Changes between Version 32 and Version 33 of OpenCL_Memo

Timestamp:

Dec 12, 2011 6:57:12 PM (13 years ago)

Author:

nakasato

Comment:

--

OpenCL_Memo

@@ -1 @@
-== Latest Driver ==
-http://support.amd.com/us/gpudownload/linux/Pages/radeon_linux.aspx?type=2.4.1&product=2.4.1.3.42&lang=English
+= Tips =
+== Disable auto vectorization ==
+In the section 6.7.2 (187P) 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 to dump the assembly code for a kernel targeted for AVX instructions with Intel SDK (version 1.5).
+
+||                  || lines || performance ||
+|| without the hint || 1567  ||             ||
+|| with the hint    || 333   ||             ||
+
+This hint amazingly reduce the size of the generated kernel code. 
+
+
+= SDK and driver = 
 
 == Latest SDK ==
@@ -7 +17 @@
 Intel http://software.intel.com/en-us/articles/vcsource-tools-opencl-sdk/
 
+== Latest Driver for AMD ==
+http://support.amd.com/us/gpudownload/linux/Pages/radeon_linux.aspx?type=2.4.1&product=2.4.1.3.42&lang=English
+
+
+= old info =
 == Standard Compute Layer Library ==
 http://www.browndeertechnology.com/stdcl.html
@@ -47 +62 @@
 Note this option is generally regarded as "bad" for security. Be careful.
 
-=== icc ===
+= Random notes =
+== icc ==
 http://software.intel.com/en-us/articles/using-intel-compilers-for-linux-with-ubuntu/
 
-
-=== packages ===
+== packages ==
 Ubuntu 10.04.1 LTS
 {{{
@@ -65 +80 @@
 http://forums.amd.com/devforum/messageview.cfm?catid=390&threadid=147002
 
-
-=== process affinity ===
+== process affinity ==
 From command line: http://www.cyberciti.biz/tips/setting-processor-affinity-certain-task-or-process.html
 
 http://www.open-mpi.org/projects/hwloc/
 
-=== DOUBLE ===
+== DOUBLE ==
 http://developer.amd.com/support/KnowledgeBase/Lists/KnowledgeBase/DispForm.aspx?ID=92