From: "Paul A. Clarke via Libc-alpha" <libc-alpha@sourceware.org>
To: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
Cc: Tulio Magno Quites Machado Filho <tuliom@linux.ibm.com>,
"libc-alpha@sourceware.org" <libc-alpha@sourceware.org>
Subject: Re: [PATCH v3 5/7] math: Remove powerpc e_hypot
Date: Wed, 10 Nov 2021 08:43:48 -0600 [thread overview]
Message-ID: <20211110144348.GB4930@li-24c3614c-2adc-11b2-a85c-85f334518bdb.ibm.com> (raw)
In-Reply-To: <VE1PR08MB5599A27A3DE03FC5902CDF4F83939@VE1PR08MB5599.eurprd08.prod.outlook.com>
On Wed, Nov 10, 2021 at 02:34:09PM +0000, Wilco Dijkstra wrote:
> > The patches see poorer performance on Power10, also:
>
> Was that with the last patch to remove the redirects as well? The latest version
> is still slower even with that on AArch64...
Sorry that wasn't clear. I tested with all 7 patches in the series applied.
PC
> I think the new algorithm will always be slower due to the dependent sqrt and
> division. So it's hard to improve unless we only use it for special cases (eg. when
> ax and ay are close). Returning sqrt (fma (ax, ax, ay * ay)) is about twice as fast
> and gives just over 1 ULP, so we're losing a lot of performance for a small ULP
> improvement.
next prev parent reply other threads:[~2021-11-10 14:44 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-01 20:20 [PATCH v3 0/7] Improve hypot() Adhemerval Zanella via Libc-alpha
2021-11-01 20:20 ` [PATCH v3 1/7] math: Simplify hypotf implementation Adhemerval Zanella via Libc-alpha
2021-11-01 20:20 ` [PATCH v3 2/7] math: Use an improved algorithm for hypot (dbl-64) Adhemerval Zanella via Libc-alpha
2021-11-01 20:20 ` [PATCH v3 3/7] math: Use an improved algorithm for hypotl (ldbl-96) Adhemerval Zanella via Libc-alpha
2021-11-01 20:20 ` [PATCH v3 4/7] math: Use an improved algorithm for hypotl (ldbl-128) Adhemerval Zanella via Libc-alpha
2021-11-01 20:20 ` [PATCH v3 5/7] math: Remove powerpc e_hypot Adhemerval Zanella via Libc-alpha
2021-11-09 19:28 ` Paul A. Clarke via Libc-alpha
2021-11-10 14:34 ` Wilco Dijkstra via Libc-alpha
2021-11-10 14:43 ` Paul A. Clarke via Libc-alpha [this message]
2021-11-10 14:47 ` Adhemerval Zanella via Libc-alpha
2021-11-11 17:05 ` Wilco Dijkstra via Libc-alpha
2021-11-11 17:13 ` Adhemerval Zanella via Libc-alpha
2021-11-11 19:48 ` Wilco Dijkstra via Libc-alpha
2021-11-11 20:54 ` Adhemerval Zanella via Libc-alpha
2021-11-01 20:20 ` [PATCH v3 6/7] i386: Move hypot implementation to C Adhemerval Zanella via Libc-alpha
2021-11-01 20:20 ` [PATCH v3 7/7] math: Remove the error handling wrapper from hypot and hypotf Adhemerval Zanella via Libc-alpha
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=20211110144348.GB4930@li-24c3614c-2adc-11b2-a85c-85f334518bdb.ibm.com \
--to=libc-alpha@sourceware.org \
--cc=Wilco.Dijkstra@arm.com \
--cc=pc@us.ibm.com \
--cc=tuliom@linux.ibm.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).