Samsung ARM Cortex A15 Dual vs. NVIDIA Tegra 3

Exynos ARMv7 rev 4 testing on Ubuntu 12.04 via the Phoronix Test Suite. Benchmarking for a future article on Phoronix.com.

HTML result view exported from: https://openbenchmarking.org/result/1212131-SU-1212087RA30.

Samsung ARM Cortex A15 Dual vs. NVIDIA Tegra 3ProcessorMotherboardMemoryDiskGraphicsNetworkOSKernelDesktopDisplay ServerCompilerFile-SystemScreen ResolutionARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.7Exynos 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 4.7ext41366x768ARMv7 rev 9 @ 1.40GHz (4 Cores)cardhu1024MB16GB SEM16G + 32GB SD32GNVIDIA TEGRARealtek RTL8111/8168B3.1.10-gfc993d9 (armv7l)GCC 4.6ext31366x1536Ubuntu 12.10ARMv7 rev 4 (2 Cores)SAMSUNG EXYNOS5 (Flattened Device Tree)2048MB4GB M4G1FA + 8GB SD08GLinaro 12.113.6.0-10612-g9d11689 (armv7l)GCC 4.7ext4OpenBenchmarking.orgCompiler Details- ARM Cortex A15 1.7GHz Dual: --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 - NVIDIA Tegra 3 - Ubuntu 12.04: --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 - NVIDIA Tegra 3 - Ubuntu 12.10: --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 - ArndaleGCC4.7: --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 Details- ARM Cortex A15 1.7GHz Dual, NVIDIA Tegra 3 - Ubuntu 12.04, NVIDIA Tegra 3 - Ubuntu 12.10: Scaling Governor: ondemandSystem Details- Python 2.7.3.

Samsung ARM Cortex A15 Dual vs. NVIDIA Tegra 3stream: Copystream: Scalestream: Triadstream: Addclomp: Static OMP Speedupdolfyn: Computational Fluid Dynamicsffte: N=64, 1D Complex FFT Routinehmmer: Pfam Database Searchmafft: Multiple Sequence Alignmentcachebench: Readcachebench: Writecachebench: Read / Modify / Writescimark2: Compositescimark2: Monte Carloscimark2: Fast Fourier Transformscimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationscimark2: Jacobi Successive Over-Relaxationtscp: AI Chess Performancevpxenc: vpxencx264: H.264 Video Encodingcompress-7zip: Compress Speed Testc-ray: Total Timecompress-pbzip2: 256MB File Compressionprimesieve: 1e12 Prime Number Generationsmallpt: Global Illumination Renderer; 100 Samplescrafty: Elapsed Timeencode-mp3: WAV To MP3encode-ogg: WAV To Oggffmpeg: H.264 HD To NTSC DVpovray: Total Timeopenssl: RSA 4096-bit Performancepybench: Total For Average Test Timesnginx: Static Web Page Servingphpbench: PHP Benchmark SuiteARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.76251.246114.155189.585656.601.64159.981484.87115.1137.352572.443723.557115.32270.01160.8636.35339.64455.45357.751462651.4310.141685312.0084.57832.9511770.06142.2731.53159.1619379.9084213273.57220501523.821519.351273.091286.180.74477.22544.44366.2959.451933.822827.602878.200.408.321499559.11113.99427691.72422.9947315.90139642146.61132241387.161339.671268.611285.260.74462.43367.3851.201939.552848.202862.320.408.181513539.61109.38426491.47424.0747045.90133462131.78134865708.645347.164421.424860.181.83871.52193.371523.092678.234513.381087550.282019132712848.2014729OpenBenchmarking.org

Stream

Type: Copy

OpenBenchmarking.orgMB/s, More Is BetterStream 2009-04-11Type: CopyARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.713002600390052006500SE +/- 52.68, N = 10SE +/- 3.98, N = 10SE +/- 35.01, N = 20SE +/- 3.32, N = 106251.241523.821387.165708.641. (CC) gcc options: -O2 -fopenmp

Stream

Type: Scale

OpenBenchmarking.orgMB/s, More Is BetterStream 2009-04-11Type: ScaleARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.713002600390052006500SE +/- 45.43, N = 10SE +/- 4.74, N = 10SE +/- 44.70, N = 20SE +/- 2.30, N = 106114.151519.351339.675347.161. (CC) gcc options: -O2 -fopenmp

Stream

Type: Triad

OpenBenchmarking.orgMB/s, More Is BetterStream 2009-04-11Type: TriadARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.711002200330044005500SE +/- 32.03, N = 10SE +/- 0.51, N = 10SE +/- 4.48, N = 10SE +/- 1.86, N = 105189.581273.091268.614421.421. (CC) gcc options: -O2 -fopenmp

Stream

Type: Add

OpenBenchmarking.orgMB/s, More Is BetterStream 2009-04-11Type: AddARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.712002400360048006000SE +/- 41.07, N = 10SE +/- 0.68, N = 10SE +/- 2.65, N = 10SE +/- 2.07, N = 105656.601286.181285.264860.181. (CC) gcc options: -O2 -fopenmp

CLOMP

Static OMP Speedup

OpenBenchmarking.orgSpeedup, More Is BetterCLOMP 3.3Static OMP SpeedupARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.70.41180.82361.23541.64722.059SE +/- 0.13, N = 10SE +/- 0.00, N = 5SE +/- 0.00, N = 5SE +/- 0.02, N = 51.640.740.741.831. (CC) gcc options: --openmp -O3 -lm

Dolfyn

Computational Fluid Dynamics

OpenBenchmarking.orgSeconds, Fewer Is BetterDolfyn 0.527Computational Fluid DynamicsARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10100200300400500SE +/- 0.31, N = 3SE +/- 4.90, N = 3SE +/- 4.13, N = 3159.98477.22462.43

FFTE

Test: N=64, 1D Complex FFT Routine

OpenBenchmarking.orgMFLOPS, More Is BetterFFTE 5.0Test: N=64, 1D Complex FFT RoutineARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04ArndaleGCC4.730060090012001500SE +/- 0.35, N = 3SE +/- 0.02, N = 3SE +/- 1.80, N = 31484.87544.44871.52-lmpichf90 -lmpich -lopa -lmpl -lrt -lcr -lpthread-pthread -lmpi_f90 -lmpi_f77 -lmpi -lopen-rte -lopen-pal -ldl -lnsl -lutil -lm1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp

Timed HMMer Search

Pfam Database Search

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database SearchARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.780160240320400SE +/- 0.36, N = 3SE +/- 4.08, N = 3SE +/- 5.46, N = 3SE +/- 1.46, N = 3115.11366.29367.38193.371. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm

Timed MAFFT Alignment

Multiple Sequence Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence AlignmentARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.101326395265SE +/- 0.17, N = 3SE +/- 2.43, N = 6SE +/- 0.79, N = 337.3559.4551.201. (CC) gcc options: -O3 -lm -lpthread

CacheBench

Test: Read

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: ReadARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.76001200180024003000SE +/- 8.68, N = 3SE +/- 22.43, N = 3SE +/- 12.37, N = 3SE +/- 0.14, N = 32572.441933.821939.551523.091. (CC) gcc options: -lrt

CacheBench

Test: Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: WriteARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.78001600240032004000SE +/- 15.25, N = 3SE +/- 27.74, N = 3SE +/- 25.25, N = 3SE +/- 0.14, N = 33723.552827.602848.202678.231. (CC) gcc options: -lrt

CacheBench

Test: Read / Modify / Write

OpenBenchmarking.orgMB/s, More Is BetterCacheBenchTest: Read / Modify / WriteARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.715003000450060007500SE +/- 6.72, N = 3SE +/- 49.68, N = 3SE +/- 41.68, N = 3SE +/- 0.24, N = 37115.322878.202862.324513.381. (CC) gcc options: -lrt

SciMark

Computational Test: Composite

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: CompositeARM Cortex A15 1.7GHz Dual60120180240300SE +/- 0.18, N = 4270.01

SciMark

Computational Test: Monte Carlo

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte CarloARM Cortex A15 1.7GHz Dual4080120160200SE +/- 0.12, N = 4160.86

SciMark

Computational Test: Fast Fourier Transform

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier TransformARM Cortex A15 1.7GHz Dual816243240SE +/- 0.67, N = 436.35

SciMark

Computational Test: Sparse Matrix Multiply

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix MultiplyARM Cortex A15 1.7GHz Dual70140210280350SE +/- 0.73, N = 4339.64

SciMark

Computational Test: Dense LU Matrix Factorization

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix FactorizationARM Cortex A15 1.7GHz Dual100200300400500SE +/- 0.39, N = 4455.45

SciMark

Computational Test: Jacobi Successive Over-Relaxation

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-RelaxationARM Cortex A15 1.7GHz Dual80160240320400SE +/- 0.42, N = 4357.75

TSCP

AI Chess Performance

OpenBenchmarking.orgNodes Per Second, More Is BetterTSCP 1.81AI Chess PerformanceARM Cortex A15 1.7GHz Dual30K60K90K120K150KSE +/- 95.53, N = 5146265

VP8 libvpx Encoding

vpxenc

OpenBenchmarking.orgFrames Per Second, More Is BetterVP8 libvpx Encoding 1.1.0vpxencARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.100.32180.64360.96541.28721.609SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 31.430.400.401. (CC) gcc options: -lvpx -lm -lpthread

x264

H.264 Video Encoding

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2012-10-03H.264 Video EncodingARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.103691215SE +/- 0.06, N = 3SE +/- 0.15, N = 3SE +/- 0.18, N = 610.148.328.18

7-Zip Compression

Compress Speed Test

OpenBenchmarking.orgMIPS, More Is Better7-Zip Compression 9.20.1Compress Speed TestARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.7400800120016002000SE +/- 6.01, N = 3SE +/- 11.46, N = 3SE +/- 12.66, N = 3SE +/- 2.40, N = 316851499151310871. (CXX) g++ options: -pipe -lpthread

C-Ray

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.7120240360480600SE +/- 0.68, N = 3SE +/- 0.14, N = 3SE +/- 5.19, N = 3SE +/- 13.84, N = 6312.00559.11539.61550.281. (CC) gcc options: -lm -lpthread -O3

Parallel BZIP2 Compression

256MB File Compression

OpenBenchmarking.orgSeconds, Fewer Is BetterParallel BZIP2 Compression 1.1.6256MB File CompressionARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10306090120150SE +/- 0.80, N = 3SE +/- 1.25, N = 3SE +/- 0.71, N = 384.57113.99109.381. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 4.01e12 Prime Number GenerationARM Cortex A15 1.7GHz Dual2004006008001000SE +/- 13.74, N = 6832.951. (CXX) g++ options: -O2 -fopenmp

Smallpt

Global Illumination Renderer; 100 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 SamplesARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.79001800270036004500SE +/- 4.04, N = 3SE +/- 16.71, N = 3SE +/- 7.00, N = 3SE +/- 12.12, N = 31177427642642019-mtune=cortex-a15 -marm -mfpu=neon1. (CXX) g++ options: -fopenmp

Crafty

Elapsed Time

OpenBenchmarking.orgSeconds, Fewer Is BetterCrafty 23.4Elapsed TimeARM Cortex A15 1.7GHz Dual0.01350.0270.04050.0540.0675SE +/- 0.00, N = 30.061. (CC) gcc options: -lstdc++ -lm

LAME MP3 Encoding

WAV To MP3

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3ARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10306090120150SE +/- 0.08, N = 5SE +/- 0.13, N = 5SE +/- 0.21, N = 5142.2791.7291.47

Ogg Encoding

WAV To Ogg

OpenBenchmarking.orgSeconds, Fewer Is BetterOgg Encoding 1.3.0WAV To OggARM Cortex A15 1.7GHz Dual714212835SE +/- 0.11, N = 531.531. (CC) gcc options: -O2 -ffast-math -fsigned-char -mtune=cortex-a15 -marm -mfpu=neon -lm -logg

FFmpeg

H.264 HD To NTSC DV

OpenBenchmarking.orgSeconds, Fewer Is BetterFFmpeg 1.0H.264 HD To NTSC DVARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.1090180270360450SE +/- 0.95, N = 3SE +/- 2.26, N = 3SE +/- 2.65, N = 3159.16422.99424.07-lbz21. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lm -pthread -lrt

POV-Ray

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterPOV-Ray 3.6.1Total TimeARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10100020003000400050001937473147041. (CXX) g++ options: -pipe -O3 -lz -lm

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.1cRSA 4096-bit PerformanceARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.103691215SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 39.905.905.901. (CC) gcc options: -march=armv7-a -O3 -lssl -lcrypto -ldl

PyBench

Total For Average Test Times

OpenBenchmarking.orgMilliseconds, Fewer Is BetterPyBench 2008-08-14Total For Average Test TimesARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.73K6K9K12K15KSE +/- 11.05, N = 3SE +/- 4.06, N = 3SE +/- 6.24, N = 3SE +/- 28.94, N = 38421139641334613271

NGINX Benchmark

Static Web Page Serving

OpenBenchmarking.orgRequests Per Second, More Is BetterNGINX Benchmark 1.0.11Static Web Page ServingARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.77001400210028003500SE +/- 109.38, N = 6SE +/- 13.99, N = 3SE +/- 39.92, N = 3SE +/- 36.67, N = 33273.572146.612131.782848.20-lcrypto1. (CC) gcc options: -lpthread -lcrypt -lz

PHPBench

PHP Benchmark Suite

OpenBenchmarking.orgScore, More Is BetterPHPBench 0.8.1PHP Benchmark SuiteARM Cortex A15 1.7GHz DualNVIDIA Tegra 3 - Ubuntu 12.04NVIDIA Tegra 3 - Ubuntu 12.10ArndaleGCC4.75K10K15K20K25KSE +/- 158.19, N = 3SE +/- 36.10, N = 3SE +/- 19.92, N = 3SE +/- 100.52, N = 322050132241348614729

Phoronix Test Suite v10.8.4