Intel Core i7 Ivy Bridge GCC Compiler Tuning GCC 4.7.0 compiler tuning with Intel Ivy Bridge looking at the performance of various compiler flags. Testing for a future article on Phoronix.com. Tested options were march=nocona, march=core2, march=corei7, march=corei7-avx, and march=core-avx-i. The -O3 was also set for the CFLAG/CXXFLAGS for all runs.
HTML result view exported from: https://openbenchmarking.org/result/1206055-SU-INTELCORE01&sor&grr .
Intel Core i7 Ivy Bridge GCC Compiler Tuning Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution march=nocona march=core2 march=corei7 march=corei7-avx march=core-avx-i Intel Core i7-3770K @ 3.50GHz (8 Cores) ECS Z77H2-A2X v1.0 Intel Ivy Bridge DRAM 15360MB 240GB OCZ VERTEX3 Intel Ivy Bridge Realtek ALC892 DELL P2210H Realtek RTL8111/8168B Ubuntu 12.04 3.4.0-999-generic (x86_64) Unity 5.10.0 X Server 1.11.3 intel 2.18.0 2.1 Mesa 8.1-devel (git-137c5ec) GCC 4.7.0 ext4 1920x1080 OpenBenchmarking.org Compiler Details - --disable-multilib --enable-checking=release --enable-languages=c,c++,fortran --enable-lto Processor Details - Scaling Governor: ondemand System Details - Compiz was running on this system.
Intel Core i7 Ivy Bridge GCC Compiler Tuning apache: Static Web Page Serving pgbench: TPC-B Transactions Per Second nero2d: Total Time encode-mp3: WAV To MP3 dcraw: RAW To PPM Image Conversion compress-lzma: 256MB File Compression smallpt: Global Illumination Renderer; 100 Samples c-ray: Total Time build-php: Time To Compile himeno: Poisson Pressure Solver graphics-magick: Local Adaptive Thresholding graphics-magick: HWB Color Space graphics-magick: Resizing graphics-magick: Sharpen graphics-magick: Blur ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping byte: Dhrystone 2 hmmer: Pfam Database Search march=nocona march=core2 march=corei7 march=corei7-avx march=core-avx-i 33671.40 3066.14 414.67 13.16 16.09 132.49 25 80.37 24.91 1620.37 84 204 166 84 136 132.95 27036432.83 10.15 33993.62 3063.39 410.68 13.50 15.90 132.60 25 101.14 26.55 1646.22 83 202 165 84 135 133.03 26589940.70 10.12 34158.30 3060.46 408.94 13.35 15.81 132.47 25 90.94 26.64 1636.54 83 202 165 83 134 132.44 26626074.10 10.18 34163.64 3038.40 409.41 13.22 16.15 132.66 24 86.31 27.09 1655.26 84 204 173 96 144 136.93 26633781.23 10.14 33480.13 3028.57 408.70 13.25 16.18 132.32 25 89.82 27.05 1646.10 84 204 173 96 144 137.13 26620703.27 10.07 OpenBenchmarking.org
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.2.21 Static Web Page Serving march=corei7-avx march=corei7 march=core2 march=nocona march=core-avx-i 7K 14K 21K 28K 35K SE +/- 227.87, N = 3 SE +/- 474.66, N = 3 SE +/- 288.23, N = 3 SE +/- 143.72, N = 3 SE +/- 367.46, N = 3 34163.64 34158.30 33993.62 33671.40 33480.13 -march=corei7-avx -march=corei7 -march=core2 -march=nocona -march=core-avx-i 1. (CC) gcc options: -pthread -O3 -lm -lexpat -lrt -lcrypt -lpthread -ldl
PostgreSQL pgbench TPC-B Transactions Per Second OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 8.4.11 TPC-B Transactions Per Second march=nocona march=core2 march=corei7 march=corei7-avx march=core-avx-i 700 1400 2100 2800 3500 SE +/- 14.86, N = 3 SE +/- 12.53, N = 3 SE +/- 6.70, N = 3 SE +/- 10.73, N = 3 SE +/- 24.76, N = 3 3066.14 3063.39 3060.46 3038.40 3028.57 -march=nocona -march=core2 -march=corei7 -march=corei7-avx -march=core-avx-i 1. (CC) gcc options: -O3 -fno-strict-aliasing -fwrapv -lpgport -lpq -lcrypt -ldl -lm
Open FMM Nero2D Total Time OpenBenchmarking.org Seconds, Fewer Is Better Open FMM Nero2D 2.0.2 Total Time march=core-avx-i march=corei7 march=corei7-avx march=core2 march=nocona 90 180 270 360 450 408.70 408.94 409.41 410.68 414.67 -march=core-avx-i -march=corei7 -march=corei7-avx -march=core2 -march=nocona 1. (CXX) g++ options: -O3 -lfftw3 -llapack -lblas -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.99.3 WAV To MP3 march=nocona march=corei7-avx march=core-avx-i march=corei7 march=core2 3 6 9 12 15 SE +/- 0.02, N = 5 SE +/- 0.02, N = 5 SE +/- 0.03, N = 5 SE +/- 0.01, N = 5 SE +/- 0.02, N = 5 13.16 13.22 13.25 13.35 13.50
dcraw RAW To PPM Image Conversion OpenBenchmarking.org Seconds, Fewer Is Better dcraw RAW To PPM Image Conversion march=corei7 march=core2 march=nocona march=corei7-avx march=core-avx-i 4 8 12 16 20 SE +/- 0.22, N = 3 SE +/- 0.17, N = 3 SE +/- 0.17, N = 3 SE +/- 0.21, N = 3 SE +/- 0.21, N = 3 15.81 15.90 16.09 16.15 16.18 -march=corei7 -march=core2 -march=nocona -march=corei7-avx -march=core-avx-i 1. (CC) gcc options: -O3 -lm
LZMA Compression 256MB File Compression OpenBenchmarking.org Seconds, Fewer Is Better LZMA Compression 256MB File Compression march=core-avx-i march=corei7 march=nocona march=core2 march=corei7-avx 30 60 90 120 150 SE +/- 0.21, N = 3 SE +/- 0.17, N = 3 SE +/- 0.37, N = 3 SE +/- 0.19, N = 3 SE +/- 0.13, N = 3 132.32 132.47 132.49 132.60 132.66 -march=core-avx-i -march=corei7 -march=nocona -march=core2 -march=corei7-avx 1. (CC) gcc options: -O3
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples march=corei7-avx march=nocona march=core2 march=corei7 march=core-avx-i 6 12 18 24 30 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 24 25 25 25 25 -march=corei7-avx -march=nocona -march=core2 -march=corei7 -march=core-avx-i 1. (CXX) g++ options: -fopenmp -O3
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time march=nocona march=corei7-avx march=core-avx-i march=corei7 march=core2 20 40 60 80 100 SE +/- 6.43, N = 6 SE +/- 5.81, N = 6 SE +/- 6.72, N = 6 SE +/- 7.96, N = 6 SE +/- 2.52, N = 6 80.37 86.31 89.82 90.94 101.14 -march=nocona -march=corei7-avx -march=core-avx-i -march=corei7 -march=core2 1. (CC) gcc options: -lm -lpthread -O3
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 5.2.9 Time To Compile march=nocona march=core2 march=corei7 march=core-avx-i march=corei7-avx 6 12 18 24 30 SE +/- 0.01, N = 3 SE +/- 0.06, N = 3 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 SE +/- 0.07, N = 3 24.91 26.55 26.64 27.05 27.09 -march=nocona -march=core2 -march=corei7 -march=core-avx-i -march=corei7-avx 1. (CC) gcc options: -O3 -pedantic -ldl -lz -lm
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver march=corei7-avx march=core2 march=core-avx-i march=corei7 march=nocona 400 800 1200 1600 2000 SE +/- 4.68, N = 3 SE +/- 12.22, N = 3 SE +/- 4.78, N = 3 SE +/- 18.31, N = 3 SE +/- 6.23, N = 3 1655.26 1646.22 1646.10 1636.54 1620.37 -march=corei7-avx -march=core2 -march=core-avx-i -march=corei7 -march=nocona 1. (CC) gcc options: -O3
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding march=core-avx-i march=corei7-avx march=nocona march=corei7 march=core2 20 40 60 80 100 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 84 84 84 83 83 -march=core-avx-i -march=corei7-avx -march=nocona -march=corei7 -march=core2 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lz -lm -lrt -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: HWB Color Space march=core-avx-i march=corei7-avx march=nocona march=corei7 march=core2 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 204 204 204 202 202 -march=core-avx-i -march=corei7-avx -march=nocona -march=corei7 -march=core2 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lz -lm -lrt -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Resizing march=core-avx-i march=corei7-avx march=nocona march=corei7 march=core2 40 80 120 160 200 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 173 173 166 165 165 -march=core-avx-i -march=corei7-avx -march=nocona -march=corei7 -march=core2 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lz -lm -lrt -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Sharpen march=core-avx-i march=corei7-avx march=core2 march=nocona march=corei7 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 SE +/- 0.33, N = 3 96 96 84 84 83 -march=core-avx-i -march=corei7-avx -march=core2 -march=nocona -march=corei7 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lz -lm -lrt -lpthread
GraphicsMagick Operation: Blur OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.12 Operation: Blur march=core-avx-i march=corei7-avx march=nocona march=core2 march=corei7 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 +/- 0.33, N = 3 144 144 136 135 134 -march=core-avx-i -march=corei7-avx -march=nocona -march=core2 -march=corei7 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -pthread -ltiff -lfreetype -lXext -lSM -lICE -lX11 -lz -lm -lrt -lpthread
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.2w Phong Rendering With Soft-Shadow Mapping march=core-avx-i march=corei7-avx march=core2 march=nocona march=corei7 30 60 90 120 150 SE +/- 0.21, N = 3 SE +/- 0.42, N = 3 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 SE +/- 0.16, N = 3 137.13 136.93 133.03 132.95 132.44 -march=core-avx-i -march=corei7-avx -march=core2 -march=nocona -march=corei7 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 march=nocona march=corei7-avx march=corei7 march=core-avx-i march=core2 6M 12M 18M 24M 30M SE +/- 10729.97, N = 3 SE +/- 6613.46, N = 3 SE +/- 1818.89, N = 3 SE +/- 3694.38, N = 3 SE +/- 16796.57, N = 3 27036432.83 26633781.23 26626074.10 26620703.27 26589940.70 -march=nocona -march=corei7-avx -march=corei7 -march=core-avx-i -march=core2 1. (CC) gcc options: -O3
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search march=core-avx-i march=core2 march=corei7-avx march=nocona march=corei7 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.14, N = 3 SE +/- 0.03, N = 3 SE +/- 0.17, N = 3 10.07 10.12 10.14 10.15 10.18 -march=core-avx-i -march=core2 -march=corei7-avx -march=nocona -march=corei7 1. (CC) gcc options: -O3 -pthread -lhmmer -lsquid -lm
Phoronix Test Suite v10.8.5