Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 1705048-RI-MERGE366949 ARM vs Thumb GCC comparison - Phoronix Test Suite ARM vs Thumb GCC comparison ARMv7 codegen impact of ARM/Thumb mode in GCC 4.9, 7.1, 8.0
HTML result view exported from: https://openbenchmarking.org/result/1705048-RI-MERGE366949&export=txt&sor&rro .
ARM vs Thumb GCC comparison Processor Motherboard Memory Disk Graphics OS Kernel Display Server Compiler File-System Screen Resolution GCC 7.1 thumb #1 GCC 7.1 arm #1 GCC 8.0 thumb #1 GCC 8.0 arm #1 GCC 4.9 thumb #1 GCC 4.9 arm #1 GCC 4.9 thumb #2 GCC 4.9 arm #2 GCC 7.1 thumb #2 GCC 7.1 arm #2 GCC 8.0 thumb #2 GCC 8.0 arm #2 ARMv7 rev 1 @ 1.73GHz (4 Cores) ODROIDC 915MB 64GB 00000 ARM Mali Ubuntu 14.04 3.10.80-20-odrobian (armv7l) X Server 1.15.1 GCC 7.0.1 20170422 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.0 ext4 1280x1024 GCC 8.0.0 20170501 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.0 GCC 4.9.4 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.0 GCC 7.0.1 20170422 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.0 GCC 8.0.0 20170501 + Clang 3.6.0-2ubuntu1~trusty1 + LLVM 3.6.0 OpenBenchmarking.org Compiler Details - GCC 7.1 thumb #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 --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 - GCC 7.1 arm #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 --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 - GCC 8.0 thumb #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 --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 - GCC 8.0 arm #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 --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 - GCC 4.9 thumb #1: --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 - GCC 4.9 arm #1: --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 - GCC 4.9 thumb #2: --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 - GCC 4.9 arm #2: --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 - GCC 7.1 thumb #2: --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 - GCC 7.1 arm #2: --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 - GCC 8.0 thumb #2: --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 - GCC 8.0 arm #2: --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 - Scaling Governor: meson_cpufreq performance
ARM vs Thumb GCC comparison ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping himeno: Poisson Pressure Solver c-ray: Total Time primesieve: 1e12 Prime Number Generation stockfish: Total Time tachyon: Total Time scimark2: Composite scimark2: Monte Carlo scimark2: Fast Fourier Transform scimark2: Sparse Matrix Multiply scimark2: Dense LU Matrix Factorization scimark2: Jacobi Successive Over-Relaxation tscp: AI Chess Performance smallpt: Global Illumination Renderer; 100 Samples n-queens: Elapsed Time GCC 7.1 thumb #1 GCC 7.1 arm #1 GCC 8.0 thumb #1 GCC 8.0 arm #1 GCC 4.9 thumb #1 GCC 4.9 arm #1 GCC 4.9 thumb #2 GCC 4.9 arm #2 GCC 7.1 thumb #2 GCC 7.1 arm #2 GCC 8.0 thumb #2 GCC 8.0 arm #2 15.62 88.14 244.36 1025.35 43893 109.82 102.67 58.11 22.88 98.19 115.42 218.72 186603 285 195.85 15.86 79.09 245.33 1027.16 51235 108.99 104.64 67.70 22.29 98.18 115.53 219.48 189365 284 201.24 16.52 84.18 243.38 1028.37 43547 109.73 104.05 58.14 21.07 99.02 116.86 225.17 185241 285 195.83 15.83 62.49 243.76 1028.02 52205 109.52 103.46 67.19 22.45 97.00 114.10 216.56 190842 285 201.30 15.56 91.27 265.69 877.15 41922 110.57 100.30 56.95 21.32 98.24 124.60 200.40 179364 284 185.41 15.79 81.69 266.74 1029.43 53864 108.87 99.97 64.56 22.64 97.15 122.69 192.80 187058 284 227.37 OpenBenchmarking.org
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3a Phong Rendering With Soft-Shadow Mapping GCC 4.9 thumb #1 GCC 7.1 thumb #1 GCC 4.9 arm #1 GCC 8.0 arm #1 GCC 7.1 arm #1 GCC 8.0 thumb #1 4 8 12 16 20 SE +/- 0.08, N = 3 SE +/- 0.02, N = 2 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 15.56 15.62 15.79 15.83 15.86 16.52 -mthumb -marm -marm -marm -mthumb 1. (CXX) g++ options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -ffast-math -mtune=native -flto -lSDL -lstdc++
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver GCC 8.0 arm #1 GCC 7.1 arm #1 GCC 4.9 arm #1 GCC 8.0 thumb #1 GCC 7.1 thumb #1 GCC 4.9 thumb #1 20 40 60 80 100 SE +/- 1.31, N = 6 SE +/- 1.02, N = 3 SE +/- 0.96, N = 3 SE +/- 1.59, N = 3 SE +/- 0.23, N = 3 SE +/- 1.21, N = 3 62.49 79.09 81.69 84.18 88.14 91.27 -marm -marm -marm -mthumb -mthumb -mthumb 1. (CC) gcc options: -O3 -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time GCC 4.9 arm #1 GCC 4.9 thumb #1 GCC 7.1 arm #1 GCC 7.1 thumb #1 GCC 8.0 arm #1 GCC 8.0 thumb #1 60 120 180 240 300 SE +/- 1.92, N = 3 SE +/- 1.04, N = 3 SE +/- 1.31, N = 3 SE +/- 0.30, N = 3 SE +/- 0.22, N = 3 SE +/- 0.19, N = 3 266.74 265.69 245.33 244.36 243.76 243.38 -marm -mthumb -marm -mthumb -marm -mthumb 1. (CC) gcc options: -lm -lpthread -O3 -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 5.4.2 1e12 Prime Number Generation GCC 4.9 arm #1 GCC 8.0 thumb #1 GCC 8.0 arm #1 GCC 7.1 arm #1 GCC 7.1 thumb #1 GCC 4.9 thumb #1 200 400 600 800 1000 SE +/- 10.97, N = 3 SE +/- 1.95, N = 3 SE +/- 5.44, N = 3 SE +/- 0.31, N = 3 SE +/- 5.98, N = 3 SE +/- 3.08, N = 3 1029.43 1028.37 1028.02 1027.16 1025.35 877.15 -marm -mthumb -marm -marm -mthumb -mthumb 1. (CXX) g++ options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -fopenmp
Stockfish Total Time OpenBenchmarking.org ms, Fewer Is Better Stockfish 2014-11-26 Total Time GCC 4.9 arm #1 GCC 8.0 arm #1 GCC 7.1 arm #1 GCC 7.1 thumb #1 GCC 8.0 thumb #1 GCC 4.9 thumb #1 12K 24K 36K 48K 60K SE +/- 60.67, N = 3 SE +/- 221.70, N = 3 SE +/- 58.33, N = 3 SE +/- 663.13, N = 6 SE +/- 710.15, N = 3 SE +/- 122.93, N = 3 53864 52205 51235 43893 43547 41922 -marm -marm -marm -mthumb -mthumb -mthumb 1. (CXX) g++ options: -lpthread -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -fno-exceptions -fno-rtti -ansi -pedantic -O3 -flto
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.98.9 Total Time GCC 4.9 thumb #1 GCC 7.1 thumb #1 GCC 8.0 thumb #1 GCC 8.0 arm #1 GCC 7.1 arm #1 GCC 4.9 arm #1 20 40 60 80 100 SE +/- 0.36, N = 3 SE +/- 0.45, N = 3 SE +/- 0.36, N = 3 SE +/- 0.28, N = 3 SE +/- 0.39, N = 3 SE +/- 0.13, N = 3 110.57 109.82 109.73 109.52 108.99 108.87
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite GCC 4.9 arm #1 GCC 4.9 thumb #1 GCC 7.1 thumb #1 GCC 8.0 arm #1 GCC 8.0 thumb #1 GCC 7.1 arm #1 20 40 60 80 100 SE +/- 1.17, N = 4 SE +/- 1.12, N = 4 SE +/- 1.09, N = 4 SE +/- 1.35, N = 4 SE +/- 1.07, N = 4 SE +/- 1.08, N = 4 99.97 100.30 102.67 103.46 104.05 104.64 -marm -mthumb -mthumb -marm -mthumb -marm 1. (CC) gcc options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -lm
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo GCC 4.9 thumb #1 GCC 7.1 thumb #1 GCC 8.0 thumb #1 GCC 4.9 arm #1 GCC 8.0 arm #1 GCC 7.1 arm #1 15 30 45 60 75 SE +/- 0.47, N = 4 SE +/- 0.43, N = 4 SE +/- 0.44, N = 4 SE +/- 0.56, N = 4 SE +/- 0.60, N = 4 SE +/- 0.49, N = 4 56.95 58.11 58.14 64.56 67.19 67.70 -mthumb -mthumb -mthumb -marm -marm -marm 1. (CC) gcc options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -lm
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform GCC 8.0 thumb #1 GCC 4.9 thumb #1 GCC 7.1 arm #1 GCC 8.0 arm #1 GCC 4.9 arm #1 GCC 7.1 thumb #1 5 10 15 20 25 SE +/- 0.17, N = 4 SE +/- 0.32, N = 4 SE +/- 0.17, N = 4 SE +/- 0.21, N = 4 SE +/- 0.24, N = 4 SE +/- 0.18, N = 4 21.07 21.32 22.29 22.45 22.64 22.88 -mthumb -mthumb -marm -marm -marm -mthumb 1. (CC) gcc options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -lm
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply GCC 8.0 arm #1 GCC 4.9 arm #1 GCC 7.1 arm #1 GCC 7.1 thumb #1 GCC 4.9 thumb #1 GCC 8.0 thumb #1 20 40 60 80 100 SE +/- 1.37, N = 4 SE +/- 1.31, N = 4 SE +/- 1.13, N = 4 SE +/- 1.12, N = 4 SE +/- 1.21, N = 4 SE +/- 1.20, N = 4 97.00 97.15 98.18 98.19 98.24 99.02 -marm -marm -marm -mthumb -mthumb -mthumb 1. (CC) gcc options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -lm
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization GCC 8.0 arm #1 GCC 7.1 thumb #1 GCC 7.1 arm #1 GCC 8.0 thumb #1 GCC 4.9 arm #1 GCC 4.9 thumb #1 30 60 90 120 150 SE +/- 1.55, N = 4 SE +/- 1.27, N = 4 SE +/- 1.25, N = 4 SE +/- 1.44, N = 4 SE +/- 1.56, N = 4 SE +/- 1.39, N = 4 114.10 115.42 115.53 116.86 122.69 124.60 -marm -mthumb -marm -mthumb -marm -mthumb 1. (CC) gcc options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -lm
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation GCC 4.9 arm #1 GCC 4.9 thumb #1 GCC 8.0 arm #1 GCC 7.1 thumb #1 GCC 7.1 arm #1 GCC 8.0 thumb #1 50 100 150 200 250 SE +/- 2.19, N = 4 SE +/- 2.23, N = 4 SE +/- 3.03, N = 4 SE +/- 2.47, N = 4 SE +/- 2.37, N = 4 SE +/- 2.33, N = 4 192.80 200.40 216.56 218.72 219.48 225.17 -marm -mthumb -marm -mthumb -marm -mthumb 1. (CC) gcc options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -lm
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance GCC 4.9 thumb #1 GCC 8.0 thumb #1 GCC 7.1 thumb #1 GCC 4.9 arm #1 GCC 7.1 arm #1 GCC 8.0 arm #1 40K 80K 120K 160K 200K SE +/- 1328.11, N = 5 SE +/- 1601.83, N = 5 SE +/- 1317.11, N = 5 SE +/- 1704.24, N = 5 SE +/- 1793.38, N = 5 SE +/- 1539.07, N = 5 179364 185241 186603 187058 189365 190842 -mthumb -mthumb -mthumb -marm -marm -marm 1. (CC) gcc options: -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -O3 -march=native
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples GCC 8.0 arm #1 GCC 8.0 thumb #1 GCC 7.1 thumb #1 GCC 7.1 arm #1 GCC 4.9 arm #1 GCC 4.9 thumb #1 60 120 180 240 300 SE +/- 1.53, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 285 285 285 284 284 284 -marm -mthumb -mthumb -marm -marm -mthumb 1. (CXX) g++ options: -fopenmp -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time GCC 4.9 arm #1 GCC 8.0 arm #1 GCC 7.1 arm #1 GCC 7.1 thumb #1 GCC 8.0 thumb #1 GCC 4.9 thumb #1 50 100 150 200 250 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 227.37 201.30 201.24 195.85 195.83 185.41 -marm -marm -marm -mthumb -mthumb -mthumb 1. (CC) gcc options: -static -fopenmp -mcpu=cortex-a5 -Ofast -fomit-frame-pointer -fipa-pta -mfpu=neon-vfpv4 -ftree-vectorize -frename-registers -O3 -march=native
Phoronix Test Suite v10.8.4