Quad-Core Cortex-A15 big.LITTLE ARM Linux Comparison Comparing different ARM and x86 systems, in particular looking at the ARM Cortex-A15 quad-core + Cortex-A7 quad-core big.LITTLE configuration from a Samsung Exynos 5 Octa SoC on the Hardkernel ODROID-XUs. The ARM x86 tests for a future article on Phoronix.com.
HTML result view exported from: https://openbenchmarking.org/result/1611045-LO-MERGE258799&grs&export=pdf&sor .
Quad-Core Cortex-A15 big.LITTLE ARM Linux Comparison Processor Motherboard Memory Disk Monitor Chipset Graphics Audio Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution ODROID XU4 QC A15 Intel i7 Exynos ARMv7 rev 3 @ 1.40GHz (8 Cores) ODROID-XU3 2048MB 128GB SL128 DELL U2410 Ubuntu 15.04 3.10.103+ (armv7l) MATE 1.8.2 X Server 1.17.1 2.1 Mesa 10.5.9 GCC 4.9.2 ext4 1280x1024 Intel Core i7-4770 @ 3.90GHz (8 Cores) Dell 0XCR8D Intel 4th Gen Core DRAM 2 x 4096 MB DDR3-1600MHz 500GB Seagate ST500DM002-1BD14 Intel Gen7 Intel Xeon E3-1200 v3/4th Intel Connection I217-LM 3.19.0-15-generic (x86_64) 1680x1050 OpenBenchmarking.org Compiler Details - ODROID XU4 QC A15: --build=arm-linux-gnueabihf --disable-browser-plugin --disable-libitm --disable-libquadmath --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-multilib --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch-directory=arm --with-arch=armv7-a --with-float=hard --with-fpu=vfpv3-d16 --with-mode=thumb -v - Intel i7: --build=x86_64-linux-gnu --disable-browser-plugin --disable-vtable-verify --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,c++,java,go,d,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=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-arch-directory=amd64 --with-multilib-list=m32,m64,mx32 --with-tune=generic -v Processor Details - ODROID XU4 QC A15: Scaling Governor: exynos_cpufreq performance - Intel i7: Scaling Governor: intel_pstate powersave
Quad-Core Cortex-A15 big.LITTLE ARM Linux Comparison smallpt: Global Illumination Renderer; 100 Samples npb: SP.A npb: MG.B lammps: Rhodopsin Protein ffte: N=64, 1D Complex FFT Routine apache: Static Web Page Serving npb: LU.A npb: UA.A compress-7zip: Compress Speed Test c-ray: Total Time ODROID XU4 QC A15 Intel i7 603 813.27 952.76 156.66 1909.19 2417.87 913.82 3.41 107.45 77 5911.36 6073.92 32.32 5929.63 45460.59 14778.60 51.12 21635 22.79 OpenBenchmarking.org
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples Intel i7 ODROID XU4 QC A15 130 260 390 520 650 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 77 603 1. (CXX) g++ options: -fopenmp
NAS Parallel Benchmarks Test / Class: SP.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: SP.A Intel i7 ODROID XU4 QC A15 1300 2600 3900 5200 6500 SE +/- 100.88, N = 3 SE +/- 2.34, N = 3 5911.36 813.27 1. (F9X) gfortran options: -fopenmp
NAS Parallel Benchmarks Test / Class: MG.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: MG.B Intel i7 ODROID XU4 QC A15 1300 2600 3900 5200 6500 SE +/- 3.25, N = 3 SE +/- 4.89, N = 3 6073.92 952.76 1. (F9X) gfortran options: -fopenmp
LAMMPS Molecular Dynamics Simulator Test: Rhodopsin Protein OpenBenchmarking.org Loop Time, Fewer Is Better LAMMPS Molecular Dynamics Simulator 1.0 Test: Rhodopsin Protein Intel i7 ODROID XU4 QC A15 30 60 90 120 150 SE +/- 0.07, N = 3 SE +/- 0.14, N = 3 32.32 156.66 1. (CXX) g++ options: -lfftw -lmpich
FFTE Test: N=64, 1D Complex FFT Routine OpenBenchmarking.org MFLOPS, More Is Better FFTE 5.0 Test: N=64, 1D Complex FFT Routine Intel i7 ODROID XU4 QC A15 1300 2600 3900 5200 6500 SE +/- 10.44, N = 3 SE +/- 0.11, N = 3 5929.63 1909.19 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_f90 -lmpi_f77 -lmpi -ldl -lhwloc
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.2.21 Static Web Page Serving Intel i7 ODROID XU4 QC A15 10K 20K 30K 40K 50K SE +/- 886.22, N = 6 SE +/- 4.93, N = 3 45460.59 2417.87 1. (CC) gcc options: -O2 -pthread -lm -lrt -lcrypt -lpthread -ldl
NAS Parallel Benchmarks Test / Class: LU.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: LU.A Intel i7 ODROID XU4 QC A15 3K 6K 9K 12K 15K SE +/- 217.57, N = 3 SE +/- 7.26, N = 3 14778.60 913.82 1. (F9X) gfortran options: -fopenmp
NAS Parallel Benchmarks Test / Class: UA.A OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.3 Test / Class: UA.A Intel i7 ODROID XU4 QC A15 12 24 36 48 60 SE +/- 0.36, N = 3 SE +/- 0.01, N = 3 51.12 3.41 1. (F9X) gfortran options: -fopenmp
Meta Performance Per Dollar Performance Per Dollar OpenBenchmarking.org Performance Per Dollar, More Is Better Meta Performance Per Dollar Performance Per Dollar ODROID XU4 QC A15 4 8 12 16 20 15.79 1. $74 reported cost. Average result: 1168.39.
Apache Benchmark Performance / Cost - Static Web Page Serving OpenBenchmarking.org Requests Per Second Per Dollar, More Is Better Apache Benchmark 2.2.21 Performance / Cost - Static Web Page Serving ODROID XU4 QC A15 8 16 24 32 40 32.67 1. $74 reported cost.
FFTE Performance / Cost - Test: N=64, 1D Complex FFT Routine OpenBenchmarking.org MFLOPS Per Dollar, More Is Better FFTE 5.0 Performance / Cost - Test: N=64, 1D Complex FFT Routine ODROID XU4 QC A15 6 12 18 24 30 25.80 1. $74 reported cost.
NAS Parallel Benchmarks Performance / Cost - Test / Class: UA.A OpenBenchmarking.org Total Mop/s Per Dollar, More Is Better NAS Parallel Benchmarks 3.3 Performance / Cost - Test / Class: UA.A ODROID XU4 QC A15 0.0113 0.0226 0.0339 0.0452 0.0565 0.05 1. $74 reported cost.
NAS Parallel Benchmarks Performance / Cost - Test / Class: SP.A OpenBenchmarking.org Total Mop/s Per Dollar, More Is Better NAS Parallel Benchmarks 3.3 Performance / Cost - Test / Class: SP.A ODROID XU4 QC A15 3 6 9 12 15 10.99 1. $74 reported cost.
NAS Parallel Benchmarks Performance / Cost - Test / Class: MG.B OpenBenchmarking.org Total Mop/s Per Dollar, More Is Better NAS Parallel Benchmarks 3.3 Performance / Cost - Test / Class: MG.B ODROID XU4 QC A15 3 6 9 12 15 12.88 1. $74 reported cost.
NAS Parallel Benchmarks Performance / Cost - Test / Class: LU.A OpenBenchmarking.org Total Mop/s Per Dollar, More Is Better NAS Parallel Benchmarks 3.3 Performance / Cost - Test / Class: LU.A ODROID XU4 QC A15 3 6 9 12 15 12.35 1. $74 reported cost.
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 9.20.1 Compress Speed Test Intel i7 5K 10K 15K 20K 25K SE +/- 354.69, N = 3 21635 1. (CXX) g++ options: -pipe -lpthread
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time Intel i7 ODROID XU4 QC A15 20 40 60 80 100 SE +/- 0.01, N = 3 SE +/- 2.63, N = 6 22.79 107.45 1. (CC) gcc options: -lm -lpthread -O3
Phoronix Test Suite v10.8.5