Changes between Version 35 and Version 36 of OpenCL_Memo


Ignore:
Timestamp:
Dec 12, 2011 7:00:33 PM (13 years ago)
Author:
nakasato
Comment:

--

Legend:

Unmodified
Added
Removed
Modified
  • OpenCL_Memo

    v35 v36  
    1 = Tips = 
     1= OpenCL Notes = 
    22== Disable auto vectorization == 
    33In the section 6.7.2 (187 page) in the OpenCL Specification Version: 1.1 (Revision: 33), "__attribute__((vec_type_hint(<typen>))" is described. This hint controls the autovectorizer in the compiler for OpenCL C. I tested this feature by dumping the assembly code for a kernel targeted for AVX instructions with Intel SDK (version 1.5). 
    44 
    5 ||                  || lines || performance || 
    6 || without the hint || 1567  ||             || 
    7 || with the hint    || 333   ||             || 
     5||               || lines || performance || 
     6|| no hint      || 1567  ||             || 
     7|| with the hint || 333   ||             || 
    88 
    99This hint amazingly reduces the size of the generated kernel code! Cool.  
    1010 
    11  
    12 = SDK and driver =  
     11== SDK and driver ==  
    1312 
    1413== Latest SDK == 
     
    1615 
    1716Intel http://software.intel.com/en-us/articles/vcsource-tools-opencl-sdk/ 
     17 
     18Nvidia  
     19 
     20Apple'SDK comes with MacOS X only 
    1821 
    1922== Latest Driver for AMD ==