From: Michael Morrell via <qemu-devel@nongnu.org>
To: qemu-devel@nongnu.org, qemu-devel@nongnu.org
Subject: Denormal input handling
Date: Wed, 26 May 2021 19:02:55 +0000 (UTC) [thread overview]
Message-ID: <746277332.296230.1622055775751@mail.yahoo.com> (raw)
In-Reply-To: 746277332.296230.1622055775751.ref@mail.yahoo.com
I see support in QEMU for architectures which have a denormal input flag bit and those that have a "flush inputs to zero" control bit, but the implementation is not specializable and seems wrong for x86 at least.
For example, in sf_canonicalize, if the input is denormal and "flush_inputs_to_zero" is true, the "input denormal" flag is set and then the value is set to a zero value, and if the input is denormal and "flush_inputs_to_zero" is false, then the input is simply normalized.
I think the behavior should be for denormal inputs that if "flush_inputs_to_zero" is true, then set the value to zero (without setting the "input denormal" flag); and if "flush_inputs_to_zero" is false, set the "input denormal" flag and normalize the input.
This matches what x86 does (I'm not sure about other architectures).
Am I missing something? If not, I can work on a patch (there are several places which check "flush_inputs_to_zero" which will need to be changed).
Michael
next parent reply other threads:[~2021-05-26 19:10 UTC|newest]
Thread overview: 14+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <746277332.296230.1622055775751.ref@mail.yahoo.com>
2021-05-26 19:02 ` Michael Morrell via [this message]
2021-05-26 19:23 ` Denormal input handling Richard Henderson
2021-05-26 19:28 ` Richard Henderson
2021-05-26 19:52 ` Michael Morrell via
2021-05-26 20:15 ` Richard Henderson
2021-05-26 17:37 Michael Morrell
2021-05-26 20:18 ` Peter Maydell
2021-05-26 21:59 ` Michael Morrell
2021-05-27 1:14 ` Richard Henderson
2021-06-21 23:13 ` Michael Morrell
2021-06-21 23:30 ` Richard Henderson
2021-06-21 23:39 ` Michael Morrell
2021-06-22 0:57 ` Michael Morrell
2021-06-22 18:50 ` Michael Morrell
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=746277332.296230.1622055775751@mail.yahoo.com \
--to=qemu-devel@nongnu.org \
--cc=morrell@alumni.ucsd.edu \
/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 NNTP newsgroup(s).