From: Joseph Myers <joseph@codesourcery.com>
To: "Maciej W. Rozycki" <macro@linux-mips.org>
Cc: Steve Ellcey <sellcey@imgtec.com>, <gcc-patches@gcc.gnu.org>,
Catherine Moore <clm@codesourcery.com>,
Matthew Fortune <matthew.fortune@imgtec.com>
Subject: Re: [Patch, MIPS] Enable fp-contract on MIPS and update -mfused-madd
Date: Mon, 15 Jun 2015 21:37:00 -0000 [thread overview]
Message-ID: <alpine.DEB.2.10.1506152047390.9772@digraph.polyomino.org.uk> (raw)
In-Reply-To: <alpine.LFD.2.11.1506152042580.5418@eddie.linux-mips.org>
On Mon, 15 Jun 2015, Maciej W. Rozycki wrote:
> operands negated. That negation, implemented with the IEEE Std 754-2008
> `negate' operation that you referred to, by definition is required to
> operate on the sign of its operand in a specific way even if the operand
> is a qNaN.
>
> So for example `fmsM4', that is specified at the RTL level as (fma:M OP1
> OP2 (neg:M OP3)) will not produce the correct result with the fused
> version of the MIPS MSUB.fmt instruction in the case where OP1 and OP2 are
> numeric data patterns and OP3 is a qNaN data pattern that has its sign bit
> clear. As specified by IEEE Std 754-2008 the (neg:M OP3) operation is
> required to invert the sign bit of the qNaN data pattern in calculating
> TMP3, and then the (fma:M OP1 OP2 TMP3) operation is required to pass the
> TMP3 qNaN data pattern unchanged in calculating the final result.
It is only required (well, recommended) to pass the *payload*. The sign
bit is not part of the payload. "For all other operations, this standard
does not specify the sign bit of a NaN result, even when there is only one
input NaN, or when the NaN is produced from an invalid operation.".
--
Joseph S. Myers
joseph@codesourcery.com
next prev parent reply other threads:[~2015-06-15 20:52 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-06-11 20:09 Steve Ellcey
2015-06-11 20:39 ` Joseph Myers
2015-06-15 20:52 ` Maciej W. Rozycki
2015-06-15 21:37 ` Joseph Myers [this message]
2015-06-15 22:00 ` Maciej W. Rozycki
2015-06-15 22:09 ` Joseph Myers
2015-06-16 12:19 ` Maciej W. Rozycki
2015-06-16 12:26 ` Joseph Myers
2015-06-16 13:28 ` Maciej W. Rozycki
2015-06-16 16:13 ` Joseph Myers
2015-06-17 10:43 ` Richard Sandiford
2015-06-17 17:45 ` Steve Ellcey
2015-06-17 18:44 ` Maciej W. Rozycki
2015-06-17 18:52 ` Richard Sandiford
2015-06-17 21:09 ` Steve Ellcey
2015-06-17 22:06 ` Matthew Fortune
2015-06-18 12:32 ` Maciej W. Rozycki
2015-06-18 16:02 ` Steve Ellcey
2015-06-29 16:10 ` Maciej W. Rozycki
2015-06-29 19:07 ` Matthew Fortune
2015-06-29 19:46 ` Moore, Catherine
2015-07-06 17:35 ` Steve Ellcey
2015-06-30 7:35 ` Richard Biener
2015-06-18 12:04 ` Maciej W. Rozycki
2015-06-17 19:51 ` Steve Ellcey
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=alpine.DEB.2.10.1506152047390.9772@digraph.polyomino.org.uk \
--to=joseph@codesourcery.com \
--cc=clm@codesourcery.com \
--cc=gcc-patches@gcc.gnu.org \
--cc=macro@linux-mips.org \
--cc=matthew.fortune@imgtec.com \
--cc=sellcey@imgtec.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).