public inbox for
 help / color / mirror / Atom feed
From: Florian Weimer <>
To: Jakub Jelinek <>
Cc: Jason Merrill <>,  Michael Matz <>,
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: <> (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.


  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:

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \ \ \ \ \ \ \

* 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).