GCC 4.9 Compiler Optimization Tuning AMD Kaveri

AMD Steamroller CPU Cores on AMD A10-7850K Kaveri APU compiler optimization tuning with various march= values. Benchmarks by Michael Larabel for a future article on Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1401282-PL-GCC49COMP74&gru&rdt.

GCC 4.9 Compiler Optimization Tuning AMD KaveriProcessorMotherboardChipsetMemoryDiskGraphicsAudioMonitorNetworkOSKernelDesktopDisplay DriverCompilerFile-SystemScreen Resolutionbdver3bdver2bdver1barcelonak8AMD A10-7850K APU with Radeon R7 @ 3.70GHz (4 Cores)Gigabyte F2A88XM-D3HAMD Device 14227168MB120GB KINGSTON SV300S3AMD Kaveri 1024MBATI R6xx HDMITSB-TVRealtek RTL8111/8168/8411Ubuntu 14.043.13.0-5-generic (x86_64)Unity 7.1.2radeon 7.2.99GCC 4.9.0 20140126 + Clang 3.4 + LLVM 3.4ext41920x1080OpenBenchmarking.orgKernel Details- radeon.dpm=1Compiler Details- --disable-multilib --enable-checking=release --enable-languages=c,c++,fortranProcessor Details- Scaling Governor: acpi-cpufreq ondemand

GCC 4.9 Compiler Optimization Tuning AMD Kaverix264: H.264 Video Encodinggraphics-magick: Blurgraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdingscimark2: Compositescimark2: Monte Carloscimark2: Fast Fourier Transformscimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationscimark2: Jacobi Successive Over-Relaxationhimeno: Poisson Pressure Solvertscp: AI Chess Performancebuild-apache: Time To Compilebuild-php: Time To Compilec-ray: Total Timeencode-flac: WAV To FLACbdver3bdver2bdver1barcelonak883.831068113313980641.05413.6470.77866.811165.94688.08902.9873910158.8358.4840.545.5283.851108113313981644.89423.2871.15877.911164.64687.47905.3073870758.9158.5440.555.4784.141088713313981640.56423.7368.50860.411162.41687.76894.2773831159.0758.4540.675.2983.66937212013876629.44384.4768.99849.341155.51688.88898.3374269058.6856.6053.336.9083.43977110612677636.54397.8673.59865.921156.29689.02867.3676011358.5556.5487.906.62OpenBenchmarking.org

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2014-01-09H.264 Video Encodingbdver3bdver2bdver1barcelonak820406080100SE +/- 0.25, N = 5SE +/- 0.64, N = 5SE +/- 0.73, N = 5SE +/- 0.46, N = 5SE +/- 0.71, N = 583.8383.8584.1483.6683.43-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fomit-frame-pointer -fno-tree-vectorize

GraphicsMagick

Operation: Blur

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Blurbdver3bdver2bdver1barcelonak820406080100SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31061101089397-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ljbig -lwebp -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Sharpen

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Sharpenbdver3bdver2bdver1barcelonak820406080100SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 38181877271-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ljbig -lwebp -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Resizing

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Resizingbdver3bdver2bdver1barcelonak8306090120150SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3133133133120106-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ljbig -lwebp -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: HWB Color Space

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: HWB Color Spacebdver3bdver2bdver1barcelonak8306090120150SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3139139139138126-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ljbig -lwebp -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

GraphicsMagick

Operation: Local Adaptive Thresholding

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.19Operation: Local Adaptive Thresholdingbdver3bdver2bdver1barcelonak820406080100SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 38081817677-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ljbig -lwebp -ljpeg -lXext -lSM -lICE -lX11 -llzma -lxml2 -lz -lm -lpthread

SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Compositebdver3bdver2bdver1barcelonak8140280420560700SE +/- 1.36, N = 4SE +/- 1.36, N = 4SE +/- 1.89, N = 4SE +/- 4.49, N = 4SE +/- 1.68, N = 4641.05644.89640.56629.44636.54-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CXX) g++ options: -O3

SciMark

Computational Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlobdver3bdver2bdver1barcelonak890180270360450SE +/- 10.39, N = 4SE +/- 1.61, N = 4SE +/- 0.77, N = 4SE +/- 0.60, N = 4SE +/- 7.32, N = 4413.64423.28423.73384.47397.86-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CXX) g++ options: -O3

SciMark

Computational Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transformbdver3bdver2bdver1barcelonak81632486480SE +/- 0.16, N = 4SE +/- 0.10, N = 4SE +/- 1.36, N = 4SE +/- 0.94, N = 4SE +/- 0.22, N = 470.7771.1568.5068.9973.59-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CXX) g++ options: -O3

SciMark

Computational Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiplybdver3bdver2bdver1barcelonak82004006008001000SE +/- 7.27, N = 4SE +/- 2.24, N = 4SE +/- 9.94, N = 4SE +/- 15.60, N = 4SE +/- 4.11, N = 4866.81877.91860.41849.34865.92-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CXX) g++ options: -O3

SciMark

Computational Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorizationbdver3bdver2bdver1barcelonak830060090012001500SE +/- 2.87, N = 4SE +/- 3.97, N = 4SE +/- 1.67, N = 4SE +/- 5.67, N = 4SE +/- 6.32, N = 41165.941164.641162.411155.511156.29-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CXX) g++ options: -O3

SciMark

Computational Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxationbdver3bdver2bdver1barcelonak8150300450600750SE +/- 0.38, N = 4SE +/- 0.80, N = 4SE +/- 0.38, N = 4SE +/- 0.08, N = 4SE +/- 0.12, N = 4688.08687.47687.76688.88689.02-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CXX) g++ options: -O3

Himeno Benchmark

Poisson Pressure Solver

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solverbdver3bdver2bdver1barcelonak82004006008001000SE +/- 3.10, N = 3SE +/- 1.51, N = 3SE +/- 9.68, N = 3SE +/- 0.19, N = 3SE +/- 6.79, N = 3902.98905.30894.27898.33867.36-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -O3

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess Performancebdver3bdver2bdver1barcelonak8160K320K480K640K800KSE +/- 198.20, N = 5SE +/- 671.07, N = 5SE +/- 699.90, N = 5SE +/- 600.77, N = 5SE +/- 257.20, N = 5739101738707738311742690760113-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -O3

Timed Apache Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Apache Compilation 2.4.7Time To Compilebdver3bdver2bdver1barcelonak81326395265SE +/- 0.12, N = 3SE +/- 0.12, N = 3SE +/- 0.21, N = 3SE +/- 0.15, N = 3SE +/- 0.19, N = 358.8358.9159.0758.6858.55

Timed PHP Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To Compilebdver3bdver2bdver1barcelonak81326395265SE +/- 0.01, N = 3SE +/- 0.07, N = 3SE +/- 0.10, N = 3SE +/- 0.04, N = 3SE +/- 0.06, N = 358.4858.5458.4556.6056.54-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -O3 -pedantic -ldl -lz -lm

C-Ray

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Timebdver3bdver2bdver1barcelonak820406080100SE +/- 0.07, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.09, N = 3SE +/- 0.02, N = 340.5440.5540.6753.3387.90-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CC) gcc options: -lm -lpthread -O3

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.0WAV To FLACbdver3bdver2bdver1barcelonak8246810SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 5SE +/- 0.01, N = 5SE +/- 0.02, N = 55.525.475.296.906.62-march=bdver3-march=bdver2-march=bdver1-march=barcelona-march=k81. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm


Phoronix Test Suite v10.8.5