[LLVMdev] Use of movupd instead of movapd for x86

Chris Lattner clattner at apple.com
Fri Feb 25 10:10:08 PST 2011


On Feb 25, 2011, at 12:54 AM, Sebastien DELDON-GNB wrote:

> Hi all,
>  
>  
> Is there a way to force llc to generate movupd instruction instead of movapd for x86 target ?
> I know that movapd is more performant, but I would like to measure degradation when alignment constraints are not met.
>  

You can hack loads and stores to have alignment of 1 in the IR, or hack LLC itself.

-Chris

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20110225/c3be42cd/attachment.html>


More information about the llvm-dev mailing list