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. march=nocona: Processor: Intel Core i7-3770K @ 3.50GHz (8 Cores), Motherboard: ECS Z77H2-A2X v1.0, Chipset: Intel Ivy Bridge DRAM, Memory: 15360MB, Disk: 240GB OCZ VERTEX3, Graphics: Intel Ivy Bridge, Audio: Realtek ALC892, Monitor: DELL P2210H, Network: Realtek RTL8111/8168B OS: Ubuntu 12.04, Kernel: 3.4.0-999-generic (x86_64), Desktop: Unity 5.10.0, Display Server: X Server 1.11.3, Display Driver: intel 2.18.0, OpenGL: 2.1 Mesa 8.1-devel (git-137c5ec), Compiler: GCC 4.7.0, File-System: ext4, Screen Resolution: 1920x1080 march=core2: Processor: Intel Core i7-3770K @ 3.50GHz (8 Cores), Motherboard: ECS Z77H2-A2X v1.0, Chipset: Intel Ivy Bridge DRAM, Memory: 15360MB, Disk: 240GB OCZ VERTEX3, Graphics: Intel Ivy Bridge, Audio: Realtek ALC892, Monitor: DELL P2210H, Network: Realtek RTL8111/8168B OS: Ubuntu 12.04, Kernel: 3.4.0-999-generic (x86_64), Desktop: Unity 5.10.0, Display Server: X Server 1.11.3, Display Driver: intel 2.18.0, OpenGL: 2.1 Mesa 8.1-devel (git-137c5ec), Compiler: GCC 4.7.0, File-System: ext4, Screen Resolution: 1920x1080 march=corei7: Processor: Intel Core i7-3770K @ 3.50GHz (8 Cores), Motherboard: ECS Z77H2-A2X v1.0, Chipset: Intel Ivy Bridge DRAM, Memory: 15360MB, Disk: 240GB OCZ VERTEX3, Graphics: Intel Ivy Bridge, Audio: Realtek ALC892, Monitor: DELL P2210H, Network: Realtek RTL8111/8168B OS: Ubuntu 12.04, Kernel: 3.4.0-999-generic (x86_64), Desktop: Unity 5.10.0, Display Server: X Server 1.11.3, Display Driver: intel 2.18.0, OpenGL: 2.1 Mesa 8.1-devel (git-137c5ec), Compiler: GCC 4.7.0, File-System: ext4, Screen Resolution: 1920x1080 march=corei7-avx: Processor: Intel Core i7-3770K @ 3.50GHz (8 Cores), Motherboard: ECS Z77H2-A2X v1.0, Chipset: Intel Ivy Bridge DRAM, Memory: 15360MB, Disk: 240GB OCZ VERTEX3, Graphics: Intel Ivy Bridge, Audio: Realtek ALC892, Monitor: DELL P2210H, Network: Realtek RTL8111/8168B OS: Ubuntu 12.04, Kernel: 3.4.0-999-generic (x86_64), Desktop: Unity 5.10.0, Display Server: X Server 1.11.3, Display Driver: intel 2.18.0, OpenGL: 2.1 Mesa 8.1-devel (git-137c5ec), Compiler: GCC 4.7.0, File-System: ext4, Screen Resolution: 1920x1080 march=core-avx-i: Processor: Intel Core i7-3770K @ 3.50GHz (8 Cores), Motherboard: ECS Z77H2-A2X v1.0, Chipset: Intel Ivy Bridge DRAM, Memory: 15360MB, Disk: 240GB OCZ VERTEX3, Graphics: Intel Ivy Bridge, Audio: Realtek ALC892, Monitor: DELL P2210H, Network: Realtek RTL8111/8168B OS: Ubuntu 12.04, Kernel: 3.4.0-999-generic (x86_64), Desktop: Unity 5.10.0, Display Server: X Server 1.11.3, Display Driver: intel 2.18.0, OpenGL: 2.1 Mesa 8.1-devel (git-137c5ec), Compiler: GCC 4.7.0, File-System: ext4, Screen Resolution: 1920x1080 Timed HMMer Search 2.3.2 Pfam Database Search Seconds < Lower Is Better march=nocona ..... 10.15 |===================================================== march=core2 ...... 10.12 |===================================================== march=corei7 ..... 10.18 |===================================================== march=corei7-avx . 10.14 |===================================================== march=core-avx-i . 10.07 |==================================================== BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 LPS > Higher Is Better march=nocona ..... 27036432.83 |=============================================== march=core2 ...... 26589940.70 |============================================== march=corei7 ..... 26626074.10 |============================================== march=corei7-avx . 26633781.23 |============================================== march=core-avx-i . 26620703.27 |============================================== TTSIOD 3D Renderer 2.2w Phong Rendering With Soft-Shadow Mapping FPS > Higher Is Better march=nocona ..... 132.95 |================================================== march=core2 ...... 133.03 |================================================== march=corei7 ..... 132.44 |================================================== march=corei7-avx . 136.93 |==================================================== march=core-avx-i . 137.13 |==================================================== GraphicsMagick 1.3.12 Operation: Blur Iterations Per Minute > Higher Is Better march=nocona ..... 136 |==================================================== march=core2 ...... 135 |==================================================== march=corei7 ..... 134 |=================================================== march=corei7-avx . 144 |======================================================= march=core-avx-i . 144 |======================================================= GraphicsMagick 1.3.12 Operation: Sharpen Iterations Per Minute > Higher Is Better march=nocona ..... 84 |================================================= march=core2 ...... 84 |================================================= march=corei7 ..... 83 |================================================ march=corei7-avx . 96 |======================================================== march=core-avx-i . 96 |======================================================== GraphicsMagick 1.3.12 Operation: Resizing Iterations Per Minute > Higher Is Better march=nocona ..... 166 |===================================================== march=core2 ...... 165 |==================================================== march=corei7 ..... 165 |==================================================== march=corei7-avx . 173 |======================================================= march=core-avx-i . 173 |======================================================= GraphicsMagick 1.3.12 Operation: HWB Color Space Iterations Per Minute > Higher Is Better march=nocona ..... 204 |======================================================= march=core2 ...... 202 |====================================================== march=corei7 ..... 202 |====================================================== march=corei7-avx . 204 |======================================================= march=core-avx-i . 204 |======================================================= GraphicsMagick 1.3.12 Operation: Local Adaptive Thresholding Iterations Per Minute > Higher Is Better march=nocona ..... 84 |======================================================== march=core2 ...... 83 |======================================================= march=corei7 ..... 83 |======================================================= march=corei7-avx . 84 |======================================================== march=core-avx-i . 84 |======================================================== Himeno Benchmark 3.0 Poisson Pressure Solver MFLOPS > Higher Is Better march=nocona ..... 1620.37 |================================================== march=core2 ...... 1646.22 |=================================================== march=corei7 ..... 1636.54 |================================================== march=corei7-avx . 1655.26 |=================================================== march=core-avx-i . 1646.10 |=================================================== Timed PHP Compilation 5.2.9 Time To Compile Seconds < Lower Is Better march=nocona ..... 24.91 |================================================= march=core2 ...... 26.55 |==================================================== march=corei7 ..... 26.64 |==================================================== march=corei7-avx . 27.09 |===================================================== march=core-avx-i . 27.05 |===================================================== C-Ray 1.1 Total Time Seconds < Lower Is Better march=nocona ..... 80.37 |========================================= march=core2 ...... 101.14 |==================================================== march=corei7 ..... 90.94 |=============================================== march=corei7-avx . 86.31 |============================================ march=core-avx-i . 89.82 |============================================== Smallpt 1.0 Global Illumination Renderer; 100 Samples Seconds < Lower Is Better march=nocona ..... 25 |======================================================== march=core2 ...... 25 |======================================================== march=corei7 ..... 25 |======================================================== march=corei7-avx . 24 |====================================================== march=core-avx-i . 25 |======================================================== LZMA Compression 256MB File Compression Seconds < Lower Is Better march=nocona ..... 132.49 |==================================================== march=core2 ...... 132.60 |==================================================== march=corei7 ..... 132.47 |==================================================== march=corei7-avx . 132.66 |==================================================== march=core-avx-i . 132.32 |==================================================== dcraw RAW To PPM Image Conversion Seconds < Lower Is Better march=nocona ..... 16.09 |===================================================== march=core2 ...... 15.90 |==================================================== march=corei7 ..... 15.81 |==================================================== march=corei7-avx . 16.15 |===================================================== march=core-avx-i . 16.18 |===================================================== LAME MP3 Encoding 3.99.3 WAV To MP3 Seconds < Lower Is Better march=nocona ..... 13.16 |==================================================== march=core2 ...... 13.50 |===================================================== march=corei7 ..... 13.35 |==================================================== march=corei7-avx . 13.22 |==================================================== march=core-avx-i . 13.25 |==================================================== Open FMM Nero2D 2.0.2 Total Time Seconds < Lower Is Better march=nocona ..... 414.67 |==================================================== march=core2 ...... 410.68 |=================================================== march=corei7 ..... 408.94 |=================================================== march=corei7-avx . 409.41 |=================================================== march=core-avx-i . 408.70 |=================================================== PostgreSQL pgbench 8.4.11 TPC-B Transactions Per Second TPS > Higher Is Better march=nocona ..... 3066.14 |=================================================== march=core2 ...... 3063.39 |=================================================== march=corei7 ..... 3060.46 |=================================================== march=corei7-avx . 3038.40 |=================================================== march=core-avx-i . 3028.57 |================================================== Apache Benchmark 2.2.21 Static Web Page Serving Requests Per Second > Higher Is Better march=nocona ..... 33671.40 |================================================= march=core2 ...... 33993.62 |================================================== march=corei7 ..... 34158.30 |================================================== march=corei7-avx . 34163.64 |================================================== march=core-avx-i . 33480.13 |=================================================