LLVM Clang 3.2 Loop Vectorizer
Intel Core i7-3960X testing of the automatic loop vectorizer in LLVM 3.2 with the Clang compiler. Benchmarking by Michael Larabel for a future article on phoronix.com.


Default: 

	Processor: Intel Core i7-3960X @ 3.30GHz (12 Cores), Motherboard: Intel DX79SI, Chipset: Intel Xeon E5/Core, Memory: 8192MB, Disk: 64GB OCZ VERTEX, Graphics: AMD Radeon HD 4650 512MB, Audio: Realtek ALC892, Monitor: DELL S2409W, Network: Intel 82579LM Gigabit Connection

	OS: Ubuntu 12.10, Kernel: 3.5.0-17-generic (x86_64), Desktop: Unity 6.8.0, Display Server: X Server 1.13.0, Display Driver: radeon 6.99.99, OpenGL: 2.1 Mesa 9.0 Gallium 0.4, Compiler: Clang 3.2 (SVN 166775) + LLVM 3.2svn, File-System: ext4, Screen Resolution: 1920x1080

Loop Vectorization: 

	Processor: Intel Core i7-3960X @ 3.30GHz (12 Cores), Motherboard: Intel DX79SI, Chipset: Intel Xeon E5/Core, Memory: 8192MB, Disk: 64GB OCZ VERTEX, Graphics: AMD Radeon HD 4650 512MB, Audio: Realtek ALC892, Monitor: DELL S2409W, Network: Intel 82579LM Gigabit Connection

	OS: Ubuntu 12.10, Kernel: 3.5.0-17-generic (x86_64), Desktop: Unity 6.8.0, Display Server: X Server 1.13.0, Display Driver: radeon 6.99.99, OpenGL: 2.1 Mesa 9.0 Gallium 0.4, Compiler: Clang 3.2 (SVN 166775) + LLVM 3.2svn, File-System: ext4, Screen Resolution: 1920x1080

2012-10-27 15:48: 

	Processor: AMD Athlon II X3 455 @ 3.30GHz (3 Cores), Motherboard: Gigabyte GA-MA790X-DS4, Chipset: AMD nee ATI RD780 + SB600, Memory: 4096MB, Disk: 500GB Seagate ST3500418AS + 250GB 2500BEV External + 500GB My Passport 0730, Graphics: ATI Radeon HD 3800 512MB (851/1143MHz), Audio: Realtek ALC889A, Monitor: ASUS VH242H, Network: Realtek RTL8111/8168B + Ralink RT3060 Wireless 802.11n 1T/1R

	OS: SUSE LINUX 12.2, Kernel: 3.4.11-2.16-desktop (x86_64), Desktop: KDE 4.8.5, Display Server: X Server 1.12.3, Display Driver: fglrx 8.97.2, OpenGL: 3.3.11653, Compiler: GCC 4.7, File-System: btrfs, Screen Resolution: 1920x1080


Timed HMMer Search 2.3.2
Pfam Database Search
Seconds < Lower Is Better
Default ............ 15.35 |===============================
Loop Vectorization . 15.37 |===============================
2012-10-27 15:48 ... 25.61 |===================================================


GraphicsMagick 1.3.16
Operation: Blur
Iterations Per Minute > Higher Is Better
Default ............ 82 |======================================================
Loop Vectorization . 73 |================================================


GraphicsMagick 1.3.16
Operation: Sharpen
Iterations Per Minute > Higher Is Better
Default ............ 31 |======================================================
Loop Vectorization . 31 |======================================================


GraphicsMagick 1.3.16
Operation: Resizing
Iterations Per Minute > Higher Is Better
Default ............ 89 |======================================================
Loop Vectorization . 84 |===================================================


GraphicsMagick 1.3.16
Operation: HWB Color Space
Iterations Per Minute > Higher Is Better
Default ............ 123 |=====================================================
Loop Vectorization . 122 |=====================================================


GraphicsMagick 1.3.16
Operation: Local Adaptive Thresholding
Iterations Per Minute > Higher Is Better
Default ............ 44 |======================================================
Loop Vectorization . 20 |=========================


Himeno Benchmark 3.0
Poisson Pressure Solver
MFLOPS > Higher Is Better
Default ............ 1595.35 |=================================================
Loop Vectorization . 1554.66 |================================================
2012-10-27 15:48 ... 619.36  |===================


C-Ray 1.1
Total Time
Seconds < Lower Is Better
Default ............ 20.92 |=============
Loop Vectorization . 23.15 |===============
2012-10-27 15:48 ... 80.86 |===================================================


Smallpt 1.0
Global Illumination Renderer; 100 Samples
Seconds < Lower Is Better
Default ............ 153 |===============================
Loop Vectorization . 157 |===============================
2012-10-27 15:48 ... 265 |=====================================================


PostgreSQL pgbench 8.4.11
TPC-B Transactions Per Second
TPS > Higher Is Better
Default ............ 324.77 |================================================
Loop Vectorization . 336.65 |==================================================
2012-10-27 15:48 ... 20.85  |===