Intel Core i9-9900KS testing with a ASUS PRIME Z390-A (1502 BIOS) and ASUS Intel UHD 630 CFL GT2 3GB on Ubuntu 20.04 via the Phoronix Test Suite.
1 Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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,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_pstate powersave - CPU Microcode: 0xcc - Thermald 1.9.1Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of VMX unsupported + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled
2 3 Processor: Intel Core i9-9900KS @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (1502 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 32GB, Disk: 240GB Corsair Force MP510, Graphics: ASUS Intel UHD 630 CFL GT2 3GB (1200MHz), Audio: Realtek ALC1220, Monitor: G237HL, Network: Intel I219-V
OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc8daily20201005-generic (x86_64) 20201004, Desktop: GNOME Shell 3.36.2, Display Server: X Server 1.20.8, OpenGL: 4.6 Mesa 20.2.6, OpenCL: OpenCL 2.1, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Botan Botan is a BSD-licensed cross-platform open-source C++ crypto library "cryptography toolkit" that supports most publicly known cryptographic algorithms. The project's stated goal is to be "the best option for cryptography in C++ by offering the tools necessary to implement a range of practical systems, such as TLS protocol, X.509 certificates, modern AEAD ciphers, PKCS#11 and TPM hardware support, password hashing, and post quantum crypto schemes." Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI 3 2 1 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 112.99 112.94 112.98 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: KASUMI - Decrypt 3 2 1 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 107.88 107.76 107.86 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 3 2 1 1000 2000 3000 4000 5000 SE +/- 0.22, N = 3 SE +/- 0.54, N = 3 SE +/- 0.17, N = 3 4815.62 4814.83 4815.97 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: AES-256 - Decrypt 3 2 1 1000 2000 3000 4000 5000 SE +/- 0.04, N = 3 SE +/- 0.85, N = 3 SE +/- 4.51, N = 3 4812.42 4811.18 4806.10 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish 3 2 1 90 180 270 360 450 SE +/- 1.83, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 434.66 436.12 436.08 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Twofish - Decrypt 3 2 1 90 180 270 360 450 SE +/- 0.95, N = 3 SE +/- 0.15, N = 3 SE +/- 0.18, N = 3 436.74 437.29 437.30 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish 3 2 1 120 240 360 480 600 SE +/- 0.10, N = 3 SE +/- 0.40, N = 3 SE +/- 0.05, N = 3 543.95 543.39 543.60 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: Blowfish - Decrypt 3 2 1 120 240 360 480 600 SE +/- 0.03, N = 3 SE +/- 0.37, N = 3 SE +/- 0.04, N = 3 539.34 539.02 539.24 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: CAST-256 3 2 1 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 171.96 171.95 171.95 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: CAST-256 - Decrypt 3 2 1 40 80 120 160 200 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 172.15 172.08 172.09 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 3 2 1 200 400 600 800 1000 SE +/- 1.80, N = 3 SE +/- 3.02, N = 3 SE +/- 0.12, N = 3 914.45 913.03 916.11 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenBenchmarking.org MiB/s, More Is Better Botan 2.17.3 Test: ChaCha20Poly1305 - Decrypt 3 2 1 200 400 600 800 1000 SE +/- 0.54, N = 3 SE +/- 0.82, N = 3 SE +/- 0.56, N = 3 908.47 907.95 908.31 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
OpenSCAD OpenSCAD is a programmer-focused solid 3D CAD modeller. OpenSCAD is free software and allows creating 3D CAD objects in a script-based modelling environment. This test profile will use the system-provided OpenSCAD program otherwise and time how long it takes tn render different SCAD assets to PNG output. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Pistol 3 2 1 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.21, N = 3 SE +/- 0.07, N = 3 100.81 100.98 100.77 1. OpenSCAD version 2019.05
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Retro Car 3 2 1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 17.37 17.35 17.26 1. OpenSCAD version 2019.05
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Mini-ITX Case 3 2 1 10 20 30 40 50 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 0.07, N = 3 42.08 42.05 41.91 1. OpenSCAD version 2019.05
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Projector Mount Swivel 3 2 1 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.42, N = 3 SE +/- 0.21, N = 3 94.97 93.91 92.93 1. OpenSCAD version 2019.05
OpenBenchmarking.org Seconds, Fewer Is Better OpenSCAD Render: Leonardo Phone Case Slim 3 2 1 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 17.05 16.94 16.98 1. OpenSCAD version 2019.05
Basis Universal Basis Universal is a GPU texture codec. 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 1.13 Settings: ETC1S 3 2 1 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 SE +/- 0.03, N = 3 23.37 23.39 23.46 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 0 3 2 1 2 4 6 8 10 SE +/- 0.005, N = 3 SE +/- 0.003, N = 3 SE +/- 0.000, N = 3 7.089 7.091 7.172 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
OpenBenchmarking.org Seconds, Fewer Is Better Basis Universal 1.13 Settings: UASTC Level 2 3 2 1 8 16 24 32 40 SE +/- 0.12, N = 3 SE +/- 0.10, N = 3 SE +/- 0.02, N = 3 33.39 33.37 33.46 1. (CXX) g++ options: -std=c++11 -fvisibility=hidden -fPIC -fno-strict-aliasing -O3 -rdynamic -lm -lpthread
Basis Universal Basis Universal is a GPU texture codec. 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 1.13 Settings: UASTC Level 3 3 2 1 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 63.59 63.56 63.54 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 2.4 Preset: Medium 3 2 1 1.3039 2.6078 3.9117 5.2156 6.5195 SE +/- 0.0062, N = 3 SE +/- 0.0051, N = 3 SE +/- 0.0231, N = 3 5.7737 5.7757 5.7949 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.4 Preset: Thorough 3 2 1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 14.91 14.91 14.92 1. (CXX) g++ options: -O3 -flto -pthread
OpenBenchmarking.org Seconds, Fewer Is Better ASTC Encoder 2.4 Preset: Exhaustive 3 2 1 30 60 90 120 150 SE +/- 0.16, N = 3 SE +/- 0.14, N = 3 SE +/- 0.12, N = 3 113.89 113.77 113.89 1. (CXX) g++ options: -O3 -flto -pthread
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: SqueezeNetV1.0 3 2 1 1.1122 2.2244 3.3366 4.4488 5.561 SE +/- 0.027, N = 3 SE +/- 0.030, N = 3 SE +/- 0.029, N = 3 4.943 4.882 4.899 MIN: 4.65 / MAX: 16.5 MIN: 4.68 / MAX: 5.58 MIN: 4.71 / MAX: 7.4 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: resnet-v2-50 3 2 1 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 25.41 25.25 25.31 MIN: 25.17 / MAX: 37.2 MIN: 25.09 / MAX: 35.04 MIN: 25.08 / MAX: 37.21 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: MobileNetV2_224 3 2 1 0.6037 1.2074 1.8111 2.4148 3.0185 SE +/- 0.063, N = 3 SE +/- 0.051, N = 3 SE +/- 0.063, N = 3 2.683 2.655 2.672 MIN: 2.37 / MAX: 4.91 MIN: 2.35 / MAX: 3.81 MIN: 2.34 / MAX: 4.31 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: mobilenet-v1-1.0 3 2 1 0.5279 1.0558 1.5837 2.1116 2.6395 SE +/- 0.010, N = 3 SE +/- 0.006, N = 3 SE +/- 0.007, N = 3 2.346 2.333 2.329 MIN: 2.28 / MAX: 3.63 MIN: 2.27 / MAX: 3.55 MIN: 2.26 / MAX: 4.96 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 1.1.3 Model: inception-v3 3 2 1 7 14 21 28 35 SE +/- 0.16, N = 3 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 29.80 29.67 29.45 MIN: 29.45 / MAX: 42.01 MIN: 29.48 / MAX: 42.09 MIN: 29.17 / MAX: 40.18 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
SHOC Scalable HeterOgeneous Computing The CUDA and OpenCL version of Vetter's Scalable HeterOgeneous Computing benchmark suite. SHOC provides a number of different benchmark programs for evaluating the performance and stability of compute devices. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GFLOPS, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: S3D 3 2 1 5 10 15 20 25 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 20.85 20.85 20.99 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
OpenBenchmarking.org GHash/s, More Is Better SHOC Scalable HeterOgeneous Computing 2020-04-17 Target: OpenCL - Benchmark: MD5 Hash 3 2 1 0.0869 0.1738 0.2607 0.3476 0.4345 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 SE +/- 0.0000, N = 3 0.3860 0.3861 0.3861 1. (CXX) g++ options: -O2 -lSHOCCommonMPI -lSHOCCommonOpenCL -lSHOCCommon -lOpenCL -lrt -pthread -lmpi_cxx -lmpi
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI initiative. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 3 2 1 0.8049 1.6098 2.4147 3.2196 4.0245 SE +/- 0.00251, N = 3 SE +/- 0.00753, N = 3 SE +/- 0.01205, N = 3 3.56577 3.57455 3.57740 MIN: 3.26 MIN: 3.24 MIN: 3.23 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 3 2 1 2 4 6 8 10 SE +/- 0.01559, N = 3 SE +/- 0.00679, N = 3 SE +/- 0.00549, N = 3 8.16788 8.14695 8.26103 MIN: 8.03 MIN: 8 MIN: 8.14 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.3752 0.7504 1.1256 1.5008 1.876 SE +/- 0.00123, N = 3 SE +/- 0.00242, N = 3 SE +/- 0.00165, N = 3 1.66550 1.66579 1.66747 MIN: 1.51 MIN: 1.51 MIN: 1.51 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.4122 0.8244 1.2366 1.6488 2.061 SE +/- 0.00185, N = 3 SE +/- 0.00543, N = 3 SE +/- 0.00346, N = 3 1.82340 1.82910 1.83215 MIN: 1.78 MIN: 1.78 MIN: 1.79 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 3 2 1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 14.29 14.30 14.28 MIN: 14.2 MIN: 14.2 MIN: 14.2 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 3 2 1 2 4 6 8 10 SE +/- 0.00592, N = 3 SE +/- 0.01330, N = 3 SE +/- 0.00652, N = 3 8.87618 8.86501 8.83898 MIN: 4.77 MIN: 4.67 MIN: 4.68 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 3 2 1 2 4 6 8 10 SE +/- 0.00264, N = 3 SE +/- 0.01698, N = 3 SE +/- 0.00984, N = 3 6.61557 6.64659 6.63993 MIN: 5.99 MIN: 6 MIN: 6 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 3 2 1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 14.01 14.00 14.03 MIN: 13.88 MIN: 13.9 MIN: 13.92 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.4826 0.9652 1.4478 1.9304 2.413 SE +/- 0.00152, N = 3 SE +/- 0.00224, N = 3 SE +/- 0.00353, N = 3 2.14452 2.14385 2.14490 MIN: 1.97 MIN: 1.97 MIN: 1.94 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.8948 1.7896 2.6844 3.5792 4.474 SE +/- 0.01771, N = 3 SE +/- 0.01212, N = 3 SE +/- 0.02149, N = 3 3.93216 3.93198 3.97706 MIN: 3.62 MIN: 3.64 MIN: 3.65 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 3 2 1 700 1400 2100 2800 3500 SE +/- 4.35, N = 3 SE +/- 3.80, N = 3 SE +/- 5.97, N = 3 3405.99 3405.32 3408.16 MIN: 3393.27 MIN: 3391.39 MIN: 3391.46 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 3 2 1 400 800 1200 1600 2000 SE +/- 0.20, N = 3 SE +/- 1.72, N = 3 SE +/- 0.88, N = 3 1852.05 1851.14 1852.13 MIN: 1846.88 MIN: 1843.95 MIN: 1846.26 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 3 2 1 700 1400 2100 2800 3500 SE +/- 0.89, N = 3 SE +/- 0.58, N = 3 SE +/- 3.64, N = 3 3413.88 3413.02 3414.52 MIN: 3407.32 MIN: 3406.86 MIN: 3404.15 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 3 2 1 400 800 1200 1600 2000 SE +/- 1.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.58, N = 3 1851.30 1850.82 1852.26 MIN: 1843.57 MIN: 1844.82 MIN: 1846.85 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 3 2 1 0.7097 1.4194 2.1291 2.8388 3.5485 SE +/- 0.00951, N = 3 SE +/- 0.00442, N = 3 SE +/- 0.00701, N = 3 3.14943 3.15157 3.15433 MIN: 3.09 MIN: 3.1 MIN: 3.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 3 2 1 700 1400 2100 2800 3500 SE +/- 0.66, N = 3 SE +/- 26.13, N = 3 SE +/- 2.52, N = 3 3415.35 3445.23 3413.97 MIN: 3409.68 MIN: 3408.23 MIN: 3402.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 3 2 1 400 800 1200 1600 2000 SE +/- 1.53, N = 3 SE +/- 1.24, N = 3 SE +/- 3.26, N = 3 1854.40 1851.22 1854.88 MIN: 1846.77 MIN: 1841.63 MIN: 1847.25 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.1.2 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 3 2 1 0.774 1.548 2.322 3.096 3.87 SE +/- 0.00188, N = 3 SE +/- 0.00274, N = 3 SE +/- 0.00410, N = 3 3.43914 3.43359 3.44003 MIN: 3.18 MIN: 3.17 MIN: 3.15 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Xcompact3d Incompact3d Xcompact3d Incompact3d is a Fortran-MPI based, finite difference high-performance code for solving the incompressible Navier-Stokes equation and as many as you need scalar transport equations. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 129 Cells Per Direction 3 2 1 8 16 24 32 40 SE +/- 0.31, N = 3 SE +/- 0.34, N = 3 SE +/- 0.35, N = 3 34.38 34.44 34.34 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
OpenBenchmarking.org Seconds, Fewer Is Better Xcompact3d Incompact3d 2021-03-11 Input: input.i3d 193 Cells Per Direction 3 2 1 30 60 90 120 150 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 121.74 121.83 121.69 1. (F9X) gfortran options: -cpp -O2 -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
Stockfish This is a test of Stockfish, an advanced open-source C++11 chess benchmark that can scale up to 512 CPU threads. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 13 Total Time 3 2 1 5M 10M 15M 20M 25M SE +/- 377829.22, N = 3 SE +/- 299604.32, N = 3 SE +/- 294389.71, N = 4 23832208 23501591 23777878 1. (CXX) g++ options: -lgcov -m64 -lpthread -fno-exceptions -std=c++17 -fprofile-use -fno-peel-loops -fno-tracer -pedantic -O3 -msse -msse3 -mpopcnt -mavx2 -msse4.1 -mssse3 -msse2 -mbmi2 -flto -flto=jobserver
Zstd Compression This test measures the time needed to compress/decompress a sample file (a FreeBSD disk image - FreeBSD-12.2-RELEASE-amd64-memstick.img) using Zstd compression with options for different compression levels / settings. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3 - Compression Speed 3 2 1 500 1000 1500 2000 2500 SE +/- 12.46, N = 3 SE +/- 16.90, N = 3 SE +/- 12.12, N = 3 2388.4 2374.5 2379.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3 - Decompression Speed 3 2 1 900 1800 2700 3600 4500 SE +/- 1.88, N = 3 SE +/- 19.69, N = 3 SE +/- 4.56, N = 3 4180.3 4164.5 4186.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8 - Compression Speed 3 2 1 70 140 210 280 350 SE +/- 0.88, N = 3 SE +/- 2.23, N = 3 SE +/- 1.66, N = 3 327.5 327.6 332.6 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8 - Decompression Speed 3 2 1 900 1800 2700 3600 4500 SE +/- 5.58, N = 3 SE +/- 5.34, N = 3 SE +/- 11.68, N = 3 4307.7 4308.9 4312.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Compression Speed 3 2 1 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 34.6 34.6 34.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19 - Decompression Speed 3 2 1 900 1800 2700 3600 4500 SE +/- 4.27, N = 3 SE +/- 1.35, N = 3 SE +/- 10.42, N = 3 3981.9 3983.1 3969.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3, Long Mode - Compression Speed 3 2 1 300 600 900 1200 1500 SE +/- 6.67, N = 3 SE +/- 10.72, N = 3 SE +/- 5.14, N = 3 1177.1 1156.9 1164.0 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 3, Long Mode - Decompression Speed 3 2 1 1000 2000 3000 4000 5000 SE +/- 1.29, N = 3 SE +/- 5.89, N = 3 SE +/- 7.93, N = 3 4442.7 4437.7 4433.4 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8, Long Mode - Compression Speed 3 2 1 90 180 270 360 450 SE +/- 2.94, N = 3 SE +/- 2.00, N = 3 SE +/- 4.78, N = 3 387.2 378.4 395.1 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 8, Long Mode - Decompression Speed 3 2 1 1000 2000 3000 4000 5000 SE +/- 22.35, N = 3 SE +/- 1.73, N = 3 SE +/- 2.70, N = 3 4574.8 4601.3 4609.8 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Compression Speed 3 2 1 7 14 21 28 35 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 31.5 31.8 31.9 1. (CC) gcc options: -O3 -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.4.9 Compression Level: 19, Long Mode - Decompression Speed 3 2 1 900 1800 2700 3600 4500 SE +/- 5.83, N = 3 SE +/- 0.96, N = 3 SE +/- 9.00, N = 3 3939.4 3963.9 3957.5 1. (CC) gcc options: -O3 -pthread -lz -llzma
Sysbench This is a benchmark of Sysbench with the built-in CPU and memory sub-tests. Sysbench is a scriptable multi-threaded benchmark tool based on LuaJIT. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/sec, More Is Better Sysbench 1.0.20 Test: RAM / Memory 3 2 1 6K 12K 18K 24K 30K SE +/- 41.95, N = 3 SE +/- 138.44, N = 3 SE +/- 98.12, N = 3 28338.59 28491.74 28391.47 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
OpenBenchmarking.org Events Per Second, More Is Better Sysbench 1.0.20 Test: CPU 3 2 1 4K 8K 12K 16K 20K SE +/- 16.54, N = 3 SE +/- 20.02, N = 3 SE +/- 14.24, N = 3 19367.30 19382.71 19380.34 1. (CC) gcc options: -pthread -O2 -funroll-loops -rdynamic -ldl -laio -lm
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 4K 3 2 1 0.027 0.054 0.081 0.108 0.135 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.12 0.12 0.12 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 4K 3 2 1 0.7695 1.539 2.3085 3.078 3.8475 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 3.39 3.41 3.42 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 4K 3 2 1 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 13.14 13.12 13.16 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 4K 3 2 1 2 4 6 8 10 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 6.30 6.32 6.34 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K 3 2 1 9 18 27 36 45 SE +/- 0.51, N = 4 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 37.12 37.94 38.68 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K 3 2 1 11 22 33 44 55 SE +/- 0.07, N = 3 SE +/- 0.10, N = 3 SE +/- 0.53, N = 15 48.78 48.72 47.78 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 0 Two-Pass - Input: Bosphorus 1080p 3 2 1 0.0855 0.171 0.2565 0.342 0.4275 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 0.38 0.37 0.38 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 4 Two-Pass - Input: Bosphorus 1080p 3 2 1 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 6.75 6.73 6.76 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Realtime - Input: Bosphorus 1080p 3 2 1 6 12 18 24 30 SE +/- 0.22, N = 3 SE +/- 0.29, N = 5 SE +/- 0.24, N = 3 25.07 24.95 25.06 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 6 Two-Pass - Input: Bosphorus 1080p 3 2 1 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.17, N = 3 19.21 19.11 19.68 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 1080p 3 2 1 30 60 90 120 150 SE +/- 1.32, N = 12 SE +/- 1.89, N = 3 SE +/- 0.42, N = 3 121.96 122.64 124.39 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.0 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 1080p 3 2 1 30 60 90 120 150 SE +/- 2.02, N = 4 SE +/- 0.46, N = 3 SE +/- 1.63, N = 6 139.82 140.39 141.48 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
SVT-VP9 This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-VP9 CPU-based multi-threaded video encoder for the VP9 video format with a sample YUV input video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: VMAF Optimized - Input: Bosphorus 1080p 3 2 1 40 80 120 160 200 SE +/- 0.26, N = 3 SE +/- 0.43, N = 3 SE +/- 0.19, N = 3 172.10 172.24 173.31 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p 3 2 1 40 80 120 160 200 SE +/- 0.09, N = 3 SE +/- 0.47, N = 3 SE +/- 0.31, N = 3 175.06 175.27 176.29 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.3 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p 3 2 1 30 60 90 120 150 SE +/- 0.35, N = 3 SE +/- 0.13, N = 3 SE +/- 0.26, N = 3 136.05 136.22 136.76 1. (CC) gcc options: -O3 -fcommon -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
dav1d Dav1d is an open-source, speedy AV1 video decoder. This test profile times how long it takes to decode sample AV1 video content. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Chimera 1080p 3 2 1 160 320 480 640 800 SE +/- 0.90, N = 3 SE +/- 2.01, N = 3 SE +/- 1.00, N = 3 732.83 731.76 733.64 MIN: 537.85 / MAX: 1141.98 MIN: 538.01 / MAX: 1138.02 MIN: 538.11 / MAX: 1144.18 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Summer Nature 4K 3 2 1 40 80 120 160 200 SE +/- 0.19, N = 3 SE +/- 0.13, N = 3 SE +/- 0.14, N = 3 184.16 184.25 185.13 MIN: 173.76 / MAX: 209.16 MIN: 173.91 / MAX: 209.75 MIN: 174.56 / MAX: 210.52 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Summer Nature 1080p 3 2 1 140 280 420 560 700 SE +/- 0.54, N = 3 SE +/- 0.67, N = 3 SE +/- 1.42, N = 3 647.63 649.67 648.26 MIN: 582.84 / MAX: 717.06 MIN: 588.3 / MAX: 717.46 MIN: 589.55 / MAX: 721.08 1. (CC) gcc options: -pthread -lm
OpenBenchmarking.org FPS, More Is Better dav1d 0.8.2 Video Input: Chimera 1080p 10-bit 3 2 1 40 80 120 160 200 SE +/- 1.42, N = 3 SE +/- 1.75, N = 3 SE +/- 0.13, N = 3 163.76 164.40 160.91 MIN: 104.03 / MAX: 384.96 MIN: 103.73 / MAX: 392.07 MIN: 103.41 / MAX: 410.16 1. (CC) gcc options: -pthread -lm
SVT-HEVC This is a test of the Intel Open Visual Cloud Scalable Video Technology SVT-HEVC CPU-based multi-threaded video encoder for the HEVC / H.265 video format with a sample 1080p YUV video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 1 - Input: Bosphorus 1080p 3 2 1 2 4 6 8 10 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 6.84 6.84 6.85 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 7 - Input: Bosphorus 1080p 3 2 1 20 40 60 80 100 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 105.78 105.90 106.19 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 1080p 3 2 1 50 100 150 200 250 SE +/- 0.43, N = 3 SE +/- 0.19, N = 3 SE +/- 0.11, N = 3 229.36 229.42 230.27 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10 3 2 1 0.7133 1.4266 2.1399 2.8532 3.5665 SE +/- 0.012, N = 3 SE +/- 0.010, N = 3 SE +/- 0.004, N = 3 3.170 3.160 3.154 1. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 6, Lossless 3 2 1 14 28 42 56 70 SE +/- 0.14, N = 3 SE +/- 0.11, N = 3 SE +/- 0.15, N = 3 62.40 62.39 62.67 1. (CXX) g++ options: -O3 -fPIC -lm
OpenBenchmarking.org Seconds, Fewer Is Better libavif avifenc 0.9.0 Encoder Speed: 10, Lossless 3 2 1 1.3021 2.6042 3.9063 5.2084 6.5105 SE +/- 0.012, N = 3 SE +/- 0.013, N = 3 SE +/- 0.013, N = 3 5.787 5.771 5.778 1. (CXX) g++ options: -O3 -fPIC -lm
ViennaCL ViennaCL is an open-source linear algebra library written in C++ and with support for OpenCL and OpenMP. This test profile makes use of ViennaCL's built-in benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sCOPY 3 2 1 7 14 21 28 35 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 28.3 28.2 28.2 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sAXPY 3 2 1 10 20 30 40 50 SE +/- 0.09, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 42.8 42.9 42.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - sDOT 3 2 1 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 47.9 47.9 47.9 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dCOPY 3 2 1 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 26.2 26.2 26.2 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dAXPY 3 2 1 9 18 27 36 45 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 39.3 39.3 39.3 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dDOT 3 2 1 10 20 30 40 50 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 44.1 44.1 44.1 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-N 3 2 1 10 20 30 40 50 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 45.5 45.6 45.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMV-T 3 2 1 11 22 33 44 55 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 46.5 46.5 46.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NN 3 2 1 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 34.8 34.8 34.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-NT 3 2 1 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 34.1 34.2 34.1 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TN 3 2 1 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.03, N = 3 36.5 36.4 36.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: CPU BLAS - dGEMM-TT 3 2 1 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 35.5 35.5 35.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sCOPY 3 2 1 8 16 24 32 40 SE +/- 0.06, N = 3 SE +/- 0.10, N = 3 SE +/- 0.06, N = 3 33.3 33.3 32.9 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sAXPY 3 2 1 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 34.6 34.6 34.6 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - sDOT 3 2 1 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 37.6 37.6 37.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dCOPY 3 2 1 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 34.2 34.1 34.0 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dAXPY 3 2 1 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.03, N = 3 35.4 35.3 35.3 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-N 3 2 1 9 18 27 36 45 SE +/- 0.00, N = 3 37.9 38.1 37.9 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GB/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMV-T 3 2 1 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 34.8 34.7 34.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NN 3 2 1 5 10 15 20 25 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 18.9 18.9 18.9 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-NT 3 2 1 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 16.4 16.5 16.5 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TN 3 2 1 4 8 12 16 20 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 15.8 15.8 15.8 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
OpenBenchmarking.org GFLOPs/s, More Is Better ViennaCL 1.7.1 Test: OpenCL BLAS - dGEMM-TT 3 2 1 4 8 12 16 20 SE +/- 0.00, N = 2 SE +/- 0.00, N = 2 SE +/- 0.00, N = 2 15.7 15.7 15.7 1. (CXX) g++ options: -fopenmp -O3 -rdynamic -lOpenCL
GNU Radio GNU Radio is a free software development toolkit providing signal processing blocks to implement software-defined radios (SDR) and signal processing systems. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Five Back to Back FIR Filters 3 2 1 300 600 900 1200 1500 SE +/- 15.25, N = 3 SE +/- 9.72, N = 3 SE +/- 12.45, N = 3 1188.7 1195.5 1190.2 1. 3.8.1.0
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Signal Source (Cosine) 3 2 1 600 1200 1800 2400 3000 SE +/- 2.72, N = 3 SE +/- 2.10, N = 3 SE +/- 3.36, N = 3 3011.2 3011.4 3003.2 1. 3.8.1.0
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FIR Filter 3 2 1 200 400 600 800 1000 SE +/- 2.94, N = 3 SE +/- 3.57, N = 3 SE +/- 1.65, N = 3 818.3 820.0 822.3 1. 3.8.1.0
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: IIR Filter 3 2 1 140 280 420 560 700 SE +/- 0.81, N = 3 SE +/- 1.34, N = 3 SE +/- 1.14, N = 3 665.0 664.9 666.1 1. 3.8.1.0
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: FM Deemphasis Filter 3 2 1 200 400 600 800 1000 SE +/- 1.55, N = 3 SE +/- 1.84, N = 3 SE +/- 2.38, N = 3 837.3 837.7 836.7 1. 3.8.1.0
OpenBenchmarking.org MiB/s, More Is Better GNU Radio Test: Hilbert Transform 3 2 1 130 260 390 520 650 SE +/- 1.23, N = 3 SE +/- 2.62, N = 3 SE +/- 1.07, N = 3 620.2 618.3 618.0 1. 3.8.1.0
Liquid-DSP LiquidSDR's Liquid-DSP is a software-defined radio (SDR) digital signal processing library. This test profile runs a multi-threaded benchmark of this SDR/DSP library focused on embedded platform usage. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 1 - Buffer Length: 256 - Filter Length: 57 3 2 1 14M 28M 42M 56M 70M SE +/- 27834.83, N = 3 SE +/- 1763.83, N = 3 SE +/- 881.92, N = 3 67599667 67632333 67629667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 2 - Buffer Length: 256 - Filter Length: 57 3 2 1 30M 60M 90M 120M 150M SE +/- 35276.68, N = 3 SE +/- 367891.89, N = 3 SE +/- 40551.75, N = 3 130663333 130046667 130183333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 4 - Buffer Length: 256 - Filter Length: 57 3 2 1 50M 100M 150M 200M 250M SE +/- 321679.62, N = 3 SE +/- 375470.08, N = 3 SE +/- 265476.51, N = 3 251473333 251576667 250856667 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 8 - Buffer Length: 256 - Filter Length: 57 3 2 1 100M 200M 300M 400M 500M SE +/- 2209451.92, N = 3 SE +/- 514274.03, N = 3 SE +/- 1523508.38, N = 3 453086667 452073333 452713333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 16 - Buffer Length: 256 - Filter Length: 57 3 2 1 110M 220M 330M 440M 550M SE +/- 199360.09, N = 3 SE +/- 188355.46, N = 3 SE +/- 324054.18, N = 3 500016667 500263333 500333333 1. (CC) gcc options: -O3 -pthread -lm -lc -lliquid
LuaRadio LuaRadio is a lightweight software-defined radio (SDR) framework built atop LuaJIT. LuaRadio provides a suite of source, sink, and processing blocks, with a simple API for defining flow graphs, running flow graphs, creating blocks, and creating data types. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MiB/s, More Is Better LuaRadio 0.9.1 Test: Five Back to Back FIR Filters 3 2 1 300 600 900 1200 1500 SE +/- 4.98, N = 3 SE +/- 3.21, N = 3 SE +/- 2.64, N = 3 1291.8 1292.4 1297.9
srsLTE srsLTE is an open-source LTE software radio suite created by Software Radio Systems (SRS). srsLTE can be used for building your own software defined (SDR) LTE mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Samples / Second, More Is Better srsLTE 20.10.1 Test: OFDM_Test 3 2 1 30M 60M 90M 120M 150M SE +/- 665832.81, N = 3 SE +/- 821245.67, N = 3 SE +/- 416333.20, N = 3 128500000 128466667 126700000 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org eNb Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test 3 2 1 60 120 180 240 300 SE +/- 0.84, N = 3 SE +/- 0.73, N = 3 SE +/- 0.19, N = 3 295.0 291.8 293.2 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
OpenBenchmarking.org UE Mb/s, More Is Better srsLTE 20.10.1 Test: PHY_DL_Test 3 2 1 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 113.4 112.2 112.7 1. (CXX) g++ options: -std=c++11 -fno-strict-aliasing -march=native -mfpmath=sse -mavx2 -fvisibility=hidden -O3 -fno-trapping-math -fno-math-errno -rdynamic -lpthread -lbladeRF -lm -lfftw3f -lmbedcrypto
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 0.8.2 Throughput Test: Kostya 3 2 1 0.6975 1.395 2.0925 2.79 3.4875 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.09 3.10 3.10 1. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.org GB/s, More Is Better simdjson 0.8.2 Throughput Test: LargeRandom 3 2 1 0.2408 0.4816 0.7224 0.9632 1.204 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 1.07 1.07 1.07 1. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.org GB/s, More Is Better simdjson 0.8.2 Throughput Test: PartialTweets 3 2 1 0.9855 1.971 2.9565 3.942 4.9275 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 4.37 4.38 4.38 1. (CXX) g++ options: -O3 -pthread
OpenBenchmarking.org GB/s, More Is Better simdjson 0.8.2 Throughput Test: DistinctUserID 3 2 1 1.0238 2.0476 3.0714 4.0952 5.119 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.54 4.55 4.53 1. (CXX) g++ options: -O3 -pthread
1 Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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,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_pstate powersave - CPU Microcode: 0xcc - Thermald 1.9.1Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of VMX unsupported + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled
Testing initiated at 31 March 2021 08:02 by user phoronix.
2 Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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,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_pstate powersave - CPU Microcode: 0xcc - Thermald 1.9.1Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of VMX unsupported + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled
Testing initiated at 31 March 2021 14:28 by user phoronix.
3 Processor: Intel Core i9-9900KS @ 5.00GHz (8 Cores / 16 Threads), Motherboard: ASUS PRIME Z390-A (1502 BIOS), Chipset: Intel Cannon Lake PCH, Memory: 32GB, Disk: 240GB Corsair Force MP510, Graphics: ASUS Intel UHD 630 CFL GT2 3GB (1200MHz), Audio: Realtek ALC1220, Monitor: G237HL, Network: Intel I219-V
OS: Ubuntu 20.04, Kernel: 5.9.0-050900rc8daily20201005-generic (x86_64) 20201004, Desktop: GNOME Shell 3.36.2, Display Server: X Server 1.20.8, OpenGL: 4.6 Mesa 20.2.6, OpenCL: OpenCL 2.1, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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,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_pstate powersave - CPU Microcode: 0xcc - Thermald 1.9.1Python Notes: Python 2.7.18rc1 + Python 3.8.2Security Notes: itlb_multihit: KVM: Mitigation of VMX unsupported + 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 Enhanced IBRS IBPB: conditional RSB filling + srbds: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled
Testing initiated at 31 March 2021 20:41 by user phoronix.