From: Richard Henderson <rth@cygnus.com>
To: N8TM@aol.com, rth@cygnus.com, hjstein@bfr.co.il,
toon@moene.indiv.nluug.nl
Cc: egcs@cygnus.com
Subject: Re: FLOATING-POINT CONSISTENCY, -FFLOAT-STORE, AND X86
Date: Fri, 18 Dec 1998 22:36:00 -0000 [thread overview]
Message-ID: <19981218223608.B23547@dot.cygnus.com> (raw)
In-Reply-To: <15d89fe9.367b4072@aol.com>
On Sat, Dec 19, 1998 at 12:58:10AM -0500, N8TM@aol.com wrote:
> How much extra time?
One extra cycle on read; since we're committed to read-modify-write
anyway, probably one to three extra cycles on write depending on
if we actually straddle a 16-byte boundary.
> Is it feasible to make the XFmode spills use aligned addresses,
> and would alignment be as much of an improvement as in DFmode?
If we were to spill in XFmode, then yes, alignment would be just
as important as in DFmode.
> The only quantification I've seen is my test of one application
> indicating that changing spills from SFmode to XFmode appears to
> make that application run 25% longer on a PPro.
I have not tried quantifing the change. I would want to examine
things more closely, however, because 25% seems low to me.
And before I even did that, someone would have to do a much better
job convincing me that it was even a good idea. Cause from where
I'm sitting now, I agree with Toon that the idea is losing all the
way around.
r~
next prev parent reply other threads:[~1998-12-18 22:36 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
1998-12-18 21:58 N8TM
1998-12-18 22:36 ` Richard Henderson [this message]
1998-12-19 13:41 ` Marc Lehmann
-- strict thread matches above, loose matches on Subject: below --
1998-12-22 13:30 Toon Moene
1998-12-22 11:07 John Wehle
1998-12-21 23:30 N8TM
1998-12-19 15:17 Geert Bosch
1998-12-20 8:09 ` Toon Moene
1998-12-22 4:17 ` Dave Love
1998-12-19 14:26 N8TM
1998-12-19 14:23 N8TM
1998-12-20 13:51 ` Marc Lehmann
1998-12-20 13:52 ` Marc Lehmann
1998-12-19 13:00 N8TM
1998-12-19 9:05 N8TM
1998-12-19 12:39 ` Toon Moene
1998-12-19 14:42 ` Dave Love
1998-12-18 23:07 N8TM
1998-12-19 13:39 ` Marc Lehmann
1998-12-17 1:43 N8TM
1998-12-17 12:35 ` Marc Lehmann
1998-12-18 12:14 ` Dave Love
1998-12-18 14:25 ` Gerald Pfeifer
1998-12-19 13:50 ` Dave Love
1998-12-18 18:37 ` Marc Lehmann
1998-12-19 14:03 ` Dave Love
1998-12-16 6:10 N8TM
1998-12-15 0:05 N8TM
1998-12-15 10:01 ` Joe Buck
1998-12-13 6:19 Stephen L Moshier
1998-12-13 10:49 ` Craig Burley
1998-12-13 15:18 ` Stephen L Moshier
1998-12-14 8:49 ` Craig Burley
1998-12-14 9:25 ` Joe Buck
1998-12-14 14:30 ` Edward Jason Riedy
1998-12-15 0:04 ` Craig Burley
1998-12-03 6:34 N8TM
1998-12-04 15:23 ` Craig Burley
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=19981218223608.B23547@dot.cygnus.com \
--to=rth@cygnus.com \
--cc=N8TM@aol.com \
--cc=egcs@cygnus.com \
--cc=hjstein@bfr.co.il \
--cc=toon@moene.indiv.nluug.nl \
/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).