AMD Zen 2 GCC compiler benchmarks on Ubuntu Linux. Tests by Michael Larabel for a future article.
-O3 -march=x86-64 Environment Notes: CXXFLAGS=-O3-march=x86-64 CFLAGS=-O3-march=x86-64Compiler Notes: --disable-multilib --enable-checking=releaseProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled
-O3 -march=znver1 Environment Notes: CXXFLAGS=-O3-march=znver1 CFLAGS=-O3-march=znver1Compiler Notes: --disable-multilib --enable-checking=releaseProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled
-O3 -march=znver2 Processor: AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (0066 BIOS), Chipset: AMD Device 1480, Memory: 16384MB, Disk: 2000GB Force MP600, Graphics: Sapphire AMD Baffin [Polaris11] 4GB (1300/1750MHz), Audio: AMD Device aae0, Monitor: ASUS VP28U, Network: Realtek Device 8125 + Intel I211 + Intel Device 2723
OS: Ubuntu 18.04, Kernel: 5.2.0-999-generic (x86_64) 20190703, Desktop: GNOME Shell 3.28.3, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 4.5 Mesa 18.2.2 (LLVM 7.0.0), Compiler: GCC 9.1.0, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2Compiler Notes: --disable-multilib --enable-checking=releaseProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled
ryzen3800x4200 Processor: AMD Ryzen 7 3800X 8-Core @ 4.20GHz (8 Cores / 16 Threads) , Motherboard: ASUS TUF GAMING X570-PLUS_BR (1405 BIOS) , Chipset: AMD Starship/Matisse , Memory: 16GB , Disk: 480GB Force MP510 + 320GB SAMSUNG HD322HJ , Graphics: NVIDIA GeForce GTX 960 2GB (1126/3505MHz) , Audio: NVIDIA GM206 HD Audio , Network: Realtek RTL8111/8168/8411 + Broadcom BCM4360 802.11ac
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: MATE 1.24.0, Display Server: X Server 1.20.7, Display Driver: NVIDIA 435.21, OpenGL: 4.6.0, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Compiler 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: acpi-cpufreq performance - CPU Microcode: 0x8701013Python Notes: + Python 3.8.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 ryzen3800x4200 -O3 -march=znver1 -O3 -march=znver2 4K 8K 12K 16K 20K SE +/- 314.37, N = 3 SE +/- 83.01, N = 3 SE +/- 71.31, N = 3 18240 19405 19960 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -march=znver1 -march=znver2 1. (CC) gcc options: -pthread -O3 -lm
CppPerformanceBenchmarks CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Math Library -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 ryzen3800x4200 70 140 210 280 350 SE +/- 4.58, N = 4 SE +/- 5.00, N = 3 SE +/- 1.69, N = 3 SE +/- 0.19, N = 3 312.01 311.77 309.02 281.88 -march=x86-64 -march=znver1 -march=znver2 1. (CXX) g++ options: -O3 -std=c++11
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 2K 4K 6K 8K 10K SE +/- 9.60, N = 3 SE +/- 7.75, N = 3 SE +/- 34.96, N = 3 SE +/- 28.05, N = 3 5968.30 7039.43 7660.90 8001.67 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -march=znver1 -march=znver2 1. (CC) gcc options: -pthread -O3 -lm
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write ryzen3800x4200 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 6K 12K 18K 24K 30K SE +/- 14.38, N = 3 SE +/- 361.55, N = 15 SE +/- 197.60, N = 3 SE +/- 169.86, N = 3 16722.39 29380.50 30044.32 30143.80 -O2 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
VP9 libvpx Encoding This is a standard video encoding performance test of Google's libvpx library and the vpxenc command for the VP9/WebM format using a sample 1080p video. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.0 vpxenc VP9 1080p Video Encode -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 ryzen3800x4200 40 80 120 160 200 SE +/- 0.98, N = 3 SE +/- 0.55, N = 3 SE +/- 0.86, N = 3 SE +/- 1.23, N = 3 174.40 175.34 175.99 202.41 -march=znver1 -march=znver2 -march=x86-64 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 20K 40K 60K 80K 100K SE +/- 703.67, N = 14 SE +/- 879.11, N = 15 SE +/- 1084.23, N = 15 SE +/- 1283.75, N = 15 94377.50 107814.85 110755.89 112447.77 -O2 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 1. (CC) gcc options: -lm -rdynamic
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only ryzen3800x4200 -O3 -march=znver2 -O3 -march=znver1 -O3 -march=x86-64 80K 160K 240K 320K 400K SE +/- 844.67, N = 3 SE +/- 738.26, N = 3 SE +/- 539.80, N = 3 SE +/- 837.27, N = 3 264125.57 382751.07 383329.30 385510.95 -O2 -O3 -march=znver2 -O3 -march=znver1 -O3 -march=x86-64 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
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 9 Total Time ryzen3800x4200 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver1 9M 18M 27M 36M 45M SE +/- 251488.84, N = 3 SE +/- 265193.75, N = 3 SE +/- 75524.60, N = 3 SE +/- 208989.61, N = 3 27465891 39471726 39537930 39908751 -march=znver2 -march=x86-64 -march=znver1 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
Memcached mcperf This is a test of twmperf/mcperf with memcached. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set -O3 -march=x86-64 -O3 -march=znver1 ryzen3800x4200 -O3 -march=znver2 15K 30K 45K 60K 75K SE +/- 807.63, N = 4 SE +/- 1488.06, N = 15 SE +/- 77.26, N = 3 SE +/- 4868.10, N = 15 60770.80 60810.38 63869.30 69121.64 -O3 -march=x86-64 -O3 -march=znver1 -O2 -O3 -march=znver2 1. (CC) gcc options: -lm -rdynamic
MKL-DNN This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: IP Batch 1D - Data Type: f32 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 ryzen3800x4200 40 80 120 160 200 SE +/- 2.27, N = 15 SE +/- 2.44, N = 15 SE +/- 3.65, N = 15 SE +/- 0.23, N = 3 159.95 158.46 152.36 22.64 -march=znver1 - MIN: 108.37 -march=znver2 - MIN: 112.01 -march=x86-64 - MIN: 109.43 MIN: 13.13 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
GraphicsMagick This is a test of GraphicsMagick with its OpenMP implementation that performs various imaging tests to stress the system's CPU. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Sharpen ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 40 80 120 160 200 SE +/- 0.58, N = 3 156 179 193 194 -O2 -lgomp -O3 -march=x86-64 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl -O3 -march=znver1 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl -O3 -march=znver2 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Rotate -O3 -march=znver1 -O3 -march=x86-64 ryzen3800x4200 -O3 -march=znver2 60 120 180 240 300 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 1.33, N = 3 260 261 261 276 -O3 -march=znver1 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl -O3 -march=x86-64 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl -O2 -lgomp -O3 -march=znver2 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.30 Operation: Resizing -O3 -march=x86-64 ryzen3800x4200 -O3 -march=znver1 -O3 -march=znver2 60 120 180 240 300 SE +/- 1.53, N = 3 270 276 279 285 -O3 -march=x86-64 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl -O2 -lgomp -O3 -march=znver1 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl -O3 -march=znver2 -ljbig -lwebp -lwebpmux -ltiff -ljpeg -llzma -lbz2 -ldl 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
Himeno Benchmark The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 300 600 900 1200 1500 SE +/- 4.19, N = 3 SE +/- 13.46, N = 3 SE +/- 22.06, N = 3 SE +/- 12.91, N = 3 1274.46 1336.77 1345.95 1347.96 -march=x86-64 -march=znver1 -march=znver2 1. (CC) gcc options: -O3 -mavx2
Timed PHP Compilation This test times how long it takes to build PHP 5 with the Zend engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.1.9 Time To Compile ryzen3800x4200 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 12 24 36 48 60 SE +/- 0.23, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 SE +/- 0.34, N = 3 54.85 53.44 53.41 52.89 -O2 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 1. (CC) gcc options: -pedantic -ldl -lz -lm
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SET ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 400K 800K 1200K 1600K 2000K SE +/- 24405.05, N = 15 SE +/- 28039.49, N = 15 SE +/- 26581.97, N = 15 SE +/- 26820.33, N = 15 1893390.85 2074827.24 2080013.12 2089609.47 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
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 ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 14 28 42 56 70 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 60.32 43.20 39.46 39.42 -march=x86-64 -march=znver2 -march=znver1 1. (CC) gcc options: -lm -lpthread -O3
MKL-DNN This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Deconvolution Batch deconv_1d - Data Type: f32 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 ryzen3800x4200 50 100 150 200 250 SE +/- 2.51, N = 3 SE +/- 1.89, N = 11 SE +/- 2.63, N = 6 SE +/- 0.18, N = 3 221.00 219.29 216.70 31.01 -march=x86-64 - MIN: 202.64 -march=znver1 - MIN: 203.58 -march=znver2 - MIN: 202.77 MIN: 29.38 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: GET ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 700K 1400K 2100K 2800K 3500K SE +/- 18403.22, N = 3 SE +/- 58033.83, N = 15 SE +/- 61045.92, N = 12 SE +/- 62689.04, N = 13 2695667.50 3026826.32 3090850.69 3126726.23 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
AOBench AOBench is a lightweight ambient occlusion renderer, written in C. The test profile is using a size of 2048 x 2048. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 ryzen3800x4200 8 16 24 32 40 SE +/- 0.32, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 36.49 35.14 34.64 32.23 -march=x86-64 -march=znver1 -march=znver2 1. (CC) gcc options: -lm -O3
7-Zip Compression This is a test of 7-Zip using p7zip with its integrated benchmark feature or upstream 7-Zip for the Windows x64 build. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test ryzen3800x4200 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 20K 40K 60K 80K 100K SE +/- 103.41, N = 3 SE +/- 193.52, N = 3 SE +/- 205.86, N = 3 SE +/- 419.64, N = 3 54535 78412 78562 78655 1. (CXX) g++ options: -pipe -lpthread
John The Ripper This is a benchmark of John The Ripper, which is a password cracker. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish ryzen3800x4200 -O3 -march=znver2 -O3 -march=znver1 -O3 -march=x86-64 6K 12K 18K 24K 30K SE +/- 8.95, N = 3 SE +/- 50.35, N = 3 SE +/- 51.72, N = 3 SE +/- 61.75, N = 3 13993 20232 28221 28401 -lbz2 -lbz2 -lbz2 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt
XZ Compression This test measures the time needed to compress a sample file (an Ubuntu file-system image) using XZ compression. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 32.87 25.22 25.21 25.09 -O2 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 1. (CC) gcc options: -pthread -fvisibility=hidden
SciMark This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 800 1600 2400 3200 4000 SE +/- 1.56, N = 3 SE +/- 27.49, N = 3 SE +/- 7.70, N = 3 SE +/- 7.82, N = 3 618.82 2786.33 3128.65 3700.64 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 1. (CC) gcc options: -lm
MKL-DNN This is a test of the Intel MKL-DNN as the Intel Math Kernel Library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better MKL-DNN 2019-04-16 Harness: Convolution Batch conv_alexnet - Data Type: f32 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 ryzen3800x4200 500 1000 1500 2000 2500 SE +/- 19.59, N = 3 SE +/- 12.02, N = 3 SE +/- 11.23, N = 3 SE +/- 0.83, N = 3 2562.89 2524.93 2512.04 331.47 -march=znver1 - MIN: 2476.4 -march=znver2 - MIN: 2478.96 -march=x86-64 - MIN: 2466.12 MIN: 327.27 1. (CXX) g++ options: -O3 -std=c++11 -march=native -mtune=native -fPIC -fopenmp -pie -lmklml_intel -ldl
CppPerformanceBenchmarks CppPerformanceBenchmarks is a set of C++ compiler performance benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Function Objects ryzen3800x4200 -O3 -march=znver1 -O3 -march=x86-64 -O3 -march=znver2 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.16, N = 3 SE +/- 0.16, N = 3 15.63 14.99 14.90 14.56 -march=znver1 -march=x86-64 -march=znver2 1. (CXX) g++ options: -std=c++11 -O3
FLAC Audio Encoding This test times how long it takes to encode a sample WAV file to FLAC format five times. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC -O3 -march=znver1 -O3 -march=znver2 ryzen3800x4200 -O3 -march=x86-64 2 4 6 8 10 SE +/- 0.038, N = 5 SE +/- 0.060, N = 5 SE +/- 0.009, N = 5 SE +/- 0.040, N = 5 8.150 8.120 7.922 7.750 -O3 -march=znver1 -logg -O3 -march=znver2 -logg -O2 -O3 -march=x86-64 -logg 1. (CXX) g++ options: -fvisibility=hidden -lm
LAME MP3 Encoding LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 6 12 18 24 30 SE +/- 0.005, N = 3 SE +/- 0.070, N = 3 SE +/- 0.121, N = 3 SE +/- 0.088, N = 4 26.537 7.160 7.040 6.980 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 1. (CC) gcc options: -lncurses -lm
x265 This is a simple test of the x265 encoder run on the CPU with a sample 1080p video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x265 3.0 H.265 1080p Video Encoding ryzen3800x4200 -O3 -march=znver2 -O3 -march=znver1 -O3 -march=x86-64 12 24 36 48 60 SE +/- 0.28, N = 3 SE +/- 0.11, N = 3 SE +/- 0.12, N = 3 SE +/- 0.08, N = 3 45.82 52.91 53.15 53.33 -march=znver2 -lnuma -march=znver1 -lnuma -march=x86-64 -lnuma 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 -O3 -march=znver1 ryzen3800x4200 -O3 -march=znver2 12K 24K 36K 48K 60K SE +/- 455.36, N = 3 SE +/- 114.46, N = 3 SE +/- 647.09, N = 3 51757 54956 56652 -march=znver1 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -march=znver2 1. (CC) gcc options: -pthread -O3 -lm
x264 This is a simple test of the x264 encoder run on the CPU (OpenCL support disabled) with a sample video file. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding ryzen3800x4200 -O3 -march=znver2 -O3 -march=znver1 -O3 -march=x86-64 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.93, N = 3 SE +/- 0.82, N = 3 SE +/- 0.64, N = 3 101.97 140.96 141.82 143.27 -march=znver2 -march=znver1 -march=x86-64 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
FFTW FFTW is a C subroutine library for computing the discrete Fourier transform (DFT) in one or more dimensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver2 -O3 -march=znver1 2K 4K 6K 8K 10K SE +/- 2.07, N = 3 SE +/- 11.52, N = 3 SE +/- 123.02, N = 3 SE +/- 53.59, N = 3 8510.60 9534.70 11231.00 11448.00 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -march=znver2 -march=znver1 1. (CC) gcc options: -pthread -O3 -lm
Bullet Physics Engine This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Raytests ryzen3800x4200 -O3 -march=znver1 -O3 -march=x86-64 -O3 -march=znver2 0.4848 0.9696 1.4544 1.9392 2.424 SE +/- 0.000756, N = 3 SE +/- 0.018779, N = 3 SE +/- 0.020748, N = 3 SE +/- 0.002581, N = 3 2.154750 2.130000 2.090000 2.060000 -march=znver1 -march=x86-64 -march=znver2 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
TSCP This is a performance test of TSCP, Tom Kerrigan's Simple Chess Program, which has a built-in performance benchmark. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance ryzen3800x4200 -O3 -march=znver2 -O3 -march=x86-64 -O3 -march=znver1 300K 600K 900K 1200K 1500K SE +/- 1439.32, N = 5 SE +/- 8868.66, N = 5 SE +/- 10274.76, N = 5 SE +/- 1369.78, N = 5 1271423 1321681 1333926 1372148 -march=znver2 -march=x86-64 -march=znver1 1. (CC) gcc options: -O3 -march=native
Bullet Physics Engine This is a benchmark of the Bullet Physics Engine. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 136 Ragdolls ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 0.5016 1.0032 1.5048 2.0064 2.508 SE +/- 0.000665, N = 3 SE +/- 0.029906, N = 3 SE +/- 0.015833, N = 3 SE +/- 0.003680, N = 3 2.229157 2.170000 2.130000 2.050000 -march=x86-64 -march=znver1 -march=znver2 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Convex ryzen3800x4200 -O3 -march=znver1 -O3 -march=x86-64 -O3 -march=znver2 0.8691 1.7382 2.6073 3.4764 4.3455 SE +/- 0.000795, N = 3 SE +/- 0.032731, N = 3 SE +/- 0.037882, N = 3 SE +/- 0.007030, N = 3 3.862570 3.730000 3.700000 3.590000 -march=znver1 -march=x86-64 -march=znver2 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Stack ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 0.9426 1.8852 2.8278 3.7704 4.713 SE +/- 0.002805, N = 3 SE +/- 0.041553, N = 3 SE +/- 0.033405, N = 3 SE +/- 0.004049, N = 3 4.189241 4.080000 3.980000 3.790000 -march=x86-64 -march=znver1 -march=znver2 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 3000 Fall ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 0.7896 1.5792 2.3688 3.1584 3.948 SE +/- 0.003247, N = 3 SE +/- 0.035000, N = 3 SE +/- 0.026494, N = 3 SE +/- 0.007900, N = 3 3.509403 3.370000 3.360000 3.230000 -march=x86-64 -march=znver1 -march=znver2 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
SciMark This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 500 1000 1500 2000 2500 SE +/- 0.10, N = 3 SE +/- 20.09, N = 3 SE +/- 0.13, N = 3 SE +/- 0.28, N = 3 1259.58 2145.57 2291.62 2422.10 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization ryzen3800x4200 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 2K 4K 6K 8K 10K SE +/- 4.26, N = 3 SE +/- 73.09, N = 3 SE +/- 25.99, N = 3 SE +/- 10.78, N = 3 607.72 6959.69 8631.93 11431.93 -O3 -march=x86-64 -O3 -march=znver1 -O3 -march=znver2 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply ryzen3800x4200 -O3 -march=znver2 -O3 -march=znver1 -O3 -march=x86-64 800 1600 2400 3200 4000 SE +/- 10.72, N = 3 SE +/- 48.59, N = 3 SE +/- 48.59, N = 3 SE +/- 48.28, N = 3 750.46 3575.96 3702.03 3762.43 -O3 -march=znver2 -O3 -march=znver1 -O3 -march=x86-64 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 ryzen3800x4200 70 140 210 280 350 SE +/- 0.04, N = 3 SE +/- 0.15, N = 3 SE +/- 3.16, N = 3 SE +/- 0.10, N = 3 260.12 274.11 297.13 323.04 -O3 -march=znver1 -O3 -march=znver2 -O3 -march=x86-64 1. (CC) gcc options: -lm
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo ryzen3800x4200 -O3 -march=znver1 -O3 -march=x86-64 -O3 -march=znver2 200 400 600 800 1000 SE +/- 0.10, N = 3 SE +/- 0.16, N = 3 SE +/- 7.83, N = 3 SE +/- 1.53, N = 3 153.28 757.56 766.81 799.07 -O3 -march=znver1 -O3 -march=x86-64 -O3 -march=znver2 1. (CC) gcc options: -lm
-O3 -march=x86-64 Environment Notes: CXXFLAGS=-O3-march=x86-64 CFLAGS=-O3-march=x86-64Compiler Notes: --disable-multilib --enable-checking=releaseProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled
Testing initiated at 10 July 2019 20:33 by user phoronix.
-O3 -march=znver1 Environment Notes: CXXFLAGS=-O3-march=znver1 CFLAGS=-O3-march=znver1Compiler Notes: --disable-multilib --enable-checking=releaseProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled
Testing initiated at 7 July 2019 19:57 by user phoronix.
-O3 -march=znver2 Processor: AMD Ryzen 9 3900X 12-Core @ 3.80GHz (12 Cores / 24 Threads), Motherboard: ASUS ROG CROSSHAIR VIII HERO (WI-FI) (0066 BIOS), Chipset: AMD Device 1480, Memory: 16384MB, Disk: 2000GB Force MP600, Graphics: Sapphire AMD Baffin [Polaris11] 4GB (1300/1750MHz), Audio: AMD Device aae0, Monitor: ASUS VP28U, Network: Realtek Device 8125 + Intel I211 + Intel Device 2723
OS: Ubuntu 18.04, Kernel: 5.2.0-999-generic (x86_64) 20190703, Desktop: GNOME Shell 3.28.3, Display Server: X Server 1.20.1, Display Driver: modesetting 1.20.1, OpenGL: 4.5 Mesa 18.2.2 (LLVM 7.0.0), Compiler: GCC 9.1.0, File-System: ext4, Screen Resolution: 3840x2160
Environment Notes: CXXFLAGS=-O3-march=znver2 CFLAGS=-O3-march=znver2Compiler Notes: --disable-multilib --enable-checking=releaseProcessor Notes: Scaling Governor: acpi-cpufreq ondemandPython Notes: Python 2.7.15+ + Python 3.6.8Security Notes: l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Vulnerable + spectre_v1: Mitigation of __user pointer sanitization + spectre_v2: Vulnerable IBPB: disabled STIBP: disabled
Testing initiated at 7 July 2019 17:17 by user phoronix.
ryzen3800x4200 Processor: AMD Ryzen 7 3800X 8-Core @ 4.20GHz (8 Cores / 16 Threads), Motherboard: ASUS TUF GAMING X570-PLUS_BR (1405 BIOS), Chipset: AMD Starship/Matisse, Memory: 16GB, Disk: 480GB Force MP510 + 320GB SAMSUNG HD322HJ, Graphics: NVIDIA GeForce GTX 960 2GB (1126/3505MHz), Audio: NVIDIA GM206 HD Audio, Network: Realtek RTL8111/8168/8411 + Broadcom BCM4360 802.11ac
OS: Ubuntu 20.04, Kernel: 5.4.0-18-generic (x86_64), Desktop: MATE 1.24.0, Display Server: X Server 1.20.7, Display Driver: NVIDIA 435.21, OpenGL: 4.6.0, Compiler: GCC 9.3.0, File-System: ext4, Screen Resolution: 1920x1080
Compiler 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: acpi-cpufreq performance - CPU Microcode: 0x8701013Python Notes: + Python 3.8.2Security Notes: itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
Testing initiated at 23 March 2020 03:31 by user monster.