AMD EPYC Compiler Testing GCC 9.0 SVN With PGO

AMD EPYC compiler benchmarks for a future article on Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1807235-RA-GCCPGOEPY35&sro.

ProcessorMotherboardChipsetMemoryDiskGraphicsMonitorNetworkOSKernelCompilerFile-SystemScreen ResolutionGCC 8.2 RC1GCC 9.0 SVN -O2 -O3 -O3 native -O3 native + PGO -O2 -O3 -O3 native -O3 native + PGOAMD EPYC 7601 32-Core @ 2.20GHz (32 Cores / 64 Threads)TYAN B8026T70AE24HR (V1.02.B10 BIOS)AMD Family 17h129024MB280GB INTEL SSDPE21D280GAASPEED ASPEED FamilyVE228Broadcom Limited NetXtreme BCM5720 Gigabit PCIeUbuntu 18.104.16.0-041600-generic (x86_64)GCC 8.1.1 20180720ext41920x1080GCC 9.0.0 20180720OpenBenchmarking.orgEnvironment Details- GCC 8.2 RC1: -O2: CXXFLAGS=-O2 CFLAGS=-O2- GCC 8.2 RC1: -O3: CXXFLAGS=-O3 CFLAGS=-O3- GCC 8.2 RC1: -O3 native: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- GCC 8.2 RC1: -O3 native + PGO: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- GCC 9.0 SVN: -O2: CXXFLAGS=-O2 CFLAGS=-O2- GCC 9.0 SVN: -O3: CXXFLAGS=-O3 CFLAGS=-O3- GCC 9.0 SVN: -O3 native: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=native- GCC 9.0 SVN: -O3 native + PGO: CXXFLAGS=-O3-march=native CFLAGS=-O3-march=nativeCompiler Details- --disable-multilib --enable-checking=releaseDisk Details- NONE / data=ordered,errors=remount-ro,relatime,rwProcessor Details- Scaling Governor: acpi-cpufreq ondemandSecurity Details- __user pointer sanitization + Full AMD retpoline IBPB Protection

scimark2: Compositescimark2: Fast Fourier Transformscimark2: Jacobi Successive Over-Relaxationscimark2: Monte Carloscimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationvpxenc: vpxencfftw: Stock - 1D FFT Size 1024fftw: Stock - 2D FFT Size 1024polybench-c: 3 Matrix Multiplicationspolybench-c: Correlation Computationpolybench-c: Covariance Computationsqlite: Timed SQLite Insertionsopenssl: RSA 4096-bit Performanceaobench: 2048 x 2048 - Total Timecompress-7zip: Compress Speed Testcompress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19m-queens: Time To Solvec-ray: Total Timecrafty: Elapsed Timesmallpt: Global Illumination Renderer; 100 Samplesstockfish: Total Timetscp: AI Chess Performanceredis: SETredis: GETredis: LPUSHredis: LPOPredis: SADDpgbench: Buffer Test - Single Thread - Read Writepgbench: Buffer Test - Single Thread - Read Onlypgbench: Buffer Test - Normal Load - Read Writepgbench: Buffer Test - Normal Load - Read Onlytjbench: Decompression Throughputapache: Static Web Page Servingencode-mp3: WAV To MP3encode-flac: WAV To FLACebizzy: graphics-magick: HWB Color Spacegraphics-magick: Blurgraphics-magick: Local Adaptive Thresholdinggraphics-magick: Resizinggraphics-magick: Sharpenhmmer: Pfam Database Searchbullet: 3000 Fallbullet: 1000 Stackbullet: 136 Ragdollsbullet: 1000 Convexbullet: Prim Trimeshbullet: Convex Trimeshbullet: Rayteststtsiod-renderer: Phong Rendering With Soft-Shadow Mappinghimeno: Poisson Pressure Solvertinymembench: Standard Memcpysockperf: Latency Under Loadsockperf: Latency Ping PongGCC 8.2 RC1GCC 9.0 SVN -O2 -O3 -O3 native -O3 native + PGO -O2 -O3 -O3 native -O3 native + PGO1464.06220.52919.02561.792156.613462.3912.437194.375796.333.625.555.532.874609.3055.5298480166.1232.226.0060047004590073148525971278916.541612387.561135840.671117326.831500041.041991.7114037.1536523.78396925.91141.4315972.5914.0512.1511063912021481091811817.565.066.003.145.511.121.363.17400.361014.6612359.3019.596.661874.09221.301429.81561.852473.984683.5512.367176.775835.903.595.405.392.884609.7352.6097917166.7032.092.8459892074598375128512831332541.961813896.311187656.291143259.501517826.772044.3013985.7036248.65408599.13141.7415891.7211.1312.2711133561991471081751777.715.066.023.145.521.121.363.18441.58998.8912555.7019.676.761943.30219.381687.64556.372421.384831.7512.388518.676557.833.585.345.342.894610.6350.80100684155.6432.022.5260148664597302908510191375161.961691908.001108304.541108268.081430638.452071.7814374.1336226.69408873.25142.1816205.3210.5112.6311470092091541101851887.655.025.793.095.321.131.333.11439.54982.6712497.2019.756.421877.54219.091676.15213.982413.244865.2412.293.355.335.424617.2349.059976232.442.5160266553610808699191931112448852.6312453.201499.96220.80918.96561.292365.873432.8812.316852.405775.233.685.505.502.864612.2055.5298423168.1431.596.0257808244583720898565761319138.271580690.661130545.221078502.411542587.251973.0714101.7936232.44397574.74141.1815943.4914.2812.2211242221971461021761767.405.065.993.135.491.121.363.171014.3812422.9019.756.531877.03221.281429.31552.082458.504723.9812.217168.635601.003.635.465.492.854602.3053.0397663168.2031.642.8358928253584129758565771291788.211682310.231135535.001103652.211477048.942093.8114004.0836081.57395454.61137.8216065.2611.0012.1311091482011481041791797.745.166.013.225.531.121.363.17993.221249022.436.571940.65219.091688.09556.372458.234781.4512.378506.836531.373.665.385.412.894616.4750.7297385156.5831.562.5258762974592015458565761284845.131586367.581133637.461152018.461423169.792015.1814307.5436115.94401369.61145.6615856.0310.5012.4411116622011491041801827.635.045.783.085.291.131.333.121007.7412377.6019.881870.83219.241674.99213.952400.464845.4912.073.305.405.374623.6048.5196774147.7832.312.5058414234561495509161361166998869.0712300.60OpenBenchmarking.org

SciMark

Computational Test: Composite

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Composite-O2-O3-O3 native-O3 native + PGO400800120016002000SE +/- 3.37, N = 3SE +/- 5.53, N = 3SE +/- 5.96, N = 3SE +/- 3.46, N = 3SE +/- 2.46, N = 3SE +/- 4.50, N = 3SE +/- 4.00, N = 3SE +/- 5.95, N = 31464.061874.091943.301877.541499.961877.031940.651870.831. (CC) gcc options: -lm

SciMark

Computational Test: Fast Fourier Transform

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform-O2-O3-O3 native-O3 native + PGO50100150200250SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.10, N = 3SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.13, N = 3220.52221.30219.38219.09220.80221.28219.09219.241. (CC) gcc options: -lm

SciMark

Computational Test: Jacobi Successive Over-Relaxation

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxation-O2-O3-O3 native-O3 native + PGO400800120016002000SE +/- 0.07, N = 3SE +/- 0.16, N = 3SE +/- 0.06, N = 3SE +/- 0.26, N = 3SE +/- 0.02, N = 3SE +/- 0.17, N = 3SE +/- 0.72, N = 3SE +/- 0.23, N = 3919.021429.811687.641676.15918.961429.311688.091674.991. (CC) gcc options: -lm

SciMark

Computational Test: Monte Carlo

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlo-O2-O3-O3 native-O3 native + PGO120240360480600SE +/- 0.12, N = 3SE +/- 0.01, N = 3SE +/- 0.10, N = 3SE +/- 0.25, N = 3SE +/- 0.53, N = 3SE +/- 9.75, N = 3SE +/- 0.02, N = 3SE +/- 0.33, N = 3561.79561.85556.37213.98561.29552.08556.37213.951. (CC) gcc options: -lm

SciMark

Computational Test: Sparse Matrix Multiply

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiply-O2-O3-O3 native-O3 native + PGO5001000150020002500SE +/- 2.57, N = 3SE +/- 1.01, N = 3SE +/- 11.03, N = 3SE +/- 10.35, N = 3SE +/- 14.14, N = 3SE +/- 11.52, N = 3SE +/- 13.99, N = 3SE +/- 7.59, N = 32156.612473.982421.382413.242365.872458.502458.232400.461. (CC) gcc options: -lm

SciMark

Computational Test: Dense LU Matrix Factorization

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorization-O2-O3-O3 native-O3 native + PGO10002000300040005000SE +/- 14.02, N = 3SE +/- 27.07, N = 3SE +/- 20.82, N = 3SE +/- 17.02, N = 3SE +/- 3.21, N = 3SE +/- 19.27, N = 3SE +/- 25.52, N = 3SE +/- 24.64, N = 33462.394683.554831.754865.243432.884723.984781.454845.491. (CC) gcc options: -lm

VP9 libvpx Encoding

vpxenc

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgFrames Per Second, More Is BetterVP9 libvpx Encoding 1.7.0vpxenc-O2-O3-O3 native-O3 native + PGO3691215SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.02, N = 3SE +/- 0.05, N = 3SE +/- 0.06, N = 3SE +/- 0.14, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 312.4312.3612.3812.2912.3112.2112.3712.071. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE

FFTW

Build: Stock - Size: 1D FFT Size 1024

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 1D FFT Size 1024-O2-O3-O3 native2K4K6K8K10KSE +/- 1.72, N = 3SE +/- 8.90, N = 3SE +/- 18.71, N = 3SE +/- 176.56, N = 6SE +/- 10.71, N = 3SE +/- 1.83, N = 37194.377176.778518.676852.407168.638506.831. (CC) gcc options: -pthread -lm

FFTW

Build: Stock - Size: 2D FFT Size 1024

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.6Build: Stock - Size: 2D FFT Size 1024-O2-O3-O3 native14002800420056007000SE +/- 4.95, N = 3SE +/- 3.18, N = 3SE +/- 73.40, N = 3SE +/- 57.48, N = 3SE +/- 173.00, N = 6SE +/- 16.29, N = 35796.335835.906557.835775.235601.006531.371. (CC) gcc options: -pthread -lm

PolyBench-C

Test: 3 Matrix Multiplications

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: 3 Matrix Multiplications-O2-O3-O3 native-O3 native + PGO0.8281.6562.4843.3124.14SE +/- 0.05, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 33.623.593.583.353.683.633.663.301. (CC) gcc options: -O3 -march=native

PolyBench-C

Test: Correlation Computation

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: Correlation Computation-O2-O3-O3 native-O3 native + PGO1.24882.49763.74644.99526.244SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.04, N = 3SE +/- 0.02, N = 3SE +/- 0.00, N = 35.555.405.345.335.505.465.385.401. (CC) gcc options: -O3 -march=native

PolyBench-C

Test: Covariance Computation

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterPolyBench-C 4.2Test: Covariance Computation-O2-O3-O3 native-O3 native + PGO1.24432.48863.73294.97726.2215SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 35.535.395.345.425.505.495.415.371. (CC) gcc options: -O3 -march=native

SQLite

Timed SQLite Insertions

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterSQLite 3.22Timed SQLite Insertions-O2-O3-O3 native0.65031.30061.95092.60123.2515SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 3SE +/- 0.03, N = 3SE +/- 0.01, N = 32.872.882.892.862.852.891. (CC) gcc options: -lz -ldl -lpthread

OpenSSL

RSA 4096-bit Performance

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.1.0fRSA 4096-bit Performance-O2-O3-O3 native-O3 native + PGO10002000300040005000SE +/- 24.30, N = 3SE +/- 22.71, N = 3SE +/- 21.56, N = 3SE +/- 23.93, N = 3SE +/- 22.12, N = 3SE +/- 23.64, N = 3SE +/- 23.13, N = 3SE +/- 19.76, N = 34609.304609.734610.634617.234612.204602.304616.474623.601. (CC) gcc options: -O3 -pthread -m64 -lcrypto -ldl

AOBench

Size: 2048 x 2048 - Total Time

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterAOBenchSize: 2048 x 2048 - Total Time-O2-O3-O3 native-O3 native + PGO1224364860SE +/- 0.00, N = 3SE +/- 0.07, N = 3SE +/- 0.01, N = 3SE +/- 0.20, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.16, N = 355.5252.6050.8049.0555.5253.0350.7248.511. (CC) gcc options: -lm -O3

7-Zip Compression

Compress Speed Test

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 16.02Compress Speed Test-O2-O3-O3 native-O3 native + PGO20K40K60K80K100KSE +/- 771.81, N = 3SE +/- 586.49, N = 3SE +/- 715.28, N = 3SE +/- 555.15, N = 3SE +/- 926.79, N = 3SE +/- 935.09, N = 3SE +/- 465.88, N = 3SE +/- 1357.08, N = 3984809791710068499762984239766397385967741. (CXX) g++ options: -pipe -lpthread

Zstd Compression

Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterZstd Compression 1.3.4Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19-O2-O3-O3 native-O3 native + PGO4080120160200SE +/- 0.62, N = 3SE +/- 0.68, N = 3SE +/- 0.54, N = 3SE +/- 0.46, N = 3SE +/- 0.51, N = 3SE +/- 1.43, N = 3SE +/- 0.24, N = 3166.12166.70155.64168.14168.20156.58147.781. (CC) gcc options: -pthread -lz -llzma

m-queens

Time To Solve

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is Betterm-queens 1.1Time To Solve-O2-O3-O3 native-O3 native + PGO816243240SE +/- 0.09, N = 3SE +/- 0.14, N = 3SE +/- 0.14, N = 3SE +/- 0.19, N = 3SE +/- 0.15, N = 3SE +/- 0.13, N = 3SE +/- 0.16, N = 3SE +/- 0.16, N = 332.2232.0932.0232.4431.5931.6431.5632.311. (CXX) g++ options: -fopenmp -O2 -march=native

C-Ray

Total Time

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time-O2-O3-O3 native-O3 native + PGO246810SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 36.002.842.522.516.022.832.522.501. (CC) gcc options: -lm -lpthread -O3

Crafty

Elapsed Time

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgNodes Per Second, More Is BetterCrafty 25.2Elapsed Time-O2-O3-O3 native-O3 native + PGO1.3M2.6M3.9M5.2M6.5MSE +/- 8016.22, N = 3SE +/- 13110.39, N = 3SE +/- 5146.22, N = 3SE +/- 11021.16, N = 3SE +/- 9192.37, N = 3SE +/- 2607.25, N = 3SE +/- 13470.58, N = 3SE +/- 2577.32, N = 3600470059892076014866602665557808245892825587629758414231. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm

Smallpt

Global Illumination Renderer; 100 Samples

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 Samples-O2-O3-O3 native-O3 native + PGO0.91.82.73.64.5SE +/- 0.21, N = 6444343441. (CXX) g++ options: -fopenmp

Stockfish

Total Time

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgNodes Per Second, More Is BetterStockfish 9Total Time-O2-O3-O3 native-O3 native + PGO13M26M39M52M65MSE +/- 219692.26, N = 3SE +/- 551889.61, N = 3SE +/- 576746.80, N = 3SE +/- 512120.63, N = 3SE +/- 346634.55, N = 3SE +/- 236832.99, N = 3SE +/- 756265.41, N = 3SE +/- 419233.35, N = 359007314598375125973029061080869583720895841297559201545561495501. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto

TSCP

AI Chess Performance

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performance-O2-O3-O3 native-O3 native + PGO200K400K600K800K1000KSE +/- 833.02, N = 5SE +/- 766.17, N = 5SE +/- 1018.49, N = 5SE +/- 421.22, N = 5SE +/- 595.69, N = 5SE +/- 421.22, N = 5SE +/- 1116.56, N = 58525978512838510199191938565768565778565769161361. (CC) gcc options: -O3 -march=native

Redis

Test: SET

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SET-O2-O3-O3 native300K600K900K1200K1500KSE +/- 9618.90, N = 3SE +/- 23587.86, N = 6SE +/- 13759.71, N = 3SE +/- 22403.96, N = 6SE +/- 24024.35, N = 3SE +/- 31380.33, N = 61278916.541332541.961375161.961319138.271291788.211284845.131. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: GET

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: GET-O2-O3-O3 native400K800K1200K1600K2000KSE +/- 40550.88, N = 6SE +/- 34086.99, N = 6SE +/- 37527.46, N = 6SE +/- 7906.34, N = 3SE +/- 40793.79, N = 6SE +/- 25099.79, N = 61612387.561813896.311691908.001580690.661682310.231586367.581. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: LPUSH

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPUSH-O2-O3-O3 native300K600K900K1200K1500KSE +/- 21056.82, N = 3SE +/- 2157.90, N = 3SE +/- 18347.41, N = 6SE +/- 18588.25, N = 4SE +/- 17323.31, N = 6SE +/- 12639.17, N = 31135840.671187656.291108304.541130545.221135535.001133637.461. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: LPOP

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: LPOP-O2-O3-O3 native200K400K600K800K1000KSE +/- 2162.33, N = 3SE +/- 15264.52, N = 3SE +/- 4079.04, N = 3SE +/- 8709.47, N = 3SE +/- 19911.75, N = 3SE +/- 21693.88, N = 31117326.831143259.501108268.081078502.411103652.211152018.461. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

Redis

Test: SADD

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgRequests Per Second, More Is BetterRedis 4.0.8Test: SADD-O2-O3-O3 native300K600K900K1200K1500KSE +/- 32509.56, N = 6SE +/- 35661.81, N = 6SE +/- 4081.67, N = 3SE +/- 11436.45, N = 3SE +/- 22572.62, N = 4SE +/- 3767.82, N = 31500041.041517826.771430638.451542587.251477048.941423169.791. (CC) gcc options: -ggdb -rdynamic -lm -ldl -pthread

PostgreSQL pgbench

Scaling: Buffer Test - Test: Single Thread - Mode: Read Write

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Write-O2-O3-O3 native400800120016002000SE +/- 14.24, N = 3SE +/- 30.23, N = 5SE +/- 12.52, N = 3SE +/- 7.20, N = 3SE +/- 39.87, N = 3SE +/- 37.36, N = 31991.712044.302071.781973.072093.812015.181. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

Scaling: Buffer Test - Test: Single Thread - Mode: Read Only

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Single Thread - Mode: Read Only-O2-O3-O3 native3K6K9K12K15KSE +/- 215.85, N = 3SE +/- 266.50, N = 3SE +/- 113.33, N = 3SE +/- 72.75, N = 3SE +/- 140.09, N = 3SE +/- 152.49, N = 314037.1513985.7014374.1314101.7914004.0814307.541. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Write

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Write-O2-O3-O3 native8K16K24K32K40KSE +/- 62.00, N = 3SE +/- 81.46, N = 3SE +/- 133.09, N = 3SE +/- 96.17, N = 3SE +/- 193.85, N = 3SE +/- 66.03, N = 336523.7836248.6536226.6936232.4436081.5736115.941. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

PostgreSQL pgbench

Scaling: Buffer Test - Test: Normal Load - Mode: Read Only

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgTPS, More Is BetterPostgreSQL pgbench 10.3Scaling: Buffer Test - Test: Normal Load - Mode: Read Only-O2-O3-O3 native90K180K270K360K450KSE +/- 2225.51, N = 3SE +/- 1716.32, N = 3SE +/- 1289.79, N = 3SE +/- 1546.59, N = 3SE +/- 3629.20, N = 3SE +/- 3319.69, N = 3396925.91408599.13408873.25397574.74395454.61401369.611. (CC) gcc options: -fno-strict-aliasing -fwrapv -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm

libjpeg-turbo tjbench

Test: Decompression Throughput

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMegapixels/sec, More Is Betterlibjpeg-turbo tjbench 1.5.3Test: Decompression Throughput-O2-O3-O3 native306090120150SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.01, N = 3SE +/- 0.03, N = 3SE +/- 1.71, N = 3SE +/- 0.05, N = 3141.43141.74142.18141.18137.82145.661. (CC) gcc options: -lm

Apache Benchmark

Static Web Page Serving

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.29Static Web Page Serving-O2-O3-O3 native3K6K9K12K15KSE +/- 132.55, N = 3SE +/- 188.72, N = 3SE +/- 193.23, N = 3SE +/- 80.25, N = 3SE +/- 74.41, N = 3SE +/- 89.48, N = 315972.5915891.7216205.3215943.4916065.2615856.031. (CC) gcc options: -shared -fPIC -pthread

LAME MP3 Encoding

WAV To MP3

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.100WAV To MP3-O2-O3-O3 native48121620SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 314.0511.1310.5114.2811.0010.501. (CC) gcc options: -lm

FLAC Audio Encoding

WAV To FLAC

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.2WAV To FLAC-O2-O3-O3 native3691215SE +/- 0.01, N = 5SE +/- 0.12, N = 5SE +/- 0.19, N = 5SE +/- 0.09, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 512.1512.2712.6312.2212.1312.441. (CXX) g++ options: -fvisibility=hidden -logg -lm

ebizzy

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgRecords/s, More Is Betterebizzy 0.3-O2-O3-O3 native-O3 native + PGO200K400K600K800K1000KSE +/- 16592.93, N = 4SE +/- 18183.13, N = 4SE +/- 28582.82, N = 6SE +/- 20234.15, N = 6SE +/- 17876.02, N = 3SE +/- 14780.83, N = 3SE +/- 23788.74, N = 6SE +/- 4974.04, N = 3110639111133561147009111244811242221109148111166211669981. (CC) gcc options: -pthread -lpthread -O3 -march=native

GraphicsMagick

Operation: HWB Color Space

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.28Operation: HWB Color Space-O2-O3-O3 native50100150200250SE +/- 0.58, N = 32021992091972012011. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Blur

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.28Operation: Blur-O2-O3-O3 native306090120150SE +/- 0.67, N = 31481471541461481491. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Local Adaptive Thresholding

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.28Operation: Local Adaptive Thresholding-O2-O3-O3 native20406080100SE +/- 1.00, N = 3SE +/- 0.33, N = 31091081101021041041. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Resizing

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.28Operation: Resizing-O2-O3-O3 native4080120160200SE +/- 0.88, N = 3SE +/- 1.00, N = 3SE +/- 1.20, N = 3SE +/- 0.58, N = 3SE +/- 0.33, N = 3SE +/- 1.00, N = 31811751851761791801. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

GraphicsMagick

Operation: Sharpen

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.28Operation: Sharpen-O2-O3-O3 native40801201602001811771881761791821. (CC) gcc options: -fopenmp -pthread -ljbig -lwebp -lwebpmux -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread

Timed HMMer Search

Pfam Database Search

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database Search-O2-O3-O3 native246810SE +/- 0.03, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.02, N = 3SE +/- 0.04, N = 3SE +/- 0.07, N = 37.567.717.657.407.747.631. (CC) gcc options: -pthread -lhmmer -lsquid -lm

Bullet Physics Engine

Test: 3000 Fall

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 3000 Fall-O2-O3-O3 native1.1612.3223.4834.6445.805SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 6SE +/- 0.05, N = 35.065.065.025.065.165.041. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Stack

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Stack-O2-O3-O3 native246810SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.02, N = 3SE +/- 0.02, N = 36.006.025.795.996.015.781. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 136 Ragdolls

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 136 Ragdolls-O2-O3-O3 native0.72451.4492.17352.8983.6225SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 33.143.143.093.133.223.081. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: 1000 Convex

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: 1000 Convex-O2-O3-O3 native1.24432.48863.73294.97726.2215SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.02, N = 35.515.525.325.495.535.291. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Prim Trimesh

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Prim Trimesh-O2-O3-O3 native0.25430.50860.76291.01721.2715SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.121.121.131.121.121.131. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Convex Trimesh

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Convex Trimesh-O2-O3-O3 native0.3060.6120.9181.2241.53SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.361.361.331.361.361.331. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

Bullet Physics Engine

Test: Raytests

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgSeconds, Fewer Is BetterBullet Physics Engine 2.81Test: Raytests-O2-O3-O3 native0.71551.4312.14652.8623.5775SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 33.173.183.113.173.173.121. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3aPhong Rendering With Soft-Shadow Mapping-O2-O3-O3 native100200300400500SE +/- 1.81, N = 3SE +/- 1.61, N = 3SE +/- 1.94, N = 3400.36441.58439.54-O2-O3-O3 -march=native1. (CXX) g++ options: -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++

Himeno Benchmark

Poisson Pressure Solver

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-O2-O3-O3 native-O3 native + PGO2004006008001000SE +/- 1.94, N = 3SE +/- 2.17, N = 3SE +/- 0.78, N = 3SE +/- 0.73, N = 3SE +/- 0.47, N = 3SE +/- 5.36, N = 3SE +/- 4.57, N = 3SE +/- 0.64, N = 31014.66998.89982.67852.631014.38993.221007.74869.071. (CC) gcc options: -O3 -mavx2

Tinymembench

Standard Memcpy

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memcpy-O2-O3-O3 native-O3 native + PGO3K6K9K12K15K12359.3012555.7012497.2012453.2012422.9012490.0012377.6012300.601. (CC) gcc options: -O2 -lm

Tinymembench

Standard Memset

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgMB/s, More Is BetterTinymembench 2018-05-28Standard Memset-O2-O3-O3 native-O3 native + PGO2K4K6K8K10K9978.6010037.7010063.109975.209989.4010039.709982.809982.901. (CC) gcc options: -O2 -lm

Sockperf

Test: Latency Under Load

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Under Load-O2-O3-O3 native510152025SE +/- 0.09, N = 5SE +/- 0.31, N = 10SE +/- 0.30, N = 10SE +/- 0.42, N = 10SE +/- 2.62, N = 10SE +/- 0.24, N = 819.5919.6719.7519.7522.4319.881. (CXX) g++ options: --param -rdynamic -ldl -lpthread

Sockperf

Test: Latency Ping Pong

GCC 8.2 RC1GCC 9.0 SVNOpenBenchmarking.orgusec, Fewer Is BetterSockperf 3.4Test: Latency Ping Pong-O2-O3-O3 native246810SE +/- 0.08, N = 10SE +/- 0.07, N = 5SE +/- 0.11, N = 10SE +/- 0.12, N = 10SE +/- 0.09, N = 66.666.766.426.536.571. (CXX) g++ options: --param -rdynamic -ldl -lpthread

Phoronix Test Suite v10.8.4