GCC 4.8 vs. LLVM Clang 3.3 SVN Compiler Benchmarking GCC 4.7.2 versus GCC 4.8.0 versus LLVM Clang 3.2 versus LLVM Clang 3.3 SVN compiler benchmarking from an Intel Core i7 990X Gulftown system running Ubuntu 13.04 Linux. Compiler GCC benchmarks for a future article on Phoronix.com.
HTML result view exported from: https://openbenchmarking.org/result/1303255-FO-GCC48LLVM06&grw&sor .
GCC 4.8 vs. LLVM Clang 3.3 SVN Compiler Benchmarking Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.2 LLVM Clang 3.3 SVN Intel Core i7 990X @ 3.47GHz (12 Cores) MSI X58M (MS-7593) v1.0 Intel 5520/5500/X58 + ICH10R 12288MB 1000GB Western Digital WD1003FBYX-0 NVIDIA GeForce 8400 GS 512MB (500/333MHz) Realtek ALC889 Realtek RTL8111/8168B Ubuntu 13.04 3.8.0-12-generic (x86_64) Unity 6.6.0 X Server 1.13.2 NVIDIA 313.26 3.3.0 NVIDIA 313.26 GCC 4.7.2 ext4 1920x1080 GCC 4.7 Clang 3.2 + LLVM 3.2svn Clang 3.3 (SVN 177878) + LLVM 3.3svn OpenBenchmarking.org Compiler Details - GCC 4.7.2: --enable-checking=release --enable-languages=c,c++,fortran --enable-lto - GCC 4.8.0: --build=x86_64-linux-gnu --disable-cloog-version-check --disable-ppl-version-check --disable-werror --enable-checking=release --enable-clocale=gnu --enable-cloog-backend=ppl --enable-gnu-unique-object --enable-languages=c,c++,go,fortran,objc,obj-c++ --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-nls --enable-objc-gc --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-cloog --with-multilib-list=m32,m64,mx32 --with-tune=generic -v - LLVM Clang 3.2: Optimized build; Built Mar 25 2013 (15:48:44); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7 - LLVM Clang 3.3 SVN: Optimized build; Built Mar 25 2013 (12:54:43); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7 Processor Details - Scaling Governor: ondemand OpenCL Details - GCC 4.8.0: GPU Compute Cores: 8 System Details - GCC 4.8.0: GPU Compute Cores: 8.
GCC 4.8 vs. LLVM Clang 3.3 SVN Compiler Benchmarking minion: Graceful minion: Solitaire minion: Quasigroup blake2: Phoronix Test Suite v4.4.1 botan: Tiger botan: KASUMI botan: AES-256 botan: Twofish botan: CAST-256 botan: X9.19-MAC encode-flac: WAV To FLAC encode-mp3: WAV To MP3 mafft: Multiple Sequence Alignment himeno: Poisson Pressure Solver lammps: Rhodopsin Protein n-queens: Elapsed Time build-imagemagick: Time To Compile primesieve: 1e12 Prime Number Generation john-the-ripper: Blowfish john-the-ripper: Traditional DES john-the-ripper: MD5 c-ray: Total Time ffmpeg: H.264 HD To NTSC DV smallpt: Global Illumination Renderer; 100 Samples GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.2 LLVM Clang 3.3 SVN 71.58 107.44 157.81 5.96 360.43 39.35 154.60 175.13 85.71 77.12 6.99 17.23 5.67 1527.02 49.36 28.82 58.05 66.67 23.78 19.06 32 72.40 103.05 153.93 6.16 376.26 37.91 133.38 172.71 87.37 76.19 6.94 17.00 5.72 1337.12 48.46 29.66 59.67 66.79 7272 12345000 33996 18.83 19.35 32 71.84 108.48 156.36 6.77 357.40 39.34 154.74 175.13 85.56 76.77 7.98 17.41 6.19 1487.33 49.71 257.21 25.03 66.57 901 4102667 25987 23.78 19.24 31 70.29 114.74 159.10 6.85 381.89 65.75 144.74 169.82 109.43 74.87 7.88 16.83 6.13 1499.50 41.36 257.21 24.79 419.76 909 4105667 28585 23.74 19.31 285 OpenBenchmarking.org
Minion Benchmark: Graceful OpenBenchmarking.org Seconds, Fewer Is Better Minion 0.15 Benchmark: Graceful LLVM Clang 3.3 SVN GCC 4.7.2 LLVM Clang 3.2 GCC 4.8.0 16 32 48 64 80 SE +/- 0.35, N = 3 SE +/- 0.37, N = 3 SE +/- 0.08, N = 3 SE +/- 0.38, N = 3 70.29 71.58 71.84 72.40 -lz -lbz2 -lz -lbz2 -lz -lbz2 1. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt
Minion Benchmark: Solitaire OpenBenchmarking.org Seconds, Fewer Is Better Minion 0.15 Benchmark: Solitaire GCC 4.8.0 GCC 4.7.2 LLVM Clang 3.2 LLVM Clang 3.3 SVN 30 60 90 120 150 SE +/- 0.82, N = 3 SE +/- 0.76, N = 3 SE +/- 0.76, N = 3 SE +/- 0.68, N = 3 103.05 107.44 108.48 114.74 -lz -lbz2 -lz -lbz2 -lz -lbz2 1. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt
Minion Benchmark: Quasigroup OpenBenchmarking.org Seconds, Fewer Is Better Minion 0.15 Benchmark: Quasigroup GCC 4.8.0 LLVM Clang 3.2 GCC 4.7.2 LLVM Clang 3.3 SVN 40 80 120 160 200 SE +/- 0.44, N = 3 SE +/- 0.42, N = 3 SE +/- 0.19, N = 3 SE +/- 0.55, N = 3 153.93 156.36 157.81 159.10 -lz -lbz2 -lz -lbz2 -lz -lbz2 1. (CXX) g++ options: -O3 -fomit-frame-pointer -rdynamic -lboost_iostreams-mt
BLAKE2 Phoronix Test Suite v4.4.1 OpenBenchmarking.org Cycles Per Byte, Fewer Is Better BLAKE2 20121223 Phoronix Test Suite v4.4.1 GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.2 LLVM Clang 3.3 SVN 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.05, N = 3 5.96 6.16 6.77 6.85 1. (CC) gcc options: -std=gnu99 -O3 -march=native
Botan Test: Tiger OpenBenchmarking.org Mbytes/s, More Is Better Botan 1.10.3 Test: Tiger LLVM Clang 3.3 SVN GCC 4.8.0 GCC 4.7.2 LLVM Clang 3.2 80 160 240 320 400 381.89 376.26 360.43 357.40 1. (CXX) g++ options: -m64 -ldl -lpthread -lrt
Botan Test: KASUMI OpenBenchmarking.org Mbytes/s, More Is Better Botan 1.10.3 Test: KASUMI LLVM Clang 3.3 SVN GCC 4.7.2 LLVM Clang 3.2 GCC 4.8.0 15 30 45 60 75 65.75 39.35 39.34 37.91 1. (CXX) g++ options: -m64 -ldl -lpthread -lrt
Botan Test: AES-256 OpenBenchmarking.org Mbytes/s, More Is Better Botan 1.10.3 Test: AES-256 LLVM Clang 3.2 GCC 4.7.2 LLVM Clang 3.3 SVN GCC 4.8.0 30 60 90 120 150 154.74 154.60 144.74 133.38 1. (CXX) g++ options: -m64 -ldl -lpthread -lrt
Botan Test: Twofish OpenBenchmarking.org Mbytes/s, More Is Better Botan 1.10.3 Test: Twofish LLVM Clang 3.2 GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.3 SVN 40 80 120 160 200 175.13 175.13 172.71 169.82 1. (CXX) g++ options: -m64 -ldl -lpthread -lrt
Botan Test: CAST-256 OpenBenchmarking.org Mbytes/s, More Is Better Botan 1.10.3 Test: CAST-256 LLVM Clang 3.3 SVN GCC 4.8.0 GCC 4.7.2 LLVM Clang 3.2 20 40 60 80 100 109.43 87.37 85.71 85.56 1. (CXX) g++ options: -m64 -ldl -lpthread -lrt
Botan Test: X9.19-MAC OpenBenchmarking.org Mbytes/s, More Is Better Botan 1.10.3 Test: X9.19-MAC GCC 4.7.2 LLVM Clang 3.2 GCC 4.8.0 LLVM Clang 3.3 SVN 20 40 60 80 100 77.12 76.77 76.19 74.87 1. (CXX) g++ options: -m64 -ldl -lpthread -lrt
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.2.1 WAV To FLAC GCC 4.8.0 GCC 4.7.2 LLVM Clang 3.3 SVN LLVM Clang 3.2 2 4 6 8 10 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 6.94 6.99 7.88 7.98 1. (CXX) g++ options: -O3 -march=native -logg -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.99.3 WAV To MP3 LLVM Clang 3.3 SVN GCC 4.8.0 GCC 4.7.2 LLVM Clang 3.2 4 8 12 16 20 SE +/- 0.02, N = 5 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 SE +/- 0.04, N = 5 16.83 17.00 17.23 17.41
Timed MAFFT Alignment Multiple Sequence Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 6.864 Multiple Sequence Alignment GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.3 SVN LLVM Clang 3.2 2 4 6 8 10 SE +/- 0.09, N = 6 SE +/- 0.10, N = 3 SE +/- 0.13, N = 6 SE +/- 0.06, N = 3 5.67 5.72 6.13 6.19 1. (CC) gcc options: -O3 -lm -lpthread
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver GCC 4.7.2 LLVM Clang 3.3 SVN LLVM Clang 3.2 GCC 4.8.0 300 600 900 1200 1500 SE +/- 2.54, N = 3 SE +/- 2.56, N = 3 SE +/- 2.43, N = 3 SE +/- 5.16, N = 3 1527.02 1499.50 1487.33 1337.12 1. (CC) gcc options: -O3 -march=native
LAMMPS Molecular Dynamics Simulator Test: Rhodopsin Protein OpenBenchmarking.org Loop Time, Fewer Is Better LAMMPS Molecular Dynamics Simulator 1.0 Test: Rhodopsin Protein LLVM Clang 3.3 SVN GCC 4.8.0 GCC 4.7.2 LLVM Clang 3.2 11 22 33 44 55 SE +/- 0.09, N = 3 SE +/- 0.14, N = 3 SE +/- 0.18, N = 3 SE +/- 0.07, N = 3 41.36 48.46 49.36 49.71 1. (CXX) g++ options: -lfftw -lmpich
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.2 LLVM Clang 3.3 SVN 60 120 180 240 300 SE +/- 0.02, N = 3 SE +/- 0.13, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 28.82 29.66 257.21 257.21 1. (CC) gcc options: -static -fopenmp -O3 -march=native
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.8.1-10 Time To Compile LLVM Clang 3.3 SVN LLVM Clang 3.2 GCC 4.7.2 GCC 4.8.0 13 26 39 52 65 SE +/- 0.10, N = 3 SE +/- 0.11, N = 3 SE +/- 0.07, N = 3 SE +/- 0.12, N = 3 24.79 25.03 58.05 59.67
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 4.2 1e12 Prime Number Generation LLVM Clang 3.2 GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.3 SVN 90 180 270 360 450 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.45, N = 3 66.57 66.67 66.79 419.76 -fopenmp -fopenmp -fopenmp 1. (CXX) g++ options: -O2
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.9-jumbo-7 Test: Blowfish GCC 4.8.0 LLVM Clang 3.3 SVN LLVM Clang 3.2 1600 3200 4800 6400 8000 SE +/- 0.33, N = 3 SE +/- 0.67, N = 3 SE +/- 1.76, N = 3 7272 909 901 1. (CC) gcc options: -lssl -lcrypto -lm -lz -fopenmp -lcrypt -ldl
John The Ripper Test: Traditional DES OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.9-jumbo-7 Test: Traditional DES GCC 4.8.0 LLVM Clang 3.3 SVN LLVM Clang 3.2 3M 6M 9M 12M 15M SE +/- 41000.00, N = 3 SE +/- 6691.62, N = 3 SE +/- 1855.92, N = 3 12345000 4105667 4102667 1. (CC) gcc options: -lssl -lcrypto -lm -lz -fopenmp -lcrypt -ldl
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.7.9-jumbo-7 Test: MD5 GCC 4.8.0 LLVM Clang 3.3 SVN LLVM Clang 3.2 7K 14K 21K 28K 35K SE +/- 31.75, N = 3 SE +/- 75.88, N = 3 SE +/- 52.07, N = 3 33996 28585 25987 1. (CC) gcc options: -lssl -lcrypto -lm -lz -fopenmp -lcrypt -ldl
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time GCC 4.8.0 LLVM Clang 3.3 SVN GCC 4.7.2 LLVM Clang 3.2 6 12 18 24 30 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 18.83 23.74 23.78 23.78 1. (CC) gcc options: -lm -lpthread -O3 -march=native
FFmpeg H.264 HD To NTSC DV OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 1.1 H.264 HD To NTSC DV GCC 4.7.2 LLVM Clang 3.2 LLVM Clang 3.3 SVN GCC 4.8.0 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.04, N = 3 SE +/- 0.19, N = 3 SE +/- 0.18, N = 3 19.06 19.24 19.31 19.35 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -ldl -lasound -lSDL -lm -pthread -lbz2
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples LLVM Clang 3.2 GCC 4.7.2 GCC 4.8.0 LLVM Clang 3.3 SVN 60 120 180 240 300 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 31 32 32 285 1. (CXX) g++ options: -fopenmp -O3 -march=native
Phoronix Test Suite v10.8.5