From: Jan Hubicka <hubicka@ucw.cz>
To: Teresa Johnson <tejohnson@google.com>
Cc: "Martin Liška" <marxin.liska@gmail.com>,
"Jeff Law" <law@redhat.com>, "Jan Hubicka" <hubicka@ucw.cz>,
"gcc-patches@gcc.gnu.org" <gcc-patches@gcc.gnu.org>
Subject: Re: [PATCH i386] Enable -freorder-blocks-and-partition
Date: Fri, 13 Dec 2013 01:13:00 -0000 [thread overview]
Message-ID: <20131213011309.GA21107@kam.mff.cuni.cz> (raw)
In-Reply-To: <CAAe5K+VnKXQ=S2km6_73mBZ2vGBAxu9wwmi4Z_QM_ncwrT0CjA@mail.gmail.com>
> On Wed, Dec 11, 2013 at 1:21 AM, Martin Liška <marxin.liska@gmail.com> wrote:
> > Hello,
> > I prepared a collection of systemtap graphs for GIMP.
> >
> > 1) just my profile-based function reordering: 550 pages
> > 2) just -freorder-blocks-and-partitions: 646 pages
> > 3) just -fno-reorder-blocks-and-partitions: 638 pages
> >
> > Please see attached data.
>
> Thanks for the data. A few observations/questions:
>
> With both 1) (your (time-based?) reordering) and 2)
> (-freorder-blocks-and-partitions) there are a fair amount of accesses
> out of the cold section. I'm not seeing so many accesses out of the
> cold section in the apps I am looking at with splitting enabled. In
I see you already comitted the patch, so perhaps Martin's measurement assume
the pass is off by default?
I rebuilded GCC with profiledboostrap and with the linkerscript unmapping
text.unlikely. I get ICE in:
(gdb) bt
#0 diagnostic_set_caret_max_width(diagnostic_context*, int) () at ../../gcc/diagnostic.c:108
#1 0x0000000000f68457 in diagnostic_initialize (context=0x18ae000 <global_diagnostic_context>, n_opts=n_opts@entry=1290) at ../../gcc/diagnostic.c:135
#2 0x000000000100050e in general_init (argv0=<optimized out>) at ../../gcc/toplev.c:1110
#3 toplev_main(int, char**) () at ../../gcc/toplev.c:1922
#4 0x00007ffff774cbe5 in __libc_start_main () from /lib64/libc.so.6
#5 0x0000000000f7898d in _start () at ../sysdeps/x86_64/start.S:122
That is relatively early in startup process. The function seems inlined and
it fails only on second invocation, did not have time to investigate further,
yet while without -fprofile-use it starts...
On our periodic testers I see off-noise improvement in crafty 2200->2300
and regression on Vortex, 2900->2800, plus code size increase.
Honza
next prev parent reply other threads:[~2013-12-13 1:13 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-11-19 15:17 Teresa Johnson
2013-11-19 16:31 ` Jan Hubicka
2013-11-19 18:23 ` Teresa Johnson
2013-11-19 19:32 ` Jeff Law
2013-11-20 1:55 ` Teresa Johnson
[not found] ` <CAObPJ3OZHvET=QNmNtx9ZjaHZk=GhokWjoF2njr5mgwcv2ogDA@mail.gmail.com>
2013-11-28 16:34 ` Jan Hubicka
2013-12-02 15:16 ` Teresa Johnson
2013-12-02 16:17 ` Jeff Law
2013-12-02 16:53 ` Martin Liška
2013-12-11 9:21 ` Martin Liška
2013-12-12 5:51 ` Teresa Johnson
2013-12-12 20:54 ` Jan Hubicka
2013-12-13 1:13 ` Jan Hubicka [this message]
[not found] ` <CAObPJ3MLrWsTwK-23ienktyASO9YLvAXMNKUxVm3v+KC=5JzOA@mail.gmail.com>
2013-12-15 22:19 ` Martin Liška
2013-12-17 15:09 ` Teresa Johnson
2013-12-20 6:19 ` Teresa Johnson
2014-02-11 22:21 ` Teresa Johnson
2014-02-14 18:50 ` Teresa Johnson
2013-11-19 22:05 ` Andi Kleen
2013-11-19 22:10 ` Teresa Johnson
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=20131213011309.GA21107@kam.mff.cuni.cz \
--to=hubicka@ucw.cz \
--cc=gcc-patches@gcc.gnu.org \
--cc=law@redhat.com \
--cc=marxin.liska@gmail.com \
--cc=tejohnson@google.com \
/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).