From: Vineet Gupta <Vineet.Gupta1@synopsys.com>
To: Linus Torvalds <torvalds@linux-foundation.org>,
Vineet Gupta <Vineet.Gupta1@synopsys.com>
Cc: Arnd Bergmann <arnd@kernel.org>,
Peter Zijlstra <peterz@infradead.org>,
Masahiro Yamada <masahiroy@kernel.org>,
Jann Horn <jannh@google.com>, lkml <linux-kernel@vger.kernel.org>,
arcml <linux-snps-arc@lists.infradead.org>,
"linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>
Subject: Re: Heads up: gcc miscompiling initramfs zlib decompression code at -O3
Date: Fri, 30 Apr 2021 22:44:42 +0000 [thread overview]
Message-ID: <9538bb7e-a600-2211-6b4d-561b99f1deca@synopsys.com> (raw)
In-Reply-To: <CAHk-=wjJEgjCYzHZFPxTs01p7FMEHKKqXyqwRVBk6KnvHB1qVA@mail.gmail.com>
On 4/30/21 3:06 PM, Linus Torvalds wrote:
> On Fri, Apr 30, 2021 at 1:46 PM Vineet Gupta <Vineet.Gupta1@synopsys.com> wrote:
>>
>> I've hit a mainline gcc 10.2 (also gcc 9.3) bug which triggers at -O3
>> causing wrong codegen.
>
> I'd be more than happy to just disable CC_OPTIMIZE_FOR_PERFORMANCE_O3 entirely.
>
> The advantages are very questionable - with a lot of the optimizations
> at O3 being about loops, something which the kernel to a close
> approximation doesn't have.
>
> Most kernel loops are "count on one hand" iterations, and loop
> optimizations generally just make things worse.
>
> And we've had problems with -O3 before, because not only are the
> optimizations a bit esoteric, they are often relatively untested. If
> you look around at various projects (outside the kernel), -O2 is
> generally the "default".
I agree that -O2 is default, but we've had -O3 default for ARC kernel
forever, since last decade seriously. The reason I turned it on back
then was upside of 10% performance improvement on select LMBench numbers
on hardware at the time which for a rookie kernel hacker was yay momemt.
I can revisit this and see if that is still true.
> And that's entirely ignoring the gcc history - where -O3 has often
> been very buggy indeed. It's gotten much better, but I just don't see
> the upside of using -O3.
>
> In fact, it looks like we already have that
>
> depends on ARC
>
> for -O3, exactly because nobody really wants to use this.
Either that or that people are not brave enough ;-) Perhaps gcc folks
would like me to retain this as a testing ground if nothing else.
> So this bug seems to be entirely ARC-specific, in that only ARC can
> use -O3 for the kernel already.
kid in me complaining "that's not fair !"
-Vineet
next prev parent reply other threads:[~2021-04-30 22:45 UTC|newest]
Thread overview: 8+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-30 20:46 Heads up: gcc miscompiling initramfs zlib decompression code at -O3 Vineet Gupta
2021-04-30 22:06 ` Linus Torvalds
2021-04-30 22:44 ` Vineet Gupta [this message]
2021-04-30 22:52 ` Linus Torvalds
2021-05-01 21:03 ` Oleksandr Natalenko
2021-05-03 17:41 ` Linus Torvalds
2021-05-03 19:18 ` Vineet Gupta
2021-05-05 17:44 ` Heiko Carstens
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=9538bb7e-a600-2211-6b4d-561b99f1deca@synopsys.com \
--to=vineet.gupta1@synopsys.com \
--cc=arnd@kernel.org \
--cc=jannh@google.com \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-snps-arc@lists.infradead.org \
--cc=masahiroy@kernel.org \
--cc=peterz@infradead.org \
--cc=torvalds@linux-foundation.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 NNTP newsgroup(s).