AMD EPYC compiler benchmarks for a future article on Phoronix.com.
GCC 8.2 RC1: -O2 Environment Notes: CXXFLAGS=-O2 CFLAGS=-O2Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
GCC 8.2 RC1: -O3 Environment Notes: CXXFLAGS=-O3 CFLAGS=-O3Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
GCC 8.2 RC1: -O3 -march=native Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
GCC 8.2 RC1: -O3 -march=native - PGO Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: ASPEED ASPEED Family, Monitor: VE228, Network: Broadcom Limited NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.16.0-041600-generic (x86_64), Compiler: GCC 8.1.1 20180720, File-System: ext4, Screen Resolution: 1920x1080
GCC 9.0 SVN: -O2 Environment Notes: CXXFLAGS=-O2 CFLAGS=-O2Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
GCC 9.0 SVN: -O3 Environment Notes: CXXFLAGS=-O3 CFLAGS=-O3Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
GCC 9.0 SVN: -O3 -march=native Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
GCC 9.0 SVN: -O3 -march=native - PGO OS: Ubuntu 18.10, Kernel: 4.16.0-041600-generic (x86_64), Compiler: GCC 9.0.0 20180720, File-System: ext4, Screen Resolution: 1920x1080
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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo PGO -O3 -march=native -O3 -O3 -march=native -O2 120 240 360 480 600 SE +/- 0.33, N = 3 SE +/- 9.75, N = 3 SE +/- 0.02, N = 3 SE +/- 0.53, N = 3 SE +/- 0.25, N = 3 SE +/- 0.10, N = 3 SE +/- 0.12, N = 3 SE +/- 0.01, N = 3 213.95 552.08 556.37 561.29 213.98 556.37 561.79 561.85 1. (CC) gcc options: -lm
C-Ray GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time -O2 -O3 -O3 -march=native PGO -O3 -march=native 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 6.02 2.83 2.52 2.50 6.00 2.84 2.52 2.51 1. (CC) gcc options: -lm -lpthread -O3
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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation -O2 -O3 PGO -O3 -march=native -O3 -march=native 400 800 1200 1600 2000 SE +/- 0.02, N = 3 SE +/- 0.17, N = 3 SE +/- 0.23, N = 3 SE +/- 0.72, N = 3 SE +/- 0.07, N = 3 SE +/- 0.16, N = 3 SE +/- 0.26, N = 3 SE +/- 0.06, N = 3 918.96 1429.31 1674.99 1688.09 919.02 1429.81 1676.15 1687.64 1. (CC) gcc options: -lm
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization -O2 -O3 -O3 -march=native PGO -O3 -march=native 1000 2000 3000 4000 5000 SE +/- 3.21, N = 3 SE +/- 19.27, N = 3 SE +/- 25.52, N = 3 SE +/- 24.64, N = 3 SE +/- 14.02, N = 3 SE +/- 27.07, N = 3 SE +/- 20.82, N = 3 SE +/- 17.02, N = 3 3432.88 4723.98 4781.45 4845.49 3462.39 4683.55 4831.75 4865.24 1. (CC) gcc options: -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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 -O2 -O3 -O3 -march=native 4 8 12 16 20 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 14.28 11.00 10.50 14.05 11.13 10.51 1. (CC) gcc options: -lm
Smallpt GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples PGO -O3 -march=native -O3 -march=native -O2 -O3 0.9 1.8 2.7 3.6 4.5 SE +/- 0.21, N = 6 4 4 4 3 4 4 4 3 1. (CXX) g++ options: -fopenmp
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.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite -O2 PGO -O3 -march=native -O3 -O3 -march=native 400 800 1200 1600 2000 SE +/- 3.37, N = 3 SE +/- 5.53, N = 3 SE +/- 3.46, N = 3 SE +/- 5.96, N = 3 SE +/- 2.46, N = 3 SE +/- 5.95, N = 3 SE +/- 4.50, N = 3 SE +/- 4.00, N = 3 1464.06 1874.09 1877.54 1943.30 1499.96 1870.83 1877.03 1940.65 1. (CC) gcc options: -lm
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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 1024 -O2 -O3 -O3 -march=native 2K 4K 6K 8K 10K SE +/- 176.56, N = 6 SE +/- 10.71, N = 3 SE +/- 1.83, N = 3 SE +/- 8.90, N = 3 SE +/- 1.72, N = 3 SE +/- 18.71, N = 3 6852.40 7168.63 8506.83 7176.77 7194.37 8518.67 1. (CC) gcc options: -pthread -lm
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.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver PGO -O3 -march=native -O3 -march=native -O3 -O2 200 400 600 800 1000 SE +/- 0.73, N = 3 SE +/- 0.78, N = 3 SE +/- 2.17, N = 3 SE +/- 1.94, N = 3 SE +/- 0.64, N = 3 SE +/- 5.36, N = 3 SE +/- 4.57, N = 3 SE +/- 0.47, N = 3 852.63 982.67 998.89 1014.66 869.07 993.22 1007.74 1014.38 1. (CC) gcc options: -O3 -mavx2
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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 1024 -O3 -O2 -O3 -march=native 1400 2800 4200 5600 7000 SE +/- 173.00, N = 6 SE +/- 57.48, N = 3 SE +/- 16.29, N = 3 SE +/- 4.95, N = 3 SE +/- 3.18, N = 3 SE +/- 73.40, N = 3 5601.00 5775.23 6531.37 5796.33 5835.90 6557.83 1. (CC) gcc options: -pthread -lm
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: GET -O2 -O3 -march=native -O3 400K 800K 1200K 1600K 2000K SE +/- 7906.34, N = 3 SE +/- 25099.79, N = 6 SE +/- 40793.79, N = 6 SE +/- 40550.88, N = 6 SE +/- 37527.46, N = 6 SE +/- 34086.99, N = 6 1580690.66 1586367.58 1682310.23 1612387.56 1691908.00 1813896.31 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
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.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply -O2 PGO -O3 -march=native -O3 -march=native -O3 500 1000 1500 2000 2500 SE +/- 2.57, N = 3 SE +/- 10.35, N = 3 SE +/- 11.03, N = 3 SE +/- 1.01, N = 3 SE +/- 14.14, N = 3 SE +/- 7.59, N = 3 SE +/- 13.99, N = 3 SE +/- 11.52, N = 3 2156.61 2413.24 2421.38 2473.98 2365.87 2400.46 2458.23 2458.50 1. (CC) gcc options: -lm
Sockperf This is a network socket API performance benchmark. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Under Load -O3 -O3 -march=native -O2 5 10 15 20 25 SE +/- 2.62, N = 10 SE +/- 0.24, N = 8 SE +/- 0.42, N = 10 SE +/- 0.30, N = 10 SE +/- 0.31, N = 10 SE +/- 0.09, N = 5 22.43 19.88 19.75 19.75 19.67 19.59 1. (CXX) g++ options: --param -rdynamic -ldl -lpthread
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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time -O2 -O3 -O3 -march=native PGO -O3 -march=native 12 24 36 48 60 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.16, N = 3 SE +/- 0.00, N = 3 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 SE +/- 0.20, N = 3 55.52 53.03 50.72 48.51 55.52 52.60 50.80 49.05 1. (CC) gcc options: -lm -O3
Zstd Compression This test measures the time needed to compress a sample file (an Ubuntu file-system image) using Zstd compression. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 -O3 -O2 -O3 -march=native PGO -O3 -march=native 40 80 120 160 200 SE +/- 0.51, N = 3 SE +/- 0.46, N = 3 SE +/- 1.43, N = 3 SE +/- 0.24, N = 3 SE +/- 0.68, N = 3 SE +/- 0.62, N = 3 SE +/- 0.54, N = 3 168.20 168.14 156.58 147.78 166.70 166.12 155.64 1. (CC) gcc options: -pthread -lz -llzma
PolyBench-C PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: 3 Matrix Multiplications -O2 -O3 -march=native -O3 PGO -O3 -march=native 0.828 1.656 2.484 3.312 4.14 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 3.68 3.66 3.63 3.30 3.62 3.59 3.58 3.35 1. (CC) gcc options: -O3 -march=native
TTSIOD 3D Renderer A portable GPL 3D software renderer that supports OpenMP and Intel Threading Building Blocks with many different rendering modes. This version does not use OpenGL but is entirely CPU/software based. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3a Phong Rendering With Soft-Shadow Mapping -O2 -O3 -march=native -O3 100 200 300 400 500 SE +/- 1.81, N = 3 SE +/- 1.94, N = 3 SE +/- 1.61, N = 3 400.36 439.54 441.58 -O2 -O3 -march=native -O3 1. (CXX) g++ options: -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++
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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time PGO -O3 -march=native -O2 -O3 -O3 -march=native 13M 26M 39M 52M 65M SE +/- 419233.35, N = 3 SE +/- 346634.55, N = 3 SE +/- 236832.99, N = 3 SE +/- 756265.41, N = 3 SE +/- 219692.26, N = 3 SE +/- 576746.80, N = 3 SE +/- 551889.61, N = 3 SE +/- 512120.63, N = 3 56149550 58372089 58412975 59201545 59007314 59730290 59837512 61080869 1. (CXX) g++ options: -m64 -lpthread -O3 -fno-exceptions -std=c++11 -pedantic -msse -msse3 -mpopcnt -flto
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SADD -O3 -march=native -O3 -O2 300K 600K 900K 1200K 1500K SE +/- 3767.82, N = 3 SE +/- 22572.62, N = 4 SE +/- 11436.45, N = 3 SE +/- 4081.67, N = 3 SE +/- 32509.56, N = 6 SE +/- 35661.81, N = 6 1423169.79 1477048.94 1542587.25 1430638.45 1500041.04 1517826.77 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
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.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance -O3 -march=native -O3 -O2 PGO -O3 -march=native 200K 400K 600K 800K 1000K SE +/- 766.17, N = 5 SE +/- 833.02, N = 5 SE +/- 1018.49, N = 5 SE +/- 421.22, N = 5 SE +/- 421.22, N = 5 SE +/- 595.69, N = 5 SE +/- 1116.56, N = 5 851019 851283 852597 919193 856576 856576 856577 916136 1. (CC) gcc options: -O3 -march=native
GraphicsMagick GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.28 Operation: Local Adaptive Thresholding -O2 -O3 -O3 -march=native 20 40 60 80 100 SE +/- 1.00, N = 3 SE +/- 0.33, N = 3 102 104 104 108 109 110 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: SET -O2 -O3 -march=native -O3 300K 600K 900K 1200K 1500K SE +/- 9618.90, N = 3 SE +/- 23587.86, N = 6 SE +/- 13759.71, N = 3 SE +/- 31380.33, N = 6 SE +/- 24024.35, N = 3 SE +/- 22403.96, N = 6 1278916.54 1332541.96 1375161.96 1284845.13 1291788.21 1319138.27 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: LPUSH -O3 -march=native -O2 -O3 300K 600K 900K 1200K 1500K SE +/- 18347.41, N = 6 SE +/- 21056.82, N = 3 SE +/- 2157.90, N = 3 SE +/- 18588.25, N = 4 SE +/- 12639.17, N = 3 SE +/- 17323.31, N = 6 1108304.54 1135840.67 1187656.29 1130545.22 1133637.46 1135535.00 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
GraphicsMagick GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.28 Operation: Sharpen -O2 -O3 -O3 -march=native 40 80 120 160 200 176 179 182 177 181 188 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
Redis Redis is an open-source data structure server. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Requests Per Second, More Is Better Redis 4.0.8 Test: LPOP -O2 -O3 -O3 -march=native 200K 400K 600K 800K 1000K SE +/- 8709.47, N = 3 SE +/- 19911.75, N = 3 SE +/- 21693.88, N = 3 SE +/- 4079.04, N = 3 SE +/- 2162.33, N = 3 SE +/- 15264.52, N = 3 1078502.41 1103652.21 1152018.46 1108268.08 1117326.83 1143259.50 1. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Single Thread - Mode: Read Write -O2 -O3 -march=native -O3 400 800 1200 1600 2000 SE +/- 7.20, N = 3 SE +/- 37.36, N = 3 SE +/- 39.87, N = 3 SE +/- 14.24, N = 3 SE +/- 30.23, N = 5 SE +/- 12.52, N = 3 1973.07 2015.18 2093.81 1991.71 2044.30 2071.78 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
GraphicsMagick GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.28 Operation: HWB Color Space -O2 -O3 -O3 -march=native 50 100 150 200 250 SE +/- 0.58, N = 3 197 201 201 199 202 209 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.28 Operation: Resizing -O3 -O2 -O3 -march=native 40 80 120 160 200 SE +/- 1.00, N = 3 SE +/- 0.88, N = 3 SE +/- 1.20, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 1.00, N = 3 175 181 185 176 179 180 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
GraphicsMagick GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.28 Operation: Blur -O2 -O3 -O3 -march=native 30 60 90 120 150 SE +/- 0.67, N = 3 146 148 149 147 148 154 1. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
ebizzy This is a test of ebizzy, a program to generate workloads resembling web server workloads. Learn more via the OpenBenchmarking.org test page.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 -O2 -O3 -O3 -march=native PGO -O3 -march=native 200K 400K 600K 800K 1000K SE +/- 16592.93, N = 4 SE +/- 20234.15, N = 6 SE +/- 18183.13, N = 4 SE +/- 28582.82, N = 6 SE +/- 14780.83, N = 3 SE +/- 23788.74, N = 6 SE +/- 17876.02, N = 3 SE +/- 4974.04, N = 3 1106391 1112448 1113356 1147009 1109148 1111662 1124222 1166998 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
Timed HMMer Search This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search -O3 -O3 -march=native -O2 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 7.74 7.63 7.40 7.71 7.65 7.56 1. (CC) gcc options: -pthread -lhmmer -lsquid -lm
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Convex -O3 -O2 -O3 -march=native 1.2443 2.4886 3.7329 4.9772 6.2215 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 5.53 5.49 5.29 5.52 5.51 5.32 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Crafty This is a performance test of Crafty, an advanced open-source chess engine. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time -O2 PGO -O3 -march=native -O3 -march=native -O3 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 9192.37, N = 3 SE +/- 2577.32, N = 3 SE +/- 13470.58, N = 3 SE +/- 2607.25, N = 3 SE +/- 13110.39, N = 3 SE +/- 8016.22, N = 3 SE +/- 5146.22, N = 3 SE +/- 11021.16, N = 3 5780824 5841423 5876297 5892825 5989207 6004700 6014866 6026655 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
PolyBench-C PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: Correlation Computation -O2 -O3 PGO -O3 -march=native -O3 -march=native 1.2488 2.4976 3.7464 4.9952 6.244 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 5.55 5.40 5.34 5.33 5.50 5.46 5.40 5.38 1. (CC) gcc options: -O3 -march=native
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.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC -O3 -march=native -O3 -O2 3 6 9 12 15 SE +/- 0.19, N = 5 SE +/- 0.12, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.09, N = 5 SE +/- 0.02, N = 5 12.63 12.27 12.15 12.44 12.22 12.13 1. (CXX) g++ options: -fvisibility=hidden -logg -lm
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.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test PGO -O3 -march=native -O3 -march=native -O3 -O2 20K 40K 60K 80K 100K SE +/- 1357.08, N = 3 SE +/- 465.88, N = 3 SE +/- 935.09, N = 3 SE +/- 926.79, N = 3 SE +/- 586.49, N = 3 SE +/- 771.81, N = 3 SE +/- 555.15, N = 3 SE +/- 715.28, N = 3 96774 97385 97663 98423 97917 98480 99762 100684 1. (CXX) g++ options: -pipe -lpthread
PolyBench-C PolyBench-C is a C-language polyhedral benchmark suite made at the Ohio State University. Learn more via the OpenBenchmarking.org test page.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: Covariance Computation -O2 -O3 PGO -O3 -march=native -O3 -march=native 1.2443 2.4886 3.7329 4.9772 6.2215 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 5.53 5.42 5.39 5.34 5.50 5.49 5.41 5.37 1. (CC) gcc options: -O3 -march=native
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only -O3 -O2 -O3 -march=native 90K 180K 270K 360K 450K SE +/- 3629.20, N = 3 SE +/- 1546.59, N = 3 SE +/- 3319.69, N = 3 SE +/- 2225.51, N = 3 SE +/- 1716.32, N = 3 SE +/- 1289.79, N = 3 395454.61 397574.74 401369.61 396925.91 408599.13 408873.25 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. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.7.0 vpxenc PGO -O3 -march=native -O3 -O2 -O3 -march=native 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.14, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 12.07 12.21 12.31 12.37 12.29 12.36 12.38 12.43 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE
m-queens A solver for the N-queens problem with multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.1 Time To Solve PGO -O3 -march=native -O2 -O3 -O3 -march=native 8 16 24 32 40 SE +/- 0.19, N = 3 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.14, N = 3 SE +/- 0.16, N = 3 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 SE +/- 0.16, N = 3 32.44 32.22 32.09 32.02 32.31 31.64 31.59 31.56 1. (CXX) g++ options: -fopenmp -march=native -O2
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Single Thread - Mode: Read Only -O3 -O2 -O3 -march=native 3K 6K 9K 12K 15K SE +/- 266.50, N = 3 SE +/- 215.85, N = 3 SE +/- 113.33, N = 3 SE +/- 140.09, N = 3 SE +/- 72.75, N = 3 SE +/- 152.49, N = 3 13985.70 14037.15 14374.13 14004.08 14101.79 14307.54 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Raytests -O3 -O2 -O3 -march=native 0.7155 1.431 2.1465 2.862 3.5775 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.18 3.17 3.11 3.17 3.17 3.12 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Apache Benchmark This is a test of ab, which is the Apache benchmark program. This test profile measures how many requests per second a given system can sustain when carrying out 1,000,000 requests with 100 requests being carried out concurrently. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving -O3 -march=native -O3 -O2 3K 6K 9K 12K 15K SE +/- 89.48, N = 3 SE +/- 80.25, N = 3 SE +/- 74.41, N = 3 SE +/- 188.72, N = 3 SE +/- 132.55, N = 3 SE +/- 193.23, N = 3 15856.03 15943.49 16065.26 15891.72 15972.59 16205.32 1. (CC) gcc options: -shared -fPIC -pthread
SQLite This is a simple benchmark of SQLite. At present this test profile just measures the time to perform a pre-defined number of insertions on an indexed database. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.22 Timed SQLite Insertions -O3 -march=native -O3 -O2 0.6503 1.3006 1.9509 2.6012 3.2515 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 2.89 2.86 2.85 2.89 2.88 2.87 1. (CC) gcc options: -lz -ldl -lpthread
PostgreSQL pgbench This is a simple benchmark of PostgreSQL using pgbench. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 10.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write -O3 -O3 -march=native -O2 8K 16K 24K 32K 40K SE +/- 193.85, N = 3 SE +/- 66.03, N = 3 SE +/- 96.17, N = 3 SE +/- 133.09, N = 3 SE +/- 81.46, N = 3 SE +/- 62.00, N = 3 36081.57 36115.94 36232.44 36226.69 36248.65 36523.78 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
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.
GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform PGO -O3 -march=native -O3 -march=native -O2 -O3 50 100 150 200 250 SE +/- 0.05, N = 3 SE +/- 0.10, N = 3 SE +/- 0.20, N = 3 SE +/- 0.09, N = 3 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 219.09 219.38 220.52 221.30 219.09 219.24 220.80 221.28 1. (CC) gcc options: -lm
Tinymembench GCC 8.2 RC1 GCC 9.0 SVN OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset PGO -O3 -march=native -O2 -O3 -march=native -O3 2K 4K 6K 8K 10K 9975.20 9978.60 10037.70 10063.10 9982.80 9982.90 9989.40 10039.70 1. (CC) gcc options: -O2 -lm
OpenSSL OpenSSL is an open-source toolkit that implements SSL (Secure Sockets Layer) and TLS (Transport Layer Security) protocols. This test measures the RSA 4096-bit performance of OpenSSL. Learn more via the OpenBenchmarking.org test page.
GCC 9.0 SVN GCC 8.2 RC1 OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.0f RSA 4096-bit Performance -O3 -O2 -O3 -march=native PGO -O3 -march=native 1000 2000 3000 4000 5000 SE +/- 23.64, N = 3 SE +/- 22.12, N = 3 SE +/- 23.13, N = 3 SE +/- 19.76, N = 3 SE +/- 24.30, N = 3 SE +/- 22.71, N = 3 SE +/- 21.56, N = 3 SE +/- 23.93, N = 3 4602.30 4612.20 4616.47 4623.60 4609.30 4609.73 4610.63 4617.23 1. (CC) gcc options: -O3 -pthread -m64 -lcrypto -ldl
GCC 8.2 RC1: -O2 Environment Notes: CXXFLAGS=-O2 CFLAGS=-O2Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 21 July 2018 11:29 by user phoronix.
GCC 8.2 RC1: -O3 Environment Notes: CXXFLAGS=-O3 CFLAGS=-O3Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 20 July 2018 18:42 by user phoronix.
GCC 8.2 RC1: -O3 -march=native Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 20 July 2018 11:08 by user phoronix.
GCC 8.2 RC1: -O3 -march=native - PGO Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: ASPEED ASPEED Family, Monitor: VE228, Network: Broadcom Limited NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.16.0-041600-generic (x86_64), Compiler: GCC 8.1.1 20180720, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 20 July 2018 17:05 by user phoronix.
GCC 9.0 SVN: -O2 Environment Notes: CXXFLAGS=-O2 CFLAGS=-O2Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 21 July 2018 09:03 by user phoronix.
GCC 9.0 SVN: -O3 Environment Notes: CXXFLAGS=-O3 CFLAGS=-O3Compiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 21 July 2018 06:35 by user phoronix.
GCC 9.0 SVN: -O3 -march=native Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 20 July 2018 21:03 by user phoronix.
GCC 9.0 SVN: -O3 -march=native - PGO Processor: AMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads), Motherboard: TYAN B8026T70AE24HR (V1.02.B10 BIOS), Chipset: AMD Family 17h, Memory: 129024MB, Disk: 280GB INTEL SSDPE21D280GA, Graphics: ASPEED ASPEED Family, Monitor: VE228, Network: Broadcom Limited NetXtreme BCM5720 Gigabit PCIe
OS: Ubuntu 18.10, Kernel: 4.16.0-041600-generic (x86_64), Compiler: GCC 9.0.0 20180720, File-System: ext4, Screen Resolution: 1920x1080
Environment Notes: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Notes: --disable-multilib --enable-checking=releaseDisk Notes: NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Notes: Scaling Governor: acpi-cpufreq ondemandSecurity Notes: __user pointer sanitization + Full AMD retpoline IBPB Protection
Testing initiated at 21 July 2018 01:40 by user phoronix.