From: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
To: Adhemerval Zanella Netto <adhemerval.zanella@linaro.org>,
'GNU C Library' <libc-alpha@sourceware.org>
Subject: Re: [PATCH] math: Improve fmod(f) performance
Date: Thu, 13 Apr 2023 20:45:38 +0000 [thread overview]
Message-ID: <PAWPR08MB89828DFAF4C1BD00EFA5B25283989@PAWPR08MB8982.eurprd08.prod.outlook.com> (raw)
In-Reply-To: <0baece75-8f99-da08-4094-18f99238cb12@linaro.org>
Hi Adhemerval,
> So at least with current 'close-exponents' from bench-fmod, which was
> generated from exponents between -10 and 10, the gain is more modest
> (and normal inputs does show a small regression). This should be ok,
> but I also think we need to outline that A72 gains might not show on
> different hardware.
On a SkyLake I'm seeing this for fmod:
master patch
subnormals 51.34 45.92 (+11.8%)
normal 436.9 420.5 (+3.9%)
close-exponents 56.44 53.11 (+6.3%)
And on Zen2:
master patch
subnormals 10.83 10.39 (+4.2%)
normal 336.1 335.8 (+0.01%)
close-exponents 14.90 14.11 (+5.6%)
So it shows good improvements across the board. It's odd your results on AMD are
worse than my Zen 2 results - are there large variations between runs? I did quite a
few runs to get a fast result and increased iterations of the math benchmarks 10x.
I can't explain why the gains on AArch64 are so much larger - the reduced instruction
counts and branches for the common cases seem to make a big difference. On x86
there are still many MOVABS instructions which are problematic for decode.
> So maybe also add another bench-fmod set for |x/y| < 2^12 to show
> the potential gains.
I'm not sure how that would improve things - ideally we need more realistic
inputs (ie. actual traces) but we could change the existing inputs into workloads
to give it a more difficult problem. Changing close-exponents into a workload
shows 11.0% lower latency and 11.9% better throughput on my SkyLake. On Zen 2
I see 1% lower latency and 7.4% better throughput. Neoverse V1 shows 25.1%
lower latency and 23.9% better throughput.
Cheers,
Wilco
next prev parent reply other threads:[~2023-04-13 20:45 UTC|newest]
Thread overview: 4+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-04-13 14:29 Wilco Dijkstra
2023-04-13 15:58 ` Adhemerval Zanella Netto
2023-04-13 20:45 ` Wilco Dijkstra [this message]
2023-04-13 20:56 ` Adhemerval Zanella Netto
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=PAWPR08MB89828DFAF4C1BD00EFA5B25283989@PAWPR08MB8982.eurprd08.prod.outlook.com \
--to=wilco.dijkstra@arm.com \
--cc=adhemerval.zanella@linaro.org \
--cc=libc-alpha@sourceware.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).