ARM64 gcc codegen comparison

gcc 5.4/6.3/7.0 benchmarks running on a Cortex-A53

HTML result view exported from: https://openbenchmarking.org/result/1701128-TA-GCCCOMPAR79&rdt.

ARM64 gcc codegen comparisonProcessorMotherboardMemoryDiskOSKernelCompilerFile-SystemScreen Resolutiongcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorizeAArch64 rev 4 @ 1.50GHz (4 Cores)Amlogic2048MB32GB 00000 + 16GB NCardUbuntu 16.043.14.29 (aarch64)GCC 5.4.0 20160609 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0ext41920x3240GCC 7.0.0 20170110 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0AArch64 rev 4 @ 1.55GHz (4 Cores)GCC 6.3.0 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0GCC 5.4.0 20160609 + Clang 3.8.0-2ubuntu4 + LLVM 3.8.0OpenBenchmarking.orgCompiler Details- gcc5 A72 LTO: --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 - gcc5 thunderx 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-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 - gcc7 thunderx 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- gcc7 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- gcc7 A53 vectorize LTO: --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- gcc6 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- gcc6 A53 mtune/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- gcc6 A57 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- gcc5 A57 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-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 Disk Details- gcc5 A72 LTO: DEADLINE / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc5 thunderx vectorize: DEADLINE / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc7 thunderx vectorize: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc7 A53 vectorize: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc7 A53 vectorize LTO: CFQ / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc6 A53: DEADLINE / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc6 A53 mtune/vectorize: DEADLINE / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc6 A57 vectorize: DEADLINE / commit=30,errors=remount-ro,noatime,nodiratime,rw- gcc5 A57 vectorize: DEADLINE / commit=30,errors=remount-ro,noatime,nodiratime,rwProcessor Details- Scaling Governor: meson_cpufreq performance

ARM64 gcc codegen comparisonpostmark: 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: GETgcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize13632916.642917.54185.5534.62549.963048.7022.57223.05604.68172102.6582.0321.20305506.4913514472.854497.17193.8834.78554.443045.8321.86152.96591.80171103.6381.4921.20303529.9113512821.432817.45190.6334.46554.833210.2023.01149.82566.21167102.7571.4121.50318926.0213634581.324580.39196.9035.42552.843212.1023.16187.97543.16167101.9569.2721.50310344.7313784829.914825.13180.5333.16554.373213.7723.77184.81540.95168101.7567.6421.50311785.0213784847.384844.14172.7336.10554.943129.5022.01200.00610.66169101.9971.6521.30315587.0613784812.664809.44175.0934.23553.023125.7721.99199.00592.00169101.6171.8221.23317672.2413564621.044624.88164.6134.94555.053123.2321.71144.49571.71168101.9976.9421.23324752.0513614614.264613.36189.2934.01554.313052.8322.48150.16574.61173102.0579.4721.30311665.33OpenBenchmarking.org

PostMark

Disk Transaction Performance

OpenBenchmarking.orgTPS, More Is BetterPostMark 1.51Disk Transaction Performancegcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize30060090012001500SE +/- 2.67, N = 3SE +/- 4.04, N = 3SE +/- 0.00, N = 3SE +/- 2.67, N = 3SE +/- 2.67, N = 3SE +/- 2.67, N = 3SE +/- 2.67, N = 3SE +/- 2.33, N = 3SE +/- 6.49, N = 31363135113511363137813781378135613611. (CC) gcc options: -O3

RAMspeed SMP

Type: Copy - Benchmark: Integer

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Integergcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize100020003000400050002916.644472.852821.434581.324829.914847.384812.664621.044614.26

RAMspeed SMP

Type: Copy - Benchmark: Floating Point

OpenBenchmarking.orgMB/s, More Is BetterRAMspeed SMP 3.5.0Type: Copy - Benchmark: Floating Pointgcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize100020003000400050002917.544497.172817.454580.394825.134844.144809.444624.884613.36

FFTW

Build: Stock - Size: 2D FFT Size 2048

OpenBenchmarking.orgMflops, More Is BetterFFTW 3.3.4Build: Stock - Size: 2D FFT Size 2048gcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize4080120160200SE +/- 0.18, N = 5SE +/- 0.04, N = 5SE +/- 1.10, N = 5SE +/- 0.99, N = 5SE +/- 0.49, N = 5SE +/- 0.29, N = 5SE +/- 0.28, N = 5SE +/- 0.17, N = 5SE +/- 0.26, N = 5185.55193.88190.63196.90180.53172.73175.09164.61189.29-Ofast -mcpu=cortex-a72 -flto -ffat-lto-objects -fuse-linker-plugin-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=cortex-a53 -ftree-vectorize-O3 -mcpu=cortex-a53 -ftree-vectorize -flto -ffat-lto-objects-O3 -mcpu=cortex-a53-O3 -mtune=cortex-a53 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize1. (CC) gcc options: -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -lm

Timed MAFFT Alignment

Multiple Sequence Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence Alignmentgcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize816243240SE +/- 0.01, N = 3SE +/- 0.06, N = 3SE +/- 0.73, N = 6SE +/- 0.80, N = 6SE +/- 0.70, N = 6SE +/- 0.61, N = 6SE +/- 0.48, N = 6SE +/- 0.03, N = 3SE +/- 0.54, N = 634.6234.7834.4635.4233.1636.1034.2334.9434.011. (CC) gcc options: -O3 -lm -lpthread

GMPbench

Total Time

OpenBenchmarking.orgGMPbench Score, More Is BetterGMPbench 0.2Total Timegcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize120240360480600549.96554.44554.83552.84554.37554.94553.02555.05554.31-Ofast -mcpu=cortex-a72 -flto -ffat-lto-objects -fuse-linker-plugin-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=cortex-a53 -ftree-vectorize-O3 -mcpu=cortex-a53 -ftree-vectorize -flto -ffat-lto-objects-O3 -mcpu=cortex-a53-O3 -mtune=cortex-a53 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize1. (CC) gcc options: -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -lm

Fhourstones

Complex Connect-4 Solving

OpenBenchmarking.orgKpos / sec, More Is BetterFhourstones 3.1Complex Connect-4 Solvinggcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize7001400210028003500SE +/- 1.26, N = 3SE +/- 0.86, N = 3SE +/- 0.76, N = 3SE +/- 0.35, N = 3SE +/- 0.22, N = 3SE +/- 1.20, N = 3SE +/- 3.94, N = 3SE +/- 2.96, N = 3SE +/- 1.51, N = 33048.703045.833210.203212.103213.773129.503125.773123.233052.831. (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 Mappinggcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize612182430SE +/- 0.01, N = 3SE +/- 0.08, N = 3SE +/- 0.00, N = 3SE +/- 0.01, N = 3SE +/- 0.01, N = 3SE +/- 0.05, N = 3SE +/- 0.03, N = 3SE +/- 0.04, N = 3SE +/- 0.13, N = 322.5721.8623.0123.1623.7722.0121.9921.7122.48-Ofast -mcpu=cortex-a72 -ffat-lto-objects -fuse-linker-plugin-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=cortex-a53 -ftree-vectorize-O3 -mcpu=cortex-a53 -ftree-vectorize -ffat-lto-objects-O3 -mcpu=cortex-a53-O3 -mtune=cortex-a53 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize1. (CXX) g++ options: -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -flto -ffast-math -mtune=native -lSDL -lstdc++

C-Ray

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Timegcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize50100150200250SE +/- 0.09, N = 3SE +/- 2.40, N = 6SE +/- 1.37, N = 3SE +/- 0.69, N = 3SE +/- 0.17, N = 3SE +/- 1.39, N = 3SE +/- 1.80, N = 3SE +/- 0.08, N = 3SE +/- 0.19, N = 3223.05152.96149.82187.97184.81200.00199.00144.49150.16-Ofast -mcpu=cortex-a72 -flto -ffat-lto-objects -fuse-linker-plugin-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=cortex-a53 -ftree-vectorize-mcpu=cortex-a53 -ftree-vectorize -flto -ffat-lto-objects-mcpu=cortex-a53-mtune=cortex-a53 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize1. (CC) gcc options: -lm -lpthread -O3 -fomit-frame-pointer -fipa-pta -march=armv8-a+crc

Primesieve

1e12 Prime Number Generation

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 5.4.21e12 Prime Number Generationgcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize130260390520650SE +/- 9.47, N = 4SE +/- 10.05, N = 6SE +/- 2.99, N = 3SE +/- 3.01, N = 3SE +/- 8.42, N = 3SE +/- 15.34, N = 6SE +/- 17.98, N = 6SE +/- 4.25, N = 3SE +/- 8.11, N = 6604.68591.80566.21543.16540.95610.66592.00571.71574.61-Ofast -mcpu=cortex-a72 -flto -ffat-lto-objects -fuse-linker-plugin-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=cortex-a53 -ftree-vectorize-O3 -mcpu=cortex-a53 -ftree-vectorize -flto -ffat-lto-objects-O3 -mcpu=cortex-a53-O3 -mtune=cortex-a53 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize1. (CXX) g++ options: -fomit-frame-pointer -fipa-pta -march=armv8-a+crc -fopenmp

Smallpt

Global Illumination Renderer; 100 Samples

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 Samplesgcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize4080120160200SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.33, N = 3SE +/- 0.33, N = 3SE +/- 0.00, N = 3172171167167168169169168173-Ofast -mcpu=cortex-a72 -flto -ffat-lto-objects -fuse-linker-plugin-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=cortex-a53 -ftree-vectorize-O3 -mcpu=cortex-a53 -ftree-vectorize -flto -ffat-lto-objects-O3 -mcpu=cortex-a53-O3 -mtune=cortex-a53 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize1. (CXX) g++ options: -fopenmp -fomit-frame-pointer -fipa-pta -march=armv8-a+crc

Sudokut

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterSudokut 0.4Total Timegcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize20406080100SE +/- 0.73, N = 3SE +/- 0.78, N = 3SE +/- 0.76, N = 3SE +/- 0.20, N = 3SE +/- 0.21, N = 3SE +/- 0.23, N = 3SE +/- 0.05, N = 3SE +/- 0.17, N = 3SE +/- 0.11, N = 3102.65103.63102.75101.95101.75101.99101.61101.99102.05

Tachyon

Total Time

OpenBenchmarking.orgSeconds, Fewer Is BetterTachyon 0.98.9Total Timegcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize20406080100SE +/- 0.09, N = 3SE +/- 0.53, N = 3SE +/- 0.06, N = 3SE +/- 0.08, N = 3SE +/- 0.11, N = 3SE +/- 0.09, N = 3SE +/- 0.24, N = 3SE +/- 0.20, N = 3SE +/- 0.09, N = 382.0381.4971.4169.2767.6471.6571.8276.9479.47

OpenSSL

RSA 4096-bit Performance

OpenBenchmarking.orgSigns Per Second, More Is BetterOpenSSL 1.0.1gRSA 4096-bit Performancegcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize510152025SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.00, N = 3SE +/- 0.03, N = 3SE +/- 0.03, N = 3SE +/- 0.00, N = 321.2021.2021.5021.5021.5021.3021.2321.2321.301. (CC) gcc options: -O3 -fomit-frame-pointer -lssl -lcrypto -ldl

Redis

Test: GET

OpenBenchmarking.orgRequests Per Second, More Is BetterRedis 3.0.1Test: GETgcc5 A72 LTOgcc5 thunderx vectorizegcc7 thunderx vectorizegcc7 A53 vectorizegcc7 A53 vectorize LTOgcc6 A53gcc6 A53 mtune/vectorizegcc6 A57 vectorizegcc5 A57 vectorize70K140K210K280K350KSE +/- 3249.19, N = 3SE +/- 5780.31, N = 3SE +/- 2784.59, N = 3SE +/- 4662.92, N = 6SE +/- 2239.53, N = 3SE +/- 3145.13, N = 3SE +/- 1273.24, N = 3SE +/- 1024.45, N = 3SE +/- 1214.02, N = 3305506.49303529.91318926.02310344.73311785.02315587.06317672.24324752.05311665.33-Ofast -mcpu=cortex-a72 -flto -ffat-lto-objects -fuse-linker-plugin-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=thunderx -ftree-vectorize-Ofast -mcpu=cortex-a53 -ftree-vectorize-O3 -mcpu=cortex-a53 -ftree-vectorize -flto -ffat-lto-objects-O3 -mcpu=cortex-a53-O3 -mtune=cortex-a53 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize-Ofast -mcpu=cortex-a57 -ftree-vectorize1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl -O2 -fomit-frame-pointer -fipa-pta -march=armv8-a+crc

Phoronix Test Suite v10.8.4