* [Bug tree-optimization/54077] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
@ 2012-07-24 9:39 ` wbrana at gmail dot com
2012-07-24 9:41 ` wbrana at gmail dot com
` (17 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-07-24 9:39 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #1 from wbrana <wbrana at gmail dot com> 2012-07-24 09:39:37 UTC ---
Created attachment 27863
--> http://gcc.gnu.org/bugzilla/attachment.cgi?id=27863
AddSubInternalFPF.clang.txt
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
2012-07-24 9:39 ` [Bug tree-optimization/54077] " wbrana at gmail dot com
@ 2012-07-24 9:41 ` wbrana at gmail dot com
2012-07-24 9:42 ` wbrana at gmail dot com
` (16 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-07-24 9:41 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #2 from wbrana <wbrana at gmail dot com> 2012-07-24 09:41:21 UTC ---
Created attachment 27864
--> http://gcc.gnu.org/bugzilla/attachment.cgi?id=27864
AddSubInternalFPF.gcc.txt
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
2012-07-24 9:39 ` [Bug tree-optimization/54077] " wbrana at gmail dot com
2012-07-24 9:41 ` wbrana at gmail dot com
@ 2012-07-24 9:42 ` wbrana at gmail dot com
2012-07-24 9:43 ` wbrana at gmail dot com
` (15 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-07-24 9:42 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #3 from wbrana <wbrana at gmail dot com> 2012-07-24 09:42:27 UTC ---
Created attachment 27865
--> http://gcc.gnu.org/bugzilla/attachment.cgi?id=27865
DivideInternalFPF.clang.txt
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (2 preceding siblings ...)
2012-07-24 9:42 ` wbrana at gmail dot com
@ 2012-07-24 9:43 ` wbrana at gmail dot com
2012-07-31 9:36 ` rguenth at gcc dot gnu.org
` (14 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-07-24 9:43 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #4 from wbrana <wbrana at gmail dot com> 2012-07-24 09:43:38 UTC ---
Created attachment 27866
--> http://gcc.gnu.org/bugzilla/attachment.cgi?id=27866
DivideInternalFPF.gcc.txt
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (3 preceding siblings ...)
2012-07-24 9:43 ` wbrana at gmail dot com
@ 2012-07-31 9:36 ` rguenth at gcc dot gnu.org
2012-07-31 10:12 ` wbrana at gmail dot com
` (13 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: rguenth at gcc dot gnu.org @ 2012-07-31 9:36 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
Richard Guenther <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |t.artem at mailcity dot com
--- Comment #5 from Richard Guenther <rguenth at gcc dot gnu.org> 2012-07-31 09:35:51 UTC ---
*** Bug 54135 has been marked as a duplicate of this bug. ***
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (4 preceding siblings ...)
2012-07-31 9:36 ` rguenth at gcc dot gnu.org
@ 2012-07-31 10:12 ` wbrana at gmail dot com
2012-07-31 22:45 ` [Bug tree-optimization/54077] [4.7/4.8 Regression] " wbrana at gmail dot com
` (12 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-07-31 10:12 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #6 from wbrana <wbrana at gmail dot com> 2012-07-31 10:11:48 UTC ---
clang
FP EMULATION : 405.92 : 194.78 : 44.95
4.4.7
FP EMULATION : 337.44 : 161.92 : 37.36
4.5.4
FP EMULATION : 320.08 : 153.59 : 35.44
4.6.3
FP EMULATION : 320.68 : 153.88 : 35.51
4.7.1
FP EMULATION : 227.32 : 109.08 : 25.17
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (5 preceding siblings ...)
2012-07-31 10:12 ` wbrana at gmail dot com
@ 2012-07-31 22:45 ` wbrana at gmail dot com
2012-08-01 11:00 ` wbrana at gmail dot com
` (11 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-07-31 22:45 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #7 from wbrana <wbrana at gmail dot com> 2012-07-31 22:45:25 UTC ---
4.7 20110626
FP EMULATION : 318.44 : 152.80 : 35.26
4.7 20110703
FP EMULATION : 228.08 : 109.44 : 25.25
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (6 preceding siblings ...)
2012-07-31 22:45 ` [Bug tree-optimization/54077] [4.7/4.8 Regression] " wbrana at gmail dot com
@ 2012-08-01 11:00 ` wbrana at gmail dot com
2012-08-01 18:46 ` ubizjak at gmail dot com
` (10 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-08-01 11:00 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #8 from wbrana <wbrana at gmail dot com> 2012-08-01 10:59:46 UTC ---
If I didn't make mistake it seems big slow down is caused by revision 175752
Date: Fri Jul 1 10:00:25 2011 +0000
2011-07-01 Kai Tietz <ktietz@redhat.com>
* tree-ssa-forwprop.c (simplify_bitwise_binary): Fix typo.
2011-07-01 Kai Tietz <ktietz@redhat.com>
* gcc.dg/tree-ssa/bitwise-sink.c: New test.
175751
FP EMULATION : 318.76 : 152.96 : 35.29
175752
FP EMULATION : 227.68 : 109.25 : 25.21
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (7 preceding siblings ...)
2012-08-01 11:00 ` wbrana at gmail dot com
@ 2012-08-01 18:46 ` ubizjak at gmail dot com
2012-08-01 22:35 ` wbrana at gmail dot com
` (9 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: ubizjak at gmail dot com @ 2012-08-01 18:46 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
Uros Bizjak <ubizjak at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |ktietz at gcc dot gnu.org,
| |ubizjak at gmail dot com
--- Comment #9 from Uros Bizjak <ubizjak at gmail dot com> 2012-08-01 18:46:34 UTC ---
Adding CC.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (8 preceding siblings ...)
2012-08-01 18:46 ` ubizjak at gmail dot com
@ 2012-08-01 22:35 ` wbrana at gmail dot com
2012-08-05 10:57 ` wbrana at gmail dot com
` (8 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-08-01 22:35 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #10 from wbrana <wbrana at gmail dot com> 2012-08-01 22:35:29 UTC ---
Reversion of 175752 on latest 4.7 branch improved FP EMU by 41%, but made
ASSIGNMENT worse by 8%.
with 175752
NUMERIC SORT : 1562.9 : 40.08 : 13.16
STRING SORT : 730.08 : 326.22 : 50.49
BITFIELD : 5.956e+08 : 102.17 : 21.34
FP EMULATION : 232.96 : 111.79 : 25.79
FOURIER : 36191 : 41.16 : 23.12
ASSIGNMENT : 63.469 : 241.51 : 62.64
IDEA : 9512 : 145.48 : 43.20
HUFFMAN : 3475.8 : 96.38 : 30.78
NEURAL NET : 80.296 : 128.99 : 54.26
LU DECOMPOSITION : 2696.9 : 139.71 : 100.89
without 175752
NUMERIC SORT : 1526.9 : 39.16 : 12.86
STRING SORT : 724.96 : 323.93 : 50.14
BITFIELD : 5.962e+08 : 102.27 : 21.36
FP EMULATION : 328.32 : 157.54 : 36.35
FOURIER : 36275 : 41.26 : 23.17
ASSIGNMENT : 58.37 : 222.11 : 57.61
IDEA : 9480 : 144.99 : 43.05
HUFFMAN : 3453.1 : 95.75 : 30.58
NEURAL NET : 79.128 : 127.11 : 53.47
LU DECOMPOSITION : 2733.4 : 141.60 : 102.25
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (9 preceding siblings ...)
2012-08-01 22:35 ` wbrana at gmail dot com
@ 2012-08-05 10:57 ` wbrana at gmail dot com
2012-08-27 8:43 ` wbrana at gmail dot com
` (7 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-08-05 10:57 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #11 from wbrana <wbrana at gmail dot com> 2012-08-05 10:56:58 UTC ---
I found something strange. There is much smaller slow down in ASSIGNMENT
without 175752 with Gentoo Hardened patches
gcc version 4.7.2 20120804 (prerelease) (Gentoo Hardened 4.7.2 p1.2, pie-0.5.3)
ASSIGNMENT : 62.95 : 239.53 : 62.13
latest gcc 4.7 branch
ASSIGNMENT : 58.29 : 221.80 : 57.53
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (10 preceding siblings ...)
2012-08-05 10:57 ` wbrana at gmail dot com
@ 2012-08-27 8:43 ` wbrana at gmail dot com
2012-09-07 10:15 ` rguenth at gcc dot gnu.org
` (6 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-08-27 8:43 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
Richard Guenther <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|--- |4.7.2
--- Comment #12 from wbrana <wbrana at gmail dot com> 2012-08-27 08:42:38 UTC ---
4.8 has improved
20120813
FP EMULATION : 229.84 : 110.29 : 25.45
20120827
FP EMULATION : 281.4 : 135.03 : 31.16
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (11 preceding siblings ...)
2012-08-27 8:43 ` wbrana at gmail dot com
@ 2012-09-07 10:15 ` rguenth at gcc dot gnu.org
2012-09-20 10:20 ` jakub at gcc dot gnu.org
` (5 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: rguenth at gcc dot gnu.org @ 2012-09-07 10:15 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
Richard Guenther <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Priority|P3 |P2
--- Comment #13 from Richard Guenther <rguenth at gcc dot gnu.org> 2012-09-07 10:14:28 UTC ---
I can't see any such regression on our autotesters. They run with
-O3 -ffast-math -funroll-loops -march=native on various AMD architectures.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (12 preceding siblings ...)
2012-09-07 10:15 ` rguenth at gcc dot gnu.org
@ 2012-09-20 10:20 ` jakub at gcc dot gnu.org
2012-10-04 14:25 ` wbrana at gmail dot com
` (4 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: jakub at gcc dot gnu.org @ 2012-09-20 10:20 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
Jakub Jelinek <jakub at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.7.2 |4.7.3
--- Comment #14 from Jakub Jelinek <jakub at gcc dot gnu.org> 2012-09-20 10:13:55 UTC ---
GCC 4.7.2 has been released.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] [4.7/4.8 Regression] Bytemark FP EMULATION 44% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (13 preceding siblings ...)
2012-09-20 10:20 ` jakub at gcc dot gnu.org
@ 2012-10-04 14:25 ` wbrana at gmail dot com
2012-11-11 16:37 ` [Bug tree-optimization/54077] Bytemark FP EMULATION 9%-15% " wbrana at gmail dot com
` (3 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-10-04 14:25 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #15 from wbrana <wbrana at gmail dot com> 2012-10-04 14:25:29 UTC ---
I can reliably reproduce bug on Core 2.
Reverting 175752 reliably fixes bug.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 9%-15% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (14 preceding siblings ...)
2012-10-04 14:25 ` wbrana at gmail dot com
@ 2012-11-11 16:37 ` wbrana at gmail dot com
2012-11-12 13:17 ` wbrana at gmail dot com
` (2 subsequent siblings)
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-11-11 16:37 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
wbrana <wbrana at gmail dot com> changed:
What |Removed |Added
----------------------------------------------------------------------------
Summary|[4.7/4.8 Regression] |Bytemark FP EMULATION
|Bytemark FP EMULATION 44% |9%-15% slower than with
|slower than with clang |clang
--- Comment #16 from wbrana <wbrana at gmail dot com> 2012-11-11 16:36:40 UTC ---
on newer CPU
clang 3.1
FP EMULATION : 594.52 : 285.28 : 65.83
gcc 4.8 branch
FP EMULATION : 544 : 261.04 : 60.23
gcc 4.7 branch
FP EMULATION : 520.32 : 249.67 : 57.61
gcc 4.6 branch
FP EMULATION : 507.84 : 243.69 : 56.23
reverting of 175752 has no effect on 4.7 in case of FP EMU
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 9%-15% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (15 preceding siblings ...)
2012-11-11 16:37 ` [Bug tree-optimization/54077] Bytemark FP EMULATION 9%-15% " wbrana at gmail dot com
@ 2012-11-12 13:17 ` wbrana at gmail dot com
2013-04-11 7:59 ` rguenth at gcc dot gnu.org
2014-06-12 13:53 ` rguenth at gcc dot gnu.org
18 siblings, 0 replies; 20+ messages in thread
From: wbrana at gmail dot com @ 2012-11-12 13:17 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
--- Comment #17 from wbrana <wbrana at gmail dot com> 2012-11-12 13:17:08 UTC ---
there is another bug caused by revision 175752
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=55286
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 9%-15% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (16 preceding siblings ...)
2012-11-12 13:17 ` wbrana at gmail dot com
@ 2013-04-11 7:59 ` rguenth at gcc dot gnu.org
2014-06-12 13:53 ` rguenth at gcc dot gnu.org
18 siblings, 0 replies; 20+ messages in thread
From: rguenth at gcc dot gnu.org @ 2013-04-11 7:59 UTC (permalink / raw)
To: gcc-bugs
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.7.3 |4.7.4
--- Comment #18 from Richard Biener <rguenth at gcc dot gnu.org> 2013-04-11 07:59:03 UTC ---
GCC 4.7.3 is being released, adjusting target milestone.
^ permalink raw reply [flat|nested] 20+ messages in thread
* [Bug tree-optimization/54077] Bytemark FP EMULATION 9%-15% slower than with clang
2012-07-24 9:38 [Bug tree-optimization/54077] New: Bytemark FP EMULATION 44% slower than with clang wbrana at gmail dot com
` (17 preceding siblings ...)
2013-04-11 7:59 ` rguenth at gcc dot gnu.org
@ 2014-06-12 13:53 ` rguenth at gcc dot gnu.org
18 siblings, 0 replies; 20+ messages in thread
From: rguenth at gcc dot gnu.org @ 2014-06-12 13:53 UTC (permalink / raw)
To: gcc-bugs
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=54077
Richard Biener <rguenth at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
Target Milestone|4.7.4 |---
--- Comment #19 from Richard Biener <rguenth at gcc dot gnu.org> ---
Unsetting target milestone of open non-regression bug from version of branch
being closed.
^ permalink raw reply [flat|nested] 20+ messages in thread