ARMv7 Cortex A9 GCC 4.7 LTO Link-Time Optimizations

GCC 4.7 benchmarks of GCC 4.7.2 LTO. Testing the compiler link-time optimization performance with the -flto CFLAGS/CXXFLAGS. Benchmarking from a NVIDIA tegra 3 Cardhu quad-core ARM Cortex-A9 tablet. Benchmarking for future article on Phoronix by Michael Larabel.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1303016-PTS-GCC48ARM14
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results

Limit displaying results to tests within:

Audio Encoding 2 Tests
Timed Code Compilation 2 Tests
C/C++ Compiler Tests 6 Tests
CPU Massive 6 Tests
Creator Workloads 5 Tests
Encoding 4 Tests
Multi-Core 6 Tests
Programmer / Developer System Benchmarks 2 Tests
Single-Threaded 2 Tests
Video Encoding 2 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
Performance Per
Dollar
Date
Run
  Test
  Duration
Stock
February 26 2013
 
GCC LTO
February 28 2013
 
Invert Hiding All Results Option
 
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

Stock

Compiler Notes: --build=arm-linux-gnueabihf --disable-cloog-version-check --disable-libitm --disable-ppl-version-check --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-cloog-backend=ppl --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch=armv7-a --with-cloog --with-float=hard --with-fpu=vfpv3-d16 --with-mode=thumb -v
Processor Notes: Scaling Governor: ondemand

GCC LTO

Processor: ARMv7 rev 9 @ 1.40GHz (4 Cores), Motherboard: cardhu, Memory: 1024MB, Disk: 16GB SEM16G + 32GB SD32G, Graphics: NVIDIA TEGRA, Network: Realtek RTL8111/8168B

OS: Ubuntu 13.04, Kernel: 3.1.10-gfc993d9 (armv7l), Compiler: GCC 4.7, File-System: ext3, Screen Resolution: 1366x1536

ARMv7 Cortex A9 GCC 4.7 LTO Link-Time OptimizationsOpenBenchmarking.orgPhoronix Test SuiteARMv7 rev 9 @ 1.40GHz (4 Cores)cardhu1024MB16GB SEM16G + 32GB SD32GNVIDIA TEGRARealtek RTL8111/8168BUbuntu 13.043.1.10-gfc993d9 (armv7l)GCC 4.7ext31366x1536ProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelCompilerFile-SystemScreen ResolutionARMv7 Cortex A9 GCC 4.7 LTO Link-Time Optimizations PerformanceSystem Logs- --build=arm-linux-gnueabihf --disable-cloog-version-check --disable-libitm --disable-ppl-version-check --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-cloog-backend=ppl --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch=armv7-a --with-cloog --with-float=hard --with-fpu=vfpv3-d16 --with-mode=thumb -v - Scaling Governor: ondemand

Stock vs. GCC LTO ComparisonPhoronix Test SuiteBaseline+36.5%+36.5%+73%+73%+109.5%+109.5%12.1%11.8%6.7%4.4%3.6%Time To Compile145.8%Time To Compile44.9%HWB Color SpaceBlurSharpenWAV To MP3Total TimeTimed PHP CompilationTimed ImageMagick CompilationGraphicsMagickGraphicsMagickGraphicsMagickLAME MP3 EncodingOpen FMM Nero2DStockGCC LTO

ARMv7 Cortex A9 GCC 4.7 LTO Link-Time Optimizationsvpxenc: vpxencgraphics-magick: Blurgraphics-magick: Sharpengraphics-magick: Resizinggraphics-magick: HWB Color Spacegraphics-magick: Local Adaptive Thresholdingbuild-imagemagick: Time To Compilebuild-php: Time To Compileencode-flac: WAV To FLACencode-mp3: WAV To MP3ffmpeg: H.264 HD To NTSC DVnero2d: Total TimeStockGCC LTO0.4017152533171123.07492.4340.5893.26354.364374.940.4019162537171627.511210.4840.6589.29354.494223.39OpenBenchmarking.org

VP8 libvpx Encoding

OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 1.1.0vpxencStockGCC LTO0.090.180.270.360.45SE +/- 0.00, N = 3SE +/- 0.00, N = 30.400.401. (CC) gcc options: -lvpx -lm -lpthread
OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 1.1.0vpxencStockGCC LTO12345Min: 0.4 / Avg: 0.4 / Max: 0.4Min: 0.4 / Avg: 0.4 / Max: 0.41. (CC) gcc options: -lvpx -lm -lpthread

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: BlurStockGCC LTO510152025SE +/- 0.33, N = 3SE +/- 0.00, N = 31719-flto1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: BlurStockGCC LTO510152025Min: 17 / Avg: 17.33 / Max: 18Min: 19 / Avg: 19 / Max: 191. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: SharpenStockGCC LTO48121620SE +/- 0.25, N = 4SE +/- 0.25, N = 41516-flto1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: SharpenStockGCC LTO48121620Min: 15 / Avg: 15.25 / Max: 16Min: 15 / Avg: 15.75 / Max: 161. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: ResizingStockGCC LTO612182430SE +/- 0.00, N = 3SE +/- 0.00, N = 32525-flto1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: ResizingStockGCC LTO612182430Min: 25 / Avg: 25 / Max: 25Min: 25 / Avg: 25 / Max: 251. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color SpaceStockGCC LTO918273645SE +/- 0.67, N = 3SE +/- 0.33, N = 33337-flto1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color SpaceStockGCC LTO816243240Min: 32 / Avg: 33.33 / Max: 34Min: 37 / Avg: 37.33 / Max: 381. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive ThresholdingStockGCC LTO48121620SE +/- 0.29, N = 4SE +/- 0.29, N = 41717-flto1. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread
OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive ThresholdingStockGCC LTO48121620Min: 16 / Avg: 16.5 / Max: 17Min: 16 / Avg: 16.5 / Max: 171. (CC) gcc options: -std=gnu99 -fopenmp -O2 -pthread -lz -lm -lgomp -lpthread

Timed ImageMagick Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.8.1-10Time To CompileStockGCC LTO30060090012001500SE +/- 20.61, N = 3SE +/- 5.86, N = 31123.071627.51
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.8.1-10Time To CompileStockGCC LTO30060090012001500Min: 1085.14 / Avg: 1123.07 / Max: 1156Min: 1617.57 / Avg: 1627.51 / Max: 1637.84

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To CompileStockGCC LTO30060090012001500SE +/- 8.22, N = 4SE +/- 19.22, N = 3492.431210.48-flto1. (CC) gcc options: -O2 -pedantic -ldl -lz -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To CompileStockGCC LTO2004006008001000Min: 480.68 / Avg: 492.43 / Max: 516.8Min: 1172.17 / Avg: 1210.48 / Max: 1232.431. (CC) gcc options: -O2 -pedantic -ldl -lz -lm

FLAC Audio Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.2.1WAV To FLACStockGCC LTO918273645SE +/- 0.50, N = 5SE +/- 0.62, N = 540.5840.65-flto1. (CXX) g++ options: -O2 -logg -lm
OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.2.1WAV To FLACStockGCC LTO816243240Min: 39.87 / Avg: 40.58 / Max: 42.52Min: 39.85 / Avg: 40.65 / Max: 43.141. (CXX) g++ options: -O2 -logg -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.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3StockGCC LTO20406080100SE +/- 0.05, N = 5SE +/- 0.03, N = 593.2689.29
OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3StockGCC LTO20406080100Min: 93.06 / Avg: 93.26 / Max: 93.39Min: 89.2 / Avg: 89.29 / Max: 89.34

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 1.1H.264 HD To NTSC DVStockGCC LTO80160240320400SE +/- 1.60, N = 3SE +/- 1.74, N = 3354.36354.491. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lm -pthread
OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 1.1H.264 HD To NTSC DVStockGCC LTO60120180240300Min: 351.93 / Avg: 354.36 / Max: 357.36Min: 352.13 / Avg: 354.49 / Max: 357.881. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lm -pthread

Open FMM Nero2D

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen FMM Nero2D 2.0.2Total TimeStockGCC LTO90018002700360045004374.944223.39-flto1. (CXX) g++ options: -O2 -lfftw3 -llapack -lblas -lgfortran -lm

Stock

Compiler Notes: --build=arm-linux-gnueabihf --disable-cloog-version-check --disable-libitm --disable-ppl-version-check --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-cloog-backend=ppl --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch=armv7-a --with-cloog --with-float=hard --with-fpu=vfpv3-d16 --with-mode=thumb -v
Processor Notes: Scaling Governor: ondemand

Testing initiated at 26 February 2013 10:08 by user ubuntu.

GCC LTO

Processor: ARMv7 rev 9 @ 1.40GHz (4 Cores), Motherboard: cardhu, Memory: 1024MB, Disk: 16GB SEM16G + 32GB SD32G, Graphics: NVIDIA TEGRA, Network: Realtek RTL8111/8168B

OS: Ubuntu 13.04, Kernel: 3.1.10-gfc993d9 (armv7l), Compiler: GCC 4.7, File-System: ext3, Screen Resolution: 1366x1536

Compiler Notes: --build=arm-linux-gnueabihf --disable-cloog-version-check --disable-libitm --disable-ppl-version-check --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-cloog-backend=ppl --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch=armv7-a --with-cloog --with-float=hard --with-fpu=vfpv3-d16 --with-mode=thumb -v
Processor Notes: Scaling Governor: ondemand

Testing initiated at 28 February 2013 06:04 by user ubuntu.