Intel Core i7-4790K testing with a Gigabyte Z97-HD3P (F4 BIOS) and Gigabyte Intel Haswell Desktop 2GB on Ubuntu 19.10 via the Phoronix Test Suite.
1 Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-offload-targets=nvptx-none,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 -vProcessor Notes: Scaling Governor: intel_cpufreq ondemand - CPU Microcode: 0x28 - Thermald 1.9Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
2 3 Processor: Intel Core i7-4790K @ 4.40GHz (4 Cores / 8 Threads), Motherboard: Gigabyte Z97-HD3P (F4 BIOS), Chipset: Intel 4th Gen Core DRAM, Memory: 16GB, Disk: 120GB OCZ TRION100, Graphics: Gigabyte Intel Haswell Desktop 2GB (1250MHz), Audio: Intel Xeon E3-1200 v3/4th, Monitor: LG Ultra HD, Network: Realtek RTL8111/8168/8411
OS: Ubuntu 19.10, Kernel: 5.9.0-050900rc8daily20201009-generic (x86_64) 20201008, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.8, Vulkan: 1.1.102, Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 3840x2160
HPC Challenge HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL 1 2 3 20 40 60 80 100 SE +/- 1.21, N = 4 SE +/- 1.01, N = 6 SE +/- 1.45, N = 3 90.31 90.14 92.16 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Basis Universal Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 + RDO Post-Processing 1 2 3 200 400 600 800 1000 SE +/- 1.28, N = 3 SE +/- 2.85, N = 3 SE +/- 12.55, N = 4 945.48 949.41 972.13 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Exhaustive 1 2 3 120 240 360 480 600 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 SE +/- 0.25, N = 3 568.11 567.56 568.09 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
CLOMP CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Speedup, More Is Better CLOMP 1.2 Static OMP Speedup 1 2 3 0.2925 0.585 0.8775 1.17 1.4625 SE +/- 0.05, N = 12 SE +/- 0.05, N = 12 SE +/- 0.03, N = 12 1.3 1.1 1.3 1. (CC) gcc options: -fopenmp -O3 -lm
GROMACS The GROMACS (GROningen MAchine for Chemical Simulations) molecular dynamics package testing on the CPU with the water_GMX50 data. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020.3 Water Benchmark 1 2 3 0.0929 0.1858 0.2787 0.3716 0.4645 SE +/- 0.005, N = 3 SE +/- 0.003, N = 3 SE +/- 0.006, N = 4 0.410 0.413 0.408 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Slow 1 2 3 0.486 0.972 1.458 1.944 2.43 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.16 2.16 2.16 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Medium 1 2 3 0.4995 0.999 1.4985 1.998 2.4975 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 2.21 2.22 2.21 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
Build2 This test profile measures the time to bootstrap/install the build2 C++ build toolchain from source. Build2 is a cross-platform build toolchain for C/C++ code and features Cargo-like features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.13 Time To Compile 1 2 3 60 120 180 240 300 SE +/- 1.13, N = 3 SE +/- 1.16, N = 3 SE +/- 2.21, N = 3 252.46 250.26 254.65
BRL-CAD BRL-CAD 7.28.0 is a cross-platform, open-source solid modeling system with built-in benchmark mode. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.30.8 VGR Performance Metric 1 2 3 10K 20K 30K 40K 50K 48175 48237 48599 1. (CXX) g++ options: -std=c++11 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lGLdispatch -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm
Basis Universal Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 3 1 2 3 30 60 90 120 150 SE +/- 0.14, N = 3 SE +/- 0.28, N = 3 SE +/- 0.06, N = 3 145.88 145.79 145.87 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Asian Dragon Obj 1 2 3 1.1723 2.3446 3.5169 4.6892 5.8615 SE +/- 0.0107, N = 3 SE +/- 0.0125, N = 3 SE +/- 0.0051, N = 3 5.2035 5.2101 5.1860 MIN: 5.16 / MAX: 5.26 MIN: 5.17 / MAX: 5.28 MIN: 5.15 / MAX: 5.26
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Crown 1 2 3 1.0689 2.1378 3.2067 4.2756 5.3445 SE +/- 0.0091, N = 3 SE +/- 0.0037, N = 3 SE +/- 0.0074, N = 3 4.7507 4.7423 4.7225 MIN: 4.71 / MAX: 4.83 MIN: 4.71 / MAX: 4.82 MIN: 4.69 / MAX: 4.82
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer ISPC - Model: Asian Dragon Obj 1 2 3 1.3335 2.667 4.0005 5.334 6.6675 SE +/- 0.0176, N = 3 SE +/- 0.0196, N = 3 SE +/- 0.0272, N = 3 5.8902 5.9266 5.8849 MIN: 5.83 / MAX: 6 MIN: 5.87 / MAX: 6.03 MIN: 5.81 / MAX: 5.99
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer ISPC - Model: Crown 1 2 3 1.2125 2.425 3.6375 4.85 6.0625 SE +/- 0.0366, N = 3 SE +/- 0.0293, N = 3 SE +/- 0.0582, N = 3 5.3888 5.3469 5.3392 MIN: 5.28 / MAX: 5.51 MIN: 5.26 / MAX: 5.47 MIN: 5.19 / MAX: 5.51
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m 1 2 3 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.68, N = 3 SE +/- 0.05, N = 3 16.57 17.41 16.59 MIN: 16.28 / MAX: 16.95 MIN: 16.52 / MAX: 269.38 MIN: 16.38 / MAX: 20.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd 1 2 3 8 16 24 32 40 SE +/- 0.38, N = 3 SE +/- 0.27, N = 3 SE +/- 0.14, N = 3 33.77 34.18 34.18 MIN: 32.69 / MAX: 43.46 MIN: 32.78 / MAX: 44.2 MIN: 33.24 / MAX: 46.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny 1 2 3 10 20 30 40 50 SE +/- 0.68, N = 3 SE +/- 0.74, N = 3 SE +/- 0.15, N = 3 46.17 45.80 44.16 MIN: 44.33 / MAX: 61 MIN: 43.83 / MAX: 58.33 MIN: 43.39 / MAX: 57.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet50 1 2 3 14 28 42 56 70 SE +/- 0.54, N = 3 SE +/- 8.74, N = 3 SE +/- 0.55, N = 3 51.24 60.76 52.10 MIN: 50.5 / MAX: 66.36 MIN: 51.25 / MAX: 1056.17 MIN: 50.52 / MAX: 64.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: alexnet 1 2 3 5 10 15 20 25 SE +/- 0.13, N = 3 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 22.14 22.41 22.28 MIN: 21.81 / MAX: 24.68 MIN: 21.96 / MAX: 34.32 MIN: 21.96 / MAX: 22.64 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet18 1 2 3 6 12 18 24 30 SE +/- 0.29, N = 3 SE +/- 0.19, N = 3 SE +/- 0.32, N = 3 25.79 25.81 25.77 MIN: 24.99 / MAX: 28.18 MIN: 25.13 / MAX: 40.98 MIN: 25 / MAX: 26.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: vgg16 1 2 3 20 40 60 80 100 SE +/- 0.26, N = 3 SE +/- 0.32, N = 3 SE +/- 0.21, N = 3 109.45 109.70 109.11 MIN: 108.54 / MAX: 123.94 MIN: 108.72 / MAX: 136.67 MIN: 108.06 / MAX: 125.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: googlenet 1 2 3 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 23.63 23.53 23.97 MIN: 23.33 / MAX: 36.77 MIN: 23.31 / MAX: 26.84 MIN: 23.72 / MAX: 36.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: blazeface 1 2 3 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 5.13, N = 3 SE +/- 0.03, N = 3 2.58 7.67 2.61 MIN: 2.47 / MAX: 2.74 MIN: 2.41 / MAX: 416.67 MIN: 2.53 / MAX: 2.69 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 1 2 3 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 11.33 11.71 11.56 MIN: 11.18 / MAX: 14.87 MIN: 11.47 / MAX: 14.37 MIN: 11.28 / MAX: 25.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mnasnet 1 2 3 2 4 6 8 10 SE +/- 0.06, N = 3 SE +/- 0.09, N = 3 SE +/- 0.10, N = 3 6.80 6.96 6.81 MIN: 6.62 / MAX: 10.18 MIN: 6.68 / MAX: 21.89 MIN: 6.53 / MAX: 7.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 1 2 3 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 9.52 9.45 9.49 MIN: 9.42 / MAX: 11.19 MIN: 9.35 / MAX: 12.21 MIN: 9.39 / MAX: 11.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 1 2 3 2 4 6 8 10 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 7.05 7.14 7.06 MIN: 6.84 / MAX: 8.55 MIN: 6.95 / MAX: 21.34 MIN: 6.87 / MAX: 10.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 1 2 3 3 6 9 12 15 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 8.35 9.10 8.59 MIN: 7.99 / MAX: 21.73 MIN: 8.89 / MAX: 12.03 MIN: 8.33 / MAX: 13.54 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mobilenet 1 2 3 7 14 21 28 35 SE +/- 0.06, N = 3 SE +/- 0.24, N = 3 SE +/- 0.09, N = 3 31.35 31.76 31.53 MIN: 31.01 / MAX: 43.41 MIN: 31.13 / MAX: 48.02 MIN: 31.22 / MAX: 33.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Embree Intel Embree is a collection of high-performance ray-tracing kernels for execution on CPUs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.9.0 Binary: Pathtracer - Model: Asian Dragon 1 2 3 1.2631 2.5262 3.7893 5.0524 6.3155 SE +/- 0.0040, N = 3 SE +/- 0.0161, N = 3 SE +/- 0.0036, N = 3 5.5806 5.6139 5.5696 MIN: 5.53 / MAX: 5.66 MIN: 5.54 / MAX: 5.72 MIN: 5.5 / MAX: 5.65
NCNN NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m 1 2 3 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.12, N = 3 16.39 16.58 16.45 MIN: 16.23 / MAX: 18.48 MIN: 16.23 / MAX: 31.03 MIN: 16.16 / MAX: 17.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd 1 2 3 8 16 24 32 40 SE +/- 0.07, N = 3 SE +/- 0.57, N = 3 SE +/- 0.27, N = 3 33.22 34.57 33.46 MIN: 32.95 / MAX: 34.34 MIN: 33.72 / MAX: 36.89 MIN: 32.94 / MAX: 43.71 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny 1 2 3 10 20 30 40 50 SE +/- 0.72, N = 3 SE +/- 0.29, N = 3 SE +/- 0.38, N = 3 44.08 44.90 44.45 MIN: 42.69 / MAX: 58.93 MIN: 44.01 / MAX: 52.5 MIN: 43.34 / MAX: 46.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 1 2 3 12 24 36 48 60 SE +/- 0.10, N = 3 SE +/- 0.27, N = 3 SE +/- 0.47, N = 3 50.69 51.56 51.48 MIN: 50.36 / MAX: 63.24 MIN: 50.54 / MAX: 64.38 MIN: 50.22 / MAX: 66.07 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet 1 2 3 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 22.24 22.43 22.25 MIN: 21.89 / MAX: 24.72 MIN: 21.97 / MAX: 35.74 MIN: 22 / MAX: 36.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 1 2 3 6 12 18 24 30 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 SE +/- 0.08, N = 3 25.78 26.11 25.78 MIN: 25.38 / MAX: 39.91 MIN: 25.75 / MAX: 41.28 MIN: 25.3 / MAX: 26.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 1 2 3 20 40 60 80 100 SE +/- 0.57, N = 3 SE +/- 0.82, N = 3 SE +/- 0.12, N = 3 109.27 110.79 108.96 MIN: 108.04 / MAX: 121.43 MIN: 109.24 / MAX: 127.6 MIN: 108.21 / MAX: 115.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet 1 2 3 6 12 18 24 30 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 23.93 24.27 23.85 MIN: 23.66 / MAX: 24.5 MIN: 23.92 / MAX: 27 MIN: 23.58 / MAX: 37.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface 1 2 3 0.594 1.188 1.782 2.376 2.97 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 2.57 2.64 2.55 MIN: 2.37 / MAX: 2.66 MIN: 2.6 / MAX: 2.69 MIN: 2.49 / MAX: 2.61 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 1 2 3 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.13, N = 3 11.28 11.80 11.60 MIN: 10.83 / MAX: 19.59 MIN: 11.52 / MAX: 12.14 MIN: 11.37 / MAX: 26.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet 1 2 3 2 4 6 8 10 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 6.83 7.04 6.84 MIN: 6.61 / MAX: 7.1 MIN: 6.85 / MAX: 9.1 MIN: 6.59 / MAX: 10.33 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 1 2 3 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 9.47 9.45 9.48 MIN: 9.36 / MAX: 12.12 MIN: 9.32 / MAX: 12.68 MIN: 9.35 / MAX: 13.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 1 2 3 2 4 6 8 10 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 6.91 7.09 7.10 MIN: 6.69 / MAX: 12.06 MIN: 6.9 / MAX: 10.15 MIN: 6.88 / MAX: 9.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 1 2 3 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 8.25 9.03 8.54 MIN: 8.02 / MAX: 11.6 MIN: 8.75 / MAX: 11.63 MIN: 8.16 / MAX: 12.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet 1 2 3 7 14 21 28 35 SE +/- 0.26, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 31.47 32.22 31.64 MIN: 30.7 / MAX: 45.93 MIN: 31.89 / MAX: 45.17 MIN: 31.25 / MAX: 55.14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 1 2 3 2K 4K 6K 8K 10K SE +/- 6.10, N = 3 SE +/- 7.59, N = 3 SE +/- 25.14, N = 3 8480.05 8426.98 8475.51 MIN: 8460.68 MIN: 8406.64 MIN: 8432.62 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 1 2 3 2K 4K 6K 8K 10K SE +/- 11.29, N = 3 SE +/- 13.64, N = 3 SE +/- 20.61, N = 3 8489.11 8413.38 8482.73 MIN: 8460.3 MIN: 8383.33 MIN: 8441.98 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 1 2 3 2K 4K 6K 8K 10K SE +/- 17.63, N = 3 SE +/- 20.81, N = 3 SE +/- 15.35, N = 3 8495.75 8410.76 8446.75 MIN: 8463.89 MIN: 8366.44 MIN: 8413.69 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Very Fast 1 2 3 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 6.06 6.07 6.07 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 4K 1 2 3 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 6.55 6.59 6.56 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 1 2 3 1000 2000 3000 4000 5000 SE +/- 15.27, N = 3 SE +/- 16.47, N = 3 SE +/- 24.18, N = 3 4741.15 4713.76 4758.63 MIN: 4705.91 MIN: 4686.24 MIN: 4700.29 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 1 2 3 1000 2000 3000 4000 5000 SE +/- 22.26, N = 3 SE +/- 5.23, N = 3 SE +/- 19.23, N = 3 4741.20 4714.60 4729.75 MIN: 4710.31 MIN: 4700.85 MIN: 4687.53 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 1 2 3 1000 2000 3000 4000 5000 SE +/- 0.95, N = 3 SE +/- 15.09, N = 3 SE +/- 3.10, N = 3 4730.40 4693.24 4743.29 MIN: 4721.36 MIN: 4657.74 MIN: 4730.58 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Stockfish This is a test of Stockfish, an advanced C++11 chess benchmark that can scale up to 128 CPU cores. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 12 Total Time 1 2 3 2M 4M 6M 8M 10M SE +/- 42720.90, N = 3 SE +/- 53934.69, N = 3 SE +/- 100608.19, N = 3 7990112 7986287 7918799 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++17 -pedantic -O3 -msse -msse3 -mpopcnt -msse4.1 -mssse3 -msse2 -flto -flto=jobserver
Node.js V8 Web Tooling Benchmark Running the V8 project's Web-Tooling-Benchmark under Node.js. The Web-Tooling-Benchmark stresses JavaScript-related workloads common to web developers like Babel and TypeScript and Babylon. This test profile can test the system's JavaScript performance with Node.js. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org runs/s, More Is Better Node.js V8 Web Tooling Benchmark 1 2 3 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 11.06 11.27 11.22 1. Nodejs
v10.15.2
Basis Universal Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 2 1 2 3 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.08, N = 3 SE +/- 0.22, N = 3 74.39 74.25 74.44 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Thorough 1 2 3 15 30 45 60 75 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 69.57 69.61 69.61 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Basis Universal Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: ETC1S 1 2 3 16 32 48 64 80 SE +/- 0.54, N = 3 SE +/- 0.68, N = 3 SE +/- 0.38, N = 3 73.39 72.62 73.28 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: Kostya 1 2 3 0.153 0.306 0.459 0.612 0.765 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.68 0.68 0.68 1. (CXX) g++ options: -O3 -pthread
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Slow 1 2 3 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 9.46 9.46 9.45 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.4 Acceleration: CPU - Scene: Supercar 1 2 3 0.3805 0.761 1.1415 1.522 1.9025 SE +/- 0.005, N = 3 SE +/- 0.002, N = 3 SE +/- 0.002, N = 3 1.684 1.687 1.691
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Medium 1 2 3 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 9.73 9.75 9.73 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
DDraceNetwork OpenBenchmarking.org Milliseconds, Fewer Is Better DDraceNetwork 15.2.3 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore2 - Total Frame Time 1 2 3 7 14 21 28 35 Min: 3.55 / Avg: 22.02 / Max: 28.05 Min: 5.55 / Avg: 22.02 / Max: 28.23 Min: 4.01 / Avg: 22.02 / Max: 31.07 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 15.2.3 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore2 1 2 3 10 20 30 40 50 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 45.46 45.40 45.44 MIN: 25.16 / MAX: 257.86 MIN: 33.02 / MAX: 50.63 MIN: 25.99 / MAX: 180.9 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.org Milliseconds, Fewer Is Better DDraceNetwork 15.2.3 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap - Total Frame Time 1 2 3 5 10 15 20 25 Min: 4.45 / Avg: 9.95 / Max: 18.41 Min: 4.4 / Avg: 9.98 / Max: 16.99 Min: 4.46 / Avg: 9.94 / Max: 17 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 15.2.3 Resolution: 1920 x 1080 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap 1 2 3 20 40 60 80 100 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 101.15 100.65 100.85 MIN: 54.32 / MAX: 224.92 MIN: 58.03 / MAX: 227.27 MIN: 37.89 / MAX: 224.47 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.org Milliseconds, Fewer Is Better DDraceNetwork 15.2.3 Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap - Total Frame Time 1 2 3 13 26 39 52 65 Min: 6.24 / Avg: 33.97 / Max: 65.29 Min: 5.76 / Avg: 33.96 / Max: 57.53 Min: 5.77 / Avg: 34.02 / Max: 65.99 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 15.2.3 Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: Multeasymap 1 2 3 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 29.58 29.60 29.53 MIN: 14.88 / MAX: 175.93 MIN: 14.76 / MAX: 161.92 MIN: 15.15 / MAX: 181.72 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
Min Avg Max 1 72.3 76.8 85.1 2 71.6 76.6 84.9 3 72.0 76.7 82.4 OpenBenchmarking.org Milliseconds, Fewer Is Better DDraceNetwork 15.2.3 Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore2 - Total Frame Time 20 40 60 80 100 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.org Frames Per Second, More Is Better DDraceNetwork 15.2.3 Resolution: 3840 x 2160 - Mode: Fullscreen - Renderer: OpenGL 3.3 - Zoom: Default - Demo: RaiNyMore2 1 2 3 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 13.03 13.05 13.03 MIN: 11.75 / MAX: 13.98 MIN: 10.32 / MAX: 14.01 MIN: 11.77 / MAX: 14.01 1. (CXX) g++ options: -O3 -rdynamic -lcrypto -lz -lrt -lpthread -lcurl -lfreetype -lSDL2 -lwavpack -lopusfile -lopus -logg -lGL -lX11 -lnotify -lgdk_pixbuf-2.0 -lgio-2.0 -lgobject-2.0 -lglib-2.0
OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 9 - Compression Speed 1 2 3 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.85, N = 3 51.28 51.28 50.11 1. (CC) gcc options: -O3
OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Decompression Speed 1 2 3 1400 2800 4200 5600 7000 SE +/- 1.59, N = 3 SE +/- 1.58, N = 3 SE +/- 1.37, N = 3 6530.1 6527.5 6523.6 1. (CC) gcc options: -O3
OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 3 - Compression Speed 1 2 3 12 24 36 48 60 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 SE +/- 0.23, N = 3 52.25 52.40 51.92 1. (CC) gcc options: -O3
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: DistinctUserID 1 2 3 0.1733 0.3466 0.5199 0.6932 0.8665 SE +/- 0.01, N = 3 SE +/- 0.01, N = 4 SE +/- 0.01, N = 3 0.77 0.74 0.74 1. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: LargeRandom 1 2 3 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
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 4K - Video Preset: Ultra Fast 1 2 3 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 10.98 10.96 11.00 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
simdjson This is a benchmark of SIMDJSON, a high performance JSON parser. SIMDJSON aims to be the fastest JSON parser and is used by projects like Microsoft FishStore, Yandex ClickHouse, Shopify, and others. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better simdjson 0.7.1 Throughput Test: PartialTweets 1 2 3 0.1643 0.3286 0.4929 0.6572 0.8215 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 0.73 0.71 0.73 1. (CXX) g++ options: -O3 -pthread
Waifu2x-NCNN Vulkan Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: No 1 2 3 6 12 18 24 30 SE +/- 1.00, N = 12 SE +/- 0.11, N = 3 SE +/- 0.06, N = 3 24.78 25.94 25.93
Libplacebo Libplacebo is a multimedia rendering library based on the core rendering code of the MPV player. The libplacebo benchmark relies on the Vulkan API and tests various primitives. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better Libplacebo 2.72.2 Test: av1_grain_lap 1 2 3 150 300 450 600 750 SE +/- 0.24, N = 3 SE +/- 0.36, N = 3 SE +/- 0.22, N = 3 711.86 711.51 711.76 1. (CXX) g++ options: -lm -lglslang -lHLSL -lOGLCompiler -lOSDependent -lSPIRV -lSPVRemapper -lpthread -pthread -pipe -std=c++11 -fvisibility=hidden -fPIC -MD -MQ -MF
OpenBenchmarking.org FPS, More Is Better Libplacebo 2.72.2 Test: hdr_peakdetect 1 2 3 11K 22K 33K 44K 55K SE +/- 736.78, N = 3 SE +/- 90.21, N = 3 SE +/- 107.39, N = 3 48607.60 49578.62 49012.32 1. (CXX) g++ options: -lm -lglslang -lHLSL -lOGLCompiler -lOSDependent -lSPIRV -lSPVRemapper -lpthread -pthread -pipe -std=c++11 -fvisibility=hidden -fPIC -MD -MQ -MF
OpenBenchmarking.org FPS, More Is Better Libplacebo 2.72.2 Test: polar_nocompute 1 2 3 3K 6K 9K 12K 15K SE +/- 29.01, N = 3 SE +/- 37.92, N = 3 SE +/- 44.87, N = 3 13186.91 13223.20 13109.55 1. (CXX) g++ options: -lm -lglslang -lHLSL -lOGLCompiler -lOSDependent -lSPIRV -lSPVRemapper -lpthread -pthread -pipe -std=c++11 -fvisibility=hidden -fPIC -MD -MQ -MF
OpenBenchmarking.org FPS, More Is Better Libplacebo 2.72.2 Test: deband_heavy 1 2 3 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.09, N = 3 18.95 18.95 19.04 1. (CXX) g++ options: -lm -lglslang -lHLSL -lOGLCompiler -lOSDependent -lSPIRV -lSPVRemapper -lpthread -pthread -pipe -std=c++11 -fvisibility=hidden -fPIC -MD -MQ -MF
OpenBenchmarking.org MB/s, More Is Better LZ4 Compression 1.9.3 Compression Level: 1 - Compression Speed 1 2 3 1200 2400 3600 4800 6000 SE +/- 7.62, N = 3 SE +/- 5.97, N = 3 SE +/- 2.69, N = 3 5671.51 5687.38 5697.27 1. (CC) gcc options: -O3
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 1 2 3 2 4 6 8 10 SE +/- 0.00679, N = 3 SE +/- 0.09722, N = 3 SE +/- 0.11002, N = 15 6.86508 6.94358 8.22358 MIN: 6.69 MIN: 6.67 MIN: 7.36 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
PHPBench PHPBench is a benchmark suite for PHP. It performs a large number of simple tests in order to bench various aspects of the PHP interpreter. PHPBench can be used to compare hardware, operating systems, PHP versions, PHP accelerators and caches, compiler options, etc. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite 1 2 3 150K 300K 450K 600K 750K SE +/- 448.34, N = 3 SE +/- 2148.66, N = 3 SE +/- 709.37, N = 3 710293 709965 709282
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Very Fast 1 2 3 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 24.57 24.56 24.60 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
yquake2 This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: Software CPU - Resolution: 3840 x 2160 1 2 3 7 14 21 28 35 SE +/- 0.09, N = 3 SE +/- 0.24, N = 3 SE +/- 0.03, N = 3 27.8 28.0 28.5 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
Waifu2x-NCNN Vulkan Waifu2x-NCNN is an NCNN neural network implementation of the Waifu2x converter project and accelerated using the Vulkan API. NCNN is a high performance neural network inference framework optimized for mobile and other platforms developed by Tencent. This test profile times how long it takes to increase the resolution of a sample image with Vulkan. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Waifu2x-NCNN Vulkan 20200818 Scale: 2x - Denoise: 3 - TAA: Yes 1 2 3 2 4 6 8 10 SE +/- 0.059, N = 12 SE +/- 0.096, N = 4 SE +/- 0.085, N = 15 6.950 6.535 6.824
Sunflow Rendering System This test runs benchmarks of the Sunflow Rendering System. The Sunflow Rendering System is an open-source render engine for photo-realistic image synthesis with a ray-tracing core. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Sunflow Rendering System 0.07.2 Global Illumination + Image Synthesis 1 2 3 0.524 1.048 1.572 2.096 2.62 SE +/- 0.012, N = 3 SE +/- 0.019, N = 3 SE +/- 0.024, N = 3 2.280 2.293 2.329 MIN: 2.17 / MAX: 2.91 MIN: 2.17 / MAX: 2.99 MIN: 2.21 / MAX: 3.04
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 1 2 3 1.1917 2.3834 3.5751 4.7668 5.9585 SE +/- 0.00331, N = 3 SE +/- 0.00978, N = 3 SE +/- 0.09775, N = 15 4.25914 4.16433 5.29626 MIN: 4.15 MIN: 4.05 MIN: 4.25 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 1 2 3 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.13, N = 3 SE +/- 0.15, N = 15 14.25 15.07 15.42 MIN: 14.13 MIN: 14.72 MIN: 14.53 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.20, N = 3 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 12.39 12.60 12.10 MIN: 11.1 MIN: 11.17 MIN: 10.95 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.11, N = 3 10.75 10.72 10.78 MIN: 10.34 MIN: 9.95 MIN: 10.43 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
x265 This is a simple test of the x265 encoder run on the CPU with 1080p and 4K options for H.265 video encode performance with x265. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.4 Video Input: Bosphorus 1080p 1 2 3 7 14 21 28 35 SE +/- 0.08, N = 3 SE +/- 0.14, N = 3 SE +/- 0.07, N = 3 29.94 30.16 29.89 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.03949, N = 3 SE +/- 0.14569, N = 3 SE +/- 0.04734, N = 3 9.14529 9.09658 9.18743 MIN: 8.74 MIN: 8.69 MIN: 8.82 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 1 2 3 1.1744 2.3488 3.5232 4.6976 5.872 SE +/- 0.00525, N = 3 SE +/- 0.00946, N = 3 SE +/- 0.01621, N = 3 5.21940 5.17862 5.18374 MIN: 4.85 MIN: 4.94 MIN: 4.84 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Medium 1 2 3 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 10.39 10.39 10.39 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
Kvazaar This is a test of Kvazaar as a CPU-based H.265 video encoder written in the C programming language and optimized in Assembly. Kvazaar is the winner of the 2016 ACM Open-Source Software Competition and developed at the Ultra Video Group, Tampere University, Finland. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better Kvazaar 2.0 Video Input: Bosphorus 1080p - Video Preset: Ultra Fast 1 2 3 10 20 30 40 50 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 43.43 43.68 43.61 1. (CC) gcc options: -pthread -ftree-vectorize -fvisibility=hidden -O2 -lpthread -lm -lrt
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 1 2 3 2 4 6 8 10 SE +/- 0.01016, N = 3 SE +/- 0.01547, N = 3 SE +/- 0.06654, N = 3 6.16771 6.06418 6.08402 MIN: 5.88 MIN: 5.69 MIN: 5.81 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
yquake2 This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 3.x - Resolution: 3840 x 2160 1 2 3 14 28 42 56 70 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 62.8 62.6 62.7 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
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: Software CPU - Resolution: 2560 x 1440 1 2 3 14 28 42 56 70 SE +/- 0.31, N = 3 SE +/- 0.43, N = 3 SE +/- 0.19, N = 3 60.3 59.7 60.8 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
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 1.x - Resolution: 3840 x 2160 1 2 3 15 30 45 60 75 SE +/- 0.09, N = 3 SE +/- 0.22, N = 3 SE +/- 0.06, N = 3 67.1 67.2 67.0 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
Basis Universal Basis Universal is a GPU texture codoec. This test times how long it takes to convert sRGB PNGs into Basis Univeral assets with various settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.12 Settings: UASTC Level 0 1 2 3 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.16, N = 3 SE +/- 0.02, N = 3 10.58 10.72 10.50 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
ASTC Encoder ASTC Encoder (astcenc) is for the Adaptive Scalable Texture Compression (ASTC) format commonly used with OpenGL, OpenGL ES, and Vulkan graphics APIs. This test profile does a coding test of both compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.0 Preset: Fast 1 2 3 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 7.65 7.70 7.70 1. (CXX) g++ options: -std=c++14 -fvisibility=hidden -O3 -flto -mfpmath=sse -mavx2 -mpopcnt -lpthread
yquake2 This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: Software CPU - Resolution: 1920 x 1080 1 2 3 20 40 60 80 100 SE +/- 0.87, N = 3 SE +/- 0.98, N = 3 SE +/- 0.38, N = 3 98.0 97.6 97.8 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 OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 1 2 3 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.09, N = 3 26.07 26.14 25.74 MIN: 25.78 MIN: 25.95 MIN: 25.45 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 1 2 3 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.16, N = 3 26.42 26.92 27.06 MIN: 26.19 MIN: 26.51 MIN: 26.33 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
yquake2 This is a test of Yamagi Quake II. Yamagi Quake II is an enhanced client for id Software's Quake II with focus on offline and coop gameplay. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 3.x - Resolution: 2560 x 1440 1 2 3 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 SE +/- 0.17, N = 3 125.9 125.8 125.9 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
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 1.x - Resolution: 2560 x 1440 1 2 3 30 60 90 120 150 SE +/- 0.37, N = 3 SE +/- 0.55, N = 3 SE +/- 0.12, N = 3 130.4 129.8 131.0 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
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 3.x - Resolution: 1920 x 1080 1 2 3 40 80 120 160 200 SE +/- 0.53, N = 3 SE +/- 0.23, N = 3 SE +/- 0.95, N = 3 200.9 200.1 200.5 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
OpenBenchmarking.org Frames Per Second, More Is Better yquake2 7.45 Renderer: OpenGL 1.x - Resolution: 1920 x 1080 1 2 3 50 100 150 200 250 SE +/- 0.42, N = 3 SE +/- 0.55, N = 3 SE +/- 0.32, N = 3 206.8 208.2 207.6 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
oneDNN OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 1 2 3 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 11.33 11.29 11.16 MIN: 10.76 MIN: 10.69 MIN: 10.46 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 1 2 3 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.26, N = 3 SE +/- 0.12, N = 3 16.54 17.53 16.63 MIN: 16.27 MIN: 16.55 MIN: 16.28 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
HPC Challenge HPC Challenge (HPCC) is a cluster-focused benchmark consisting of the HPL Linpack TPP benchmark, DGEMM, STREAM, PTRANS, RandomAccess, FFT, and communication bandwidth and latency. This HPC Challenge test profile attempts to ship with standard yet versatile configuration/input files though they can be modified. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Max Ping Pong Bandwidth 1 2 3 4K 8K 12K 16K 20K SE +/- 146.25, N = 3 SE +/- 639.68, N = 3 SE +/- 289.88, N = 3 19281.57 19517.86 18703.03 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth 1 2 3 0.7636 1.5272 2.2908 3.0544 3.818 SE +/- 0.09620, N = 3 SE +/- 0.10194, N = 3 SE +/- 0.24447, N = 3 3.39365 2.82967 3.21355 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency 1 2 3 0.0736 0.1472 0.2208 0.2944 0.368 SE +/- 0.04635, N = 3 SE +/- 0.00582, N = 3 SE +/- 0.04588, N = 3 0.27879 0.32700 0.27847 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access 1 2 3 0.0061 0.0122 0.0183 0.0244 0.0305 SE +/- 0.00052, N = 3 SE +/- 0.00077, N = 3 SE +/- 0.00050, N = 3 0.02650 0.02625 0.02713 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad 1 2 3 0.9136 1.8272 2.7408 3.6544 4.568 SE +/- 0.01197, N = 3 SE +/- 0.00333, N = 3 SE +/- 0.01163, N = 3 4.03790 4.04885 4.06038 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans 1 2 3 0.1114 0.2228 0.3342 0.4456 0.557 SE +/- 0.01258, N = 3 SE +/- 0.03821, N = 3 SE +/- 0.01039, N = 3 0.49398 0.49518 0.47980 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM 1 2 3 10 20 30 40 50 SE +/- 0.53, N = 3 SE +/- 0.10, N = 3 SE +/- 0.66, N = 3 43.79 42.54 44.68 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte 1 2 3 0.4647 0.9294 1.3941 1.8588 2.3235 SE +/- 0.08108, N = 3 SE +/- 0.13431, N = 3 SE +/- 0.07276, N = 3 2.06526 1.95684 1.89310 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
1 Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-offload-targets=nvptx-none,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 -vProcessor Notes: Scaling Governor: intel_cpufreq ondemand - CPU Microcode: 0x28 - Thermald 1.9Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
Testing initiated at 19 December 2020 10:12 by user phoronix.
2 Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-offload-targets=nvptx-none,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 -vProcessor Notes: Scaling Governor: intel_cpufreq ondemand - CPU Microcode: 0x28 - Thermald 1.9Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
Testing initiated at 19 December 2020 21:01 by user phoronix.
3 Processor: Intel Core i7-4790K @ 4.40GHz (4 Cores / 8 Threads), Motherboard: Gigabyte Z97-HD3P (F4 BIOS), Chipset: Intel 4th Gen Core DRAM, Memory: 16GB, Disk: 120GB OCZ TRION100, Graphics: Gigabyte Intel Haswell Desktop 2GB (1250MHz), Audio: Intel Xeon E3-1200 v3/4th, Monitor: LG Ultra HD, Network: Realtek RTL8111/8168/8411
OS: Ubuntu 19.10, Kernel: 5.9.0-050900rc8daily20201009-generic (x86_64) 20201008, Desktop: GNOME Shell 3.34.1, Display Server: X Server 1.20.5, Display Driver: modesetting 1.20.5, OpenGL: 4.5 Mesa 19.2.8, Vulkan: 1.1.102, Compiler: GCC 9.2.1 20191008, File-System: ext4, Screen Resolution: 3840x2160
Compiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-offload-targets=nvptx-none,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 -vProcessor Notes: Scaling Governor: intel_cpufreq ondemand - CPU Microcode: 0x28 - Thermald 1.9Java Notes: OpenJDK Runtime Environment (build 11.0.7+10-post-Ubuntu-2ubuntu219.10)Python Notes: Python 2.7.17 + Python 3.7.5Security Notes: itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Mitigation of PTE Inversion; VMX: conditional cache flushes SMT vulnerable + mds: Mitigation of Clear buffers; SMT vulnerable + meltdown: Mitigation of PTI + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full generic retpoline IBPB: conditional IBRS_FW STIBP: conditional RSB filling + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
Testing initiated at 20 December 2020 09:00 by user phoronix.