--
ubizjak at gmail dot com changed:
What|Removed |Added
Target Milestone|--- |4.3.0
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29852
--- Comment #11 from ubizjak at gmail dot com 2006-11-30 07:17 ---
Fixed, by intriducing x87 helpers.
Let's see those benchmarks fly again ;)
--
ubizjak at gmail dot com changed:
What|Removed |Added
--- Comment #10 from uros at gcc dot gnu dot org 2006-11-30 06:55 ---
Subject: Bug 29852
Author: uros
Date: Thu Nov 30 06:54:47 2006
New Revision: 119356
URL: http://gcc.gnu.org/viewcvs?root=gcc&view=rev&rev=119356
Log:
PR target/29852
* config/i386/i386.md (*truncxfsf2
--- Comment #9 from ubizjak at gmail dot com 2006-11-29 21:05 ---
(In reply to comment #8)
> The patch doesn't like me ;)
>
> [EMAIL PROTECTED]:~/src/trunk/gcc/config/i386$ patch -p0 < /tmp/p
> patching file i386.md
> Hunk #1 succeeded at 3892 (offset -49 lines).
> Hunk #2 succeeded at
--- Comment #8 from rguenth at gcc dot gnu dot org 2006-11-29 18:36 ---
The patch doesn't like me ;)
[EMAIL PROTECTED]:~/src/trunk/gcc/config/i386$ patch -p0 < /tmp/p
patching file i386.md
Hunk #1 succeeded at 3892 (offset -49 lines).
Hunk #2 succeeded at 3919 (offset -47 lines).
Hunk #
--- Comment #7 from ubizjak at gmail dot com 2006-11-29 18:20 ---
Created an attachment (id=12707)
--> (http://gcc.gnu.org/bugzilla/attachment.cgi?id=12707&action=view)
Patch to enable x87 fprem and fprem1 for SSE math
I know that I've forgotten something ;)
--
ubizjak at gmail dot
--- Comment #6 from ubizjak at gmail dot com 2006-11-29 18:18 ---
(In reply to comment #5)
> Can we make sure to always emit proper truncation to SF/DFmode if not
> TARGET_MIX_SSE_I387? Just in case two fprem instructions follow each other
> and so we don't truncate by moving to memory
--- Comment #5 from rguenth at gcc dot gnu dot org 2006-11-29 16:02 ---
Can we make sure to always emit proper truncation to SF/DFmode if not
TARGET_MIX_SSE_I387? Just in case two fprem instructions follow each other
and so we don't truncate by moving to memory or SSE registers. It wou
--- Comment #4 from ubizjak at gmail dot com 2006-11-29 15:58 ---
(In reply to comment #3)
> So another possibility is to adjust the 387 patterns to be enabled even
> without
> TARGET_MIX_SSE_I387.
>
Considering the fact that even solaris x86_64 libm [1] uses these functions for
DFmod
--- Comment #3 from rguenth at gcc dot gnu dot org 2006-11-29 10:49 ---
So another possibility is to adjust the 387 patterns to be enabled even without
TARGET_MIX_SSE_I387.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29852
--- Comment #2 from burnus at gcc dot gnu dot org 2006-11-29 10:38 ---
If one uses -mfpmath=387 or -mfpmath=sse,387, the speed also dramatically
increases.
Results with test case below on a Athlon64:
icc -O3 test.c; time ./a.out
d=12.216410, r=10.26
real0m2.549s; user
--- Comment #1 from rguenth at gcc dot gnu dot org 2006-11-15 21:20 ---
Confirmed. SSE doesn't have something like 387 fprem though, so this is
probably
a library problem. (Note that remainder is one of the few extra things to
basic arithmetics that IEEE 754 specifies).
--
rguenth
12 matches
Mail list logo
