 5.10 Git 23 Oct: NONE / errors=remount-ro,no_fc,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8701021 Graphics Details - GLAMOR Python Details - Python 3.8.5 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Linux 5.10 Ryzen 7 3800XT ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - squeezenet stress-ng: System V Message Passing ncnn: Vulkan GPU - resnet50 hackbench: 8 - Process hackbench: 4 - Process hackbench: 8 - Thread hackbench: 4 - Thread hackbench: 16 - Process hackbench: 16 - Thread hackbench: 2 - Process hackbench: 2 - Thread dav1d: Chimera 1080p ncnn: Vulkan GPU - shufflenet-v2 hackbench: 32 - Process lammps: 20k Atoms dav1d: Summer Nature 4K dav1d: Summer Nature 1080p lammps: Rhodopsin Protein stress-ng: Memory Copying hackbench: 1 - Process hackbench: 1 - Thread stress-ng: Socket Activity postmark: Disk Transaction Performance osbench: Create Threads apache-siege: 50 ncnn: Vulkan GPU - mobilenet lczero: Eigen stress-ng: Forking apache-siege: 10 stress-ng: MMAP osbench: Create Files gpaw: Carbon Nanotube selenium: CanvasMark - Firefox stress-ng: Glibc C String Functions stress-ng: CPU Cache apache-siege: 250 selenium: ARES-6 - Firefox webp: Quality 100, Lossless selenium: Basemark - Firefox stress-ng: MEMFD libraw: Post-Processing Benchmark waifu2x-ncnn: 2x - 3 - No webp: Quality 100, Highest Compression keydb: openvino: Age Gender Recognition Retail 0013 FP32 - CPU sockperf: Latency Ping Pong ncnn: Vulkan GPU - yolov4-tiny stress-ng: SENDFILE leveldb: Hot Read apache-siege: 100 dolfyn: Computational Fluid Dynamics couchdb: 100 - 1000 - 24 leveldb: Rand Read selenium: Kraken - Firefox lczero: BLAS espeak: Text-To-Speech Synthesis apache-siege: 200 waifu2x-ncnn: 2x - 3 - Yes webp: Quality 100 stress-ng: Context Switching tnn: CPU - SqueezeNet v1.1 vkfft: osbench: Launch Programs compress-zstd: 19 stress-ng: Malloc ncnn: Vulkan GPU - vgg16 x265: Bosphorus 4K realsr-ncnn: 4x - No selenium: Jetstream - Firefox realsr-ncnn: 4x - Yes dav1d: Chimera 1080p 10-bit tensorflow-lite: NASNet Mobile kvazaar: Bosphorus 1080p - Very Fast svt-av1: Enc Mode 0 - 1080p stress-ng: Semaphores stress-ng: NUMA kvazaar: Bosphorus 1080p - Ultra Fast ncnn: CPU - resnet18 tnn: CPU - MobileNet v2 ncnn: CPU-v3-v3 - mobilenet-v3 compress-zstd: 3 openvino: Person Detection 0106 FP32 - CPU ncnn: CPU - vgg16 ncnn: CPU - efficientnet-b0 leveldb: Overwrite svt-av1: Enc Mode 4 - 1080p ncnn: CPU - mnasnet osbench: Memory Allocations svt-av1: Enc Mode 8 - 1080p openvino: Face Detection 0106 FP16 - CPU ncnn: CPU - blazeface kvazaar: Bosphorus 4K - Slow x265: Bosphorus 1080p selenium: Octane - Firefox leveldb: Overwrite webp: Default mafft: Multiple Sequence Alignment - LSU RNA openvino: Face Detection 0106 FP16 - CPU kvazaar: Bosphorus 1080p - Slow stress-ng: Glibc Qsort Data Sorting kvazaar: Bosphorus 1080p - Medium kvazaar: Bosphorus 4K - Medium leveldb: Rand Fill blender: Pabellon Barcelona - CPU-Only ncnn: CPU - resnet50 leveldb: Rand Fill leveldb: Seq Fill sockperf: Throughput leveldb: Seq Fill blender: Classroom - CPU-Only stress-ng: Matrix Math blender: Barbershop - CPU-Only blender: Fishy Cat - CPU-Only openvino: Age Gender Recognition Retail 0013 FP16 - CPU ncnn: CPU - shufflenet-v2 kvazaar: Bosphorus 4K - Ultra Fast caffe: GoogleNet - CPU - 100 ncnn: CPU - alexnet leveldb: Seek Rand blender: BMW27 - CPU-Only caffe: AlexNet - CPU - 100 stress-ng: Crypto tensorflow-lite: Mobilenet Quant namd: ATPase Simulation - 327,506 Atoms openvino: Face Detection 0106 FP32 - CPU gromacs: Water Benchmark selenium: StyleBench - Firefox openvino: Age Gender Recognition Retail 0013 FP32 - CPU ncnn: CPU - mobilenet tensorflow-lite: Inception ResNet V2 tensorflow-lite: SqueezeNet stress-ng: Atomic openvino: Person Detection 0106 FP32 - CPU kvazaar: Bosphorus 4K - Very Fast stress-ng: CPU Stress ncnn: CPU - squeezenet tensorflow-lite: Inception V4 openvino: Person Detection 0106 FP16 - CPU ncnn: CPU - yolov4-tiny leveldb: Rand Delete tensorflow-lite: Mobilenet Float webp: Quality 100, Lossless, Highest Compression stress-ng: Vector Math basemark: Vulkan - 1920 x 1080 - Medium basemark: Vulkan - 1920 x 1080 - High xonotic: 1920 x 1080 - Ultimate unigine-super: 1920 x 1080 - Fullscreen - Ultra - OpenGL unigine-super: 1920 x 1080 - Fullscreen - High - OpenGL tesseract: 1920 x 1080 influxdb: 1024 - 10000 - 2,5000,1 - 10000 influxdb: 64 - 10000 - 2,5000,1 - 10000 influxdb: 4 - 10000 - 2,5000,1 - 10000 selenium: WASM collisionDetection - Firefox selenium: WASM imageConvolute - Firefox selenium: Speedometer - Firefox selenium: Maze Solver - Firefox selenium: Jetstream 2 - Firefox selenium: WebXPRT - Firefox openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Person Detection 0106 FP16 - CPU openvino: Face Detection 0106 FP32 - CPU ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - blazeface ncnn: CPU - googlenet ncnn: CPU-v2-v2 - mobilenet-v2 selenium: MotionMark - Firefox leveldb: Fill Sync leveldb: Fill Sync osbench: Create Processes sockperf: Latency Under Load ior: Read Test ior: Write Test Linux 5.9.1 Linux 5.10 Git 23 Oct 6.15 9.76 15.14 7.35 6.84 16.09 14.82 11459628.02 23.43 20.544 10.750 21.078 11.125 42.756 43.667 5.774 6.003 490.58 3.99 94.682 6.458 159.70 455.55 6.214 3443.50 4.491 4.714 6765.81 7896 9.769917 88406.23 11.30 593 51191.56 34254.15 184.29 12.063223 379.346 14235 583277.59 21.37 76561.94 40.05 15.426 906.01 589.68 40.16 3.035 6.723 623244.73 0.57 3.566 18.76 151380.14 7.350 92711.94 15.416 94.670 7.316 743.2 600 28.252 82538.86 19.944 2.136 4257616.04 237.723 10851 38.183530 30.8 83874667.83 53.64 11.54 47.531 228.28 363.352 102.41 160650 59.41 0.115 1161533.53 219.61 110.29 19.15 247.257 5.60 3749.4 1.49 76.30 7.96 32.4 3.246 5.09 75.081348 27.280 1.87 1.89 5.79 50.61 37823 54.645 1.398 11.493 2137.28 24.96 141.17 25.59 5.87 54.775 498.42 32.10 32.3 33.4 696486 53.027 447.04 40473.69 648.28 208.00 6806.09 4.71 29.17 128607 17.28 11.143 155.68 52917 2406.52 126774 2.19358 2141.33 0.775 85.6 6759.07 19.50 2415433 185313 764049.46 2669.23 16.39 3567.53 18.67 2672843 2665.58 31.35 50.604 124015 32.163 76006.77 606.02 119.63 315.0188537 18.0 41.2 529.0309 1451332.5 1420949.5 1225807.0 364.7 27.1 98.3 4.4 107.972 273 0.57 1.49 1.87 9.98 1.53 18.24 6.38 116.88 6684.944 0.3 20.608719 67.366 347.81 159.91 7.72 12.06 18.67 9.02 8.15 18.99 17.43 13469379.61 27.14 23.585 12.316 24.089 12.707 48.603 49.415 6.524 6.744 436.85 4.46 105.473 5.848 144.76 417.41 5.736 3212.42 4.774 4.980 6454.54 7575 9.380182 84898.97 11.74 616 49488.99 33189.87 189.96 12.404537 389.706 13858 598962.95 20.83 74632.41 39.06 15.054 884.84 602.89 39.30 3.099 6.851 612175.88 0.58 3.626 19.06 148999.83 7.467 91299.42 15.653 93.241 7.428 732.0 609 27.842 81351.09 20.235 2.167 4198734.92 234.495 10706 38.693746 30.4 82826646.86 54.30 11.40 48.114 225.69 367.415 101.36 162185 58.89 0.114 1151702.00 217.83 109.42 19.00 245.437 5.56 3723.2 1.48 75.80 7.91 32.2 3.226 5.06 74.654976 27.126 1.88 1.88 5.76 50.35 37642 54.896 1.404 11.444 2128.90 24.87 141.68 25.50 5.85 54.953 500.00 32.00 32.2 33.3 698513 53.170 448.22 40575.62 646.68 208.50 6822.19 4.72 29.11 128858 17.25 11.162 155.43 52833 2402.77 126948 2.19643 2138.56 0.774 85.7 6751.86 19.48 2417670 185481 764678.98 2667.29 16.38 3565.42 18.66 2674193 2666.60 31.36 50.619 124051 32.167 76005.99 273 0.57 1.49 1.87 9.98 1.53 18.24 6.38 111.81 6147.487 0.3 20.927588 98.686 394.46 195.45 OpenBenchmarking.org
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 6.15 7.72 MIN: 5.77 / MAX: 10.07 MIN: 7.45 / MAX: 16.74 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet18 Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 9.76 12.06 MIN: 8.39 / MAX: 20.03 MIN: 11.58 / MAX: 20.2 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: efficientnet-b0 Linux 5.9.1 Linux 5.10 Git 23 Oct 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 15.14 18.67 MIN: 14.22 / MAX: 21.44 MIN: 18.2 / MAX: 26.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 7.35 9.02 MIN: 6.95 / MAX: 16.06 MIN: 8.64 / MAX: 18.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mnasnet Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 6.84 8.15 MIN: 6.52 / MAX: 14.49 MIN: 7.8 / MAX: 16.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: googlenet Linux 5.9.1 Linux 5.10 Git 23 Oct 5 10 15 20 25 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 16.09 18.99 MIN: 15.17 / MAX: 27.56 MIN: 18.54 / MAX: 30.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: squeezenet Linux 5.9.1 Linux 5.10 Git 23 Oct 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 14.82 17.43 MIN: 13.9 / MAX: 28.87 MIN: 17.04 / MAX: 27.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: System V Message Passing Linux 5.10 Git 23 Oct Linux 5.9.1 3M 6M 9M 12M 15M SE +/- 17928.61, N = 3 SE +/- 25794.08, N = 3 13469379.61 11459628.02 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet50 Linux 5.9.1 Linux 5.10 Git 23 Oct 6 12 18 24 30 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 23.43 27.14 MIN: 21.98 / MAX: 37.49 MIN: 22.09 / MAX: 36.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Hackbench Count: 8 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Process Linux 5.9.1 Linux 5.10 Git 23 Oct 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 20.54 23.59 1. (CC) gcc options: -lpthread
Hackbench Count: 4 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Process Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 10.75 12.32 1. (CC) gcc options: -lpthread
Hackbench Count: 8 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Thread Linux 5.9.1 Linux 5.10 Git 23 Oct 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 21.08 24.09 1. (CC) gcc options: -lpthread
Hackbench Count: 4 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Thread Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 11.13 12.71 1. (CC) gcc options: -lpthread
Hackbench Count: 16 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process Linux 5.9.1 Linux 5.10 Git 23 Oct 11 22 33 44 55 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 42.76 48.60 1. (CC) gcc options: -lpthread
Hackbench Count: 16 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread Linux 5.9.1 Linux 5.10 Git 23 Oct 11 22 33 44 55 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 43.67 49.42 1. (CC) gcc options: -lpthread
Hackbench Count: 2 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Process Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.033, N = 3 SE +/- 0.029, N = 3 5.774 6.524 1. (CC) gcc options: -lpthread
Hackbench Count: 2 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Thread Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.031, N = 3 SE +/- 0.055, N = 3 6.003 6.744 1. (CC) gcc options: -lpthread
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Chimera 1080p Linux 5.9.1 Linux 5.10 Git 23 Oct 110 220 330 440 550 SE +/- 1.87, N = 3 SE +/- 4.03, N = 10 490.58 436.85 MIN: 377.92 / MAX: 704.59 MIN: 320.22 / MAX: 628.69 1. (CC) gcc options: -pthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: shufflenet-v2 Linux 5.9.1 Linux 5.10 Git 23 Oct 1.0035 2.007 3.0105 4.014 5.0175 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.99 4.46 MIN: 3.83 / MAX: 4.63 MIN: 4.39 / MAX: 5.13 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Hackbench Count: 32 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Linux 5.9.1 Linux 5.10 Git 23 Oct 20 40 60 80 100 SE +/- 0.87, N = 3 SE +/- 1.42, N = 4 94.68 105.47 1. (CC) gcc options: -lpthread
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: 20k Atoms Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.028, N = 3 SE +/- 0.017, N = 3 6.458 5.848 1. (CXX) g++ options: -O3 -pthread -lm
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Summer Nature 4K Linux 5.9.1 Linux 5.10 Git 23 Oct 40 80 120 160 200 SE +/- 0.07, N = 3 SE +/- 1.51, N = 7 159.70 144.76 MIN: 140.75 / MAX: 170.03 MIN: 116.22 / MAX: 154.79 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 Linux 5.9.1 Linux 5.10 Git 23 Oct 100 200 300 400 500 SE +/- 1.52, N = 3 SE +/- 3.47, N = 3 455.55 417.41 MIN: 381.07 / MAX: 495.69 MIN: 343.92 / MAX: 453.56 1. (CC) gcc options: -pthread
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: Rhodopsin Protein Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.064, N = 15 SE +/- 0.067, N = 3 6.214 5.736 1. (CXX) g++ options: -O3 -pthread -lm
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Memory Copying Linux 5.9.1 Linux 5.10 Git 23 Oct 700 1400 2100 2800 3500 SE +/- 16.57, N = 3 SE +/- 33.77, N = 3 3443.50 3212.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
Hackbench Count: 1 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Process Linux 5.9.1 Linux 5.10 Git 23 Oct 1.0742 2.1484 3.2226 4.2968 5.371 SE +/- 0.005, N = 3 SE +/- 0.016, N = 3 4.491 4.774 1. (CC) gcc options: -lpthread
Hackbench Count: 1 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Thread Linux 5.9.1 Linux 5.10 Git 23 Oct 1.1205 2.241 3.3615 4.482 5.6025 SE +/- 0.030, N = 3 SE +/- 0.016, N = 3 4.714 4.980 1. (CC) gcc options: -lpthread
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Socket Activity Linux 5.9.1 Linux 5.10 Git 23 Oct 1500 3000 4500 6000 7500 SE +/- 18.37, N = 3 SE +/- 65.15, N = 3 6765.81 6454.54 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
PostMark Disk Transaction Performance OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance Linux 5.9.1 Linux 5.10 Git 23 Oct 2K 4K 6K 8K 10K SE +/- 84.00, N = 3 7896 7575 1. (CC) gcc options: -O3
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Linux 5.10 Git 23 Oct Linux 5.9.1 3 6 9 12 15 SE +/- 0.069936, N = 3 SE +/- 0.091455, N = 10 9.380182 9.769917 1. (CC) gcc options: -lm
Apache Siege Concurrent Users: 50 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 50 Linux 5.9.1 Linux 5.10 Git 23 Oct 20K 40K 60K 80K 100K SE +/- 812.43, N = 3 SE +/- 629.92, N = 3 88406.23 84898.97 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mobilenet Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 11.30 11.74 MIN: 10.53 / MAX: 24.46 MIN: 10.99 / MAX: 19.76 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LeelaChessZero Backend: Eigen OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: Eigen Linux 5.10 Git 23 Oct Linux 5.9.1 130 260 390 520 650 SE +/- 7.80, N = 3 SE +/- 6.46, N = 9 616 593 1. (CXX) g++ options: -flto -pthread
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Forking Linux 5.9.1 Linux 5.10 Git 23 Oct 11K 22K 33K 44K 55K SE +/- 214.03, N = 3 SE +/- 293.91, N = 3 51191.56 49488.99 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
Apache Siege Concurrent Users: 10 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 10 Linux 5.9.1 Linux 5.10 Git 23 Oct 7K 14K 21K 28K 35K SE +/- 361.59, N = 3 SE +/- 377.38, N = 6 34254.15 33189.87 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Stress-NG Test: MMAP OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MMAP Linux 5.10 Git 23 Oct Linux 5.9.1 40 80 120 160 200 SE +/- 0.11, N = 3 SE +/- 0.28, N = 3 189.96 184.29 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 12.06 12.40 1. (CC) gcc options: -lm
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube Linux 5.9.1 Linux 5.10 Git 23 Oct 80 160 240 320 400 SE +/- 0.31, N = 3 SE +/- 0.69, N = 3 379.35 389.71 1. (CC) gcc options: -pthread -shared -fwrapv -O2 -lxc -lblas -lmpi
Selenium Benchmark: CanvasMark - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: CanvasMark - Browser: Firefox Linux 5.9.1 Linux 5.10 Git 23 Oct 3K 6K 9K 12K 15K SE +/- 80.60, N = 3 SE +/- 139.74, N = 3 14235 13858 1. Linux 5.9.1: firefox 81.0.2 2. Linux 5.10 Git 23 Oct: firefox 82.0
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc C String Functions Linux 5.10 Git 23 Oct Linux 5.9.1 130K 260K 390K 520K 650K SE +/- 9660.65, N = 3 SE +/- 6366.90, N = 3 598962.95 583277.59 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: CPU Cache OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Cache Linux 5.9.1 Linux 5.10 Git 23 Oct 5 10 15 20 25 SE +/- 0.26, N = 15 SE +/- 0.24, N = 15 21.37 20.83 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
Apache Siege Concurrent Users: 250 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 250 Linux 5.9.1 Linux 5.10 Git 23 Oct 16K 32K 48K 64K 80K SE +/- 56.33, N = 3 SE +/- 693.79, N = 3 76561.94 74632.41 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Selenium Benchmark: ARES-6 - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: ARES-6 - Browser: Firefox Linux 5.10 Git 23 Oct Linux 5.9.1 9 18 27 36 45 SE +/- 0.15, N = 3 SE +/- 0.08, N = 3 39.06 40.05 1. Linux 5.10 Git 23 Oct: firefox 82.0 2. Linux 5.9.1: firefox 81.0.2
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 Linux 5.10 Git 23 Oct Linux 5.9.1 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 15.05 15.43 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Selenium Benchmark: Basemark - Browser: Firefox OpenBenchmarking.org Overall Score, More Is Better Selenium Benchmark: Basemark - Browser: Firefox Linux 5.9.1 Linux 5.10 Git 23 Oct 200 400 600 800 1000 SE +/- 13.26, N = 3 SE +/- 12.88, N = 3 906.01 884.84 1. Linux 5.9.1: firefox 81.0.2 2. Linux 5.10 Git 23 Oct: firefox 82.0
Stress-NG Test: MEMFD OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: MEMFD Linux 5.10 Git 23 Oct Linux 5.9.1 130 260 390 520 650 SE +/- 2.11, N = 3 SE +/- 1.72, N = 3 602.89 589.68 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark Linux 5.9.1 Linux 5.10 Git 23 Oct 9 18 27 36 45 SE +/- 0.40, N = 3 SE +/- 0.28, N = 3 40.16 39.30 1. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: No Linux 5.9.1 Linux 5.10 Git 23 Oct 0.6973 1.3946 2.0919 2.7892 3.4865 SE +/- 0.006, N = 3 SE +/- 0.050, N = 3 3.035 3.099
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.081, N = 3 SE +/- 0.010, N = 3 6.723 6.851 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 6.0.16 Linux 5.9.1 Linux 5.10 Git 23 Oct 130K 260K 390K 520K 650K SE +/- 1265.44, N = 3 SE +/- 679.54, N = 3 623244.73 612175.88 1. (CXX) g++ options: -O2 -levent_openssl -levent -lcrypto -lssl -lpthread -lz -lpcre
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 0.1305 0.261 0.3915 0.522 0.6525 SE +/- 0.00, N = 6 SE +/- 0.01, N = 3 0.57 0.58
Sockperf Test: Latency Ping Pong OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Ping Pong Linux 5.9.1 Linux 5.10 Git 23 Oct 0.8159 1.6318 2.4477 3.2636 4.0795 SE +/- 0.023, N = 21 SE +/- 0.038, N = 8 3.566 3.626 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: yolov4-tiny Linux 5.9.1 Linux 5.10 Git 23 Oct 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 18.76 19.06 MIN: 16.96 / MAX: 30.81 MIN: 17.4 / MAX: 28.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Stress-NG Test: SENDFILE OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: SENDFILE Linux 5.9.1 Linux 5.10 Git 23 Oct 30K 60K 90K 120K 150K SE +/- 527.85, N = 3 SE +/- 137.45, N = 3 151380.14 148999.83 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
LevelDB Benchmark: Hot Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.050, N = 3 SE +/- 0.001, N = 3 7.350 7.467 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Apache Siege Concurrent Users: 100 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 100 Linux 5.9.1 Linux 5.10 Git 23 Oct 20K 40K 60K 80K 100K SE +/- 475.78, N = 3 SE +/- 1178.45, N = 3 92711.94 91299.42 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Dolfyn Computational Fluid Dynamics OpenBenchmarking.org Seconds, Fewer Is Better Dolfyn 0.527 Computational Fluid Dynamics Linux 5.9.1 Linux 5.10 Git 23 Oct 4 8 12 16 20 SE +/- 0.12, N = 3 SE +/- 0.19, N = 3 15.42 15.65
Apache CouchDB Bulk Size: 100 - Inserts: 1000 - Rounds: 24 OpenBenchmarking.org Seconds, Fewer Is Better Apache CouchDB 3.1.1 Bulk Size: 100 - Inserts: 1000 - Rounds: 24 Linux 5.10 Git 23 Oct Linux 5.9.1 20 40 60 80 100 SE +/- 0.65, N = 3 SE +/- 1.46, N = 3 93.24 94.67 1. (CXX) g++ options: -std=c++14 -lmozjs-68 -lm -lerl_interface -lei -fPIC -MMD
LevelDB Benchmark: Random Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.013, N = 3 SE +/- 0.022, N = 3 7.316 7.428 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Selenium Benchmark: Kraken - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Firefox Linux 5.10 Git 23 Oct Linux 5.9.1 160 320 480 640 800 SE +/- 6.38, N = 3 SE +/- 1.63, N = 3 732.0 743.2 1. Linux 5.10 Git 23 Oct: firefox 82.0 2. Linux 5.9.1: firefox 81.0.2
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.26 Backend: BLAS Linux 5.10 Git 23 Oct Linux 5.9.1 130 260 390 520 650 SE +/- 6.57, N = 3 SE +/- 8.57, N = 3 609 600 1. (CXX) g++ options: -flto -pthread
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis Linux 5.10 Git 23 Oct Linux 5.9.1 7 14 21 28 35 SE +/- 0.20, N = 4 SE +/- 0.02, N = 4 27.84 28.25 1. (CC) gcc options: -O2 -std=c99
Apache Siege Concurrent Users: 200 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 200 Linux 5.9.1 Linux 5.10 Git 23 Oct 20K 40K 60K 80K 100K SE +/- 569.47, N = 3 SE +/- 833.80, N = 3 82538.86 81351.09 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Waifu2x-NCNN Vulkan Scale: 2x - Denoise: 3 - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes Linux 5.9.1 Linux 5.10 Git 23 Oct 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 19.94 20.24
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 Linux 5.9.1 Linux 5.10 Git 23 Oct 0.4876 0.9752 1.4628 1.9504 2.438 SE +/- 0.029, N = 3 SE +/- 0.028, N = 3 2.136 2.167 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Context Switching Linux 5.9.1 Linux 5.10 Git 23 Oct 900K 1800K 2700K 3600K 4500K SE +/- 51803.89, N = 3 SE +/- 18567.71, N = 3 4257616.04 4198734.92 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 Linux 5.10 Git 23 Oct Linux 5.9.1 50 100 150 200 250 SE +/- 1.91, N = 3 SE +/- 0.40, N = 3 234.50 237.72 MIN: 227.72 / MAX: 238.75 MIN: 234.13 / MAX: 246.23 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 2020-09-29 Linux 5.9.1 Linux 5.10 Git 23 Oct 2K 4K 6K 8K 10K SE +/- 5.21, N = 3 SE +/- 7.67, N = 3 10851 10706
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs Linux 5.9.1 Linux 5.10 Git 23 Oct 9 18 27 36 45 SE +/- 0.30, N = 3 SE +/- 0.50, N = 3 38.18 38.69 1. (CC) gcc options: -lm
Zstd Compression Compression Level: 19 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 19 Linux 5.9.1 Linux 5.10 Git 23 Oct 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.10, N = 3 30.8 30.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
Stress-NG Test: Malloc OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Malloc Linux 5.9.1 Linux 5.10 Git 23 Oct 20M 40M 60M 80M 100M SE +/- 81223.46, N = 3 SE +/- 53241.35, N = 3 83874667.83 82826646.86 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: vgg16 Linux 5.9.1 Linux 5.10 Git 23 Oct 12 24 36 48 60 SE +/- 0.11, N = 3 SE +/- 0.01, N = 3 53.64 54.30 MIN: 53.18 / MAX: 62.42 MIN: 53.75 / MAX: 58.98 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 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.12, N = 8 SE +/- 0.16, N = 3 11.54 11.40 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No Linux 5.9.1 Linux 5.10 Git 23 Oct 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 47.53 48.11
Selenium Benchmark: Jetstream - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream - Browser: Firefox Linux 5.9.1 Linux 5.10 Git 23 Oct 50 100 150 200 250 SE +/- 0.59, N = 3 SE +/- 0.48, N = 3 228.28 225.69 1. Linux 5.9.1: firefox 81.0.2 2. Linux 5.10 Git 23 Oct: firefox 82.0
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Linux 5.9.1 Linux 5.10 Git 23 Oct 80 160 240 320 400 SE +/- 0.20, N = 3 SE +/- 0.04, N = 3 363.35 367.42
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.7.0 Video Input: Chimera 1080p 10-bit Linux 5.9.1 Linux 5.10 Git 23 Oct 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.21, N = 3 102.41 101.36 MIN: 67.85 / MAX: 233.27 MIN: 67.25 / MAX: 225.76 1. (CC) gcc options: -pthread
TensorFlow Lite Model: NASNet Mobile OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: NASNet Mobile Linux 5.9.1 Linux 5.10 Git 23 Oct 30K 60K 90K 120K 150K SE +/- 597.97, N = 3 SE +/- 1913.90, N = 3 160650 162185
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 5.9.1 Linux 5.10 Git 23 Oct 13 26 39 52 65 SE +/- 0.18, N = 3 SE +/- 0.12, N = 3 59.41 58.89 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 0.0259 0.0518 0.0777 0.1036 0.1295 SE +/- 0.000, N = 3 SE +/- 0.000, N = 3 0.115 0.114 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Semaphores Linux 5.9.1 Linux 5.10 Git 23 Oct 200K 400K 600K 800K 1000K SE +/- 4093.36, N = 3 SE +/- 248.14, N = 3 1161533.53 1151702.00 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
Stress-NG Test: NUMA OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: NUMA Linux 5.9.1 Linux 5.10 Git 23 Oct 50 100 150 200 250 SE +/- 1.31, N = 3 SE +/- 0.91, N = 3 219.61 217.83 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
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 5.9.1 Linux 5.10 Git 23 Oct 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.28, N = 3 110.29 109.42 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18 Linux 5.10 Git 23 Oct Linux 5.9.1 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 19.00 19.15 MIN: 18.84 / MAX: 19.51 MIN: 18.92 / MAX: 34.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: MobileNet v2 Linux 5.10 Git 23 Oct Linux 5.9.1 50 100 150 200 250 SE +/- 2.46, N = 3 SE +/- 2.08, N = 3 245.44 247.26 MIN: 237.89 / MAX: 264.7 MIN: 241.93 / MAX: 271.83 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 Linux 5.10 Git 23 Oct Linux 5.9.1 1.26 2.52 3.78 5.04 6.3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 5.56 5.60 MIN: 5.44 / MAX: 7.78 MIN: 5.44 / MAX: 17.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Zstd Compression Compression Level: 3 OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.5 Compression Level: 3 Linux 5.9.1 Linux 5.10 Git 23 Oct 800 1600 2400 3200 4000 SE +/- 8.41, N = 3 SE +/- 6.89, N = 3 3749.4 3723.2 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenVINO Model: Person Detection 0106 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU Linux 5.9.1 Linux 5.10 Git 23 Oct 0.3353 0.6706 1.0059 1.3412 1.6765 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.49 1.48
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16 Linux 5.10 Git 23 Oct Linux 5.9.1 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.09, N = 3 75.80 76.30 MIN: 75.24 / MAX: 104.63 MIN: 75.89 / MAX: 81.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: efficientnet-b0 Linux 5.10 Git 23 Oct Linux 5.9.1 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 7.91 7.96 MIN: 7.81 / MAX: 8.69 MIN: 7.88 / MAX: 8.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite Linux 5.9.1 Linux 5.10 Git 23 Oct 8 16 24 32 40 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 32.4 32.2 1. (CXX) g++ options: -O3 -lsnappy -lpthread
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 0.7304 1.4608 2.1912 2.9216 3.652 SE +/- 0.007, N = 3 SE +/- 0.002, N = 3 3.246 3.226 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet Linux 5.10 Git 23 Oct Linux 5.9.1 1.1453 2.2906 3.4359 4.5812 5.7265 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 5.06 5.09 MIN: 4.97 / MAX: 5.97 MIN: 4.99 / MAX: 6.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Linux 5.10 Git 23 Oct Linux 5.9.1 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.19, N = 3 74.65 75.08 1. (CC) gcc options: -lm
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 27.28 27.13 1. (CXX) g++ options: -O3 -fcommon -fPIE -fPIC -pie
OpenVINO Model: Face Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU Linux 5.10 Git 23 Oct Linux 5.9.1 0.423 0.846 1.269 1.692 2.115 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 1.88 1.87
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface Linux 5.10 Git 23 Oct Linux 5.9.1 0.4253 0.8506 1.2759 1.7012 2.1265 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.88 1.89 MIN: 1.83 / MAX: 2.05 MIN: 1.84 / MAX: 2.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 1.3028 2.6056 3.9084 5.2112 6.514 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 5.79 5.76 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
x265 Video Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p Linux 5.9.1 Linux 5.10 Git 23 Oct 11 22 33 44 55 SE +/- 0.23, N = 3 SE +/- 0.22, N = 3 50.61 50.35 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Selenium Benchmark: Octane - Browser: Firefox OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Firefox Linux 5.9.1 Linux 5.10 Git 23 Oct 8K 16K 24K 32K 40K SE +/- 255.99, N = 3 SE +/- 221.23, N = 3 37823 37642 1. Linux 5.9.1: firefox 81.0.2 2. Linux 5.10 Git 23 Oct: firefox 82.0
LevelDB Benchmark: Overwrite OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite Linux 5.9.1 Linux 5.10 Git 23 Oct 12 24 36 48 60 SE +/- 0.17, N = 3 SE +/- 0.11, N = 3 54.65 54.90 1. (CXX) g++ options: -O3 -lsnappy -lpthread
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default Linux 5.9.1 Linux 5.10 Git 23 Oct 0.3159 0.6318 0.9477 1.2636 1.5795 SE +/- 0.015, N = 3 SE +/- 0.017, N = 3 1.398 1.404 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Timed MAFFT Alignment Multiple Sequence Alignment - LSU RNA OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 7.471 Multiple Sequence Alignment - LSU RNA Linux 5.10 Git 23 Oct Linux 5.9.1 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 11.44 11.49 1. (CC) gcc options: -std=c99 -O3 -lm -lpthread
OpenVINO Model: Face Detection 0106 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP16 - Device: CPU Linux 5.10 Git 23 Oct Linux 5.9.1 500 1000 1500 2000 2500 SE +/- 4.97, N = 3 SE +/- 7.43, N = 3 2128.90 2137.28
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 24.96 24.87 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Glibc Qsort Data Sorting Linux 5.10 Git 23 Oct Linux 5.9.1 30 60 90 120 150 SE +/- 0.45, N = 3 SE +/- 0.73, N = 3 141.68 141.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
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 5.9.1 Linux 5.10 Git 23 Oct 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 25.59 25.50 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
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 5.9.1 Linux 5.10 Git 23 Oct 1.3208 2.6416 3.9624 5.2832 6.604 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 5.87 5.85 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
LevelDB Benchmark: Random Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill Linux 5.9.1 Linux 5.10 Git 23 Oct 12 24 36 48 60 SE +/- 0.03, N = 3 SE +/- 0.12, N = 3 54.78 54.95 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Pabellon Barcelona - Compute: CPU-Only Linux 5.9.1 Linux 5.10 Git 23 Oct 110 220 330 440 550 SE +/- 0.79, N = 3 SE +/- 0.69, N = 3 498.42 500.00
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50 Linux 5.10 Git 23 Oct Linux 5.9.1 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 32.00 32.10 MIN: 31.76 / MAX: 33.97 MIN: 31.79 / MAX: 56.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LevelDB Benchmark: Random Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill Linux 5.9.1 Linux 5.10 Git 23 Oct 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 32.3 32.2 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill Linux 5.9.1 Linux 5.10 Git 23 Oct 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 33.4 33.3 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Sockperf Test: Throughput OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.4 Test: Throughput Linux 5.10 Git 23 Oct Linux 5.9.1 150K 300K 450K 600K 750K SE +/- 6321.01, N = 5 SE +/- 6634.59, N = 5 698513 696486 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill Linux 5.9.1 Linux 5.10 Git 23 Oct 12 24 36 48 60 SE +/- 0.10, N = 3 SE +/- 0.18, N = 3 53.03 53.17 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Classroom - Compute: CPU-Only Linux 5.9.1 Linux 5.10 Git 23 Oct 100 200 300 400 500 SE +/- 0.23, N = 3 SE +/- 0.57, N = 3 447.04 448.22
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Matrix Math Linux 5.10 Git 23 Oct Linux 5.9.1 9K 18K 27K 36K 45K SE +/- 427.33, N = 3 SE +/- 216.00, N = 3 40575.62 40473.69 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Barbershop - Compute: CPU-Only Linux 5.10 Git 23 Oct Linux 5.9.1 140 280 420 560 700 SE +/- 0.55, N = 3 SE +/- 0.58, N = 3 646.68 648.28
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: Fishy Cat - Compute: CPU-Only Linux 5.9.1 Linux 5.10 Git 23 Oct 50 100 150 200 250 SE +/- 0.47, N = 3 SE +/- 0.12, N = 3 208.00 208.50
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 Linux 5.10 Git 23 Oct Linux 5.9.1 1500 3000 4500 6000 7500 SE +/- 20.78, N = 3 SE +/- 15.22, N = 3 6822.19 6806.09
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: shufflenet-v2 Linux 5.9.1 Linux 5.10 Git 23 Oct 1.062 2.124 3.186 4.248 5.31 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 4.71 4.72 MIN: 4.6 / MAX: 5.6 MIN: 4.65 / MAX: 6.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
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 5.9.1 Linux 5.10 Git 23 Oct 7 14 21 28 35 SE +/- 0.11, N = 3 SE +/- 0.02, N = 3 29.17 29.11 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Caffe Model: GoogleNet - Acceleration: CPU - Iterations: 100 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Linux 5.9.1 Linux 5.10 Git 23 Oct 30K 60K 90K 120K 150K SE +/- 351.51, N = 3 SE +/- 187.00, N = 3 128607 128858 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet Linux 5.10 Git 23 Oct Linux 5.9.1 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 17.25 17.28 MIN: 17.17 / MAX: 17.41 MIN: 17.2 / MAX: 18.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LevelDB Benchmark: Seek Random OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 11.14 11.16 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.90 Blend File: BMW27 - Compute: CPU-Only Linux 5.10 Git 23 Oct Linux 5.9.1 30 60 90 120 150 SE +/- 0.06, N = 3 SE +/- 0.22, N = 3 155.43 155.68
Caffe Model: AlexNet - Acceleration: CPU - Iterations: 100 OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Linux 5.10 Git 23 Oct Linux 5.9.1 11K 22K 33K 44K 55K SE +/- 94.17, N = 3 SE +/- 83.67, N = 3 52833 52917 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Crypto Linux 5.9.1 Linux 5.10 Git 23 Oct 500 1000 1500 2000 2500 SE +/- 1.73, N = 3 SE +/- 3.59, N = 3 2406.52 2402.77 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
TensorFlow Lite Model: Mobilenet Quant OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Quant Linux 5.9.1 Linux 5.10 Git 23 Oct 30K 60K 90K 120K 150K SE +/- 94.84, N = 3 SE +/- 64.22, N = 3 126774 126948
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.14 ATPase Simulation - 327,506 Atoms Linux 5.9.1 Linux 5.10 Git 23 Oct 0.4942 0.9884 1.4826 1.9768 2.471 SE +/- 0.00186, N = 3 SE +/- 0.00110, N = 3 2.19358 2.19643
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU Linux 5.10 Git 23 Oct Linux 5.9.1 500 1000 1500 2000 2500 SE +/- 10.65, N = 3 SE +/- 3.98, N = 3 2138.56 2141.33
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.3 Water Benchmark Linux 5.9.1 Linux 5.10 Git 23 Oct 0.1744 0.3488 0.5232 0.6976 0.872 SE +/- 0.001, N = 3 SE +/- 0.002, N = 3 0.775 0.774 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
Selenium Benchmark: StyleBench - Browser: Firefox OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Firefox Linux 5.10 Git 23 Oct Linux 5.9.1 20 40 60 80 100 SE +/- 0.38, N = 3 SE +/- 0.27, N = 3 85.7 85.6 1. Linux 5.10 Git 23 Oct: firefox 82.0 2. Linux 5.9.1: firefox 81.0.2
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 1400 2800 4200 5600 7000 SE +/- 78.63, N = 6 SE +/- 51.64, N = 3 6759.07 6751.86
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet Linux 5.10 Git 23 Oct Linux 5.9.1 5 10 15 20 25 SE +/- 0.11, N = 3 SE +/- 0.09, N = 3 19.48 19.50 MIN: 19.04 / MAX: 21.7 MIN: 18.92 / MAX: 47.26 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 Linux 5.9.1 Linux 5.10 Git 23 Oct 500K 1000K 1500K 2000K 2500K SE +/- 1443.44, N = 3 SE +/- 1302.40, N = 3 2415433 2417670
TensorFlow Lite Model: SqueezeNet OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: SqueezeNet Linux 5.9.1 Linux 5.10 Git 23 Oct 40K 80K 120K 160K 200K SE +/- 63.53, N = 3 SE +/- 94.84, N = 3 185313 185481
Stress-NG Test: Atomic OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Atomic Linux 5.10 Git 23 Oct Linux 5.9.1 160K 320K 480K 640K 800K SE +/- 104.09, N = 3 SE +/- 511.18, N = 3 764678.98 764049.46 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
OpenVINO Model: Person Detection 0106 FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP32 - Device: CPU Linux 5.10 Git 23 Oct Linux 5.9.1 600 1200 1800 2400 3000 SE +/- 6.09, N = 3 SE +/- 4.38, N = 3 2667.29 2669.23
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 5.9.1 Linux 5.10 Git 23 Oct 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 16.39 16.38 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: CPU Stress Linux 5.9.1 Linux 5.10 Git 23 Oct 800 1600 2400 3200 4000 SE +/- 23.34, N = 3 SE +/- 15.17, N = 3 3567.53 3565.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet Linux 5.10 Git 23 Oct Linux 5.9.1 5 10 15 20 25 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 18.66 18.67 MIN: 18.24 / MAX: 32.62 MIN: 18.34 / MAX: 19.43 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TensorFlow Lite Model: Inception V4 OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Inception V4 Linux 5.9.1 Linux 5.10 Git 23 Oct 600K 1200K 1800K 2400K 3000K SE +/- 1325.07, N = 3 SE +/- 1229.12, N = 3 2672843 2674193
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU Linux 5.9.1 Linux 5.10 Git 23 Oct 600 1200 1800 2400 3000 SE +/- 1.24, N = 3 SE +/- 4.17, N = 3 2665.58 2666.60
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: yolov4-tiny Linux 5.9.1 Linux 5.10 Git 23 Oct 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 31.35 31.36 MIN: 31.1 / MAX: 32.16 MIN: 30.94 / MAX: 50.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LevelDB Benchmark: Random Delete OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete Linux 5.9.1 Linux 5.10 Git 23 Oct 11 22 33 44 55 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 50.60 50.62 1. (CXX) g++ options: -O3 -lsnappy -lpthread
TensorFlow Lite Model: Mobilenet Float OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2020-08-23 Model: Mobilenet Float Linux 5.9.1 Linux 5.10 Git 23 Oct 30K 60K 90K 120K 150K SE +/- 45.17, N = 3 SE +/- 67.04, N = 3 124015 124051
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 32.16 32.17 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.11.07 Test: Vector Math Linux 5.9.1 Linux 5.10 Git 23 Oct 16K 32K 48K 64K 80K SE +/- 2.74, N = 3 SE +/- 6.32, N = 3 76006.77 76005.99 1. (CC) gcc options: -O2 -std=gnu99 -lm -laio -lbsd -lcrypt -lrt -lz -ldl -lpthread -lc
Basemark GPU Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Medium OpenBenchmarking.org FPS, More Is Better Basemark GPU 1.2 Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: Medium Linux 5.9.1 130 260 390 520 650 SE +/- 2.74, N = 3 606.02 MIN: 332.72 / MAX: 1088.99
Basemark GPU Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: High OpenBenchmarking.org FPS, More Is Better Basemark GPU 1.2 Renderer: Vulkan - Resolution: 1920 x 1080 - Graphics Preset: High Linux 5.9.1 30 60 90 120 150 SE +/- 0.70, N = 3 119.63 MIN: 96.97 / MAX: 192.07
Xonotic Resolution: 1920 x 1080 - Effects Quality: Ultimate OpenBenchmarking.org Frames Per Second, More Is Better Xonotic 0.8.2 Resolution: 1920 x 1080 - Effects Quality: Ultimate Linux 5.9.1 70 140 210 280 350 SE +/- 3.01, N = 3 315.02 MIN: 41 / MAX: 835
Unigine Superposition Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Ultra - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better Unigine Superposition 1.0 Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: Ultra - Renderer: OpenGL Linux 5.9.1 4 8 12 16 20 SE +/- 0.03, N = 3 18.0 MAX: 21.6
Unigine Superposition Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: High - Renderer: OpenGL OpenBenchmarking.org Frames Per Second, More Is Better Unigine Superposition 1.0 Resolution: 1920 x 1080 - Mode: Fullscreen - Quality: High - Renderer: OpenGL Linux 5.9.1 9 18 27 36 45 SE +/- 0.06, N = 3 41.2 MAX: 52.6
Tesseract Resolution: 1920 x 1080 OpenBenchmarking.org Frames Per Second, More Is Better Tesseract 2014-05-12 Resolution: 1920 x 1080 Linux 5.9.1 110 220 330 440 550 SE +/- 0.92, N = 3 529.03
InfluxDB Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 Linux 5.9.1 300K 600K 900K 1200K 1500K SE +/- 714.22, N = 3 1451332.5
InfluxDB Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 Linux 5.9.1 300K 600K 900K 1200K 1500K SE +/- 2616.83, N = 3 1420949.5
InfluxDB Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 Linux 5.9.1 300K 600K 900K 1200K 1500K SE +/- 4975.23, N = 3 1225807.0
Selenium Benchmark: WASM collisionDetection - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Firefox Linux 5.9.1 80 160 240 320 400 SE +/- 1.70, N = 3 364.7 1. firefox 81.0.2
Selenium Benchmark: WASM imageConvolute - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Firefox Linux 5.9.1 6 12 18 24 30 SE +/- 0.25, N = 3 27.1 1. firefox 81.0.2
Selenium Benchmark: Speedometer - Browser: Firefox OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Firefox Linux 5.9.1 20 40 60 80 100 SE +/- 1.37, N = 3 98.3 1. firefox 81.0.2
Selenium Benchmark: Maze Solver - Browser: Firefox OpenBenchmarking.org Seconds, Fewer Is Better Selenium Benchmark: Maze Solver - Browser: Firefox Linux 5.9.1 0.99 1.98 2.97 3.96 4.95 SE +/- 0.00, N = 3 4.4 1. firefox 81.0.2
Selenium Benchmark: Jetstream 2 - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Firefox Linux 5.9.1 20 40 60 80 100 SE +/- 0.44, N = 3 107.97 1. firefox 81.0.2
Selenium Benchmark: WebXPRT - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: WebXPRT - Browser: Firefox Linux 5.10 Git 23 Oct Linux 5.9.1 60 120 180 240 300 SE +/- 1.00, N = 3 273 273 1. Linux 5.10 Git 23 Oct: firefox 82.0 2. Linux 5.9.1: firefox 81.0.2
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 Linux 5.9.1 Linux 5.10 Git 23 Oct 0.1283 0.2566 0.3849 0.5132 0.6415 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.57 0.57
OpenVINO Model: Person Detection 0106 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Person Detection 0106 FP16 - Device: CPU Linux 5.10 Git 23 Oct Linux 5.9.1 0.3353 0.6706 1.0059 1.3412 1.6765 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.49 1.49
OpenVINO Model: Face Detection 0106 FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2021.1 Model: Face Detection 0106 FP32 - Device: CPU Linux 5.10 Git 23 Oct Linux 5.9.1 0.4208 0.8416 1.2624 1.6832 2.104 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.87 1.87
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: alexnet Linux 5.9.1 Linux 5.10 Git 23 Oct 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 9.98 9.98 MIN: 9.01 / MAX: 20.09 MIN: 9.31 / MAX: 15.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: blazeface Linux 5.9.1 Linux 5.10 Git 23 Oct 0.3443 0.6886 1.0329 1.3772 1.7215 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.53 1.53 MIN: 1.5 / MAX: 1.69 MIN: 1.49 / MAX: 1.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet Linux 5.9.1 Linux 5.10 Git 23 Oct 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 18.24 18.24 MIN: 18.03 / MAX: 18.97 MIN: 17.96 / MAX: 72.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 Linux 5.9.1 Linux 5.10 Git 23 Oct 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 6.38 6.38 MIN: 6.26 / MAX: 7.79 MIN: 6.25 / MAX: 7.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Selenium Benchmark: MotionMark - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: MotionMark - Browser: Firefox Linux 5.9.1 Linux 5.10 Git 23 Oct 30 60 90 120 150 SE +/- 9.00, N = 6 SE +/- 6.41, N = 9 116.88 111.81 1. Linux 5.9.1: firefox 81.0.2 2. Linux 5.10 Git 23 Oct: firefox 82.0
LevelDB Benchmark: Fill Sync OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync Linux 5.10 Git 23 Oct Linux 5.9.1 1400 2800 4200 5600 7000 SE +/- 381.08, N = 3 SE +/- 154.24, N = 15 6147.49 6684.94 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Fill Sync OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync Linux 5.10 Git 23 Oct Linux 5.9.1 0.0675 0.135 0.2025 0.27 0.3375 SE +/- 0.00, N = 3 SE +/- 0.01, N = 15 0.3 0.3 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Linux 5.9.1 Linux 5.10 Git 23 Oct 5 10 15 20 25 SE +/- 0.72, N = 13 SE +/- 0.15, N = 3 20.61 20.93 1. (CC) gcc options: -lm
Sockperf Test: Latency Under Load OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Under Load Linux 5.9.1 Linux 5.10 Git 23 Oct 20 40 60 80 100 SE +/- 13.12, N = 25 SE +/- 12.91, N = 24 67.37 98.69 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
IOR Read Test OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Read Test Linux 5.10 Git 23 Oct Linux 5.9.1 90 180 270 360 450 SE +/- 31.04, N = 12 SE +/- 27.46, N = 12 394.46 347.81 MIN: 202.79 / MAX: 560.75 MIN: 159.63 / MAX: 584.11 1. (CC) gcc options: -O2 -lm -pthread -lmpi
IOR Write Test OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Write Test Linux 5.10 Git 23 Oct Linux 5.9.1 40 80 120 160 200 SE +/- 21.71, N = 12 SE +/- 18.20, N = 12 195.45 159.91 MIN: 8.49 / MAX: 357.27 MIN: 8.52 / MAX: 303.02 1. (CC) gcc options: -O2 -lm -pthread -lmpi
Phoronix Test Suite v10.8.4