--- Additional Comments From joern dot rennecke at st dot com 2005-08-04
12:13 ---
Subject: Re: unrolling does not take target register pressure into account.
steven at gcc dot gnu dot org wrote:
Could you give some specific examples of assesments that 3.4 can do and 4.1
can
--- Additional Comments From steven at gcc dot gnu dot org 2005-08-04
13:10 ---
Strength reduction already happens before loop unrolling, but I guess
there could still be new opportunities after loop unrolling. Not sure
how significant that would be.
For the number of loop
--- Additional Comments From amylaar at gcc dot gnu dot org 2005-08-04
13:36 ---
(In reply to comment #13)
Strength reduction already happens before loop unrolling, but I guess
there could still be new opportunities after loop unrolling. Not sure
how significant that would be.
--- Additional Comments From steven at gcc dot gnu dot org 2005-08-03
15:49 ---
Joern wrote:
The target register pressure is easy to calculate, and although 4.1 lacks
infrastructure for assessment of the unroll benefit (which 3.4 has), it is
certainly easier to add it there in the
--
What|Removed |Added
Status|UNCONFIRMED |NEW
Ever Confirmed||1
Last reconfirmed|-00-00 00:00:00
--- Additional Comments From cvs-commit at gcc dot gnu dot org 2005-04-12
15:48 ---
Subject: Bug 20969
CVSROOT:/cvs/gcc
Module name:gcc
Branch: sh-elf-4_1-branch
Changes by: [EMAIL PROTECTED] 2005-04-12 15:48:47
Modified files:
gcc/doc:
--- Additional Comments From cvs-commit at gcc dot gnu dot org 2005-04-12
15:50 ---
Subject: Bug 20969
CVSROOT:/cvs/gcc
Module name:gcc
Branch: sh-elf-4_1-branch
Changes by: [EMAIL PROTECTED] 2005-04-12 15:49:53
Modified files:
gcc:
--- Additional Comments From pinskia at gcc dot gnu dot org 2005-04-12
16:02 ---
Huh? no optimization should take register pressure into account. What we
should have is a reroller in
the register allocator.
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=20969
--- Additional Comments From amylaar at gcc dot gnu dot org 2005-04-12
16:10 ---
The patch has been posted here:
http://gcc.gnu.org/ml/gcc-patches/2005-04/msg01286.html
--
What|Removed |Added
--- Additional Comments From amylaar at gcc dot gnu dot org 2005-04-12
16:14 ---
(In reply to comment #3)
Huh? no optimization should take register pressure into account. What we
should have is a reroller in
the register allocator.
Do you have a set of patches to try out?
--
On Apr 12, 2005, at 12:14 PM, amylaar at gcc dot gnu dot org wrote:
--- Additional Comments From amylaar at gcc dot gnu dot org
2005-04-12 16:14 ---
(In reply to comment #3)
Huh? no optimization should take register pressure into account.
What we
should have is a reroller in
the
--- Additional Comments From pinskia at physics dot uc dot edu 2005-04-12
16:19 ---
Subject: Re: unrolling does not take target register pressure into account.
On Apr 12, 2005, at 12:14 PM, amylaar at gcc dot gnu dot org wrote:
--- Additional Comments From amylaar at gcc dot
--- Additional Comments From pinskia at gcc dot gnu dot org 2005-04-12
16:26 ---
(In reply to comment #6)
No but if we go your route, then every place where we do an
optimization, we
will then need to teach it about register pressure which is wrong. Only
the register allocator
--- Additional Comments From amylaar at gcc dot gnu dot org 2005-04-12
17:21 ---
(In reply to comment #6)
Do you have a set of patches to try out?
No but if we go your route, then every place where we do an
optimization, we
will then need to teach it about register pressure
--- Additional Comments From pinskia at gcc dot gnu dot org 2005-04-12
17:24 ---
(In reply to comment #8)
(In reply to comment #6)
Do you have a set of patches to try out?
No but if we go your route, then every place where we do an
optimization, we
will then need to teach
--
What|Removed |Added
OtherBugsDependingO|17652 |
nThis||
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=20969
--- Additional Comments From amylaar at gcc dot gnu dot org 2005-04-12
17:48 ---
(In reply to comment #9)
But if we go down that route, the register allocator has to know about
every
other optimization. Throttling register pressure is usually much simpler
than un-doing a
17 matches
Mail list logo