Please review: Optimize vector multiply on X86

[Demikhovsky, Elena]

I did the MUL optimization common for all targets. Please review.

Thanks.

-           Elena

From: Nadav Rotem [mailto:nrotem at apple.com]
Sent: Monday, June 17, 2013 19:04
To: Demikhovsky, Elena
Cc: Andrea_DiBiagio at sn.scee.net; Benjamin Kramer; llvm-commits at cs.uiuc.edu; llvm-commits-bounces at cs.uiuc.edu
Subject: Re: Please review: Optimize vector multiply on X86


On Jun 17, 2013, at 5:16 AM, "Demikhovsky, Elena" <elena.demikhovsky at intel.com<mailto: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 ?
---------------------------------------------------------------------
Intel Israel (74) Limited

This e-mail and any attachments may contain confidential material for
the sole use of the intended recipient(s). Any review or distribution
by others is strictly prohibited. If you are not the intended
recipient, please contact the sender and delete all copies.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20130619/2be125bc/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: mul2.diff
Type: application/octet-stream
Size: 9497 bytes
Desc: mul2.diff
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20130619/2be125bc/attachment.obj>