Please review: Optimize vector multiply on X86

[Nadav Rotem]

On Jun 17, 2013, at 5:16 AM, "Demikhovsky, Elena" <elena.demikhovsky at intel.com> wrote:

> Benjamin already explained me that it was the IR optimization.
> I'm proposing to do the same on DAG level because
> 1) We have the this optimization for scalar and don't have it for vector
> 2) The MUL node can be produced on DAG-level transformations of other items.
> 
> -  Elena
> 

This makes sense to me. This is going to be target-independent, right ?
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20130617/ec9d4575/attachment.html>