https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
Andrew Pinski changed:
What|Removed |Added
Known to work||12.1.0
--- Comment #12 from Andrew
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
--- Comment #11 from Wilco ---
(In reply to Martin Liška from comment #10)
> Steve, Wilco: Can the bug be marked as resolved?
No, the issue has not been fixed (a workaround was added on AArch64).
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
Martin Liška changed:
What|Removed |Added
CC||marxin at gcc dot gnu.org
--- Comment
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
--- Comment #9 from Steve Ellcey ---
> Can you let me know if my workaround helped? If useful I could backport it
> to GCC7 as well.
Yes, the patch helped. I ran spec 2017 fp rate and saw a small improvement
(0.7%). Most of the speed up was
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
--- Comment #8 from Wilco ---
(In reply to Steve Ellcey from comment #6)
> (In reply to Wilco from comment #5)
> > (In reply to Steve Ellcey from comment #4)
> > > While teaching the reassociation pass about fma's seems like the right
> > >
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
--- Comment #7 from Wilco ---
Author: wilco
Date: Mon Mar 5 14:40:55 2018
New Revision: 258248
URL: https://gcc.gnu.org/viewcvs?rev=258248=gcc=rev
Log:
[AArch64] PR84114: Avoid reassociating FMA
As discussed in the PR, the reassociation phase
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
--- Comment #6 from Steve Ellcey ---
(In reply to Wilco from comment #5)
> (In reply to Steve Ellcey from comment #4)
> > While teaching the reassociation pass about fma's seems like the right
> > answer would it be reasonable (and simpler) to
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
Wilco changed:
What|Removed |Added
CC||wilco.dijkstra at arm dot com
--- Comment #5
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
--- Comment #4 from Steve Ellcey ---
While teaching the reassociation pass about fma's seems like the right answer
would it be reasonable (and simpler) to do the fma pass
(pass_optimize_widening_mul) before
the reassociation pass (pass_reassoc)
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
--- Comment #3 from Wilco ---
(In reply to Richard Biener from comment #1)
> This is probably related to targetm.sched.reassociation_width where reassoc
> will widen a PLUS chain so several instructions will be executable in
> parallel
> without
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
Wilco changed:
What|Removed |Added
CC||wdijkstr at arm dot com
--- Comment #2 from
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=84114
Richard Biener changed:
What|Removed |Added
Keywords||missed-optimization
12 matches
Mail list logo