AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS) and AMD Radeon RX 6800 16GB on Ubuntu 22.04 via the Phoronix Test Suite. Benchmarks for a future article by Michael Larabel.
Clang 14 Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200
OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 14.0.6-1~oibaf~j, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Clang 15 OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 15.0.1-++20220915084339+3637f345d2ab-1~exp1~20220915084350.58, File-System: ext4, Screen Resolution: 3840x2160
AOM AV1 This is a test of the AOMedia AV1 encoder (libaom) developed by AOMedia and Google as the AV1 Codec Library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.4 Encoder Mode: Speed 8 Realtime - Input: Bosphorus 4K Clang 14 Clang 15 12 24 36 48 60 SE +/- 0.26, N = 3 SE +/- 0.60, N = 3 53.09 54.50 1. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.4 Encoder Mode: Speed 9 Realtime - Input: Bosphorus 4K Clang 14 Clang 15 16 32 48 64 80 SE +/- 0.07, N = 3 SE +/- 0.90, N = 3 69.71 71.09 1. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm
OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 3.4 Encoder Mode: Speed 10 Realtime - Input: Bosphorus 4K Clang 14 Clang 15 16 32 48 64 80 SE +/- 0.73, N = 3 SE +/- 0.37, N = 3 69.61 70.70 1. (CXX) g++ options: -O3 -march=native -flto -std=c++11 -U_FORTIFY_SOURCE -lm
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 MT/s, More Is Better ASTC Encoder 4.0 Preset: Medium Clang 14 Clang 15 20 40 60 80 100 SE +/- 0.18, N = 3 SE +/- 0.12, N = 3 103.37 103.54 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Thorough Clang 15 Clang 14 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 12.79 12.81 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.org MT/s, More Is Better ASTC Encoder 4.0 Preset: Exhaustive Clang 15 Clang 14 0.2979 0.5958 0.8937 1.1916 1.4895 SE +/- 0.0029, N = 3 SE +/- 0.0011, N = 3 1.3214 1.3239 1. (CXX) g++ options: -O3 -march=native -flto -pthread
OpenBenchmarking.org MB/s, More Is Better C-Blosc 2.3 Test: blosclz bitshuffle Clang 14 Clang 15 3K 6K 9K 12K 15K SE +/- 37.67, N = 3 SE +/- 104.51, N = 3 14077.1 14221.4 1. (CXX) g++ options: -O3 -march=native -flto
C-Ray This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Clang 14 Clang 15 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.08, N = 3 26.00 25.97 1. (CC) gcc options: -lm -lpthread -O3 -march=native -flto
FinanceBench FinanceBench is a collection of financial program benchmarks with support for benchmarking on the GPU via OpenCL and CPU benchmarking with OpenMP. The FinanceBench test cases are focused on Black-Sholes-Merton Process with Analytic European Option engine, QMC (Sobol) Monte-Carlo method (Equity Option Example), Bonds Fixed-rate bond with flat forward curve, and Repo Securities repurchase agreement. FinanceBench was originally written by the Cavazos Lab at University of Delaware. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Repo OpenMP Clang 15 Clang 14 6K 12K 18K 24K 30K SE +/- 284.62, N = 5 SE +/- 372.37, N = 3 26383.03 26297.79 1. (CXX) g++ options: -O3 -march=native -fopenmp
OpenBenchmarking.org ms, Fewer Is Better FinanceBench 2016-07-25 Benchmark: Bonds OpenMP Clang 15 Clang 14 9K 18K 27K 36K 45K SE +/- 154.34, N = 3 SE +/- 20.59, N = 3 40390.20 40301.00 1. (CXX) g++ options: -O3 -march=native -fopenmp
FLAC Audio Encoding OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.4 WAV To FLAC Clang 15 Clang 14 4 8 12 16 20 SE +/- 0.03, N = 5 SE +/- 0.07, N = 5 13.72 13.08 1. (CXX) g++ options: -O3 -march=native -flto -fvisibility=hidden -logg -lm
Google Draco Draco is a library developed by Google for compressing/decompressing 3D geometric meshes and point clouds. This test profile uses some Artec3D PLY models as the sample 3D model input formats for Draco compression/decompression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Google Draco 1.5.0 Model: Lion Clang 15 Clang 14 800 1600 2400 3200 4000 SE +/- 5.46, N = 3 SE +/- 6.89, N = 3 3930 3909 1. (CXX) g++ options: -O3 -march=native -flto
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests on a sample 6000x4000 pixel JPEG image. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space Clang 14 Clang 15 300 600 900 1200 1500 SE +/- 2.52, N = 3 SE +/- 4.04, N = 3 1405 1417 1. (CC) gcc options: -fopenmp -O3 -march=native -flto -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread
JPEG XL libjxl The JPEG XL Image Coding System is designed to provide next-generation JPEG image capabilities with JPEG XL offering better image quality and compression over legacy JPEG. This test profile is currently focused on the multi-threaded JPEG XL image encode performance using the reference libjxl library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: PNG - Encode Speed: 7 Clang 14 Clang 15 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 11.60 14.82 1. (CXX) g++ options: -O3 -march=native -flto -funwind-tables -Xclang -mrelax-all -O2 -fPIE -pie
OpenBenchmarking.org MP/s, More Is Better JPEG XL libjxl 0.6.1 Input: JPEG - Encode Speed: 7 Clang 14 Clang 15 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 103.02 104.16 1. (CXX) g++ options: -O3 -march=native -flto -funwind-tables -Xclang -mrelax-all -O2 -fPIE -pie
KTX-Software toktx This is a benchmark of The Khronos Group's KTX-Software library and tools. KTX-Software provides "toktx" for converting/creating in the KTX container format for image textures. This benchmark times how long it takes to convert to KTX 2.0 format with various settings using a reference PNG sample input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better KTX-Software toktx 4.0 Settings: UASTC 3 Clang 14 Clang 15 2 4 6 8 10 SE +/- 0.004, N = 3 SE +/- 0.009, N = 3 6.502 6.486
LeelaChessZero LeelaChessZero (lc0 / lczero) is a chess engine automated vian neural networks. This test profile can be used for OpenCL, CUDA + cuDNN, and BLAS (CPU-based) benchmarking. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.28 Backend: BLAS Clang 14 Clang 15 200 400 600 800 1000 SE +/- 14.83, N = 6 SE +/- 9.69, N = 9 761 778 1. (CXX) g++ options: -flto -O3 -march=native -pthread
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: 16 - Buffer Length: 256 - Filter Length: 57 Clang 15 Clang 14 200M 400M 600M 800M 1000M SE +/- 859638.17, N = 3 SE +/- 866666.67, N = 3 976266667 1054466667 1. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid
OpenBenchmarking.org samples/s, More Is Better Liquid-DSP 2021.01.31 Threads: 32 - Buffer Length: 256 - Filter Length: 57 Clang 15 Clang 14 200M 400M 600M 800M 1000M SE +/- 1479864.86, N = 3 SE +/- 952773.73, N = 3 1100700000 1115233333 1. (CC) gcc options: -O3 -march=native -flto -pthread -lm -lc -lliquid
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 20220729 Target: CPU - Model: mobilenet Clang 15 Clang 14 3 6 9 12 15 SE +/- 0.07, N = 15 SE +/- 0.09, N = 3 11.54 11.37 MIN: 10.83 / MAX: 19.94 MIN: 10.82 / MAX: 12.01 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v2-v2 - Model: mobilenet-v2 Clang 15 Clang 14 0.9 1.8 2.7 3.6 4.5 SE +/- 0.03, N = 15 SE +/- 0.05, N = 3 4.00 3.99 MIN: 3.71 / MAX: 13.25 MIN: 3.8 / MAX: 4.54 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU-v3-v3 - Model: mobilenet-v3 Clang 15 Clang 14 0.792 1.584 2.376 3.168 3.96 SE +/- 0.02, N = 15 SE +/- 0.02, N = 3 3.52 3.52 MIN: 3.33 / MAX: 11.49 MIN: 3.44 / MAX: 3.99 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: shufflenet-v2 Clang 14 Clang 15 0.8865 1.773 2.6595 3.546 4.4325 SE +/- 0.04, N = 3 SE +/- 0.02, N = 15 3.94 3.92 MIN: 3.8 / MAX: 4.39 MIN: 3.73 / MAX: 14 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: mnasnet Clang 14 Clang 15 0.837 1.674 2.511 3.348 4.185 SE +/- 0.02, N = 3 SE +/- 0.02, N = 15 3.72 3.70 MIN: 3.63 / MAX: 4.33 MIN: 3.52 / MAX: 5.97 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: efficientnet-b0 Clang 14 Clang 15 1.1093 2.2186 3.3279 4.4372 5.5465 SE +/- 0.03, N = 3 SE +/- 0.02, N = 15 4.93 4.90 MIN: 4.83 / MAX: 5.47 MIN: 4.71 / MAX: 15.1 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: googlenet Clang 14 Clang 15 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.08, N = 15 11.07 10.86 MIN: 10.23 / MAX: 12.75 MIN: 10.16 / MAX: 40.48 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vgg16 Clang 15 Clang 14 11 22 33 44 55 SE +/- 0.27, N = 15 SE +/- 0.32, N = 3 46.99 46.68 MIN: 44.38 / MAX: 56.74 MIN: 45.34 / MAX: 53.65 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet18 Clang 15 Clang 14 3 6 9 12 15 SE +/- 0.10, N = 15 SE +/- 0.03, N = 3 11.51 11.47 MIN: 10.37 / MAX: 14.62 MIN: 10.93 / MAX: 12.71 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: alexnet Clang 14 Clang 15 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.03, N = 15 7.38 7.32 MIN: 7.09 / MAX: 8.55 MIN: 6.89 / MAX: 16.13 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: resnet50 Clang 14 Clang 15 5 10 15 20 25 SE +/- 0.04, N = 3 SE +/- 0.09, N = 15 20.11 19.71 MIN: 19.33 / MAX: 21.9 MIN: 18.65 / MAX: 28.15 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: regnety_400m Clang 14 Clang 15 3 6 9 12 15 SE +/- 0.04, N = 2 SE +/- 0.06, N = 14 11.36 11.16 MIN: 11.22 / MAX: 11.87 MIN: 10.58 / MAX: 14.9 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: CPU - Model: vision_transformer Clang 15 Clang 14 20 40 60 80 100 SE +/- 0.20, N = 15 SE +/- 0.35, N = 3 99.45 98.83 MIN: 97.82 / MAX: 192.86 MIN: 97.58 / MAX: 104.02 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread
Nettle GNU Nettle is a low-level cryptographic library used by GnuTLS and other software. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: aes256 Clang 14 Clang 15 1600 3200 4800 6400 8000 SE +/- 2.05, N = 3 SE +/- 2.86, N = 3 7286.24 7339.72 MIN: 5504.06 / MAX: 10861.66 MIN: 5536.69 / MAX: 10939.29 1. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: chacha Clang 14 Clang 15 300 600 900 1200 1500 SE +/- 2.17, N = 3 SE +/- 1.49, N = 3 1198.85 1214.34 MIN: 589.65 / MAX: 3386.11 MIN: 598.24 / MAX: 3435.95 1. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: sha512 Clang 14 Clang 15 160 320 480 640 800 SE +/- 0.19, N = 3 SE +/- 2.18, N = 3 737.49 751.68 1. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto
OpenBenchmarking.org Mbyte/s, More Is Better Nettle 3.8 Test: poly1305-aes Clang 14 Clang 15 700 1400 2100 2800 3500 SE +/- 1.13, N = 3 SE +/- 2.21, N = 3 3398.23 3419.90 1. (CC) gcc options: -O3 -march=native -flto -ggdb3 -lnettle -lm -lcrypto
OpenFOAM OpenFOAM is the leading free, open-source software for computational fluid dynamics (CFD). This test profile currently uses the drivaerFastback test case for analyzing automotive aerodynamics or alternatively the older motorBike input. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: motorBike - Mesh Time Clang 15 Clang 14 9 18 27 36 45 37.75 37.06 -lfiniteVolume -lmeshTools -lfoamToVTK -llagrangian -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: motorBike - Execution Time Clang 15 Clang 14 20 40 60 80 100 104.20 103.20 -lfiniteVolume -lmeshTools -lfoamToVTK -llagrangian -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Mesh Time Clang 15 Clang 14 9 18 27 36 45 37.58 37.26 -lfiniteVolume -lmeshTools -lfoamToVTK -llagrangian -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm
OpenBenchmarking.org Seconds, Fewer Is Better OpenFOAM 10 Input: drivaerFastback, Small Mesh Size - Execution Time Clang 15 Clang 14 80 160 240 320 400 375.34 371.08 -lfiniteVolume -lmeshTools -lfoamToVTK -llagrangian -lfileFormats 1. (CXX) g++ options: -std=c++14 -m64 -O3 -ftemplate-depth-100 -fPIC -fuse-ld=bfd -Xlinker --add-needed --no-as-needed -lgenericPatchFields -ldynamicMesh -lOpenFOAM -ldl -lm
OpenJPEG OpenJPEG is an open-source JPEG 2000 codec written in the C programming language. The default input for this test profile is the NASA/JPL-Caltech/MSSS Curiosity panorama 717MB TIFF image file converting to JPEG2000 format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenJPEG 2.4 Encode: NASA Curiosity Panorama M34 Clang 14 Clang 15 11K 22K 33K 44K 55K SE +/- 521.26, N = 5 SE +/- 295.03, N = 3 51408 49157 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test profile makes use of the built-in "openssl speed" benchmarking capabilities. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org byte/s, More Is Better OpenSSL 3.0 Algorithm: SHA256 Clang 15 Clang 14 6000M 12000M 18000M 24000M 30000M SE +/- 46992215.82, N = 3 SE +/- 16320548.29, N = 3 27681428940 29893817370 1. (CC) gcc options: -pthread -m64 -Qunused-arguments -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org sign/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Clang 15 Clang 14 1000 2000 3000 4000 5000 SE +/- 2.63, N = 3 SE +/- 2.20, N = 3 4790.2 4806.6 1. (CC) gcc options: -pthread -m64 -Qunused-arguments -O3 -march=native -flto -lssl -lcrypto -ldl
OpenBenchmarking.org verify/s, More Is Better OpenSSL 3.0 Algorithm: RSA4096 Clang 15 Clang 14 70K 140K 210K 280K 350K SE +/- 146.06, N = 3 SE +/- 17.46, N = 3 314488.2 316387.7 1. (CC) gcc options: -pthread -m64 -Qunused-arguments -O3 -march=native -flto -lssl -lcrypto -ldl
Opus Codec Encoding Opus is an open audio codec. Opus is a lossy audio compression format designed primarily for interactive real-time applications over the Internet. This test uses Opus-Tools and measures the time required to encode a WAV file to Opus. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.3.1 WAV To Opus Encode Clang 15 Clang 14 1.2458 2.4916 3.7374 4.9832 6.229 SE +/- 0.026, N = 5 SE +/- 0.020, N = 5 5.537 5.433 1. (CXX) g++ options: -O3 -march=native -flto -logg -lm
POV-Ray This is a test of POV-Ray, the Persistence of Vision Raytracer. POV-Ray is used to create 3D graphics using ray-tracing. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Clang 14 Clang 15 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 22.77 21.81 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -flto -lSDL -lSM -lICE -lX11 -lIlmImf -lIlmImf-2_5 -lImath-2_5 -lHalf-2_5 -lIex-2_5 -lIexMath-2_5 -lIlmThread-2_5 -lIlmThread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
QuantLib QuantLib is an open-source library/framework around quantitative finance for modeling, trading and risk management scenarios. QuantLib is written in C++ with Boost and its built-in benchmark used reports the QuantLib Benchmark Index benchmark score. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better QuantLib 1.21 Clang 14 Clang 15 800 1600 2400 3200 4000 SE +/- 24.48, N = 3 SE +/- 20.26, N = 3 3744.6 3848.9 1. (CXX) g++ options: -O3 -march=native -rdynamic
srsRAN srsRAN is an open-source LTE/5G software radio suite created by Software Radio Systems (SRS). The srsRAN radio suite was formerly known as srsLTE and can be used for building your own software-defined radio (SDR) 4G/5G mobile network. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Samples / Second, More Is Better srsRAN 22.04.1 Test: OFDM_Test Clang 15 Clang 14 40M 80M 120M 160M 200M SE +/- 635959.47, N = 3 SE +/- 1946792.23, N = 3 166466667 177200000 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 64-QAM Clang 14 Clang 15 120 240 360 480 600 SE +/- 0.45, N = 3 SE +/- 0.15, N = 3 533.9 543.1 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Clang 14 Clang 15 120 240 360 480 600 SE +/- 0.70, N = 3 SE +/- 0.75, N = 3 526.2 535.1 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 64-QAM Clang 14 Clang 15 40 80 120 160 200 SE +/- 0.70, N = 3 SE +/- 5.69, N = 3 201.8 203.6 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Clang 14 Clang 15 130 260 390 520 650 SE +/- 1.59, N = 3 SE +/- 3.55, N = 3 557.4 579.4 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB MIMO 256-QAM Clang 14 Clang 15 50 100 150 200 250 SE +/- 0.90, N = 3 SE +/- 0.46, N = 3 199.8 210.0 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Clang 14 Clang 15 120 240 360 480 600 SE +/- 0.33, N = 3 SE +/- 0.62, N = 3 563.4 570.1 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 4G PHY_DL_Test 100 PRB SISO 256-QAM Clang 14 Clang 15 50 100 150 200 250 SE +/- 0.78, N = 3 SE +/- 0.15, N = 3 211.4 218.3 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org eNb Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Clang 14 Clang 15 40 80 120 160 200 SE +/- 0.52, N = 3 SE +/- 0.97, N = 3 178.1 180.7 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
OpenBenchmarking.org UE Mb/s, More Is Better srsRAN 22.04.1 Test: 5G PHY_DL_NR Test 52 PRB SISO 64-QAM Clang 14 Clang 15 20 40 60 80 100 SE +/- 0.12, N = 3 SE +/- 0.35, N = 3 79.9 82.4 -latomic -ldl 1. (CXX) g++ options: -O3 -march=native -flto -std=c++14 -fno-strict-aliasing -mfpmath=sse -mavx2 -fvisibility=hidden -fno-trapping-math -fno-math-errno -lpthread -lm
SVT-AV1 OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 8 - Input: Bosphorus 4K Clang 15 Clang 14 11 22 33 44 55 SE +/- 0.45, N = 3 SE +/- 0.34, N = 3 48.38 48.51
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 10 - Input: Bosphorus 4K Clang 15 Clang 14 20 40 60 80 100 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 81.12 82.26
OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 1.2 Encoder Mode: Preset 12 - Input: Bosphorus 4K Clang 15 Clang 14 20 40 60 80 100 SE +/- 0.24, N = 3 SE +/- 0.11, N = 3 103.91 104.37
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 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: 7 - Input: Bosphorus 4K Clang 15 Clang 14 14 28 42 56 70 SE +/- 0.81, N = 3 SE +/- 0.66, N = 5 63.89 64.72 1. (CC) gcc options: -O3 -march=native -flto -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt
OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.5.0 Tuning: 10 - Input: Bosphorus 4K Clang 14 Clang 15 20 40 60 80 100 SE +/- 0.13, N = 3 SE +/- 0.05, N = 3 85.46 86.80 1. (CC) gcc options: -O3 -march=native -flto -fPIE -fPIC -O2 -pie -rdynamic -lpthread -lrt
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 4K Clang 14 Clang 15 12 24 36 48 60 SE +/- 0.50, N = 15 SE +/- 0.45, N = 12 50.12 51.39 1. (CC) gcc options: -O3 -fcommon -march=native -flto -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 4K Clang 14 Clang 15 12 24 36 48 60 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 54.40 55.56 1. (CC) gcc options: -O3 -fcommon -march=native -flto -fPIE -fPIC -fvisibility=hidden -pie -rdynamic -lpthread -lrt -lm
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet Clang 14 Clang 15 800 1600 2400 3200 4000 SE +/- 2.95, N = 3 SE +/- 3.00, N = 3 3831.70 3236.77 MIN: 3738.1 / MAX: 3946.4 MIN: 3140.1 / MAX: 3351.74 1. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 Clang 14 Clang 15 100 200 300 400 500 SE +/- 0.95, N = 3 SE +/- 0.20, N = 3 472.69 426.46 MIN: 470.05 / MAX: 476.68 MIN: 424.42 / MAX: 427.81 1. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Clang 15 Clang 14 15 30 45 60 75 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 65.32 64.57 MIN: 64.97 / MAX: 65.75 MIN: 64.4 / MAX: 64.85 1. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 Clang 14 Clang 15 70 140 210 280 350 SE +/- 0.21, N = 3 SE +/- 0.16, N = 3 304.93 302.64 MIN: 304.53 / MAX: 305.79 MIN: 302.22 / MAX: 303.12 1. (CXX) g++ options: -O3 -march=native -flto -fopenmp=libomp -pthread -fvisibility=hidden -fvisibility=default -rdynamic -ldl
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 Clang 14 Clang 15 6 12 18 24 30 SE +/- 0.21, N = 3 SE +/- 0.13, N = 3 26.53 27.37 1. (CXX) g++ options: -O3 -march=native -flto -rdynamic -lpthread -lrt -ldl -lnuma
Xmrig Xmrig is an open-source cross-platform CPU/GPU miner for RandomX, KawPow, CryptoNight and AstroBWT. This test profile is setup to measure the Xmlrig CPU mining performance. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Monero - Hash Count: 1M Clang 14 Clang 15 1500 3000 4500 6000 7500 SE +/- 60.21, N = 3 SE +/- 40.85, N = 3 7012.9 7081.8 1. (CXX) g++ options: -O3 -march=native -flto -fexceptions -fno-rtti -maes -Ofast -funroll-loops -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
OpenBenchmarking.org H/s, More Is Better Xmrig 6.12.1 Variant: Wownero - Hash Count: 1M Clang 15 Clang 14 3K 6K 9K 12K 15K SE +/- 79.54, N = 3 SE +/- 32.20, N = 3 13469.2 13589.4 1. (CXX) g++ options: -O3 -march=native -flto -fexceptions -fno-rtti -maes -Ofast -funroll-loops -rdynamic -lssl -lcrypto -luv -lpthread -lrt -ldl -lhwloc
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 1.5.0 Compression Level: 3 - Compression Speed Clang 15 Clang 14 1100 2200 3300 4400 5500 SE +/- 14.64, N = 3 SE +/- 6.01, N = 3 5121.1 5138.6 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19 - Compression Speed Clang 14 Clang 15 11 22 33 44 55 SE +/- 0.06, N = 3 SE +/- 0.06, N = 3 50.2 50.3 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Compression Speed Clang 14 Clang 15 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 36.3 36.3 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma
OpenBenchmarking.org MB/s, More Is Better Zstd Compression 1.5.0 Compression Level: 19, Long Mode - Decompression Speed Clang 15 Clang 14 800 1600 2400 3200 4000 SE +/- 4.56, N = 3 SE +/- 12.33, N = 3 3860.8 3957.9 1. (CC) gcc options: -O3 -march=native -flto -pthread -lz -llzma
Clang 14 Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200
OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 14.0.6-1~oibaf~j, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 16 September 2022 17:28 by user phoronix.
Clang 15 Processor: AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (4006 BIOS), Chipset: AMD Starship/Matisse, Memory: 32GB, Disk: 500GB Western Digital WDS500G3X0C-00SJG0, Graphics: AMD Radeon RX 6800 16GB (2475/1000MHz), Audio: AMD Navi 21 HDMI Audio, Monitor: ASUS MG28U, Network: Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200
OS: Ubuntu 22.04, Kernel: 6.0.0-060000rc5daily20220915-generic (x86_64), Desktop: GNOME Shell 42.4, Display Server: X Server 1.21.1.3 + Wayland, OpenGL: 4.6 Mesa 22.3.0-devel (git-03294e1 2022-09-16 jammy-oibaf-ppa) (LLVM 14.0.6 DRM 3.48), Vulkan: 1.3.228, Compiler: Clang 15.0.1-++20220915084339+3637f345d2ab-1~exp1~20220915084350.58, File-System: ext4, Screen Resolution: 3840x2160
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: CXXFLAGS="-O3 -march=native -flto" CFLAGS="-O3 -march=native -flto"Processor Notes: Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201016Python Notes: Python 3.10.4Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 17 September 2022 08:19 by user phoronix.