https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
ktkachov at gcc dot gnu.org changed:
What|Removed |Added
Status|NEW |RESOLVED
CC
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #12 from ktkachov at gcc dot gnu.org ---
Author: ktkachov
Date: Thu Jul 14 14:32:39 2016
New Revision: 238340
URL: https://gcc.gnu.org/viewcvs?rev=238340&root=gcc&view=rev
Log:
[vectorizer][2/2] Hook up mult synthesis logic into vecto
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #11 from Jim Wilson ---
I've spent some time looking at solutions to this problem.
One way to solve it is to simply add a mulv2di3 pattern to the aarch64 port.
The presence of a multiply pattern means we will go through expand_mult,
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #10 from Jim Wilson ---
Created attachment 38399
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=38399&action=edit
testcase unsigned long multiply by constant
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #8 from Jim Wilson ---
Created attachment 38397
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=38397&action=edit
patch to use synth_mult to generate vector multiplies
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #9 from Jim Wilson ---
Created attachment 38398
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=38398&action=edit
testcase signed long multiply by constant
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #7 from Jim Wilson ---
Created attachment 38396
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=38396&action=edit
patch to add a mulv2di3 pattern
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
vekumar at gcc dot gnu.org changed:
What|Removed |Added
CC||vekumar at gcc dot gnu.org
-
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #5 from alalaw01 at gcc dot gnu.org ---
I believe the definitive algorithm for converting multiply-by-constant into
adds+shifts(+etc.) lives in expmed.c. I don't at present have a plan for how to
reuse that, but if we could do so _in_s
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
Richard Biener changed:
What|Removed |Added
Blocks||53947
--- Comment #4 from Richard Biene
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
--- Comment #3 from alalaw01 at gcc dot gnu.org ---
Yes you are right, we have no V2DI multiply. We do have V2DI shifts + add,
however, which would work well for some constants, e.g. the multiply by 16 in
PR/65952; perhaps the vectorizer does not
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65951
Andrew Pinski changed:
What|Removed |Added
Status|UNCONFIRMED |NEW
Last reconfirmed|
12 matches
Mail list logo
