Re: [PATCH i386] Enable -freorder-blocks-and-partition

[Teresa Johnson <tejohnson@google.com>]

Thanks for the data. A few questions:

- Do you have the raw data used to generate your pdfs available? Since
you gave me the binaries, if I have the data in terms of exactly what
addresses are being plotted I can correlate with the specific cold
functions via nm. Once I know what cold functions are being hit, I
would then need the .i files and the .gcda files to reproduce the
build.

- I tried running the binaries, but don't have the necessary shared
library dependencies installed on my system:
$ ldd gimp-2.8 | grep found
libgimpwidgets-2.0.so.0 => not found
libgimpconfig-2.0.so.0 => not found
libgimpcolor-2.0.so.0 => not found
libgimpmath-2.0.so.0 => not found
libgimpthumb-2.0.so.0 => not found
libgimpmodule-2.0.so.0 => not found
libgimpbase-2.0.so.0 => not found
libgegl-0.2.so.0 => not found
libbabl-0.1.so.0 => not found

I'll try to get these installed, but the last time I did that in an
attempt to build gimp I had a lot of trouble trying to get the right
versions and get them to build for me - any chance you could build an
archive version of the gimp binary?

Thanks,
Teresa

On Sun, Dec 15, 2013 at 2:19 PM, Martin Liška <marxin.liska@gmail.com> wrote:
> On 15 December 2013 23:17, Martin Liška <marxin.liska@gmail.com> wrote:
>> Dear Jan and Teresa,
>>     Jan was right that I've been using changes which were commited by
>> Teresa and do live in trunk. So the graph with time profile presented
>> in my previous post was really with enabled
>> -freorder-blocks-and-partition. I removed the hack in varasm.c and I
>> do use classic section layout. Please open the following dump
>> (includes PDF graph+html report that shows functions with time profile
>> located in cold section and all -fdump-ipa-all dumps):
>>
>> https://drive.google.com/file/d/0B0pisUJ80pO1YW1QWUFkZjdqME0/edit?usp=sharing
>>
>> Apart from that, I created also PDF graph (https://drive.google.com/file/d/0B0pisUJ80pO1aHhPWW56dXpLVTQ/edit?usp=sharing) that
>> shows that time profile is almost perfect for GIMP. I miss just some
>> examples that do not have profile in generate phase.
>>
>> I will merge current trunk and prepare final patch.
>>
>> Are there any other data that you want to be prepared?
>>
>> Martin
>>
>>
>> On 13 December 2013 02:13, Jan Hubicka <hubicka@ucw.cz> wrote:
>>>> 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



-- 
Teresa Johnson | Software Engineer | tejohnson@google.com | 408-460-2413