GCC 6.1 Compiler Optimization Benchmarks GCC 6.1.0 compiler benchmarks with different optimization flags. Intel Xeon E5-2687W v3 GCC compiler benchmarks on Debian. Tests by Michael Larabel of Phoronix for a future article.
HTML result view exported from: https://openbenchmarking.org/result/1605151-GA-1605083HA39&grt .
GCC 6.1 Compiler Optimization Benchmarks Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Display Server Display Driver OpenGL Compiler File-System Screen Resolution Desktop -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 Intel Xeon E5-2687W v3 @ 3.50GHz (20 Cores) MSI X99S SLI PLUS (MS-7885) v1.0 Intel Xeon E7 v3/Xeon 16384MB PNY CS1211 120GB + 80GB INTEL SSDSCKGW08 AMD FirePro V7900 2048MB Realtek ALC892 ASUS PB278 Intel Connection Debian testing 4.5.0-1-amd64 (x86_64) X Server 1.18.3 modesetting 1.18.3 3.3 Mesa 11.1.3 Gallium 0.4 GCC 6.1.0 ext4 2560x1440 Intel Xeon E31245 @ 3.70GHz (8 Cores) ASUS P8B WS 3001GB Hitachi HDS72303 + 128GB SAMSUNG MZNTE128 Intel Sandybridge Server (1350MHz) Realtek Generic SyncMaster Gentoo 2.2 4.5.0-gentoo (x86_64) KDE Frameworks 5 intel 2.99.917 3.3 Mesa 11.2.2 GCC 5.3.0 + Clang 3.8.0 + LLVM 3.8.0 1920x1080 OpenBenchmarking.org Compiler Details - -O0: --disable-multilib --enable-checking=release - -Os: --disable-multilib --enable-checking=release - -Og: --disable-multilib --enable-checking=release - -O1: --disable-multilib --enable-checking=release - -O2: --disable-multilib --enable-checking=release - -O3: --disable-multilib --enable-checking=release - -O3 -march=native: --disable-multilib --enable-checking=release - -O3 -march=native -flto: --disable-multilib --enable-checking=release - -Ofast -march=native: --disable-multilib --enable-checking=release - s10: --bindir=/usr/x86_64-pc-linux-gnu/gcc-bin/5.3.0 --build=x86_64-pc-linux-gnu --datadir=/usr/share/gcc-data/x86_64-pc-linux-gnu/5.3.0 --disable-altivec --disable-fixed-point --disable-libcilkrts --disable-libmpx --disable-libmudflap --disable-libssp --disable-werror --enable-__cxa_atexit --enable-checking=release --enable-clocale=gnu --enable-languages=c,c++,java,objc,fortran --enable-libgomp --enable-libsanitizer --enable-libstdcxx-time --enable-libvtv --enable-lto --enable-multilib --enable-nls --enable-obsolete --enable-secureplt --enable-shared --enable-targets=all --enable-threads=posix --enable-vtable-verify --host=x86_64-pc-linux-gnu --includedir=/usr/lib/gcc/x86_64-pc-linux-gnu/5.3.0/include --mandir=/usr/share/gcc-data/x86_64-pc-linux-gnu/5.3.0/man --with-multilib-list=m32,m64 --with-python-dir=/share/gcc-data/x86_64-pc-linux-gnu/5.3.0/python --without-isl Processor Details - Scaling Governor: intel_pstate powersave
GCC 6.1 Compiler Optimization Benchmarks encode-flac: WAV To FLAC graphics-magick: Blur graphics-magick: Sharpen graphics-magick: Resizing graphics-magick: HWB Color Space graphics-magick: Local Adaptive Thresholding hint: FLOAT himeno: Poisson Pressure Solver encode-mp3: WAV To MP3 pgbench: Buffer Test - Normal Load - Read Write pgbench: Buffer Test - Single Thread - Read Write pgbench: Buffer Test - Heavy Contention - Read Write redis: LPOP redis: SADD redis: LPUSH redis: GET redis: SET scimark2: Composite scimark2: Monte Carlo scimark2: Fast Fourier Transform scimark2: Sparse Matrix Multiply scimark2: Dense LU Matrix Factorization scimark2: Jacobi Successive Over-Relaxation hmmer: Pfam Database Search build-imagemagick: Time To Compile build-php: Time To Compile -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 46.74 82 71 97 110 17 103731655.85 424.57 36.02 4468.97 303.93 4840.76 547091.88 491891.31 476295.97 548655.63 479934.92 1407.02 545.51 440.57 2565.94 2454.12 1028.95 13.82 9.34 5.58 10.62 110 124 168 188 68 303914359.33 1181.18 16.28 4275.85 346.32 4497.15 642758.08 607478.25 598808.52 645755.96 596757.10 1426.79 552.04 456.35 2589.56 2482.13 1053.88 10.68 32.43 11.61 8.11 113 100 149 168 54 326497871.93 1102.64 17.15 4364.38 353.15 4538.18 637156.51 582272.77 602047.96 652904.39 592312.44 1427.70 546.26 456.61 2580.32 2521.75 1033.56 8.23 13.35 8.18 7.68 137 135 168 187 76 242450705.97 1060.93 15.14 4257.86 351.47 4494.38 655900.13 605722.93 589230.57 655681.23 597265.48 1437.73 551.44 447.31 2609.45 2534.08 1046.36 10.19 27.24 9.76 6.68 131 134 174 186 82 317711776.83 1916.56 14.26 4322.67 363.87 4494.08 649030.83 598759.46 599526.56 628643.96 586099.29 1426.80 537.90 461.55 2571.06 2534.23 1029.27 11.63 38.55 16.08 6.83 130 136 171 185 83 312279718.27 1895.45 12.52 4495.93 351.89 4720.08 646935.48 605861.48 593409.02 669846.73 587251.75 1442.30 547.85 458.56 2622.50 2531.29 1051.27 13.08 55.45 17.59 7.01 138 143 180 190 85 310268777.87 2113.04 12.45 4281.30 349.97 4539.62 655097.69 615258.45 584299.37 631189.52 584905.04 1388.10 547.58 443.71 2440.96 2468.30 1039.94 13.04 55.40 18.10 312975471.93 2150.96 1445.10 614.59 465.50 2511.39 2586.62 1047.43 121.45 82.86 7.03 144 145 182 204 86 309403432.89 2019.61 11.34 656696.79 616016.48 598935.85 631191.87 588019.67 1421.80 553.28 468.61 2517.37 2519.72 1050.05 8.32 55.89 17.99 8.97 125 103 151 159 78 287050317.81 1474.95 14.45 683.11 91.81 791.05 1559720.21 1216564.21 1169238.33 1570800.87 1149452.71 1023.06 464.45 231.80 1544.66 1835.64 1038.75 15.29 74.78 34.49 OpenBenchmarking.org
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.1 WAV To FLAC -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 11 22 33 44 55 SE +/- 0.12, N = 5 SE +/- 0.05, N = 5 SE +/- 0.07, N = 5 SE +/- 0.04, N = 5 SE +/- 0.07, N = 5 SE +/- 0.04, N = 5 SE +/- 0.10, N = 5 SE +/- 0.04, N = 5 SE +/- 0.02, N = 5 46.74 10.62 8.11 7.68 6.68 6.83 7.01 7.03 8.97 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native -O2 -logg 1. (CXX) g++ options: -fvisibility=hidden -lm
GraphicsMagick Operation: Blur OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Blur -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 30 60 90 120 150 SE +/- 0.00, N = 3 SE +/- 0.58, N = 3 SE +/- 1.53, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 1.20, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 82 110 113 137 131 130 138 144 125 -O0 -ldl -Os -ldl -Og -ldl -O1 -ldl -O2 -ldl -O3 -ldl -O3 -march=native -ldl -Ofast -march=native -ldl -O2 -ljbig -lwebp -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -llzma -lbz2 -lxml2 -lgomp 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Sharpen -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 30 60 90 120 150 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 71 124 100 135 134 136 143 145 103 -O0 -ldl -Os -ldl -Og -ldl -O1 -ldl -O2 -ldl -O3 -ldl -O3 -march=native -ldl -Ofast -march=native -ldl -O2 -ljbig -lwebp -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -llzma -lbz2 -lxml2 -lgomp 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Resizing -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 1.00, N = 3 SE +/- 0.67, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.88, N = 3 97 168 149 168 174 171 180 182 151 -O0 -ldl -Os -ldl -Og -ldl -O1 -ldl -O2 -ldl -O3 -ldl -O3 -march=native -ldl -Ofast -march=native -ldl -O2 -ljbig -lwebp -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -llzma -lbz2 -lxml2 -lgomp 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: HWB Color Space -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 40 80 120 160 200 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 110 188 168 187 186 185 190 204 159 -O0 -ldl -Os -ldl -Og -ldl -O1 -ldl -O2 -ldl -O3 -ldl -O3 -march=native -ldl -Ofast -march=native -ldl -O2 -ljbig -lwebp -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -llzma -lbz2 -lxml2 -lgomp 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Local Adaptive Thresholding -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.58, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 17 68 54 76 82 83 85 86 78 -O0 -ldl -Os -ldl -Og -ldl -O1 -ldl -O2 -ldl -O3 -ldl -O3 -march=native -ldl -Ofast -march=native -ldl -O2 -ljbig -lwebp -llcms2 -ltiff -lfreetype -ljasper -ljpeg -lwmflite -llzma -lbz2 -lxml2 -lgomp 1. (CC) gcc options: -fopenmp -pthread -lXext -lSM -lICE -lX11 -lz -lm -lpthread
Hierarchical INTegration Test: FLOAT OpenBenchmarking.org QUIPs, More Is Better Hierarchical INTegration 1.0 Test: FLOAT -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 70M 140M 210M 280M 350M SE +/- 246206.62, N = 3 SE +/- 119724.21, N = 3 SE +/- 179064.26, N = 3 SE +/- 222306.33, N = 3 SE +/- 1047951.03, N = 3 SE +/- 978215.41, N = 3 SE +/- 619811.97, N = 3 SE +/- 100984.48, N = 3 SE +/- 547786.00, N = 3 SE +/- 89816.12, N = 3 103731655.85 303914359.33 326497871.93 242450705.97 317711776.83 312279718.27 310268777.87 312975471.93 309403432.89 287050317.81 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native -O3 -march=native 1. (CC) gcc options: -lm
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 500 1000 1500 2000 2500 SE +/- 0.64, N = 3 SE +/- 3.40, N = 3 SE +/- 1.19, N = 3 SE +/- 1.09, N = 3 SE +/- 4.78, N = 3 SE +/- 6.74, N = 3 SE +/- 9.13, N = 3 SE +/- 7.85, N = 3 SE +/- 3.96, N = 3 SE +/- 0.96, N = 3 424.57 1181.18 1102.64 1060.93 1916.56 1895.45 2113.04 2150.96 2019.61 1474.95 -O0 -mavx2 -Os -mavx2 -Og -mavx2 -O1 -mavx2 -O2 -mavx2 -mavx2 -march=native -mavx2 -march=native -flto -mavx2 -Ofast -march=native -mavx2 1. (CC) gcc options: -O3
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.99.3 WAV To MP3 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 8 16 24 32 40 SE +/- 0.09, N = 5 SE +/- 0.06, N = 5 SE +/- 0.06, N = 5 SE +/- 0.08, N = 5 SE +/- 0.10, N = 5 SE +/- 0.09, N = 5 SE +/- 0.10, N = 5 SE +/- 0.07, N = 5 SE +/- 0.03, N = 5 36.02 16.28 17.15 15.14 14.26 12.52 12.45 11.34 14.45 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native -O3 -ffast-math -funroll-loops -lncurses 1. (CC) gcc options: -pipe -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 9.4.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native s10 1000 2000 3000 4000 5000 SE +/- 44.94, N = 3 SE +/- 32.55, N = 3 SE +/- 64.39, N = 5 SE +/- 80.41, N = 6 SE +/- 62.15, N = 5 SE +/- 64.78, N = 6 SE +/- 18.80, N = 3 SE +/- 10.47, N = 6 4468.97 4275.85 4364.38 4257.86 4322.67 4495.93 4281.30 683.11 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -pthread -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Single Thread - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 9.4.3 Scaling: Buffer Test - Test: Single Thread - Mode: Read Write -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native s10 80 160 240 320 400 SE +/- 4.48, N = 6 SE +/- 4.13, N = 3 SE +/- 5.68, N = 6 SE +/- 5.58, N = 3 SE +/- 2.06, N = 3 SE +/- 2.78, N = 3 SE +/- 1.70, N = 3 SE +/- 0.53, N = 3 303.93 346.32 353.15 351.47 363.87 351.89 349.97 91.81 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -pthread -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 9.4.3 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native s10 1000 2000 3000 4000 5000 SE +/- 21.91, N = 3 SE +/- 27.80, N = 3 SE +/- 54.29, N = 3 SE +/- 67.44, N = 4 SE +/- 19.05, N = 3 SE +/- 40.24, N = 3 SE +/- 66.74, N = 3 SE +/- 15.48, N = 6 4840.76 4497.15 4538.18 4494.38 4494.08 4720.08 4539.62 791.05 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O2 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -pthread -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: LPOP -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 300K 600K 900K 1200K 1500K SE +/- 3542.72, N = 3 SE +/- 12533.78, N = 3 SE +/- 8860.98, N = 6 SE +/- 2503.49, N = 3 SE +/- 5733.33, N = 3 SE +/- 11650.40, N = 6 SE +/- 10960.53, N = 3 SE +/- 5651.00, N = 3 SE +/- 19069.23, N = 3 547091.88 642758.08 637156.51 655900.13 649030.83 646935.48 655097.69 656696.79 1559720.21 -std=gnu99 -pipe -g3 -O3 -funroll-loops 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: SADD -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 300K 600K 900K 1200K 1500K SE +/- 1350.43, N = 3 SE +/- 4522.27, N = 3 SE +/- 11078.60, N = 6 SE +/- 2982.88, N = 3 SE +/- 9681.71, N = 3 SE +/- 3715.65, N = 3 SE +/- 126.17, N = 3 SE +/- 126.46, N = 3 SE +/- 3417.96, N = 3 491891.31 607478.25 582272.77 605722.93 598759.46 605861.48 615258.45 616016.48 1216564.21 -std=gnu99 -pipe -g3 -O3 -funroll-loops 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: LPUSH -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 300K 600K 900K 1200K 1500K SE +/- 2663.98, N = 3 SE +/- 1356.34, N = 3 SE +/- 553.25, N = 3 SE +/- 8590.61, N = 6 SE +/- 1359.59, N = 3 SE +/- 4012.35, N = 3 SE +/- 11218.12, N = 6 SE +/- 2036.63, N = 3 SE +/- 17952.95, N = 3 476295.97 598808.52 602047.96 589230.57 599526.56 593409.02 584299.37 598935.85 1169238.33 -std=gnu99 -pipe -g3 -O3 -funroll-loops 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: GET -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 300K 600K 900K 1200K 1500K SE +/- 1566.53, N = 3 SE +/- 3565.12, N = 3 SE +/- 2604.35, N = 3 SE +/- 5335.15, N = 3 SE +/- 5831.74, N = 3 SE +/- 4253.76, N = 3 SE +/- 10870.06, N = 4 SE +/- 6785.13, N = 3 SE +/- 27357.36, N = 3 548655.63 645755.96 652904.39 655681.23 628643.96 669846.73 631189.52 631191.87 1570800.87 -std=gnu99 -pipe -g3 -O3 -funroll-loops 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 3.0.1 Test: SET -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 200K 400K 600K 800K 1000K SE +/- 7680.16, N = 3 SE +/- 5397.69, N = 3 SE +/- 1909.49, N = 3 SE +/- 1956.89, N = 3 SE +/- 6845.46, N = 3 SE +/- 8111.26, N = 5 SE +/- 8041.99, N = 3 SE +/- 2097.48, N = 3 SE +/- 3977.33, N = 3 479934.92 596757.10 592312.44 597265.48 586099.29 587251.75 584905.04 588019.67 1149452.71 -std=gnu99 -pipe -g3 -O3 -funroll-loops 1. (CC) gcc options: -ggdb -rdynamic -lm -pthread -ldl
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 300 600 900 1200 1500 SE +/- 8.59, N = 4 SE +/- 2.83, N = 4 SE +/- 3.98, N = 4 SE +/- 1.73, N = 4 SE +/- 7.42, N = 4 SE +/- 2.58, N = 4 SE +/- 4.89, N = 4 SE +/- 7.57, N = 4 SE +/- 5.38, N = 4 SE +/- 15.87, N = 4 1407.02 1426.79 1427.70 1437.73 1426.80 1442.30 1388.10 1445.10 1421.80 1023.06 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native 1. (CXX) g++ options:
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 130 260 390 520 650 SE +/- 6.16, N = 4 SE +/- 1.68, N = 4 SE +/- 5.79, N = 4 SE +/- 1.22, N = 4 SE +/- 9.59, N = 4 SE +/- 3.64, N = 4 SE +/- 5.84, N = 4 SE +/- 6.00, N = 4 SE +/- 1.67, N = 4 SE +/- 3.57, N = 4 545.51 552.04 546.26 551.44 537.90 547.85 547.58 614.59 553.28 464.45 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native 1. (CXX) g++ options:
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 100 200 300 400 500 SE +/- 5.60, N = 4 SE +/- 1.29, N = 4 SE +/- 3.34, N = 4 SE +/- 3.48, N = 4 SE +/- 2.20, N = 4 SE +/- 2.05, N = 4 SE +/- 1.70, N = 4 SE +/- 3.19, N = 4 SE +/- 0.63, N = 4 SE +/- 6.76, N = 4 440.57 456.35 456.61 447.31 461.55 458.56 443.71 465.50 468.61 231.80 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native 1. (CXX) g++ options:
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 600 1200 1800 2400 3000 SE +/- 9.07, N = 4 SE +/- 21.77, N = 4 SE +/- 13.12, N = 4 SE +/- 3.88, N = 4 SE +/- 32.30, N = 4 SE +/- 9.06, N = 4 SE +/- 12.32, N = 4 SE +/- 24.76, N = 4 SE +/- 19.13, N = 4 SE +/- 16.80, N = 4 2565.94 2589.56 2580.32 2609.45 2571.06 2622.50 2440.96 2511.39 2517.37 1544.66 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native 1. (CXX) g++ options:
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 600 1200 1800 2400 3000 SE +/- 26.42, N = 4 SE +/- 18.22, N = 4 SE +/- 4.63, N = 4 SE +/- 7.15, N = 4 SE +/- 3.32, N = 4 SE +/- 7.24, N = 4 SE +/- 10.80, N = 4 SE +/- 28.87, N = 4 SE +/- 11.60, N = 4 SE +/- 52.11, N = 4 2454.12 2482.13 2521.75 2534.08 2534.23 2531.29 2468.30 2586.62 2519.72 1835.64 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native 1. (CXX) g++ options:
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 200 400 600 800 1000 SE +/- 9.29, N = 4 SE +/- 1.16, N = 4 SE +/- 8.62, N = 4 SE +/- 3.32, N = 4 SE +/- 12.72, N = 4 SE +/- 2.16, N = 4 SE +/- 6.48, N = 4 SE +/- 6.06, N = 4 SE +/- 0.76, N = 4 SE +/- 11.16, N = 4 1028.95 1053.88 1033.56 1046.36 1029.27 1051.27 1039.94 1047.43 1050.05 1038.75 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native 1. (CXX) g++ options:
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native s10 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 SE +/- 0.05, N = 3 SE +/- 0.16, N = 6 SE +/- 0.51, N = 6 SE +/- 0.35, N = 6 SE +/- 0.68, N = 6 SE +/- 0.27, N = 6 SE +/- 0.02, N = 3 13.82 10.68 8.23 10.19 11.63 13.08 13.04 8.32 15.29 -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -Ofast -march=native -O2 1. (CC) gcc options: -pthread -lhmmer -lsquid -lm
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 30 60 90 120 150 SE +/- 0.10, N = 3 SE +/- 0.08, N = 3 SE +/- 0.13, N = 3 SE +/- 0.21, N = 3 SE +/- 0.06, N = 3 SE +/- 0.14, N = 3 SE +/- 0.23, N = 3 SE +/- 0.25, N = 3 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 9.34 32.43 13.35 27.24 38.55 55.45 55.40 121.45 55.89 74.78
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 5.2.9 Time To Compile -O0 -Os -Og -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native s10 20 40 60 80 100 SE +/- 0.02, N = 3 SE +/- 0.06, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.19, N = 3 SE +/- 0.10, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 5.58 11.61 8.18 9.76 16.08 17.59 18.10 82.86 17.99 34.49 -Os -O1 -O2 -O3 -O3 -march=native -O3 -march=native -flto -Ofast -march=native -O2 1. (CC) gcc options: -pedantic -ldl -lz -lm
Phoronix Test Suite v10.8.4