public inbox for gcc-bugs@sourceware.org
help / color / mirror / Atom feed
* [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code
@ 2006-06-01 11:34 uros at kss-loka dot si
2006-06-01 15:26 ` [Bug target/27855] " pinskia at gcc dot gnu dot org
` (35 more replies)
0 siblings, 36 replies; 38+ messages in thread
From: uros at kss-loka dot si @ 2006-06-01 11:34 UTC (permalink / raw)
To: gcc-bugs
The testcase from PR target/27827 shows another problem, this time with
-ffast-math. The runtime performance of -ffast-math code drops for ~30%.
The problem could be traced down to reassociation tree pass, because the
performance jumps back when "flag_unsafe_math_optimizations" switch is disabled
by changing every occurence in tree-ssa-reassoc.c with
(flag_unsafe_math_optimizations && 0).
To see the problem, -funsafe-math-optimizations should be added to MMFLAGS in
target/27827 example Makefile:
MM4FLAGS = $(GMMFLAGS) -funsafe-math-optimizations
Current mainline gcc produces code with following results:
-O -mfpmath=387
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.260 1663.04
-O -msse2 -mfpmath=sse
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.229 1890.47
gcc with disabled reassoc pass for floating point values:
-O -mfpmath=387
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.162 2664.87
-O -msse2 -mfpmath=sse
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.164 2633.15
--
Summary: reassociation pass produces ~30% slower matrix
multiplication code
Product: gcc
Version: 4.2.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
AssignedTo: unassigned at gcc dot gnu dot org
ReportedBy: uros at kss-loka dot si
GCC build triplet: i686-pc-linux-gnu
GCC host triplet: i686-pc-linux-gnu
GCC target triplet: i686-pc-linux-gnu
OtherBugsDependingO 27827
nThis:
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
@ 2006-06-01 15:26 ` pinskia at gcc dot gnu dot org
2006-06-02 10:04 ` uros at kss-loka dot si
` (34 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2006-06-01 15:26 UTC (permalink / raw)
To: gcc-bugs
------- Comment #1 from pinskia at gcc dot gnu dot org 2006-06-01 15:26 -------
There is nothing special about reassociation at all. In fact what you are
seeing is register allocator going funky. This what you get with x87.
--
pinskia at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Component|tree-optimization |target
Keywords| |ra
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
2006-06-01 15:26 ` [Bug target/27855] " pinskia at gcc dot gnu dot org
@ 2006-06-02 10:04 ` uros at kss-loka dot si
2006-06-02 10:19 ` pinskia at gcc dot gnu dot org
` (33 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: uros at kss-loka dot si @ 2006-06-02 10:04 UTC (permalink / raw)
To: gcc-bugs
------- Comment #2 from uros at kss-loka dot si 2006-06-02 10:04 -------
(In reply to comment #1)
> There is nothing special about reassociation at all. In fact what you are
> seeing is register allocator going funky. This what you get with x87.
This is also what you get with SSE.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
2006-06-01 15:26 ` [Bug target/27855] " pinskia at gcc dot gnu dot org
2006-06-02 10:04 ` uros at kss-loka dot si
@ 2006-06-02 10:19 ` pinskia at gcc dot gnu dot org
2006-06-02 23:20 ` steven at gcc dot gnu dot org
` (32 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2006-06-02 10:19 UTC (permalink / raw)
To: gcc-bugs
------- Comment #3 from pinskia at gcc dot gnu dot org 2006-06-02 10:19 -------
(In reply to comment #2)
> This is also what you get with SSE.
And how many registers does SSE have, not many. Try it on PPC or any processor
have more registers?
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (2 preceding siblings ...)
2006-06-02 10:19 ` pinskia at gcc dot gnu dot org
@ 2006-06-02 23:20 ` steven at gcc dot gnu dot org
2006-06-03 2:11 ` Daniel Berlin
2006-06-03 2:11 ` dberlin at dberlin dot org
` (31 subsequent siblings)
35 siblings, 1 reply; 38+ messages in thread
From: steven at gcc dot gnu dot org @ 2006-06-02 23:20 UTC (permalink / raw)
To: gcc-bugs
------- Comment #4 from steven at gcc dot gnu dot org 2006-06-02 23:19 -------
Real bug, despite Andrew's usual portion of x86-hate.
--
steven at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|UNCONFIRMED |NEW
Ever Confirmed|0 |1
Last reconfirmed|0000-00-00 00:00:00 |2006-06-02 23:19:36
date| |
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* Re: [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-02 23:20 ` steven at gcc dot gnu dot org
@ 2006-06-03 2:11 ` Daniel Berlin
0 siblings, 0 replies; 38+ messages in thread
From: Daniel Berlin @ 2006-06-03 2:11 UTC (permalink / raw)
To: gcc-bugzilla; +Cc: gcc-bugs
steven at gcc dot gnu dot org wrote:
> ------- Comment #4 from steven at gcc dot gnu dot org 2006-06-02 23:19 -------
> Real bug, despite Andrew's usual portion of x86-hate.
>
>
It'd be good to know what exactly is going wrong.
Reassociation only touches floating point because someone asked me to
make it touch floating point.
It still shouldn't have *this* much of an affect, my guess is it is
triggering some bad behavior elsewhere.
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (3 preceding siblings ...)
2006-06-02 23:20 ` steven at gcc dot gnu dot org
@ 2006-06-03 2:11 ` dberlin at dberlin dot org
2006-06-03 2:38 ` pinskia at gcc dot gnu dot org
` (30 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: dberlin at dberlin dot org @ 2006-06-03 2:11 UTC (permalink / raw)
To: gcc-bugs
------- Comment #5 from dberlin at gcc dot gnu dot org 2006-06-03 02:11 -------
Subject: Re: reassociation pass produces ~30% slower matrix
multiplication code
steven at gcc dot gnu dot org wrote:
> ------- Comment #4 from steven at gcc dot gnu dot org 2006-06-02 23:19 -------
> Real bug, despite Andrew's usual portion of x86-hate.
>
>
It'd be good to know what exactly is going wrong.
Reassociation only touches floating point because someone asked me to
make it touch floating point.
It still shouldn't have *this* much of an affect, my guess is it is
triggering some bad behavior elsewhere.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (4 preceding siblings ...)
2006-06-03 2:11 ` dberlin at dberlin dot org
@ 2006-06-03 2:38 ` pinskia at gcc dot gnu dot org
2006-06-03 2:50 ` pinskia at gcc dot gnu dot org
` (29 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2006-06-03 2:38 UTC (permalink / raw)
To: gcc-bugs
------- Comment #6 from pinskia at gcc dot gnu dot org 2006-06-03 02:38 -------
What reassociation is doing is "scheduling" the instructions further down
before the use but it exands the life time of some variables.
e.g.:
D.1563_59 = rA0_49 * rB0_50;
rC0_0_60 = D.1563_59 + rC0_0_516;
D.1564_61 = rA1_52 * rB0_50;
rC1_0_62 = D.1564_61 + rC1_0_517;
D.1565_63 = rA2_54 * rB0_50;
rC2_0_64 = D.1565_63 + rC2_0_518;
D.1566_65 = rA3_56 * rB0_50;
rC3_0_66 = D.1566_65 + rC3_0_519;
D.1567_67 = rA4_58 * rB0_50;
rC4_0_68 = D.1567_67 + rC4_0_520;
into:
D.1563_59 = rB0_50 * rA0_49;
D.1564_61 = rA1_52 * rB0_50;
D.1565_63 = rA2_54 * rB0_50;
D.1566_65 = rA3_56 * rB0_50;
D.1567_67 = rA4_58 * rB0_50;
..... (with loads, etc here)
D.1563_477 = rB0_468 * rA0_466;
rC0_0_60 = D.1563_59 + rC0_0_516;
rC0_0_82 = rC0_0_60 + D.1563_81;
rC0_0_104 = rC0_0_82 + D.1563_103;
rC0_0_126 = rC0_0_104 + D.1563_125;
rC0_0_148 = rC0_0_126 + D.1563_147;
rC0_0_170 = rC0_0_148 + D.1563_169;
rC0_0_192 = rC0_0_170 + D.1563_191;
rC0_0_214 = rC0_0_192 + D.1563_213;
rC0_0_236 = rC0_0_214 + D.1563_235;
rC0_0_258 = rC0_0_236 + D.1563_257;
rC0_0_280 = rC0_0_258 + D.1563_279;
rC0_0_302 = rC0_0_280 + D.1563_301;
rC0_0_324 = rC0_0_302 + D.1563_323;
rC0_0_346 = rC0_0_324 + D.1563_345;
rC0_0_368 = rC0_0_346 + D.1563_367;
rC0_0_390 = rC0_0_368 + D.1563_389;
rC0_0_412 = rC0_0_390 + D.1563_411;
rC0_0_434 = rC0_0_412 + D.1563_433;
rC0_0_456 = rC0_0_434 + D.1563_455;
rC0_0_478 = rC0_0_456 + D.1563_477;
Which in of itself not supressing and not nothing which reassociate should
handle special. This is what we get with a semi bad register allocation which
does nothing to reduce spilling.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (5 preceding siblings ...)
2006-06-03 2:38 ` pinskia at gcc dot gnu dot org
@ 2006-06-03 2:50 ` pinskia at gcc dot gnu dot org
2006-06-03 23:49 ` steven at gcc dot gnu dot org
` (28 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2006-06-03 2:50 UTC (permalink / raw)
To: gcc-bugs
------- Comment #7 from pinskia at gcc dot gnu dot org 2006-06-03 02:49 -------
If you change the code to be integers, this also cause the drop too with
reassociation even without -ffast-math so it is unrelated to the fact
-ffast-math turns on reassociate for floating points for fast math.
So what is happening is that the add to rC[0-4]_0 is being further down which
causes variable's life to be extended. Yes there should be a pass at the tree
level which optimizes variable's life time but I don't know how much use that
is without a better register allocator in the first place.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (6 preceding siblings ...)
2006-06-03 2:50 ` pinskia at gcc dot gnu dot org
@ 2006-06-03 23:49 ` steven at gcc dot gnu dot org
2006-06-05 15:57 ` amacleod at redhat dot com
` (27 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: steven at gcc dot gnu dot org @ 2006-06-03 23:49 UTC (permalink / raw)
To: gcc-bugs
------- Comment #8 from steven at gcc dot gnu dot org 2006-06-03 23:49 -------
You could add a basic block list scheduler at the tree level just before
out-of-ssa, with heuristics to make life times as short as possible :-)
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (7 preceding siblings ...)
2006-06-03 23:49 ` steven at gcc dot gnu dot org
@ 2006-06-05 15:57 ` amacleod at redhat dot com
2006-06-05 16:03 ` dberlin at gcc dot gnu dot org
` (26 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: amacleod at redhat dot com @ 2006-06-05 15:57 UTC (permalink / raw)
To: gcc-bugs
------- Comment #9 from amacleod at redhat dot com 2006-06-05 15:46 -------
This thread is moving dangerously close to work in progress.. :-)
I'll have something more definitive to say about it in a few weeks, but I'm
looking at doing significant register pressure reduction at out of ssa time as
a component of a larger hunk of work.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (8 preceding siblings ...)
2006-06-05 15:57 ` amacleod at redhat dot com
@ 2006-06-05 16:03 ` dberlin at gcc dot gnu dot org
2006-10-07 10:05 ` steven at gcc dot gnu dot org
` (25 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: dberlin at gcc dot gnu dot org @ 2006-06-05 16:03 UTC (permalink / raw)
To: gcc-bugs
------- Comment #10 from dberlin at gcc dot gnu dot org 2006-06-05 15:57 -------
(In reply to comment #9)
> This thread is moving dangerously close to work in progress.. :-)
> I'll have something more definitive to say about it in a few weeks, but I'm
> looking at doing significant register pressure reduction at out of ssa time as
> a component of a larger hunk of work.
Just be careful. The last time i tried something like this, it produced good
code on x86, and really crappy code everywhere else.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (9 preceding siblings ...)
2006-06-05 16:03 ` dberlin at gcc dot gnu dot org
@ 2006-10-07 10:05 ` steven at gcc dot gnu dot org
2006-10-07 16:36 ` pinskia at gcc dot gnu dot org
` (24 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: steven at gcc dot gnu dot org @ 2006-10-07 10:05 UTC (permalink / raw)
To: gcc-bugs
------- Comment #11 from steven at gcc dot gnu dot org 2006-10-07 10:05 -------
Would anyone object if I'd propose to disable reassociation for floating point
thingies on x86 for GCC 4.2? We can re-enable it if/when amacleod's new
out-of-ssa stuff fixes this for real...
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (10 preceding siblings ...)
2006-10-07 10:05 ` steven at gcc dot gnu dot org
@ 2006-10-07 16:36 ` pinskia at gcc dot gnu dot org
2007-03-02 15:35 ` ubizjak at gmail dot com
` (23 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2006-10-07 16:36 UTC (permalink / raw)
To: gcc-bugs
------- Comment #12 from pinskia at gcc dot gnu dot org 2006-10-07 16:36 -------
(In reply to comment #11)
> Would anyone object if I'd propose to disable reassociation for floating point
> thingies on x86 for GCC 4.2? We can re-enable it if/when amacleod's new
> out-of-ssa stuff fixes this for real...
Yes I do because it helps PPC which is why I added in the first place.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (11 preceding siblings ...)
2006-10-07 16:36 ` pinskia at gcc dot gnu dot org
@ 2007-03-02 15:35 ` ubizjak at gmail dot com
2007-03-02 17:43 ` pinskia at gcc dot gnu dot org
` (22 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2007-03-02 15:35 UTC (permalink / raw)
To: gcc-bugs
------- Comment #13 from ubizjak at gmail dot com 2007-03-02 15:34 -------
Any news about this problem?
Current mainline still has severe problems:
-msse3 -O2 -mfpmath=sse -ffast-math
GCC 4.3 -ffast-math double performance:
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.288 1499.91
-msse3 -O2 -mfpmath=sse
GCC 4.3 double performance:
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.192 2249.86
-msse3 -O2 -mfpmath=sse -ffast-math
GCC 4.3 -ffast-math single performance:
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.304 1420.96
-msse3 -O2 -mfpmath=sse
GCC 4.3 single performance:
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
atlasmm 60 1000 0.172 2511.48
Please consider the fact that all benchmarks are using -ffast-math nowadays. ;)
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (12 preceding siblings ...)
2007-03-02 15:35 ` ubizjak at gmail dot com
@ 2007-03-02 17:43 ` pinskia at gcc dot gnu dot org
2007-07-09 18:17 ` ubizjak at gmail dot com
` (21 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2007-03-02 17:43 UTC (permalink / raw)
To: gcc-bugs
------- Comment #14 from pinskia at gcc dot gnu dot org 2007-03-02 17:42 -------
> Please consider the fact that all benchmarks are using -ffast-math nowadays. ;)
Please also consider the fact that the register allocator has been broken since
20 years ago :) :) :) :).
And I repeat again, this has nothing to do with -ffast-math, see my comment #6
and #7 where I prove -ffast-math is not the issue and it is just the register
allocator going wrong. If anyone disables reassociation at the tree level, I
am going to object loudly.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (13 preceding siblings ...)
2007-03-02 17:43 ` pinskia at gcc dot gnu dot org
@ 2007-07-09 18:17 ` ubizjak at gmail dot com
2007-07-09 19:22 ` uros at gcc dot gnu dot org
` (20 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2007-07-09 18:17 UTC (permalink / raw)
To: gcc-bugs
------- Comment #15 from ubizjak at gmail dot com 2007-07-09 18:16 -------
New timings on x86_64 core2 (from [1])
The tests were performed on core2 in 64bit mode, using '-DREPS=10000 -O3 -msse3
-march=core2 -ffast-math' flags, with and without newly introduced
-fno-tree-reassoc flag.
The results were _interesting_, showing extreme differences in the run times:
w/o -fno-tree-reassoc:
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
-DTYPE=float: atlasmm 60 10000 2.000 2159.87
-DTYPE=double: atlasmm 60 10000 2.500 1727.89
w/ -fno-tree-reassoc:
ALGORITHM NB REPS TIME MFLOPS
========= ===== ===== ========== ==========
-DTYPE=float: atlasmm 60 10000 0.932 4634.90
-DTYPE=double: atlasmm 60 10000 1.520 2841.93
[1] http://gcc.gnu.org/ml/gcc-patches/2007-07/msg00849.html
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (14 preceding siblings ...)
2007-07-09 18:17 ` ubizjak at gmail dot com
@ 2007-07-09 19:22 ` uros at gcc dot gnu dot org
2007-12-10 10:17 ` [Bug target/27855] [4.3 regression] " ubizjak at gmail dot com
` (19 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: uros at gcc dot gnu dot org @ 2007-07-09 19:22 UTC (permalink / raw)
To: gcc-bugs
------- Comment #16 from uros at gcc dot gnu dot org 2007-07-09 19:22 -------
Subject: Bug 27855
Author: uros
Date: Mon Jul 9 19:22:03 2007
New Revision: 126491
URL: http://gcc.gnu.org/viewcvs?root=gcc&view=rev&rev=126491
Log:
PR target/27855
* doc/extend.texi: Add ftree-reassoc flag.
* common.opt (ftree-reassoc): New flag.
* tree-ssa-reassoc.c (gate_tree_ssa_reassoc): New static function.
(struct tree_opt_pass pass_reassoc): Use gate_tree_ssa_reassoc.
Modified:
trunk/gcc/ChangeLog
trunk/gcc/common.opt
trunk/gcc/doc/invoke.texi
trunk/gcc/tree-ssa-reassoc.c
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3 regression] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (15 preceding siblings ...)
2007-07-09 19:22 ` uros at gcc dot gnu dot org
@ 2007-12-10 10:17 ` ubizjak at gmail dot com
2007-12-10 10:40 ` rguenth at gcc dot gnu dot org
` (18 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2007-12-10 10:17 UTC (permalink / raw)
To: gcc-bugs
------- Comment #17 from ubizjak at gmail dot com 2007-12-10 10:16 -------
4.3 regression according to Issue 2 at
http://gcc.gnu.org/ml/gcc/2007-11/msg00753.html.
--
ubizjak at gmail dot com changed:
What |Removed |Added
----------------------------------------------------------------------------
Summary|reassociation pass produces |[4.3 regression]
|~30% slower matrix |reassociation pass produces
|multiplication code |~30% slower matrix
| |multiplication code
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3 regression] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (16 preceding siblings ...)
2007-12-10 10:17 ` [Bug target/27855] [4.3 regression] " ubizjak at gmail dot com
@ 2007-12-10 10:40 ` rguenth at gcc dot gnu dot org
2007-12-10 11:14 ` ubizjak at gmail dot com
` (17 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: rguenth at gcc dot gnu dot org @ 2007-12-10 10:40 UTC (permalink / raw)
To: gcc-bugs
------- Comment #18 from rguenth at gcc dot gnu dot org 2007-12-10 10:39 -------
I see no difference wrt -fno-tree-reassoc on x86_64 for the mmbenchv.tar.gz
benchmark. So, which is the testcase exhibiting the problem, what is the
exact architecture and optimization flags? (Yes, I enabled -ffast-math)
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|NEW |WAITING
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3 regression] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (17 preceding siblings ...)
2007-12-10 10:40 ` rguenth at gcc dot gnu dot org
@ 2007-12-10 11:14 ` ubizjak at gmail dot com
2007-12-11 5:57 ` ubizjak at gmail dot com
` (16 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2007-12-10 11:14 UTC (permalink / raw)
To: gcc-bugs
------- Comment #19 from ubizjak at gmail dot com 2007-12-10 11:14 -------
I have tried with mmbenchs.tar.gz [1] from PR 27827:
TYPE=double:
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math -fno-tree-reassoc:
atlasmm 60 1000 0.188 2297.73
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math
atlasmm 60 1000 0.284 1521.04
TYPE=float:
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math -fno-tree-reassoc
atlasmm 60 1000 0.168 2571.28
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math
atlasmm 60 1000 0.304 1420.96
gcc version 4.3.0 20071210 (experimental) [trunk revision 130738] (GCC)
Family: 15 Model: 4 Stepping: 10 Type: 0 Brand: 0
CPU Model: Pentium 4 D (Foster) Original OEM
Processor name string: Intel(R) Xeon(TM) CPU 3.60GHz
Please note that CPU runs in 32bit mode.
[1] http://gcc.gnu.org/bugzilla/attachment.cgi?id=12020
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3 regression] reassociation pass produces ~30% slower matrix multiplication code
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (18 preceding siblings ...)
2007-12-10 11:14 ` ubizjak at gmail dot com
@ 2007-12-11 5:57 ` ubizjak at gmail dot com
2007-12-26 1:37 ` [Bug target/27855] [4.3 regression] reassociation causes the RA to be confused pinskia at gcc dot gnu dot org
` (15 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2007-12-11 5:57 UTC (permalink / raw)
To: gcc-bugs
------- Comment #20 from ubizjak at gmail dot com 2007-12-11 05:57 -------
Should this be tree-optimization?
--
ubizjak at gmail dot com changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|WAITING |NEW
Last reconfirmed|2006-06-02 23:19:36 |2007-12-11 05:57:28
date| |
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (19 preceding siblings ...)
2007-12-11 5:57 ` ubizjak at gmail dot com
@ 2007-12-26 1:37 ` pinskia at gcc dot gnu dot org
2008-03-14 16:43 ` [Bug target/27855] [4.3/4.4 " rguenth at gcc dot gnu dot org
` (14 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2007-12-26 1:37 UTC (permalink / raw)
To: gcc-bugs
------- Comment #21 from pinskia at gcc dot gnu dot org 2007-12-26 01:37 -------
As mentioned, this is really a ra issue as I showed it with integers.
reassociation does nothing except for reschedule the instructions.
--
pinskia at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |pinskia at gcc dot gnu dot
| |org
Severity|normal |enhancement
GCC build triplet|i686-pc-linux-gnu |
GCC host triplet|i686-pc-linux-gnu |
Summary|[4.3 regression] |[4.3 regression]
|reassociation pass produces |reassociation causes the RA
|~30% slower matrix |to be confused
|multiplication code |
Target Milestone|--- |4.3.0
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (20 preceding siblings ...)
2007-12-26 1:37 ` [Bug target/27855] [4.3 regression] reassociation causes the RA to be confused pinskia at gcc dot gnu dot org
@ 2008-03-14 16:43 ` rguenth at gcc dot gnu dot org
2008-06-06 14:58 ` rguenth at gcc dot gnu dot org
` (13 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: rguenth at gcc dot gnu dot org @ 2008-03-14 16:43 UTC (permalink / raw)
To: gcc-bugs
------- Comment #22 from rguenth at gcc dot gnu dot org 2008-03-14 16:42 -------
Adjusting target milestone.
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.3.0 |4.3.1
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (21 preceding siblings ...)
2008-03-14 16:43 ` [Bug target/27855] [4.3/4.4 " rguenth at gcc dot gnu dot org
@ 2008-06-06 14:58 ` rguenth at gcc dot gnu dot org
2008-08-27 22:03 ` jsm28 at gcc dot gnu dot org
` (12 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: rguenth at gcc dot gnu dot org @ 2008-06-06 14:58 UTC (permalink / raw)
To: gcc-bugs
------- Comment #23 from rguenth at gcc dot gnu dot org 2008-06-06 14:56 -------
4.3.1 is being released, adjusting target milestone.
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.3.1 |4.3.2
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (22 preceding siblings ...)
2008-06-06 14:58 ` rguenth at gcc dot gnu dot org
@ 2008-08-27 22:03 ` jsm28 at gcc dot gnu dot org
2008-11-13 13:37 ` jakub at gcc dot gnu dot org
` (11 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: jsm28 at gcc dot gnu dot org @ 2008-08-27 22:03 UTC (permalink / raw)
To: gcc-bugs
------- Comment #24 from jsm28 at gcc dot gnu dot org 2008-08-27 22:01 -------
4.3.2 is released, changing milestones to 4.3.3.
--
jsm28 at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.3.2 |4.3.3
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (23 preceding siblings ...)
2008-08-27 22:03 ` jsm28 at gcc dot gnu dot org
@ 2008-11-13 13:37 ` jakub at gcc dot gnu dot org
2008-11-13 14:54 ` ubizjak at gmail dot com
` (10 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: jakub at gcc dot gnu dot org @ 2008-11-13 13:37 UTC (permalink / raw)
To: gcc-bugs
------- Comment #25 from jakub at gcc dot gnu dot org 2008-11-13 13:35 -------
Now that we have a new RA, is this still an issue?
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (24 preceding siblings ...)
2008-11-13 13:37 ` jakub at gcc dot gnu dot org
@ 2008-11-13 14:54 ` ubizjak at gmail dot com
2008-11-13 14:59 ` ubizjak at gmail dot com
` (9 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2008-11-13 14:54 UTC (permalink / raw)
To: gcc-bugs
------- Comment #26 from ubizjak at gmail dot com 2008-11-13 14:52 -------
(In reply to comment #25)
> Now that we have a new RA, is this still an issue?
Yes.
TYPE=double:
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math -fno-tree-reassoc:
atlasmm 60 1000 0.196 2203.95
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math
atlasmm 60 1000 0.276 1565.12
TYPE=float:
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math -fno-tree-reassoc
atlasmm 60 1000 0.160 2699.83
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math
atlasmm 60 1000 0.232 1861.96
gcc version 4.4.0 20081113 (experimental) [trunk revision 141819] (GCC)
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (25 preceding siblings ...)
2008-11-13 14:54 ` ubizjak at gmail dot com
@ 2008-11-13 14:59 ` ubizjak at gmail dot com
2009-01-24 10:20 ` rguenth at gcc dot gnu dot org
` (8 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2008-11-13 14:59 UTC (permalink / raw)
To: gcc-bugs
------- Comment #27 from ubizjak at gmail dot com 2008-11-13 14:58 -------
I wouldn't call this problem an enhancement. Matrix computations are affected
by this problem.
--
ubizjak at gmail dot com changed:
What |Removed |Added
----------------------------------------------------------------------------
Severity|enhancement |major
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (26 preceding siblings ...)
2008-11-13 14:59 ` ubizjak at gmail dot com
@ 2009-01-24 10:20 ` rguenth at gcc dot gnu dot org
2009-02-04 7:47 ` bonzini at gnu dot org
` (7 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: rguenth at gcc dot gnu dot org @ 2009-01-24 10:20 UTC (permalink / raw)
To: gcc-bugs
------- Comment #28 from rguenth at gcc dot gnu dot org 2009-01-24 10:19 -------
GCC 4.3.3 is being released, adjusting target milestone.
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.3.3 |4.3.4
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (27 preceding siblings ...)
2009-01-24 10:20 ` rguenth at gcc dot gnu dot org
@ 2009-02-04 7:47 ` bonzini at gnu dot org
2009-02-04 8:58 ` ubizjak at gmail dot com
` (6 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: bonzini at gnu dot org @ 2009-02-04 7:47 UTC (permalink / raw)
To: gcc-bugs
------- Comment #29 from bonzini at gnu dot org 2009-02-04 07:46 -------
A similar problem was fixed with PR38533, is this still an issue?
--
bonzini at gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |bonzini at gnu dot org
BugsThisDependsOn| |38533
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (28 preceding siblings ...)
2009-02-04 7:47 ` bonzini at gnu dot org
@ 2009-02-04 8:58 ` ubizjak at gmail dot com
2009-02-04 11:23 ` bonzini at gnu dot org
` (5 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: ubizjak at gmail dot com @ 2009-02-04 8:58 UTC (permalink / raw)
To: gcc-bugs
------- Comment #30 from ubizjak at gmail dot com 2009-02-04 08:57 -------
(In reply to comment #29)
> A similar problem was fixed with PR38533, is this still an issue?
TYPE=double:
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math -fno-tree-reassoc:
atlasmm 60 1000 0.208 2076.79
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math
atlasmm 60 1000 0.272 1588.14
TYPE=float:
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math -fno-tree-reassoc
atlasmm 60 1000 0.176 2454.39
gcc -DREPS=1000 -msse3 -O2 -mfpmath=sse -ffast-math
atlasmm 60 1000 0.168 2571.28
FLOAT case is OK now, but we regressed somehow.
DOUBLE case still shows problem and runtime regression too.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (29 preceding siblings ...)
2009-02-04 8:58 ` ubizjak at gmail dot com
@ 2009-02-04 11:23 ` bonzini at gnu dot org
2009-04-16 22:26 ` [Bug target/27855] [4.3/4.4/4.5 " pinskia at gcc dot gnu dot org
` (4 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: bonzini at gnu dot org @ 2009-02-04 11:23 UTC (permalink / raw)
To: gcc-bugs
------- Comment #31 from bonzini at gnu dot org 2009-02-04 11:22 -------
Created an attachment (id=17241)
--> (http://gcc.gnu.org/bugzilla/attachment.cgi?id=17241&action=view)
source code to reproduce the bug
Code from PR27827 that still regresses (also with -DTYPE=float, so it's not a
target-specific issue; the numbers Uros posted used different code for float
and double)
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4/4.5 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (30 preceding siblings ...)
2009-02-04 11:23 ` bonzini at gnu dot org
@ 2009-04-16 22:26 ` pinskia at gcc dot gnu dot org
2009-08-04 12:34 ` rguenth at gcc dot gnu dot org
` (3 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2009-04-16 22:26 UTC (permalink / raw)
To: gcc-bugs
--
pinskia at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Severity|major |normal
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4/4.5 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (31 preceding siblings ...)
2009-04-16 22:26 ` [Bug target/27855] [4.3/4.4/4.5 " pinskia at gcc dot gnu dot org
@ 2009-08-04 12:34 ` rguenth at gcc dot gnu dot org
2009-09-20 20:20 ` pinskia at gcc dot gnu dot org
` (2 subsequent siblings)
35 siblings, 0 replies; 38+ messages in thread
From: rguenth at gcc dot gnu dot org @ 2009-08-04 12:34 UTC (permalink / raw)
To: gcc-bugs
------- Comment #32 from rguenth at gcc dot gnu dot org 2009-08-04 12:27 -------
GCC 4.3.4 is being released, adjusting target milestone.
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.3.4 |4.3.5
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4/4.5 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (32 preceding siblings ...)
2009-08-04 12:34 ` rguenth at gcc dot gnu dot org
@ 2009-09-20 20:20 ` pinskia at gcc dot gnu dot org
2010-01-19 16:17 ` rguenth at gcc dot gnu dot org
2010-05-22 19:00 ` [Bug target/27855] [4.3/4.4/4.5/4.6 " rguenth at gcc dot gnu dot org
35 siblings, 0 replies; 38+ messages in thread
From: pinskia at gcc dot gnu dot org @ 2009-09-20 20:20 UTC (permalink / raw)
To: gcc-bugs
------- Comment #33 from pinskia at gcc dot gnu dot org 2009-09-20 20:20 -------
*** Bug 28481 has been marked as a duplicate of this bug. ***
--
pinskia at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |vda dot linux at googlemail
| |dot com
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4/4.5 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (33 preceding siblings ...)
2009-09-20 20:20 ` pinskia at gcc dot gnu dot org
@ 2010-01-19 16:17 ` rguenth at gcc dot gnu dot org
2010-05-22 19:00 ` [Bug target/27855] [4.3/4.4/4.5/4.6 " rguenth at gcc dot gnu dot org
35 siblings, 0 replies; 38+ messages in thread
From: rguenth at gcc dot gnu dot org @ 2010-01-19 16:17 UTC (permalink / raw)
To: gcc-bugs
------- Comment #34 from rguenth at gcc dot gnu dot org 2010-01-19 16:17 -------
Re-confirmed. -fsched-pressure -fschedule-insns helps recover some of the
performance, ivopts adds its share as well as re-association.
Scheduling is probably limited by ivopts producing TMRs and w/o ivopts
by plain INDIRECT_REFs. None of which are handled by the alias-export to RTL.
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Last reconfirmed|2007-12-11 05:57:28 |2010-01-19 16:17:28
date| |
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
* [Bug target/27855] [4.3/4.4/4.5/4.6 regression] reassociation causes the RA to be confused
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
` (34 preceding siblings ...)
2010-01-19 16:17 ` rguenth at gcc dot gnu dot org
@ 2010-05-22 19:00 ` rguenth at gcc dot gnu dot org
35 siblings, 0 replies; 38+ messages in thread
From: rguenth at gcc dot gnu dot org @ 2010-05-22 19:00 UTC (permalink / raw)
To: gcc-bugs
------- Comment #35 from rguenth at gcc dot gnu dot org 2010-05-22 18:11 -------
GCC 4.3.5 is being released, adjusting target milestone.
--
rguenth at gcc dot gnu dot org changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.3.5 |4.3.6
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=27855
^ permalink raw reply [flat|nested] 38+ messages in thread
end of thread, other threads:[~2010-05-22 18:17 UTC | newest]
Thread overview: 38+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2006-06-01 11:34 [Bug tree-optimization/27855] New: reassociation pass produces ~30% slower matrix multiplication code uros at kss-loka dot si
2006-06-01 15:26 ` [Bug target/27855] " pinskia at gcc dot gnu dot org
2006-06-02 10:04 ` uros at kss-loka dot si
2006-06-02 10:19 ` pinskia at gcc dot gnu dot org
2006-06-02 23:20 ` steven at gcc dot gnu dot org
2006-06-03 2:11 ` Daniel Berlin
2006-06-03 2:11 ` dberlin at dberlin dot org
2006-06-03 2:38 ` pinskia at gcc dot gnu dot org
2006-06-03 2:50 ` pinskia at gcc dot gnu dot org
2006-06-03 23:49 ` steven at gcc dot gnu dot org
2006-06-05 15:57 ` amacleod at redhat dot com
2006-06-05 16:03 ` dberlin at gcc dot gnu dot org
2006-10-07 10:05 ` steven at gcc dot gnu dot org
2006-10-07 16:36 ` pinskia at gcc dot gnu dot org
2007-03-02 15:35 ` ubizjak at gmail dot com
2007-03-02 17:43 ` pinskia at gcc dot gnu dot org
2007-07-09 18:17 ` ubizjak at gmail dot com
2007-07-09 19:22 ` uros at gcc dot gnu dot org
2007-12-10 10:17 ` [Bug target/27855] [4.3 regression] " ubizjak at gmail dot com
2007-12-10 10:40 ` rguenth at gcc dot gnu dot org
2007-12-10 11:14 ` ubizjak at gmail dot com
2007-12-11 5:57 ` ubizjak at gmail dot com
2007-12-26 1:37 ` [Bug target/27855] [4.3 regression] reassociation causes the RA to be confused pinskia at gcc dot gnu dot org
2008-03-14 16:43 ` [Bug target/27855] [4.3/4.4 " rguenth at gcc dot gnu dot org
2008-06-06 14:58 ` rguenth at gcc dot gnu dot org
2008-08-27 22:03 ` jsm28 at gcc dot gnu dot org
2008-11-13 13:37 ` jakub at gcc dot gnu dot org
2008-11-13 14:54 ` ubizjak at gmail dot com
2008-11-13 14:59 ` ubizjak at gmail dot com
2009-01-24 10:20 ` rguenth at gcc dot gnu dot org
2009-02-04 7:47 ` bonzini at gnu dot org
2009-02-04 8:58 ` ubizjak at gmail dot com
2009-02-04 11:23 ` bonzini at gnu dot org
2009-04-16 22:26 ` [Bug target/27855] [4.3/4.4/4.5 " pinskia at gcc dot gnu dot org
2009-08-04 12:34 ` rguenth at gcc dot gnu dot org
2009-09-20 20:20 ` pinskia at gcc dot gnu dot org
2010-01-19 16:17 ` rguenth at gcc dot gnu dot org
2010-05-22 19:00 ` [Bug target/27855] [4.3/4.4/4.5/4.6 " rguenth at gcc dot gnu dot org
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).