= Matrix Multiply on GPU =
== Highly optimized MM kernel ==
http://forum.beyond3d.com/showthread.php?t=54842

== MM kernel in OpenCL: Autotuning ==
http://forums.amd.com/devforum/messageview.cfm?catid=390&threadid=127963&STARTPAGE=1&FTVAR_FORUMVIEWTMP=Linear

[[Image(MM1.png)]]