Exynos 5 Dual Google Nexus 10 Samsung Exynos 5 Dual testing from a Google Nexus 10 running Ubuntu Touch Developer Preview. Benchmarking by Michael Larabel 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 1302242-FO-1302235FO17 Exynos 5 Dual Nexus 10 Processor: ARMv7 rev 4 @ 1.70GHz (2 Cores), Motherboard: Manta, Memory: 2048MB, Disk: 16GB MAG2GA
OS: Ubuntu 12.10, Kernel: 3.4.5-gf68518f (armv7l), Compiler: GCC 4.7, File-System: ext4, Screen Resolution: 2560x1600
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 -vProcessor Notes: Scaling Governor: interactive
Tegra 3 Cardhu Processor: ARMv7 rev 9 @ 1.40GHz (4 Cores)Motherboard: cardhuMemory: 1024MBDisk: 16GB SEM16G + 32GB SD32GGraphics: NVIDIA TEGRA, Network: Realtek RTL8111/8168B
OS: Ubuntu 13.04, Kernel: 3.1.10-gfc993d9 (armv7l), Compiler: GCC 4.6, File-System: ext3, Screen Resolution: 1366x1536
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 -vProcessor Notes: Scaling Governor: ondemand
Exynos 5 Dual Google Nexus 10 Processor Motherboard Memory Disk Graphics Network OS Kernel Compiler File-System Screen Resolution Exynos 5 Dual Nexus 10 Tegra 3 Cardhu ARMv7 rev 4 @ 1.70GHz (2 Cores) Manta 2048MB 16GB MAG2GA Ubuntu 12.10 3.4.5-gf68518f (armv7l) GCC 4.7 ext4 2560x1600 ARMv7 rev 9 @ 1.40GHz (4 Cores) cardhu 1024MB 16GB SEM16G + 32GB SD32G NVIDIA TEGRA Realtek RTL8111/8168B Ubuntu 13.04 3.1.10-gfc993d9 (armv7l) GCC 4.6 ext3 1366x1536 OpenBenchmarking.org Compiler Details - Exynos 5 Dual Nexus 10: --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 - Tegra 3 Cardhu: --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 Details - Exynos 5 Dual Nexus 10: Scaling Governor: interactive - Tegra 3 Cardhu: Scaling Governor: ondemand
Exynos 5 Dual Nexus 10 vs. Tegra 3 Cardhu Comparison Phoronix Test Suite Baseline +114.1% +114.1% +228.2% +228.2% +342.3% +342.3% 39.8% 11.4% D.L.M.F 456.2% S.M.M 353.1% Composite 204.3% LU.A 201.2% vpxenc 197.4% P.P.S 196.9% G.I.R.1.S 190.9% H.2.H.T.N.D 190.4% P.D.S 189% SP.A 181.1% CG.B 142.1% F.F.T 130.1% Rhodopsin Protein 121.8% Static OMP Speedup 117.6% WAV To FLAC 116.3% MG.B 112.7% BT.A 108.8% J.S.O.R 101.4% Monte Carlo 79.6% R.4.b.P 67.8% WAV To MP3 67% UA.A 45.1% Total Time 44.1% Elapsed Time S.W.P.S 36.9% S.W.P.S 34.5% Time To Compile 33.8% 2.F.C 26.2% M.S.A 24.8% H.2.V.E 23% EP.B C.S.T 9.3% SciMark SciMark SciMark NAS Parallel Benchmarks VP8 libvpx Encoding Himeno Benchmark Smallpt FFmpeg Timed HMMer Search NAS Parallel Benchmarks NAS Parallel Benchmarks SciMark LAMMPS Molecular Dynamics Simulator CLOMP FLAC Audio Encoding NAS Parallel Benchmarks NAS Parallel Benchmarks SciMark SciMark OpenSSL LAME MP3 Encoding NAS Parallel Benchmarks C-Ray N-Queens NGINX Benchmark Apache Benchmark Timed ImageMagick Compilation Parallel BZIP2 Compression Timed MAFFT Alignment x264 NAS Parallel Benchmarks 7-Zip Compression Exynos 5 Dual Nexus 10 Tegra 3 Cardhu
Exynos 5 Dual Google Nexus 10 apache: Static Web Page Serving nginx: Static Web Page Serving openssl: RSA 4096-bit Performance n-queens: Elapsed Time ffmpeg: H.264 HD To NTSC DV encode-mp3: WAV To MP3 encode-flac: WAV To FLAC smallpt: Global Illumination Renderer; 100 Samples primesieve: 1e12 Prime Number Generation compress-pbzip2: 256MB File Compression c-ray: Total Time build-imagemagick: Time To Compile compress-7zip: Compress Speed Test himeno: Poisson Pressure Solver x264: H.264 Video Encoding vpxenc: vpxenc scimark2: Jacobi Successive Over-Relaxation scimark2: Dense LU Matrix Factorization scimark2: Sparse Matrix Multiply scimark2: Fast Fourier Transform scimark2: Monte Carlo scimark2: Composite mafft: Multiple Sequence Alignment hmmer: Pfam Database Search ffte: N=64, 1D Complex FFT Routine lammps: Rhodopsin Protein npb: UA.A npb: SP.A npb: MG.B npb: LU.A npb: IS.C npb: FT.B npb: EP.B npb: CG.B npb: BT.A clomp: Static OMP Speedup postmark: Disk Transaction Performance Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 1942.27 2956.20 9.90 284.97 124.93 54.65 18.98 1469 1000.73 91.98 358.54 780.26 1628 114.91 10.07 1.16 350.79 426.69 334.10 36.51 160.98 261.82 43.20 130.02 1479.35 188.16 3.73 579.01 642.64 919.08 15.49 538.96 16.74 202.67 1399.44 1.61 154 1444.53 2159.02 5.90 203.87 362.85 91.27 41.06 4274 116.11 516.69 1044.28 1489 38.70 8.19 0.39 174.20 76.72 73.73 15.87 89.63 86.03 53.91 375.72 417.35 2.57 206.00 302.10 305.09 18.64 83.72 670.35 0.74 OpenBenchmarking.org
Apache Benchmark OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.3 Static Web Page Serving Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 400 800 1200 1600 2000 SE +/- 8.50, N = 3 SE +/- 4.38, N = 3 1942.27 1444.53 1. (CC) gcc options: -shared -fPIC -O2 -pthread
NGINX Benchmark OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.0.11 Static Web Page Serving Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 600 1200 1800 2400 3000 SE +/- 32.35, N = 3 SE +/- 32.70, N = 3 2956.20 2159.02 -lcrypto 1. (CC) gcc options: -lpthread -lcrypt -lz
OpenSSL OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.0.1c RSA 4096-bit Performance Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 9.90 5.90 1. (CC) gcc options: -march=armv7-a -O3 -lssl -lcrypto -ldl
FFmpeg OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 1.1 H.264 HD To NTSC DV Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 80 160 240 320 400 SE +/- 1.24, N = 3 SE +/- 2.33, N = 3 124.93 362.85 -lrt 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lm -pthread
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.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 900 1800 2700 3600 4500 SE +/- 93.30, N = 3 SE +/- 4.84, N = 3 1469 4274 1. (CXX) g++ options: -fopenmp
Primesieve OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 4.0 1e12 Prime Number Generation Exynos 5 Dual Nexus 10 200 400 600 800 1000 SE +/- 14.35, N = 5 1000.73 1. (CXX) g++ options: -O2 -fopenmp
Parallel BZIP2 Compression OpenBenchmarking.org Seconds, Fewer Is Better Parallel BZIP2 Compression 1.1.6 256MB File Compression Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 30 60 90 120 150 SE +/- 0.77, N = 3 SE +/- 4.41, N = 6 91.98 116.11 1. (CXX) g++ options: -O2 -pthread -lbz2 -lpthread
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.org Seconds, Fewer Is Better C-Ray 1.1 Total Time Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 110 220 330 440 550 SE +/- 3.87, N = 3 SE +/- 0.33, N = 3 358.54 516.69 1. (CC) gcc options: -lm -lpthread -O3
7-Zip Compression OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 9.20.1 Compress Speed Test Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 300 600 900 1200 1500 SE +/- 32.10, N = 3 SE +/- 4.91, N = 3 1628 1489 1. (CXX) g++ options: -pipe -lpthread
x264 OpenBenchmarking.org Frames Per Second, More Is Better x264 2013-01-28 H.264 Video Encoding Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 3 6 9 12 15 SE +/- 0.10, N = 3 SE +/- 0.13, N = 6 10.07 8.19
VP8 libvpx Encoding OpenBenchmarking.org Frames Per Second, More Is Better VP8 libvpx Encoding 1.1.0 vpxenc Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 0.261 0.522 0.783 1.044 1.305 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 1.16 0.39 1. (CC) gcc options: -lvpx -lm -lpthread
SciMark OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 80 160 240 320 400 SE +/- 0.46, N = 4 SE +/- 0.00, N = 4 350.79 174.20
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 90 180 270 360 450 SE +/- 1.73, N = 4 SE +/- 0.00, N = 4 426.69 76.72
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 70 140 210 280 350 SE +/- 0.94, N = 4 SE +/- 0.05, N = 4 334.10 73.73
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 8 16 24 32 40 SE +/- 0.25, N = 4 SE +/- 0.04, N = 4 36.51 15.87
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 40 80 120 160 200 SE +/- 0.14, N = 4 SE +/- 0.09, N = 4 160.98 89.63
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 60 120 180 240 300 SE +/- 0.55, N = 4 SE +/- 0.02, N = 4 261.82 86.03
Timed MAFFT Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 6.864 Multiple Sequence Alignment Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 12 24 36 48 60 SE +/- 0.18, N = 3 SE +/- 0.58, N = 3 43.20 53.91 1. (CC) gcc options: -O3 -lm -lpthread
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.org MFLOPS, More Is Better FFTE 5.0 Test: N=64, 1D Complex FFT Routine Exynos 5 Dual Nexus 10 300 600 900 1200 1500 SE +/- 3.30, N = 3 1479.35 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -lmpichf90 -lmpich -lopa -lmpl -lrt -lcr -lpthread
NAS Parallel Benchmarks OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: UA.A Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 0.8393 1.6786 2.5179 3.3572 4.1965 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 3.73 2.57 1. (F9X) gfortran options: -fopenmp
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.org Speedup, More Is Better CLOMP 3.3 Static OMP Speedup Exynos 5 Dual Nexus 10 Tegra 3 Cardhu 0.3623 0.7246 1.0869 1.4492 1.8115 SE +/- 0.09, N = 10 SE +/- 0.00, N = 5 1.61 0.74 1. (CC) gcc options: --openmp -O3 -lm
PostMark This is a test of NetApp's PostMark benchmark designed to simulate small-file testing similar to the tasks endured by web and mail servers. This test profile will set PostMark to perform 25,000 transactions with 500 files simultaneously with the file sizes ranging between 5 and 512 kilobytes. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance Exynos 5 Dual Nexus 10 30 60 90 120 150 SE +/- 0.00, N = 3 154 1. (CC) gcc options: -O3
Exynos 5 Dual Nexus 10 Processor: ARMv7 rev 4 @ 1.70GHz (2 Cores), Motherboard: Manta, Memory: 2048MB, Disk: 16GB MAG2GA
OS: Ubuntu 12.10, Kernel: 3.4.5-gf68518f (armv7l), Compiler: GCC 4.7, File-System: ext4, Screen Resolution: 2560x1600
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 -vProcessor Notes: Scaling Governor: interactive
Testing initiated at 23 February 2013 05:58 by user root.
Tegra 3 Cardhu 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 4.6, File-System: ext3, Screen Resolution: 1366x1536
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 -vProcessor Notes: Scaling Governor: ondemand
Testing initiated at 23 February 2013 14:13 by user ubuntu.