public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug target/98361] New: L1/L2 cache characteristics not recognized with -mtune=znver2
@ 2020-12-17 22:21 sdack at gmx dot com
2020-12-18 8:53 ` [Bug target/98361] " marxin at gcc dot gnu.org
2020-12-18 14:01 ` sdack at gmx dot com
0 siblings, 2 replies; 3+ messages in thread
From: sdack at gmx dot com @ 2020-12-17 22:21 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98361
Bug ID: 98361
Summary: L1/L2 cache characteristics not recognized with
-mtune=znver2
Product: gcc
Version: 10.2.1
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: sdack at gmx dot com
Target Milestone: ---
Hello,
I've come across an unexpected behaviour of gcc and wanted to ask for
help. I've noticed that when I specify '-march=znver2' does gcc use the
incorrect values for the L1/L2 cache. Only when '-march=native' was used
and gcc detected the CPU at run-time does it use the correct values. For
example on a Ryzen 7 3800X (a Zen 2 CPU):
$ gcc -march=znver2 --help=params -Q|fgrep cache
--param=l1-cache-line-size= 32
--param=l1-cache-size= 64
--param=l2-cache-size= 512
versus:
$ gcc -march=native --help=params -Q|fgrep cache
--param=l1-cache-line-size= 64
--param=l1-cache-size= 32
--param=l2-cache-size= 512
GCC does detect the CPU as 'znver2':
$ gcc -march=native --help=target -Q|fgrep march
-march= znver2
I've also verified this behaviour with '-mtune=znver2', and again does
GCC only use the correct values when it uses auto-detection.
Why does GCC not use the correct L1/L2 cache values when '-march=znver2'
or '-mtune=znver2' is specified?
Sven
PS: I've now also checked parts of the gcc source code and
gcc/config/i386/x86-tune-costs.h (around line 1557) does hold the correct
values and it appears these only don't get used somehow.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug target/98361] L1/L2 cache characteristics not recognized with -mtune=znver2
2020-12-17 22:21 [Bug target/98361] New: L1/L2 cache characteristics not recognized with -mtune=znver2 sdack at gmx dot com
@ 2020-12-18 8:53 ` marxin at gcc dot gnu.org
2020-12-18 14:01 ` sdack at gmx dot com
1 sibling, 0 replies; 3+ messages in thread
From: marxin at gcc dot gnu.org @ 2020-12-18 8:53 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98361
Martin Liška <marxin at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Resolution|--- |FIXED
CC| |marxin at gcc dot gnu.org
Status|UNCONFIRMED |RESOLVED
--- Comment #1 from Martin Liška <marxin at gcc dot gnu.org> ---
It's already fixed by r11-2755-ga7bbb5b1b1eb09db and the corresponding change
also landed to GCC 10 branch: g:f7e39d1f137202a5d554849f6930ade58c312acd.
^ permalink raw reply [flat|nested] 3+ messages in thread
* [Bug target/98361] L1/L2 cache characteristics not recognized with -mtune=znver2
2020-12-17 22:21 [Bug target/98361] New: L1/L2 cache characteristics not recognized with -mtune=znver2 sdack at gmx dot com
2020-12-18 8:53 ` [Bug target/98361] " marxin at gcc dot gnu.org
@ 2020-12-18 14:01 ` sdack at gmx dot com
1 sibling, 0 replies; 3+ messages in thread
From: sdack at gmx dot com @ 2020-12-18 14:01 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=98361
--- Comment #2 from Sven <sdack at gmx dot com> ---
Thank you.
I did ask about the issue on gcc-help, but I never got a notice about a fix.
Some ninja appears to have cherry-picked it for 10.2.x a few days after my
initial mail.
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2020-12-18 14:01 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-12-17 22:21 [Bug target/98361] New: L1/L2 cache characteristics not recognized with -mtune=znver2 sdack at gmx dot com
2020-12-18 8:53 ` [Bug target/98361] " marxin at gcc dot gnu.org
2020-12-18 14:01 ` sdack at gmx dot com
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).