public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
From: "jamborm at gcc dot gnu.org" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug ipa/103227] [12 Regression] 58% exchange2 regression with -Ofast -march=native on zen3 since r12-5223-gecdf414bd89e6ba251f6b3f494407139b4dbae0e
Date: Fri, 19 Nov 2021 18:18:06 +0000 [thread overview]
Message-ID: <bug-103227-4-ZbxaDZROZd@http.gcc.gnu.org/bugzilla/> (raw)
In-Reply-To: <bug-103227-4@http.gcc.gnu.org/bugzilla/>
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103227
--- Comment #4 from Martin Jambor <jamborm at gcc dot gnu.org> ---
Still, the interaction between IPA-CP and IPA-SRA is bad here. Just
looking at the optimized dump, one of the "specialized functions"
starts with:
<bb 2> [local count: 62767467]:
# DEBUG D#203 s=> row
# DEBUG row => D#203
_2 = (long int) ISRA.10821_938(D);
where the ISRA param contains the constant we wanted to specialize
for... making the clones worse than useless.
>From the IPA-CP ltrans dumps it is clear that the transformation phase
of IPA-CP considers the first parameter dead and so does not perform
the substitutions even though the parameter is replaced only by a
"subsequent" pass.
The infrastructure invokes the transform function on node
digits_2.constprop.isra/157 (note the isra) which has already been
modified by the subsequent pass (when it was cloned).
I like the idea of transformation phases better than putting
everything into tree-inline (and by extension ipa-param-manipulation)
but perhaps we have to do aggregate constant replacements there too?
next prev parent reply other threads:[~2021-11-19 18:18 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-13 21:05 [Bug tree-optimization/103227] New: 58% exchange2 regression with -Ofast -march=native on zen3 between g:1ae8edf5f73ca5c3 and g:2af63f0f53a12a72 hubicka at gcc dot gnu.org
2021-11-13 22:00 ` [Bug ipa/103227] " hubicka at gcc dot gnu.org
2021-11-13 22:11 ` hubicka at gcc dot gnu.org
2021-11-13 22:15 ` hubicka at gcc dot gnu.org
2021-11-15 9:04 ` [Bug ipa/103227] [12 Regression] 58% exchange2 regression with -Ofast -march=native on zen3 since r12-5223-gecdf414bd89e6ba251f6b3f494407139b4dbae0e rguenth at gcc dot gnu.org
2021-11-19 18:18 ` jamborm at gcc dot gnu.org [this message]
2021-11-19 21:12 ` hubicka at kam dot mff.cuni.cz
2021-11-19 21:22 ` hubicka at gcc dot gnu.org
2021-11-19 23:21 ` jamborm at gcc dot gnu.org
2021-11-20 12:32 ` hubicka at kam dot mff.cuni.cz
2021-11-20 12:39 ` hubicka at kam dot mff.cuni.cz
2021-11-21 15:16 ` cvs-commit at gcc dot gnu.org
2021-11-23 17:02 ` jamborm at gcc dot gnu.org
2021-11-24 12:52 ` jamborm at gcc dot gnu.org
2021-11-25 17:17 ` cvs-commit at gcc dot gnu.org
2021-11-26 9:19 ` hubicka at gcc dot gnu.org
2021-11-28 18:56 ` hubicka at gcc dot gnu.org
2022-12-14 0:04 ` cvs-commit at gcc dot gnu.org
2023-08-15 15:45 ` jamborm at gcc dot gnu.org
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=bug-103227-4-ZbxaDZROZd@http.gcc.gnu.org/bugzilla/ \
--to=gcc-bugzilla@gcc.gnu.org \
--cc=gcc-bugs@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).