Hi Tanya,
Looks good and usefull, but I'm not sure if it should be clang's decision if
storing and loading vec4s is better than vec3.
Anyhow, shouldn't the test check the store shuffle too?
Thanks
Guy
-----Original Message-----
From: [email protected] [mailto:[email protected]]
On Behalf Of Tanya Lattner
Sent: Wednesday, July 18, 2012 01:46
To: [email protected]
Subject: [cfe-commits] [PATCH] Optimize vec3 loads/stores
This patch treats vectors of size 3 like size 4 when loading and store which in
turn will cause more optimal code to be emitted by the backend. I've included a
test case.
Please review.
Thanks,
Tanya
---------------------------------------------------------------------
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.
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.cs.uiuc.edu/mailman/listinfo/cfe-commits
