From: Florian Weimer <fweimer@redhat.com>
To: Jakub Jelinek <jakub@redhat.com>
Cc: Jason Merrill <jason@redhat.com>, Michael Matz <matz@suse.de>,
gcc-patches@gcc.gnu.org
Subject: Re: [PATCH] libgcc: Decrease size of _Unwind_FrameState and even more size of cleared area in uw_frame_state_for
Date: Mon, 19 Sep 2022 11:25:13 +0200 [thread overview]
Message-ID: <87czbrhg1y.fsf@oldenburg.str.redhat.com> (raw)
In-Reply-To: <YyghJvwqjF31B9Kt@tucnak> (Jakub Jelinek's message of "Mon, 19 Sep 2022 09:58:30 +0200")
* Jakub Jelinek:
> The disadvantage of the patch is that touching reg[x].loc and how[x]
> now means 2 cachelines rather than one as before, and I admit beyond
> bootstrap/regtest I haven't benchmarked it in any way. Florian, could
> you retry whatever you measured to get at the 40% of time spent on the
> stack clearing to see how the numbers change?
A benchmark that unwinds through 100 frames containing a std::string
variable goes from (0b5b8ac5cb7fe92dd17ae8bd7de84640daa59e84):
min: 24418 ns
25%: 24740 ns
50%: 24790 ns
75%: 24840 ns
95%: 24937 ns
99%: 26174 ns
max: 42530 ns
avg: 24826.1 ns
to (0b5b8ac5cb7fe92dd17ae8bd7de84640daa59e84 with this patch):
min: 22307 ns
25%: 22640 ns
50%: 22713 ns
75%: 22787 ns
95%: 22948 ns
99%: 24839 ns
max: 52658 ns
avg: 22863.4 ns
So 227 ns per frame instead of 248 ns per frame, or ~9% less.
Moving cfa_how after how in struct frame_state_reg_info as an 8-bit
bitfield should avoid zeroing another 8 bytes. This shaves off another
3 ns per frame in my testing (on a Core i9-10900T, so with ERMS).
The REP STOS still dominates uw_frame_state_for execution time, but this
seems to be a profiling artifact. Replacing it with PXOR and seven
MOVUPS instructions makes the hotspot go away, but performance does not
improve. Odd.
Thanks,
Florian
next prev parent reply other threads:[~2022-09-19 9:25 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-19 7:58 Jakub Jelinek
2022-09-19 8:57 ` Richard Biener
2022-09-19 9:16 ` Jakub Jelinek
2022-09-19 9:25 ` Florian Weimer [this message]
2022-09-19 9:33 ` Jakub Jelinek
2022-09-19 13:46 ` Florian Weimer
2022-10-05 10:33 ` Patch ping (Re: [PATCH] libgcc: Decrease size of _Unwind_FrameState and even more size of cleared area in uw_frame_state_for) Jakub Jelinek
2022-10-06 8:08 ` Richard Biener
2022-10-06 22:05 ` Joseph Myers
2022-10-06 22:19 ` [committed] libgcc, arc: Fix build Jakub Jelinek
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=87czbrhg1y.fsf@oldenburg.str.redhat.com \
--to=fweimer@redhat.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=jakub@redhat.com \
--cc=jason@redhat.com \
--cc=matz@suse.de \
/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).