From: Szabolcs Nagy <szabolcs.nagy@arm.com>
To: Patrick McGehearty <patrick.mcgehearty@oracle.com>,
libc-alpha@sourceware.org
Cc: nd@arm.com
Subject: Re: [PATCH] v11 Improves __ieee754_exp() performance by greater than 5x on sparc/x86.
Date: Fri, 2 Feb 2018 14:40:30 +0000 [thread overview]
Message-ID: <361bac88-5538-227f-b6dc-76416178192c@arm.com> (raw)
In-Reply-To: <1517262265-79445-1-git-send-email-patrick.mcgehearty@oracle.com>
On 29/01/18 21:44, Patrick McGehearty wrote:
> New with this version:
> Adds updates sparc and x86_64 libm-test-ulps files (1 ulp for
> various exp tests). Rewrite of full comment to reflect current
> state of patch.
>
> Summary of patch rationale
>
> These changes will be active for all platforms that don't provide
> their own exp() routines. They will also be active for ieee754
> versions of ccos, ccosh, cosh, csin, csinh, sinh, exp10, gamma, and
> erf.
>
> Typical performance gains are 2x on Sparc s7 and 5x on x86_64.
> The former code included a slow path to assure no 1 ulp errors
> that could be 50-200 times slower than the normal path.
> Informal testing suggests perhaps 1 in 200 values might invoke
> the slow path.
>
> Using the glibc_perf tests:
> sparc (nsec) x86 (nsec)
> old new old new
> max 18180 936 4863 275
> min 399 96 15 15
> mean 5499 419 1336 24
>
i tested this patch on aarch64 against the current code
with the slow path removed and the later was about 10%
faster on both my throughput and latency benchmarks.
(i also removed the rounding mode settings in both cases
as that can be avoided at least on aarch64)
so i suggest just removing the slow path first, which
should have good enough error rate and similar performance.
i did some testing and i think it's possible to do the
common case >30% faster with similar table size and around
0.501 ulp error, with a slower path for values close to
overflow/underflow (at least on aarch64, which has
convert-to-nearest-int instruction that does not depend on
rounding mode, i'll see if it can be done in a generic way)
next prev parent reply other threads:[~2018-02-02 14:38 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-01-29 21:44 [PATCH] v11 Improves __ieee754_exp() performance by greater than 5x on sparc/x86 Patrick McGehearty
2018-02-02 14:40 ` Szabolcs Nagy [this message]
2018-02-02 15:33 ` Joseph Myers
2018-02-02 16:35 ` Szabolcs Nagy
2018-02-07 19:19 ` Patrick McGehearty
-- strict thread matches above, loose matches on Subject: below --
2018-02-08 11:40 Wilco Dijkstra
2018-02-14 1:18 ` Patrick McGehearty
2018-02-14 16:41 ` Joseph Myers
2018-02-14 20:05 ` Szabolcs Nagy
2018-02-22 19:22 ` Szabolcs Nagy
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
List information: https://www.gnu.org/software/libc/involved.html
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=361bac88-5538-227f-b6dc-76416178192c@arm.com \
--to=szabolcs.nagy@arm.com \
--cc=libc-alpha@sourceware.org \
--cc=nd@arm.com \
--cc=patrick.mcgehearty@oracle.com \
/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).