public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2
@ 2022-02-23 14:19 aros at gmx dot com
2022-02-23 18:08 ` [Bug target/104663] " pinskia at gcc dot gnu.org
` (5 more replies)
0 siblings, 6 replies; 7+ messages in thread
From: aros at gmx dot com @ 2022-02-23 14:19 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104663
Bug ID: 104663
Summary: A 50% C-Ray regression in GCC 12.0 for ADL at -O2
Product: gcc
Version: 12.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: aros at gmx dot com
Target Milestone: ---
Check the first graph at
https://www.phoronix.com/scan.php?page=article&item=gcc12-feb-alderlake&num=3
^ permalink raw reply [flat|nested] 7+ messages in thread
* [Bug target/104663] A 50% C-Ray regression in GCC 12.0 for ADL at -O2
2022-02-23 14:19 [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2 aros at gmx dot com
@ 2022-02-23 18:08 ` pinskia at gcc dot gnu.org
2022-02-23 23:43 ` pinskia at gcc dot gnu.org
` (4 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: pinskia at gcc dot gnu.org @ 2022-02-23 18:08 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104663
--- Comment #1 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
My bet is this is because the vectorizer is enabled now at -O2.
^ permalink raw reply [flat|nested] 7+ messages in thread
* [Bug target/104663] A 50% C-Ray regression in GCC 12.0 for ADL at -O2
2022-02-23 14:19 [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2 aros at gmx dot com
2022-02-23 18:08 ` [Bug target/104663] " pinskia at gcc dot gnu.org
@ 2022-02-23 23:43 ` pinskia at gcc dot gnu.org
2022-02-23 23:47 ` [Bug target/104663] [12 Regression] C-ray 1.1 performance is 50% worse at -O2 in GCC 12 than before on alderlake pinskia at gcc dot gnu.org
` (3 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: pinskia at gcc dot gnu.org @ 2022-02-23 23:43 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104663
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target| |x86_64-linux-gnu
Keywords| |missed-optimization
Target Milestone|--- |12.0
^ permalink raw reply [flat|nested] 7+ messages in thread
* [Bug target/104663] [12 Regression] C-ray 1.1 performance is 50% worse at -O2 in GCC 12 than before on alderlake
2022-02-23 14:19 [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2 aros at gmx dot com
2022-02-23 18:08 ` [Bug target/104663] " pinskia at gcc dot gnu.org
2022-02-23 23:43 ` pinskia at gcc dot gnu.org
@ 2022-02-23 23:47 ` pinskia at gcc dot gnu.org
2022-02-24 5:24 ` aros at gmx dot com
` (2 subsequent siblings)
5 siblings, 0 replies; 7+ messages in thread
From: pinskia at gcc dot gnu.org @ 2022-02-23 23:47 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104663
Andrew Pinski <pinskia at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Ever confirmed|0 |1
Last reconfirmed| |2022-02-23
Status|UNCONFIRMED |WAITING
--- Comment #2 from Andrew Pinski <pinskia at gcc dot gnu.org> ---
Someone is going to need to anlysis this. I suspect -fno-tree-vectorize gets
the performance back. This would mean most likely a cost model issue.
^ permalink raw reply [flat|nested] 7+ messages in thread
* [Bug target/104663] [12 Regression] C-ray 1.1 performance is 50% worse at -O2 in GCC 12 than before on alderlake
2022-02-23 14:19 [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2 aros at gmx dot com
` (2 preceding siblings ...)
2022-02-23 23:47 ` [Bug target/104663] [12 Regression] C-ray 1.1 performance is 50% worse at -O2 in GCC 12 than before on alderlake pinskia at gcc dot gnu.org
@ 2022-02-24 5:24 ` aros at gmx dot com
2022-02-24 9:25 ` jakub at gcc dot gnu.org
2022-02-24 9:54 ` rguenth at gcc dot gnu.org
5 siblings, 0 replies; 7+ messages in thread
From: aros at gmx dot com @ 2022-02-24 5:24 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104663
--- Comment #3 from Artem S. Tashkinov <aros at gmx dot com> ---
Also -O3 is 50% faster which sounds unreasonable.
-O2 with GCC12 is 75% slower than -O3 for GCC 11.
^ permalink raw reply [flat|nested] 7+ messages in thread
* [Bug target/104663] [12 Regression] C-ray 1.1 performance is 50% worse at -O2 in GCC 12 than before on alderlake
2022-02-23 14:19 [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2 aros at gmx dot com
` (3 preceding siblings ...)
2022-02-24 5:24 ` aros at gmx dot com
@ 2022-02-24 9:25 ` jakub at gcc dot gnu.org
2022-02-24 9:54 ` rguenth at gcc dot gnu.org
5 siblings, 0 replies; 7+ messages in thread
From: jakub at gcc dot gnu.org @ 2022-02-24 9:25 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104663
Jakub Jelinek <jakub at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |jakub at gcc dot gnu.org
--- Comment #4 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
Isn't this related or dup of PR101908 ?
^ permalink raw reply [flat|nested] 7+ messages in thread
* [Bug target/104663] [12 Regression] C-ray 1.1 performance is 50% worse at -O2 in GCC 12 than before on alderlake
2022-02-23 14:19 [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2 aros at gmx dot com
` (4 preceding siblings ...)
2022-02-24 9:25 ` jakub at gcc dot gnu.org
@ 2022-02-24 9:54 ` rguenth at gcc dot gnu.org
5 siblings, 0 replies; 7+ messages in thread
From: rguenth at gcc dot gnu.org @ 2022-02-24 9:54 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104663
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Resolution|--- |DUPLICATE
Status|WAITING |RESOLVED
--- Comment #5 from Richard Biener <rguenth at gcc dot gnu.org> ---
Yes, it is.
*** This bug has been marked as a duplicate of bug 101908 ***
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2022-02-24 9:54 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2022-02-23 14:19 [Bug rtl-optimization/104663] New: A 50% C-Ray regression in GCC 12.0 for ADL at -O2 aros at gmx dot com
2022-02-23 18:08 ` [Bug target/104663] " pinskia at gcc dot gnu.org
2022-02-23 23:43 ` pinskia at gcc dot gnu.org
2022-02-23 23:47 ` [Bug target/104663] [12 Regression] C-ray 1.1 performance is 50% worse at -O2 in GCC 12 than before on alderlake pinskia at gcc dot gnu.org
2022-02-24 5:24 ` aros at gmx dot com
2022-02-24 9:25 ` jakub at gcc dot gnu.org
2022-02-24 9:54 ` rguenth at gcc dot gnu.org
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).