Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1702269-RI-1608129KH10 Cavium Thunderx vs Amlogic S905 - Phoronix Test Suite Cavium Thunderx vs Amlogic S905 David vs Goliath?
HTML result view exported from: https://openbenchmarking.org/result/1702269-RI-1608129KH10&grw&sro .
Cavium Thunderx vs Amlogic S905 Processor Motherboard Memory Disk Graphics Network OS Kernel Display Server Display Driver OpenGL Compiler File-System Screen Resolution Thunderx S905 Unknown (96 Cores) cavium ThunderX Unknown 262144MB 240GB INTEL SSDSC2BB24 + 4 x 1000GB HGST HTS721010A9 ASPEED ASPEED Family Cavium THUNDERX Interface + Cavium THUNDERX BGX Ubuntu 16.04 4.2.0-pmu1-g749be54 (aarch64) X Server 1.18.3 NVIDIA 352.55) 1.4 GCC 5.3.0 + Clang 3.9.0 + LLVM 3.9.0svn ext4 2160x1920 Unknown @ 1.54GHz (4 Cores) Amlogic 2048MB 16GB NCard + 32GB 00000 3.14.79-vegas95 (aarch64) GCC 7.0.1 20170220 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0 1280x1440 OpenBenchmarking.org Compiler Details - Thunderx: --disable-libsanitizer --disable-libsanitizer --disable-werror --disable-werror --enable-languages=c,c++,fortran,lto,objc --enable-languages=c,c++,fortran,objc --enable-lto --enable-lto --enable-modules --enable-modules --no-create --no-recursion --with-cpu=thunderx --with-cpu=thunderx - S905: --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-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 Processor Details - S905: Scaling Governor: meson_cpufreq performance
Cavium Thunderx vs Amlogic S905 ramspeed: Integer Add ramspeed: Integer Copy ramspeed: Integer Scale ramspeed: Floating-Point Add stream: Add stream: Copy stream: Scale cachebench: Read Cache cachebench: Write Cache Thunderx S905 3118.76 3807.17 2821.40 2733.73 44608.56 40248.52 44096.67 3311.91 3384.21 3924.06 4612.18 4470.06 3950.23 390.54 322.10 345.18 2568.30 4775.82 OpenBenchmarking.org
RAMspeed SMP Integer Add OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Integer Add S905 Thunderx 800 1600 2400 3200 4000 3924.06 3118.76
RAMspeed SMP Integer Copy OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Integer Copy S905 Thunderx 1000 2000 3000 4000 5000 4612.18 3807.17
RAMspeed SMP Integer Scale OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Integer Scale S905 Thunderx 1000 2000 3000 4000 5000 4470.06 2821.40
RAMspeed SMP Floating-Point Add OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Floating-Point Add S905 Thunderx 800 1600 2400 3200 4000 3950.23 2733.73
Stream Add OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Add S905 Thunderx 10K 20K 30K 40K 50K SE +/- 17.71, N = 5 SE +/- 2003.35, N = 10 390.54 44608.56 -O3 -march=native 1. (CC) gcc options: -fopenmp
Stream Copy OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Copy S905 Thunderx 9K 18K 27K 36K 45K SE +/- 8.58, N = 5 SE +/- 1983.34, N = 5 322.10 40248.52 -O3 -march=native 1. (CC) gcc options: -fopenmp
Stream Scale OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Scale S905 Thunderx 9K 18K 27K 36K 45K SE +/- 3.00, N = 5 SE +/- 454.77, N = 3 345.18 44096.67 -O3 -march=native 1. (CC) gcc options: -fopenmp
CacheBench Read Cache OpenBenchmarking.org MB/s, More Is Better CacheBench Read Cache S905 Thunderx 700 1400 2100 2800 3500 SE +/- 2.24, N = 3 SE +/- 0.04, N = 3 2568.30 3311.91 1. (CC) gcc options: -lrt
CacheBench Write Cache OpenBenchmarking.org MB/s, More Is Better CacheBench Write Cache S905 Thunderx 1000 2000 3000 4000 5000 SE +/- 4.51, N = 3 SE +/- 0.06, N = 3 4775.82 3384.21 1. (CC) gcc options: -lrt
Phoronix Test Suite v10.8.4