public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed
From: Wilco Dijkstra <Wilco.Dijkstra@arm.com>
To: Evandro Menezes <e.menezes@samsung.com>,
	GCC Patches	<gcc-patches@gcc.gnu.org>
Cc: James Greenhalgh <James.Greenhalgh@arm.com>,
	Andrew Pinski	<pinskia@gmail.com>, nd <nd@arm.com>
Subject: Re: [AArch64] Emit division using the Newton series
Date: Fri, 01 Apr 2016 21:22:00 -0000	[thread overview]
Message-ID: <AM3PR08MB00884DBC29E8F0651E1ECEC6839A0@AM3PR08MB0088.eurprd08.prod.outlook.com> (raw)
In-Reply-To: <56FED036.2070405@samsung.com>

Evandro Menezes wrote:
> > The division variant should use the same latency reduction trick I mentioned for sqrt.
>
> I don't think that it applies here, since it doesn't have to deal with
> special cases.

No it applies as it's exactly the same calculation: x * rsqrt(y) and x * recip(y). In both
cases you don't need the final result of rsqrt(y) or recip(y), avoiding a multiply. 
Given these sequences are high latency this saving is actually quite important.

Wilco

  reply	other threads:[~2016-04-01 21:22 UTC|newest]

Thread overview: 16+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-03-17 21:14 Evandro Menezes
2016-03-23 16:24 ` Evandro Menezes
2016-03-23 16:25 ` Evandro Menezes
2016-03-31 22:23   ` Evandro Menezes
2016-04-01 13:58     ` Wilco Dijkstra
2016-04-01 19:47       ` Evandro Menezes
2016-04-01 21:22         ` Wilco Dijkstra [this message]
2016-04-01 21:56           ` Evandro Menezes
2016-04-01 22:46             ` Wilco Dijkstra
2016-04-01 22:52               ` Evandro Menezes
2016-04-04 19:06                 ` Evandro Menezes
2016-04-12 18:15                   ` Evandro Menezes
2016-04-21 18:44                     ` Evandro Menezes
2016-04-27 14:16                   ` James Greenhalgh
2016-04-27 14:44                     ` Wilco Dijkstra
2016-04-27 15:43                     ` Evandro Menezes

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=AM3PR08MB00884DBC29E8F0651E1ECEC6839A0@AM3PR08MB0088.eurprd08.prod.outlook.com \
    --to=wilco.dijkstra@arm.com \
    --cc=James.Greenhalgh@arm.com \
    --cc=e.menezes@samsung.com \
    --cc=gcc-patches@gcc.gnu.org \
    --cc=nd@arm.com \
    --cc=pinskia@gmail.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).