ARM Cortex A15 GCC Compiler Benchmarks

Benchmarks of GCC 4.6.3 vs. GCC 4.7.2 from a Samsung Exynos 5 Dual SoC with ARM Cortex A15 dual-core ARMv7 1.7GHz processor. Cortex A15 ARM compiler benchmarking for a future article on Phoronix.com.

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1211249-RA-CORTEX15G24
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
Show Result Confidence Charts

Limit displaying results to tests within:

Audio Encoding 3 Tests
Chess Test Suite 2 Tests
C/C++ Compiler Tests 12 Tests
Compression Tests 2 Tests
CPU Massive 15 Tests
Creator Workloads 8 Tests
Encoding 6 Tests
Fortran Tests 2 Tests
HPC - High Performance Computing 2 Tests
Multi-Core 9 Tests
OpenMPI Tests 2 Tests
Renderers 2 Tests
Scientific Computing 2 Tests
Server 2 Tests
Server CPU Tests 5 Tests
Single-Threaded 7 Tests
Video Encoding 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
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
GCC 4.6.3
November 24 2012
 
GCC 4.7.2
November 24 2012
 
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):

GCC 4.6.3

Processor: Exynos ARMv7 rev 4 @ 1.70GHz (2 Cores), Motherboard: SAMSUNG EXYNOS5 (Flattened Device Tree), Memory: 2048MB, Disk: 16GB SEM16G

OS: Ubuntu 12.04, Kernel: 3.4.0 (armv7l), Desktop: Unity 2D 5.16.0, Display Server: X Server 1.11.3, Compiler: GCC 4.6, File-System: ext4, Screen Resolution: 1366x768

Compiler Notes: --build=arm-linux-gnueabihf --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,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
Processor Notes: Scaling Governor: ondemand
System Notes: Python 2.7.3.

GCC 4.7.2

OS: Ubuntu 12.04, Kernel: 3.4.0 (armv7l), Desktop: Unity 2D 5.16.0, Display Server: X Server 1.11.3, Compiler: GCC 4.7, File-System: ext4, Screen Resolution: 1366x768

Compiler Notes: --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
Processor Notes: Scaling Governor: ondemand

ARM Cortex A15 GCC Compiler BenchmarksOpenBenchmarking.orgPhoronix Test SuiteExynos ARMv7 rev 4 @ 1.70GHz (2 Cores)SAMSUNG EXYNOS5 (Flattened Device Tree)2048MB16GB SEM16GUbuntu 12.043.4.0 (armv7l)Unity 2D 5.16.0X Server 1.11.3GCC 4.6GCC 4.7ext41366x768ProcessorMotherboardMemoryDiskOSKernelDesktopDisplay ServerCompilersFile-SystemScreen ResolutionARM Cortex A15 GCC Compiler Benchmarks PerformanceSystem Logs- GCC 4.6.3: --build=arm-linux-gnueabihf --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,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 - GCC 4.7.2: --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: ondemand- GCC 4.6.3: Python 2.7.3.

GCC 4.6.3 vs. GCC 4.7.2 ComparisonPhoronix Test SuiteBaseline+7.1%+7.1%+14.2%+14.2%+21.3%+21.3%28.3%18.5%18.2%17.5%6.6%6.5%5.7%4.9%3.5%3.3%3.3%2.3%2%Total TimeF.F.T1.P.N.GN.6.1.C.F.RC.S.T14.6%Time To Compile11.1%C.F.D8%vpxencStatic OMP SpeedupWriteJ.S.O.R5.2%2.F.CMonte Carlo4.5%WAV To MP34.2%D.L.M.FWAV To FLACH.2.H.T.N.DG.I.R.1.SH.2.V.EC-RaySciMarkPrimesieveFFTE7-Zip CompressionTimed PHP CompilationDolfynVP8 libvpx EncodingCLOMPCacheBenchSciMarkParallel BZIP2 CompressionSciMarkLAME MP3 EncodingSciMarkFLAC Audio EncodingFFmpegSmallptx264GCC 4.6.3GCC 4.7.2

ARM Cortex A15 GCC Compiler Benchmarkstscp: AI Chess Performancescimark2: Monte Carloscimark2: Fast Fourier Transformscimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationscimark2: Jacobi Successive Over-Relaxationcrafty: Elapsed Timeclomp: Static OMP Speedupcachebench: Readcachebench: Writecachebench: Read / Modify / Writeencode-flac: WAV To FLACencode-mp3: WAV To MP3encode-ogg: WAV To Oggdolfyn: Computational Fluid Dynamicsffte: N=64, 1D Complex FFT Routineprimesieve: 1e12 Prime Number Generationcompress-7zip: Compress Speed Testbuild-php: Time To Compilecompress-pbzip2: 256MB File Compressionvpxenc: vpxencx264: H.264 Video Encodingc-ray: Total Timeffmpeg: H.264 HD To NTSC DVsmallpt: Global Illumination Renderer; 100 Samplesnginx: Static Web Page Servingopenssl: RSA 4096-bit Performancegmpbench: Total TimeGCC 4.6.3GCC 4.7.2146968167.9037.65333.34435.03361.970.061.702570.833521.376979.6419.8152.3031.50158.911257.00957.911951255.7988.411.2110.62447.38162.5412083535.7710451.29146096160.6244.62338.23450.12344.100.061.812582.333722.677092.4419.1854.4831.75171.651476.59810.271703284.1584.301.2910.83348.61157.4011813578.559.90452.59OpenBenchmarking.org

TSCP

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceGCC 4.6.3GCC 4.7.230K60K90K120K150KSE +/- 150.74, N = 5SE +/- 233.82, N = 5146968146096

SciMark

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloGCC 4.6.3GCC 4.7.24080120160200SE +/- 0.13, N = 4SE +/- 0.12, N = 4167.90160.62

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformGCC 4.7.2GCC 4.6.31020304050SE +/- 0.29, N = 4SE +/- 0.82, N = 444.6237.65

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyGCC 4.7.2GCC 4.6.370140210280350SE +/- 0.53, N = 4SE +/- 2.68, N = 4338.23333.34

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationGCC 4.7.2GCC 4.6.3100200300400500SE +/- 2.60, N = 4SE +/- 0.92, N = 4450.12435.03

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationGCC 4.6.3GCC 4.7.280160240320400SE +/- 0.82, N = 4SE +/- 1.15, N = 4361.97344.10

Crafty

OpenBenchmarking.orgSeconds, Fewer Is BetterCrafty 23.4Elapsed TimeGCC 4.6.3GCC 4.7.20.01350.0270.04050.0540.0675SE +/- 0.01, N = 6SE +/- 0.00, N = 60.060.061. (CC) gcc options: -lstdc++ -lm

CLOMP

CLOMP is the C version of the Livermore OpenMP benchmark developed to measure OpenMP overheads and other performance impacts due to threading in order to influence future system designs. This particular test profile configuration is currently set to look at the OpenMP static schedule speed-up across all available CPU cores using the recommended test configuration. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP SpeedupGCC 4.7.2GCC 4.6.30.40730.81461.22191.62922.0365SE +/- 0.01, N = 5SE +/- 0.06, N = 101.811.701. (CC) gcc options: --openmp -O3 -lm

CacheBench

This is a performance test of CacheBench, which is part of LLCbench. CacheBench is designed to test the memory and cache bandwidth performance Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: ReadGCC 4.7.2GCC 4.6.36001200180024003000SE +/- 0.34, N = 3SE +/- 6.33, N = 32582.332570.831. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteGCC 4.7.2GCC 4.6.38001600240032004000SE +/- 17.55, N = 3SE +/- 6.16, N = 33722.673521.371. (CC) gcc options: -lrt

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteGCC 4.7.2GCC 4.6.315003000450060007500SE +/- 39.96, N = 3SE +/- 42.99, N = 37092.446979.641. (CC) gcc options: -lrt

FLAC Audio Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.2.1WAV To FLACGCC 4.7.2GCC 4.6.3510152025SE +/- 0.06, N = 5SE +/- 0.04, N = 519.1819.811. (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 MP3GCC 4.6.3GCC 4.7.21224364860SE +/- 0.05, N = 5SE +/- 0.05, N = 552.3054.48

Ogg Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.0WAV To OggGCC 4.6.3GCC 4.7.2714212835SE +/- 0.13, N = 5SE +/- 0.16, N = 531.5031.751. (CC) gcc options: -O2 -ffast-math -fsigned-char -lm -logg

Dolfyn

Dolfyn is a Computational Fluid Dynamics (CFD) code of modern numerical simulation techniques. The Dolfyn test profile measures the execution time of the bundled computational fluid dynamics demos that are bundled with Dolfyn. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsGCC 4.6.3GCC 4.7.24080120160200SE +/- 3.19, N = 6SE +/- 1.08, N = 3158.91171.65

FFTE

FFTE is a package by Daisuke Takahashi to compute Discrete Fourier Transforms of 1-, 2- and 3- dimensional sequences of length (2^p)*(3^q)*(5^r). Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 5.0Test: N=64, 1D Complex FFT RoutineGCC 4.7.2GCC 4.6.330060090012001500SE +/- 2.17, N = 3SE +/- 4.27, N = 31476.591257.001. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 4.01e12 Prime Number GenerationGCC 4.7.2GCC 4.6.32004006008001000SE +/- 9.65, N = 3SE +/- 6.82, N = 3810.27957.911. (CXX) g++ options: -O2 -fopenmp

7-Zip Compression

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 9.20.1Compress Speed TestGCC 4.6.3GCC 4.7.2400800120016002000SE +/- 6.69, N = 3SE +/- 13.53, N = 3195117031. (CXX) g++ options: -pipe -lpthread

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To CompileGCC 4.6.3GCC 4.7.260120180240300SE +/- 1.85, N = 3SE +/- 0.26, N = 3255.79284.151. (CC) gcc options: -O2 -pedantic -ldl -lz -lm

Parallel BZIP2 Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.6256MB File CompressionGCC 4.7.2GCC 4.6.320406080100SE +/- 0.42, N = 3SE +/- 0.38, N = 384.3088.411. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

VP8 libvpx Encoding

OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 1.1.0vpxencGCC 4.7.2GCC 4.6.30.29030.58060.87091.16121.4515SE +/- 0.01, N = 3SE +/- 0.00, N = 31.291.211. (CC) gcc options: -lvpx -lm -lpthread

x264

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2012-10-03H.264 Video EncodingGCC 4.7.2GCC 4.6.33691215SE +/- 0.06, N = 3SE +/- 0.08, N = 310.8310.62

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 TimeGCC 4.7.2GCC 4.6.3100200300400500SE +/- 16.52, N = 6SE +/- 7.03, N = 6348.61447.381. (CC) gcc options: -lm -lpthread -O3

FFmpeg

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 1.0H.264 HD To NTSC DVGCC 4.7.2GCC 4.6.34080120160200SE +/- 0.77, N = 3SE +/- 0.55, N = 3157.40162.541. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lm -pthread -lbz2 -lrt

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 SamplesGCC 4.7.2GCC 4.6.330060090012001500SE +/- 2.08, N = 3SE +/- 1.45, N = 3118112081. (CXX) g++ options: -fopenmp

NGINX Benchmark

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.0.11Static Web Page ServingGCC 4.7.2GCC 4.6.38001600240032004000SE +/- 70.90, N = 3SE +/- 9.45, N = 33578.553535.771. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz

OpenSSL

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.1cRSA 4096-bit PerformanceGCC 4.6.3GCC 4.7.23691215SE +/- 0.00, N = 3SE +/- 0.00, N = 310.009.901. (CC) gcc options: -march=armv7-a -O3 -lssl -lcrypto -ldl

GMPbench

OpenBenchmarking.orgGMPbench Score, More Is BetterGMPbench 0.2Total TimeGCC 4.7.2GCC 4.6.3100200300400500452.59451.291. (CC) gcc options: -O3 -fomit-frame-pointer

GCC 4.6.3

Processor: Exynos ARMv7 rev 4 @ 1.70GHz (2 Cores), Motherboard: SAMSUNG EXYNOS5 (Flattened Device Tree), Memory: 2048MB, Disk: 16GB SEM16G

OS: Ubuntu 12.04, Kernel: 3.4.0 (armv7l), Desktop: Unity 2D 5.16.0, Display Server: X Server 1.11.3, Compiler: GCC 4.6, File-System: ext4, Screen Resolution: 1366x768

Compiler Notes: --build=arm-linux-gnueabihf --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,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
Processor Notes: Scaling Governor: ondemand
System Notes: Python 2.7.3.

Testing initiated at 24 November 2012 03:42 by user user.

GCC 4.7.2

Processor: Exynos ARMv7 rev 4 @ 1.70GHz (2 Cores), Motherboard: SAMSUNG EXYNOS5 (Flattened Device Tree), Memory: 2048MB, Disk: 16GB SEM16G

OS: Ubuntu 12.04, Kernel: 3.4.0 (armv7l), Desktop: Unity 2D 5.16.0, Display Server: X Server 1.11.3, Compiler: GCC 4.7, File-System: ext4, Screen Resolution: 1366x768

Compiler Notes: --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
Processor Notes: Scaling Governor: ondemand

Testing initiated at 24 November 2012 15:13 by user user.