NVIDIA Jetson TX2 vs AMLOGIC S805 / S905 vs UGOOS UT3 RK3288

The overpriced princess trying to fend off niggardly bastards

HTML result view exported from: https://openbenchmarking.org/result/1711043-TY-1703186RI07&sor.

NVIDIA Jetson TX2 vs AMLOGIC S805 / S905 vs UGOOS UT3 RK3288ProcessorMotherboardMemoryDiskGraphicsOSKernelDesktopDisplay ServerDisplay DriverOpenGLVulkanCompilerFile-SystemScreen ResolutionNVIDIA Jetson TX2Beelink MXIII S905 vanillaBeelink MXIII S905 optimizedOdroid C1 GCC 4.9Odroid C1 GCC 7.0.1UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A12 codegen GCC 4.9UGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A17 codegen GCC 8.0ARMv8 rev 3 @ 2.00GHz (6 Cores)quill8192MB31GB 032G34NVIDIA TEGRAUbuntu 16.044.4.15-tegra (aarch64)Unity 7.4.0X Server 1.18.3NVIDIA 1.0.04.5.01.0.8GCC 5.4.0 20160609 + CUDA 8.0ext43840x2160Unknown @ 1.54GHz (4 Cores)Amlogic2048MB60GB A + 16GB NCard + 32GB 000003.14.79-vegas95 (aarch64)GCC 5.4.0 20160609 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.01280x1440GCC 7.0.1 20170315 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0GCC 4.9.4 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.01280x1024ARMv7 rev 1 @ 1.73GHz (4 Cores)ODROIDC915MB60GB A + 64GB 00000Ubuntu 14.043.10.80-20-odrobian (armv7l)X Server 1.15.1GCC 7.0.1 20170315 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.0ARMv7 rev 1 @ 1.80GHz (4 Cores)Rockchip RK3288 (Flattened Device Tree)2048MB64GB Card Reader + 16GB MAG2GA + 16GB NCardfb0Ubuntu 15.043.10.0 (armv7l)modesetting 1.17.1GCC 4.9.21920x1080GCC 8.0.0 20171101OpenBenchmarking.orgCompiler Details- NVIDIA Jetson TX2: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v- Beelink MXIII S905 vanilla: --build=aarch64-linux-gnu --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-fix-cortex-a53-843419 --enable-gnu-unique-object --enable-gtk-cairo --enable-java-awt=gtk --enable-java-home --enable-languages=c,ada,c++,java,go,d,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new -v - Beelink MXIII S905 optimized: --build=aarch64-linux-gnu --disable-bootstrap --disable-browser-plugin --disable-libquadmath --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,fortran --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=aarch64-linux-gnu --target=aarch64-linux-gnu --with-arch-directory=aarch64 --with-default-libstdcxx-abi=new- Odroid C1 GCC 4.9: --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 - Odroid C1 GCC 7.0.1: --build=arm-linux-gnueabihf --disable-bootstrap --disable-browser-plugin --disable-libitm --disable-libquadmath --disable-libstdcxx-dual-abi --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,fortran,ada --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-multilib --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch-directory=arm --with-arch=armv7-a --with-default-libstdcxx-abi=gcc4-compatible --with-float=hard --with-fpu=vfpv3 --with-mode=arm -v - UGOOS UT3 @ A5 codegen GCC 4.9: --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 - UGOOS UT3 @ A12 codegen GCC 4.9: --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 - UGOOS UT3 @ A5 codegen GCC 8.0: --build=arm-linux-gnueabihf --disable-bootstrap --disable-browser-plugin --disable-libitm --disable-libquadmath --disable-libstdcxx-dual-abi --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,fortran --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-multilib --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch-directory=arm --with-arch=armv7-a --with-default-libstdcxx-abi=gcc4-compatible --with-float=hard --with-fpu=vfpv3 --with-mode=arm -v - UGOOS UT3 @ A17 codegen GCC 8.0: --build=arm-linux-gnueabihf --disable-bootstrap --disable-browser-plugin --disable-libitm --disable-libquadmath --disable-libstdcxx-dual-abi --disable-sjlj-exceptions --disable-werror --enable-checking=release --enable-clocale=gnu --enable-gnu-unique-object --enable-languages=c,c++,fortran --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-multilib --enable-nls --enable-plugin --enable-shared --enable-threads=posix --host=arm-linux-gnueabihf --target=arm-linux-gnueabihf --with-arch-directory=arm --with-arch=armv7-a --with-default-libstdcxx-abi=gcc4-compatible --with-float=hard --with-fpu=vfpv3 --with-mode=arm -v Processor Details- NVIDIA Jetson TX2: Scaling Governor: tegra_cpufreq schedutil- Beelink MXIII S905 vanilla: Scaling Governor: meson_cpufreq performance- Beelink MXIII S905 optimized: Scaling Governor: meson_cpufreq performance- Odroid C1 GCC 4.9: Scaling Governor: meson_cpufreq conservative- Odroid C1 GCC 7.0.1: Scaling Governor: meson_cpufreq performance- UGOOS UT3 @ A5 codegen GCC 4.9: Scaling Governor: rockchip performance- UGOOS UT3 @ A12 codegen GCC 4.9: Scaling Governor: rockchip performance- UGOOS UT3 @ A5 codegen GCC 8.0: Scaling Governor: rockchip performance- UGOOS UT3 @ A17 codegen GCC 8.0: Scaling Governor: rockchip interactive

NVIDIA Jetson TX2 vs AMLOGIC S805 / S905 vs UGOOS UT3 RK3288fftw: Stock - 2D FFT Size 1024john-the-ripper: Blowfishbuild-linux-kernel: Time To Compilec-ray: Total Timesmallpt: Global Illumination Renderer; 100 Samplesencode-flac: WAV To FLACredis: GETredis: SETNVIDIA Jetson TX2Beelink MXIII S905 vanillaBeelink MXIII S905 optimizedOdroid C1 GCC 4.9Odroid C1 GCC 7.0.1UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A12 codegen GCC 4.9UGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A17 codegen GCC 8.0387.4914641108.2371.0640740.63700737.81494697.07190.808772233.83187.83690155.20252629.09179788.76193.239202234.25148.26169159.29252504.73179089.73142.715543202.79238.81283186.04154412.67117094.55136.836154390.27233.66288187.27179600.67122115.68369.4211011274.9897.0516962.23357554.23261294.84260.8411011268.98103.0417065.75316555.43261539.75384.629491622.5496.8316354.70360414.06279548.97348.779491609.1998.3416457.52353509.57265780.21OpenBenchmarking.org

FFTW

Build: Stock - Size: 2D FFT Size 1024

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.4Build: Stock - Size: 2D FFT Size 1024NVIDIA Jetson TX2UGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A17 codegen GCC 8.0UGOOS UT3 @ A12 codegen GCC 4.9Beelink MXIII S905 optimizedBeelink MXIII S905 vanillaOdroid C1 GCC 4.9Odroid C1 GCC 7.0.180160240320400SE +/- 4.81, N = 5SE +/- 2.97, N = 5SE +/- 2.94, N = 5SE +/- 3.99, N = 5SE +/- 4.78, N = 10SE +/- 0.83, N = 5SE +/- 0.77, N = 5SE +/- 0.15, N = 5SE +/- 0.43, N = 5387.49384.62369.42348.77260.84193.23190.80142.71136.83-O3 -mtune=native -fstrict-aliasing -fno-schedule-insns -ffast-math-mcpu=cortex-a5 -Ofast -marm -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-std=gnu99 -mcpu=cortex-a5 -Ofast -marm -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a17 -Ofast -marm -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-std=gnu99 -mcpu=cortex-a12 -Ofast -marm -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-Ofast -mtune=cortex-a57 -fipa-pta -march=armv8-a+crc -ftree-vectorize-O3 -mtune=native -fstrict-aliasing -fno-schedule-insns -ffast-math-std=gnu99 -mcpu=cortex-a5 -Ofast -marm -fipa-pta -mfpu=neon-vfpv4 -funroll-loops -ftree-loop-ivcanon -fivopts-mcpu=cortex-a5 -Ofast -marm -fipa-pta -mfpu=vfpv3 -funroll-loops -ftree-loop-ivcanon -fivopts1. (CC) gcc options: -fomit-frame-pointer -lm

John The Ripper

Test: Blowfish

OpenBenchmarking.orgReal C/S, More Is BetterJohn The Ripper 1.8.0Test: BlowfishNVIDIA Jetson TX2UGOOS UT3 @ A12 codegen GCC 4.9UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A17 codegen GCC 8.0UGOOS UT3 @ A5 codegen GCC 8.0Beelink MXIII S905 optimizedBeelink MXIII S905 vanillaOdroid C1 GCC 7.0.1Odroid C1 GCC 4.930060090012001500SE +/- 22.23, N = 6SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 3SE +/- 0.67, N = 31464110111019499499208776155541. (CC) gcc options: -fopenmp

Timed Linux Kernel Compilation

Time To Compile

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed Linux Kernel Compilation 4.9Time To CompileNVIDIA Jetson TX2UGOOS UT3 @ A12 codegen GCC 4.9UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A17 codegen GCC 8.0UGOOS UT3 @ A5 codegen GCC 8.0Beelink MXIII S905 vanillaBeelink MXIII S905 optimizedOdroid C1 GCC 4.9Odroid C1 GCC 7.0.19001800270036004500SE +/- 8.96, N = 3SE +/- 1.38, N = 3SE +/- 7.21, N = 3SE +/- 2.09, N = 3SE +/- 3.50, N = 3SE +/- 7.41, N = 3SE +/- 7.62, N = 3SE +/- 17.62, N = 3SE +/- 8.84, N = 31108.231268.981274.981609.191622.542233.832234.253202.794390.27

C-Ray

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total TimeNVIDIA Jetson TX2UGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A17 codegen GCC 8.0UGOOS UT3 @ A12 codegen GCC 4.9Beelink MXIII S905 optimizedBeelink MXIII S905 vanillaOdroid C1 GCC 7.0.1Odroid C1 GCC 4.950100150200250SE +/- 2.94, N = 6SE +/- 0.37, N = 3SE +/- 0.13, N = 3SE +/- 0.61, N = 3SE +/- 0.38, N = 3SE +/- 1.09, N = 3SE +/- 1.77, N = 3SE +/- 0.06, N = 3SE +/- 0.09, N = 371.0696.8397.0598.34103.04148.26187.83233.66238.81-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a17 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a12 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-Ofast -mtune=cortex-a57 -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -ftree-vectorize-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=vfpv3 -funroll-loops -ftree-loop-ivcanon -fivopts-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=vfpv3 -funroll-loops -ftree-loop-ivcanon -fivopts1. (CC) gcc options: -lm -lpthread -O3

Smallpt

Global Illumination Renderer; 100 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 SamplesUGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A17 codegen GCC 8.0Beelink MXIII S905 optimizedUGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A12 codegen GCC 4.9Odroid C1 GCC 4.9Odroid C1 GCC 7.0.1NVIDIA Jetson TX2Beelink MXIII S905 vanilla150300450600750SE +/- 0.58, N = 3SE +/- 1.20, N = 3SE +/- 0.33, N = 3SE +/- 0.58, N = 3163164169169170283288407690-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a17 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-Ofast -mtune=cortex-a57 -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -ftree-vectorize-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a12 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=vfpv3 -funroll-loops -ftree-loop-ivcanon -fivopts1. (CXX) g++ options: -fopenmp

FLAC Audio Encoding

WAV To FLAC

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.1WAV To FLACNVIDIA Jetson TX2UGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A17 codegen GCC 8.0UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A12 codegen GCC 4.9Beelink MXIII S905 vanillaBeelink MXIII S905 optimizedOdroid C1 GCC 4.9Odroid C1 GCC 7.0.14080120160200SE +/- 0.36, N = 5SE +/- 0.40, N = 5SE +/- 0.02, N = 5SE +/- 0.15, N = 5SE +/- 0.03, N = 5SE +/- 0.13, N = 5SE +/- 0.08, N = 5SE +/- 1.27, N = 5SE +/- 1.64, N = 540.6354.7057.5262.2365.75155.20159.29186.04187.27-O2-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a17 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-mcpu=cortex-a12 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-O2 -logg-Ofast -mtune=cortex-a57 -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -ftree-vectorize -logg-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=vfpv3 -funroll-loops -ftree-loop-ivcanon -fivopts -logg-mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=vfpv3 -funroll-loops -ftree-loop-ivcanon -fivopts -logg1. (CXX) g++ options: -fvisibility=hidden -lm

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETNVIDIA Jetson TX2UGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A5 codegen GCC 4.9UGOOS UT3 @ A17 codegen GCC 8.0UGOOS UT3 @ A12 codegen GCC 4.9Beelink MXIII S905 vanillaBeelink MXIII S905 optimizedOdroid C1 GCC 7.0.1Odroid C1 GCC 4.9150K300K450K600K750KSE +/- 6796.75, N = 3SE +/- 3105.33, N = 3SE +/- 2254.20, N = 3SE +/- 2210.59, N = 3SE +/- 4730.53, N = 5SE +/- 2247.82, N = 3SE +/- 2339.92, N = 3SE +/- 1782.68, N = 3SE +/- 1250.52, N = 3700737.81360414.06357554.23353509.57316555.43252629.09252504.73179600.67154412.67-std=gnu99 -pipe -g3 -O3 -funroll-loops-O2 -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-std=gnu99 -pipe -g3 -O3 -funroll-loops -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-O2 -mcpu=cortex-a17 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-O2 -mcpu=cortex-a12 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-std=gnu99 -pipe -g3 -O3 -funroll-loops-O2 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -ftree-vectorize-O2 -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=vfpv3 -funroll-loops -ftree-loop-ivcanon -fivopts1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl

Redis

Test: SET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: SETNVIDIA Jetson TX2UGOOS UT3 @ A5 codegen GCC 8.0UGOOS UT3 @ A17 codegen GCC 8.0UGOOS UT3 @ A12 codegen GCC 4.9UGOOS UT3 @ A5 codegen GCC 4.9Beelink MXIII S905 vanillaBeelink MXIII S905 optimizedOdroid C1 GCC 7.0.1Odroid C1 GCC 4.9110K220K330K440K550KSE +/- 3705.12, N = 3SE +/- 4413.82, N = 3SE +/- 2141.89, N = 3SE +/- 4560.48, N = 4SE +/- 3770.71, N = 3SE +/- 2359.99, N = 3SE +/- 1589.89, N = 3SE +/- 2197.48, N = 3SE +/- 2333.75, N = 6494697.07279548.97265780.21261539.75261294.84179788.76179089.73122115.68117094.55-std=gnu99 -pipe -g3 -O3 -funroll-loops-O2 -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-O2 -mcpu=cortex-a17 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-O2 -mcpu=cortex-a12 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-std=gnu99 -pipe -g3 -O3 -funroll-loops -mcpu=cortex-a5 -Ofast -marm -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers-std=gnu99 -pipe -g3 -O3 -funroll-loops-O2 -Ofast -mtune=cortex-a57 -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -ftree-vectorize1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl

Phoronix Test Suite v10.8.4