Sign in to follow this  
V-man

How to use SSE, inline assembly

Recommended Posts

I found this page http://www.ibm.com/developerworks/linux/library/l-ia.html?dwzone=linux so I can perhaps understand some of that AT&T syntax and port my inline assembly code to Linux. The inline assembly is done in VC++, for the Windows platform. Problem is that this is too much work. I was thinking maybe there is an easier way. Has anyone used Intel's or AMD's math toolkit? I just need to multiply matrix by vector, vector by matrix. PS : Matrices are in column major format.

Share this post


Link to post
Share on other sites
Look on compiler's sse intrinsics, you can see good example of math operations in nebula device sdk: [url]http://www.koders.com/cpp/fid6BFC8022681B932C0CFF0644DB9C58C63B59B1F8.aspx?s=sse+_mm_shuffle+nebula[/url]

Share this post


Link to post
Share on other sites
I believe gcc has some built in vectorization ability without inline assembly or intrinsics. Might want to google that.

Intrinsics are really easy to use however, and also tend to port really well between windows/unix/mac on different compilers.

Share this post


Link to post
Share on other sites
Sign in to follow this