Cortex A53 vs Cortex A5

low-power 32/64-bit ARM comparison

HTML result view exported from: https://openbenchmarking.org/result/1701165-TA-1701143TA78&sor.

Cortex A53 vs Cortex A5ProcessorMotherboardMemoryDiskOSKernelCompilerFile-SystemScreen ResolutionDisplay ServerA53 vectorize, pre-patchthunderx/vectorize, pre-patchA53 vectorize/LTO, pre patchCortex-A53Cortex-A53 vectorizeCortex-A5 VFPV4Cortex-A5 NeonAArch64 rev 4 @ 1.50GHz (4 Cores)Amlogic2048MB32GB 00000 + 16GB NCardUbuntu 16.043.14.29 (aarch64)GCC 7.0.0 20170110 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0ext41920x3240AArch64 rev 4 @ 1.55GHz (4 Cores)GCC 7.0.0 20170113 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0ARMv7 rev 1 @ 1.73GHz (4 Cores)ODROIDC916MB64GB 00000Ubuntu 14.043.10.96-149 (armv7l)X Server 1.15.1GCC 7.0.0 20170114 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.01280x1024OpenBenchmarking.orgCompiler Details- A53 vectorize, pre-patch: --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 - thunderx/vectorize, pre-patch: --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 - A53 vectorize/LTO, pre patch: --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 - Cortex-A53: --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 - Cortex-A53 vectorize: --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 - Cortex-A5 VFPV4: --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-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 - Cortex-A5 Neon: --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-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 Disk Details- A53 vectorize, pre-patch: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- thunderx/vectorize, pre-patch: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- A53 vectorize/LTO, pre patch: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- Cortex-A53: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- Cortex-A53 vectorize: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- Cortex-A5 VFPV4: CFQ / commit=25,errors=remount-ro,noatime,nodiratime,rw- Cortex-A5 Neon: CFQ / commit=25,errors=remount-ro,noatime,nodiratime,rwProcessor Details- A53 vectorize, pre-patch: Scaling Governor: meson_cpufreq performance- thunderx/vectorize, pre-patch: Scaling Governor: meson_cpufreq performance- A53 vectorize/LTO, pre patch: Scaling Governor: meson_cpufreq performance- Cortex-A53: Scaling Governor: meson_cpufreq performance- Cortex-A53 vectorize: Scaling Governor: meson_cpufreq interactive- Cortex-A5 VFPV4: Scaling Governor: meson_cpufreq performance- Cortex-A5 Neon: Scaling Governor: meson_cpufreq performance

Cortex A53 vs Cortex A5postmark: Disk Transaction Performanceramspeed: Copy - Integerramspeed: Copy - Floating Pointfftw: Stock - 2D FFT Size 2048mafft: Multiple Sequence Alignmentgmpbench: Total Timefhourstones: Complex Connect-4 Solvingttsiod-renderer: Phong Rendering With Soft-Shadow Mappingc-ray: Total Timeprimesieve: 1e12 Prime Number Generationsmallpt: Global Illumination Renderer; 100 Samplessudokut: Total Timetachyon: Total Timeopenssl: RSA 4096-bit Performanceredis: GETA53 vectorize, pre-patchthunderx/vectorize, pre-patchA53 vectorize/LTO, pre patchCortex-A53Cortex-A53 vectorizeCortex-A5 VFPV4Cortex-A5 Neon13634581.324580.39196.9035.42552.843212.1023.16187.97543.16167101.9569.2721.50310344.7313512821.432817.45190.6334.46554.833210.2023.01149.82566.21167102.7571.4121.50318926.0213784829.914825.13180.5333.16554.373213.7723.77184.81540.95168101.7567.6421.50311785.0213814965.064964.66186.2133.06552.563209.6723.47186.69553.13168101.8869.4021.50309030.6413784955.974965.60184.8132.17555.103205.4023.49186.61573.13167102.1769.3421.50313438.917251476.431365.27135.0743.74221.561211.3316.91273.18836.59306167.97107.3320.23174917.947171262.111049.66128.7545.21221.631246.7715.75235.231021.13289165.14247.9620.30177754.08OpenBenchmarking.org

PostMark

Disk Transaction Performance

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction PerformanceCortex-A53Cortex-A53 vectorizeA53 vectorize/LTO, pre patchA53 vectorize, pre-patchthunderx/vectorize, pre-patchCortex-A5 VFPV4Cortex-A5 Neon30060090012001500SE +/- 4.33, N = 3SE +/- 5.00, N = 3SE +/- 2.67, N = 3SE +/- 2.67, N = 3SE +/- 0.00, N = 3SE +/- 11.49, N = 6SE +/- 10.35, N = 3138113781378136313517257171. (CC) gcc options: -O3

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: IntegerCortex-A53Cortex-A53 vectorizeA53 vectorize/LTO, pre patchA53 vectorize, pre-patchthunderx/vectorize, pre-patchCortex-A5 VFPV4Cortex-A5 Neon110022003300440055004965.064955.974829.914581.322821.431476.431262.11

RAMspeed SMP

Type: Copy - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating PointCortex-A53 vectorizeCortex-A53A53 vectorize/LTO, pre patchA53 vectorize, pre-patchthunderx/vectorize, pre-patchCortex-A5 VFPV4Cortex-A5 Neon110022003300440055004965.604964.664825.134580.392817.451365.271049.66

FFTW

Build: Stock - Size: 2D FFT Size 2048

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.4Build: Stock - Size: 2D FFT Size 2048A53 vectorize, pre-patchthunderx/vectorize, pre-patchCortex-A53Cortex-A53 vectorizeA53 vectorize/LTO, pre patchCortex-A5 VFPV4Cortex-A5 Neon4080120160200SE +/- 0.99, N = 5SE +/- 1.10, N = 5SE +/- 0.08, N = 5SE +/- 0.21, N = 5SE +/- 0.49, N = 5SE +/- 1.16, N = 5SE +/- 0.03, N = 5196.90190.63186.21184.81180.53135.07128.75-Ofast -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=thunderx -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=cortex-a53 -march=armv8-a+crc-Ofast -mtune=cortex-a53 -march=armv8-a+crc -ftree-vectorize-O3 -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize -flto -ffat-lto-objects-mcpu=cortex-a5 -O3 -marm -mfpu=vfpv4-mcpu=cortex-a5 -Ofast -marm -mfpu=neon -ftree-vectorize1. (CC) gcc options: -fomit-frame-pointer -fipa-pta -lm

Timed MAFFT Alignment

Multiple Sequence Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence AlignmentCortex-A53 vectorizeCortex-A53A53 vectorize/LTO, pre patchthunderx/vectorize, pre-patchA53 vectorize, pre-patchCortex-A5 VFPV4Cortex-A5 Neon1020304050SE +/- 0.01, N = 3SE +/- 0.71, N = 6SE +/- 0.70, N = 6SE +/- 0.73, N = 6SE +/- 0.80, N = 6SE +/- 1.04, N = 6SE +/- 1.09, N = 632.1733.0633.1634.4635.4243.7445.211. (CC) gcc options: -O3 -lm -lpthread

GMPbench

Total Time

OpenBenchmarking.orgGMPbench Score, More Is BetterGMPbench 0.2Total TimeCortex-A53 vectorizethunderx/vectorize, pre-patchA53 vectorize/LTO, pre patchA53 vectorize, pre-patchCortex-A53Cortex-A5 NeonCortex-A5 VFPV4120240360480600555.10554.83554.37552.84552.56221.63221.56-Ofast -mtune=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=thunderx -march=armv8-a+crc -ftree-vectorize-O3 -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize -flto -ffat-lto-objects-Ofast -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=cortex-a53 -march=armv8-a+crc-mcpu=cortex-a5 -Ofast -marm -mfpu=neon -ftree-vectorize-mcpu=cortex-a5 -O3 -marm -mfpu=vfpv41. (CC) gcc options: -fomit-frame-pointer -fipa-pta -lm

Fhourstones

Complex Connect-4 Solving

OpenBenchmarking.orgKpos / sec, More Is BetterFhourstones 3.1Complex Connect-4 SolvingA53 vectorize/LTO, pre patchA53 vectorize, pre-patchthunderx/vectorize, pre-patchCortex-A53Cortex-A53 vectorizeCortex-A5 NeonCortex-A5 VFPV47001400210028003500SE +/- 0.22, N = 3SE +/- 0.35, N = 3SE +/- 0.76, N = 3SE +/- 1.47, N = 3SE +/- 1.81, N = 3SE +/- 0.22, N = 3SE +/- 17.08, N = 33213.773212.103210.203209.673205.401246.771211.331. (CC) gcc options: -O3

TTSIOD 3D Renderer

Phong Rendering With Soft-Shadow Mapping

OpenBenchmarking.orgFPS, More Is BetterTTSIOD 3D Renderer 2.3aPhong Rendering With Soft-Shadow MappingA53 vectorize/LTO, pre patchCortex-A53 vectorizeCortex-A53A53 vectorize, pre-patchthunderx/vectorize, pre-patchCortex-A5 VFPV4Cortex-A5 Neon612182430SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.02, N = 3SE +/- 0.01, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 2SE +/- 0.04, N = 323.7723.4923.4723.1623.0116.9115.75-O3 -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize -ffat-lto-objects-Ofast -mtune=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=cortex-a53 -march=armv8-a+crc-Ofast -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=thunderx -march=armv8-a+crc -ftree-vectorize-mcpu=cortex-a5 -O3 -marm -mfpu=vfpv4-mcpu=cortex-a5 -Ofast -marm -mfpu=neon -ftree-vectorize1. (CXX) g++ options: -fomit-frame-pointer -fipa-pta -flto -ffast-math -mtune=native -lSDL -lstdc++

C-Ray

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Timethunderx/vectorize, pre-patchA53 vectorize/LTO, pre patchCortex-A53 vectorizeCortex-A53A53 vectorize, pre-patchCortex-A5 NeonCortex-A5 VFPV460120180240300SE +/- 1.37, N = 3SE +/- 0.17, N = 3SE +/- 0.12, N = 3SE +/- 0.14, N = 3SE +/- 0.69, N = 3SE +/- 0.29, N = 3SE +/- 0.14, N = 3149.82184.81186.61186.69187.97235.23273.18-Ofast -mcpu=thunderx -march=armv8-a+crc -ftree-vectorize-mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize -flto -ffat-lto-objects-Ofast -mtune=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=cortex-a53 -march=armv8-a+crc-Ofast -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize-mcpu=cortex-a5 -Ofast -marm -mfpu=neon -ftree-vectorize-mcpu=cortex-a5 -marm -mfpu=vfpv41. (CC) gcc options: -lm -lpthread -O3 -fomit-frame-pointer -fipa-pta

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 5.4.21e12 Prime Number GenerationA53 vectorize/LTO, pre patchA53 vectorize, pre-patchCortex-A53thunderx/vectorize, pre-patchCortex-A53 vectorizeCortex-A5 VFPV4Cortex-A5 Neon2004006008001000SE +/- 8.42, N = 3SE +/- 3.01, N = 3SE +/- 9.14, N = 3SE +/- 2.99, N = 3SE +/- 6.92, N = 3SE +/- 6.29, N = 3SE +/- 11.32, N = 3540.95543.16553.13566.21573.13836.591021.13-O3 -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize -flto -ffat-lto-objects-Ofast -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=cortex-a53 -march=armv8-a+crc-Ofast -mcpu=thunderx -march=armv8-a+crc -ftree-vectorize-Ofast -mtune=cortex-a53 -march=armv8-a+crc -ftree-vectorize-mcpu=cortex-a5 -O3 -marm -mfpu=vfpv4-mcpu=cortex-a5 -Ofast -marm -mfpu=neon -ftree-vectorize1. (CXX) g++ options: -fomit-frame-pointer -fipa-pta -fopenmp

Smallpt

Global Illumination Renderer; 100 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 SamplesA53 vectorize, pre-patchthunderx/vectorize, pre-patchCortex-A53 vectorizeA53 vectorize/LTO, pre patchCortex-A53Cortex-A5 NeonCortex-A5 VFPV470140210280350SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3167167167168168289306-Ofast -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize-Ofast -mcpu=thunderx -march=armv8-a+crc -ftree-vectorize-Ofast -mtune=cortex-a53 -march=armv8-a+crc -ftree-vectorize-O3 -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize -flto -ffat-lto-objects-Ofast -mcpu=cortex-a53 -march=armv8-a+crc-mcpu=cortex-a5 -Ofast -marm -mfpu=neon -ftree-vectorize-mcpu=cortex-a5 -O3 -marm -mfpu=vfpv41. (CXX) g++ options: -fopenmp -fomit-frame-pointer -fipa-pta

Sudokut

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterSudokut 0.4Total TimeA53 vectorize/LTO, pre patchCortex-A53A53 vectorize, pre-patchCortex-A53 vectorizethunderx/vectorize, pre-patchCortex-A5 NeonCortex-A5 VFPV44080120160200SE +/- 0.21, N = 3SE +/- 0.10, N = 3SE +/- 0.20, N = 3SE +/- 0.09, N = 3SE +/- 0.76, N = 3SE +/- 0.34, N = 3SE +/- 2.21, N = 6101.75101.88101.95102.17102.75165.14167.97

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total TimeA53 vectorize/LTO, pre patchA53 vectorize, pre-patchCortex-A53 vectorizeCortex-A53thunderx/vectorize, pre-patchCortex-A5 VFPV4Cortex-A5 Neon50100150200250SE +/- 0.11, N = 3SE +/- 0.08, N = 3SE +/- 0.10, N = 3SE +/- 0.12, N = 3SE +/- 0.06, N = 3SE +/- 0.62, N = 3SE +/- 0.35, N = 367.6469.2769.3469.4071.41107.33247.96

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.1gRSA 4096-bit PerformanceCortex-A53 vectorizeCortex-A53A53 vectorize/LTO, pre patchthunderx/vectorize, pre-patchA53 vectorize, pre-patchCortex-A5 NeonCortex-A5 VFPV4510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.07, N = 321.5021.5021.5021.5021.5020.3020.23-fomit-frame-pointer-fomit-frame-pointer-fomit-frame-pointer-fomit-frame-pointer-fomit-frame-pointer-march=armv7-a-march=armv7-a1. (CC) gcc options: -O3 -lssl -lcrypto -ldl

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETthunderx/vectorize, pre-patchCortex-A53 vectorizeA53 vectorize/LTO, pre patchA53 vectorize, pre-patchCortex-A53Cortex-A5 NeonCortex-A5 VFPV470K140K210K280K350KSE +/- 2784.59, N = 3SE +/- 1967.34, N = 3SE +/- 2239.53, N = 3SE +/- 4662.92, N = 6SE +/- 1052.91, N = 3SE +/- 2106.27, N = 3SE +/- 3419.06, N = 3318926.02313438.91311785.02310344.73309030.64177754.08174917.94-O2 -Ofast -mcpu=thunderx -march=armv8-a+crc -ftree-vectorize-O2 -Ofast -mtune=cortex-a53 -march=armv8-a+crc -ftree-vectorize-O2 -O3 -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize -flto -ffat-lto-objects-O2 -Ofast -mcpu=cortex-a53 -march=armv8-a+crc -ftree-vectorize-O2 -Ofast -mcpu=cortex-a53 -march=armv8-a+crc-O2 -mcpu=cortex-a5 -Ofast -marm -mfpu=neon -ftree-vectorize-std=gnu99 -pipe -g3 -O3 -funroll-loops -mcpu=cortex-a5 -marm -mfpu=vfpv41. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl -fomit-frame-pointer -fipa-pta

Phoronix Test Suite v10.8.4