ARM GCC 4.7.2 Cortex-A15 Compiler Optimizations

Benchmarking compiler optimization levels on GCC 4.7.2 from a Google Nexus 10 with Samsung Exynos 5 Dual SoC. It's an ARM Cortex-A15 dual-core 1.7GHz processor. Benchmarking by Michael Larabel for a future article on Phoronix.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1302284-FO-ARMGCC47227
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:

C/C++ Compiler Tests 4 Tests
CPU Massive 5 Tests
Creator Workloads 4 Tests
Multi-Core 5 Tests
Renderers 2 Tests
Server CPU Tests 3 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
-Os
February 26 2013
 
-O0
February 25 2013
 
-O1
February 25 2013
 
-O2
February 25 2013
 
-O3
February 25 2013
 
-Ofast
February 26 2013
 
Invert Hiding All Results Option
 

Only show results where is faster than
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):


ARM GCC 4.7.2 Cortex-A15 Compiler OptimizationsOpenBenchmarking.orgPhoronix Test SuiteARMv7 rev 4 @ 1.70GHz (2 Cores)Manta2048MB16GB MAG2GAUbuntu 12.103.4.5-gf68518f (armv7l)GCC 4.7ext42560x1600ProcessorMotherboardMemoryDiskOSKernelCompilerFile-SystemScreen ResolutionARM GCC 4.7.2 Cortex-A15 Compiler Optimizations PerformanceSystem Logs- --build=arm-linux-gnueabihf --disable-libitm --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --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-float=hard --with-fpu=vfpv3-d16 --with-mode=thumb -v - Scaling Governor: interactive

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Blur-Os-Ofast-O3-O2-O1-O0714212835SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3SE +/- 0.25, N = 4293130313016-Os-Ofast-O2-O2-O1-O01. (CC) gcc options: -std=gnu99 -fopenmp -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Sharpen-Os-Ofast-O3-O2-O1-O0612182430SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 6SE +/- 0.33, N = 3SE +/- 0.00, N = 320232323197-Os-Ofast-O2-O2-O1-O01. (CC) gcc options: -std=gnu99 -fopenmp -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Resizing-Os-Ofast-O3-O2-O1-O0918273645SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3363940403616-Os-Ofast-O2-O2-O1-O01. (CC) gcc options: -std=gnu99 -fopenmp -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color Space-Os-Ofast-O3-O2-O1-O01224364860SE +/- 0.00, N = 3SE +/- 0.88, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3485547474727-Os-Ofast-O2-O2-O1-O01. (CC) gcc options: -std=gnu99 -fopenmp -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive Thresholding-Os-Ofast-O3-O2-O1-O0510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 319222222196-Os-Ofast-O2-O2-O1-O01. (CC) gcc options: -std=gnu99 -fopenmp -pthread -lXext -lSM -lICE -lX11 -lbz2 -lz -lm -lgomp -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.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-Os-Ofast-O3-O2-O1-O0306090120150SE +/- 1.80, N = 6SE +/- 1.15, N = 3SE +/- 1.96, N = 3SE +/- 5.17, N = 6SE +/- 1.57, N = 3SE +/- 0.29, N = 3100.58129.49141.55140.04108.5760.43-Os-Ofast-O2-O1-O01. (CC) gcc options: -O3

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To Compile-Os-Ofast-O3-O2-O1-O060120180240300SE +/- 0.90, N = 3SE +/- 0.83, N = 3SE +/- 1.07, N = 3SE +/- 0.77, N = 3SE +/- 0.85, N = 3SE +/- 0.25, N = 3204.10286.52285.41252.76191.56117.17-Os-Ofast-O2-O2-O1-O01. (CC) gcc options: -pedantic -ldl -lz -lm

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.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time-Os-Ofast-O3-O2-O1-O02004006008001000SE +/- 3.84, N = 3SE +/- 3.01, N = 3SE +/- 4.87, N = 5SE +/- 8.88, N = 4SE +/- 15.01, N = 6SE +/- 1.42, N = 3588.38332.87349.83523.58653.17909.85-Os-Ofast-O2-O1-O01. (CC) gcc options: -lm -lpthread -O3

Smallpt

Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 Samples-Os-Ofast-O3-O2-O1-O030060090012001500SE +/- 3.48, N = 3SE +/- 1.20, N = 3SE +/- 4.18, N = 3SE +/- 2.73, N = 3SE +/- 1.53, N = 3SE +/- 25.31, N = 378427912973293611388-Os-Ofast-O2-O1-O01. (CXX) g++ options: -fopenmp

Opus Codec Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterOpus Codec Encoding 1.0.1WAV, Opus Encode, Opus Decode-Os-Ofast-O3-O2-O1-O04080120160200SE +/- 0.03, N = 5SE +/- 0.03, N = 5SE +/- 0.02, N = 5SE +/- 0.05, N = 5SE +/- 0.17, N = 5SE +/- 0.17, N = 555.7845.7346.6447.8051.84163.43-Os-Ofast-O3 -ffast-math-O2-O1-O01. (CC) gcc options: -std=gnu99 -fPIE -pie -logg -lm -lopus

Open FMM Nero2D

OpenBenchmarking.orgSeconds, Fewer Is BetterOpen FMM Nero2D 2.0.2Total Time-Os-Ofast-O3-O2-O1-O0160032004800640080003505.782145.442149.052142.952300.707634.24-Os-Ofast-O2-O2-O1-O01. (CXX) g++ options: -lfftw3 -llapack -lblas -lgfortran -lm