* Re: [google] Increase inlining limits with FDO/LIPO
[not found] <BANLkTimYA_0zYxj12z3_Tu1Dz7BayRxW-Q@mail.gmail.com>
@ 2011-05-18 9:01 ` Xinliang David Li
2011-05-18 18:37 ` Mark Heffernan
[not found] ` <BANLkTimta+uCqZW8RX1wDoJ2GQb=GFGZ1Q@mail.gmail.com>
0 siblings, 2 replies; 11+ messages in thread
From: Xinliang David Li @ 2011-05-18 9:01 UTC (permalink / raw)
To: Mark Heffernan; +Cc: gcc-patches
To make consistent inline decisions between profile-gen and
profile-use, probably better to check these two:
flag_profile_arcs and flag_branch_probabilities. -fprofile-use
enables profile-arcs, and value profiling is enabled only when
edge/branch profiling is enabled (so no need to be checked).
David
On Tue, May 17, 2011 at 10:50 PM, Mark Heffernan <meheff@google.com> wrote:
> This small patch greatly expands the function size limits for inlining with
> FDO/LIPO. With profile information, the inliner is much more selective and
> precise and so the limits can be increased with less worry that functions
> and total code size will blow up. This speeds up x86-64 internal benchmarks
> by about geomean 1.5% to 3% with LIPO (depending on microarch), and 1% to
> 1.5% with FDO. Size increase is negligible (0.1% mean).
> Bootstrapped and regression tested on x86-64.
> Trunk testing to follow.
> Ok for google/main?
> Mark
>
> 2011-05-17 Mark Heffernan <meheff@google.com>
> * opts.c (finish_options): Increase inlining limits with profile
> generate and use.
>
> Index: opts.c
> ===================================================================
> --- opts.c (revision 173666)
> +++ opts.c (working copy)
> @@ -828,6 +828,22 @@ finish_options (struct gcc_options *opts
> opts->x_flag_split_stack = 0;
> }
> }
> +
> + if (opts->x_flag_profile_use
> + || opts->x_profile_arc_flag
> + || opts->x_flag_profile_values)
> + {
> + /* With accurate profile information, inlining is much more
> + selective and makes better decisions, so increase the
> + inlining function size limits. Changes must be added to both
> + the generate and use builds to avoid profile mismatches. */
> + maybe_set_param_value
> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
> + opts->x_param_values, opts_set->x_param_values);
> + maybe_set_param_value
> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
> + opts->x_param_values, opts_set->x_param_values);
> + }
> }
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-18 9:01 ` [google] Increase inlining limits with FDO/LIPO Xinliang David Li
@ 2011-05-18 18:37 ` Mark Heffernan
[not found] ` <BANLkTimta+uCqZW8RX1wDoJ2GQb=GFGZ1Q@mail.gmail.com>
1 sibling, 0 replies; 11+ messages in thread
From: Mark Heffernan @ 2011-05-18 18:37 UTC (permalink / raw)
To: Xinliang David Li; +Cc: gcc-patches
On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com> wrote:
> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
> enables profile-arcs, and value profiling is enabled only when
> edge/branch profiling is enabled (so no need to be checked).
I changed the location where these parameters are set to someplace
more appropriate (to where the flags are set when profile gen/use is
indicated). Verified identical binaries are generated.
OK as updated?
Mark
2011-05-18 Mark Heffernan <meheff@google.com>
* opts.c (set_profile_parameters): New function.
Index: opts.c
===================================================================
--- opts.c (revision 173666)
+++ opts.c (working copy)
@@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
opts->x_help_columns, opts, lang_mask);
}
+
+/* Set parameters to more appropriate values when profile information
+ is available. */
+static void
+set_profile_parameters (struct gcc_options *opts,
+ struct gcc_options *opts_set)
+{
+ /* With accurate profile information, inlining is much more
+ selective and makes better decisions, so increase the
+ inlining function size limits. */
+ maybe_set_param_value
+ (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
+ opts->x_param_values, opts_set->x_param_values);
+ maybe_set_param_value
+ (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
+ opts->x_param_values, opts_set->x_param_values);
+}
+
+
/* Handle target- and language-independent options. Return zero to
generate an "unknown option" message. Only options that need
extra handling need to be listed here; if you simply want
@@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
opts->x_flag_unswitch_loops = value;
if (!opts_set->x_flag_gcse_after_reload)
opts->x_flag_gcse_after_reload = value;
+ set_profile_parameters (opts, opts_set);
break;
case OPT_fprofile_generate_:
@@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
is done. */
if (!opts_set->x_flag_ipa_reference && in_lto_p)
opts->x_flag_ipa_reference = false;
+ set_profile_parameters (opts, opts_set);
break;
case OPT_fshow_column:
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
[not found] ` <BANLkTimta+uCqZW8RX1wDoJ2GQb=GFGZ1Q@mail.gmail.com>
@ 2011-05-18 19:00 ` Xinliang David Li
2011-05-18 19:41 ` Mark Heffernan
0 siblings, 1 reply; 11+ messages in thread
From: Xinliang David Li @ 2011-05-18 19:00 UTC (permalink / raw)
To: Mark Heffernan; +Cc: gcc-patches
Though not common, people can do this:
1. for profile gen:
gcc -fprofile-arcs ...
2. for profile use
gcc -fbranch-probabilities ...
The new change won't help those. Your original place will be ok if you
test profile_arcs and branch_probability flags.
David
On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
> wrote:
>>
>> To make consistent inline decisions between profile-gen and
>> profile-use, probably better to check these two:
>>
>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>> enables profile-arcs, and value profiling is enabled only when
>> edge/branch profiling is enabled (so no need to be checked).
>
> I changed the location where these parameters are set to someplace more
> appropriate (to where the flags are set when profile gen/use is indicated).
> Verified identical binaries are generated.
> OK as updated?
>
> Mark
> 2011-05-18 Mark Heffernan <meheff@google.com>
> * opts.c (set_profile_parameters): New function.
> Index: opts.c
> ===================================================================
> --- opts.c (revision 173666)
> +++ opts.c (working copy)
> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
> opts->x_help_columns, opts, lang_mask);
> }
>
> +
> +/* Set parameters to more appropriate values when profile information
> + is available. */
> +static void
> +set_profile_parameters (struct gcc_options *opts,
> + struct gcc_options *opts_set)
> +{
> + /* With accurate profile information, inlining is much more
> + selective and makes better decisions, so increase the
> + inlining function size limits. */
> + maybe_set_param_value
> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
> + opts->x_param_values, opts_set->x_param_values);
> + maybe_set_param_value
> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
> + opts->x_param_values, opts_set->x_param_values);
> +}
> +
> +
> /* Handle target- and language-independent options. Return zero to
> generate an "unknown option" message. Only options that need
> extra handling need to be listed here; if you simply want
> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
> opts->x_flag_unswitch_loops = value;
> if (!opts_set->x_flag_gcse_after_reload)
> opts->x_flag_gcse_after_reload = value;
> + set_profile_parameters (opts, opts_set);
> break;
>
> case OPT_fprofile_generate_:
> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
> is done. */
> if (!opts_set->x_flag_ipa_reference && in_lto_p)
> opts->x_flag_ipa_reference = false;
> + set_profile_parameters (opts, opts_set);
> break;
>
> case OPT_fshow_column:
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-18 19:00 ` Xinliang David Li
@ 2011-05-18 19:41 ` Mark Heffernan
2011-05-18 19:53 ` Xinliang David Li
0 siblings, 1 reply; 11+ messages in thread
From: Mark Heffernan @ 2011-05-18 19:41 UTC (permalink / raw)
To: Xinliang David Li; +Cc: gcc-patches
On Wed, May 18, 2011 at 10:52 AM, Xinliang David Li <davidxl@google.com> wrote:
> The new change won't help those. Your original place will be ok if you
> test profile_arcs and branch_probability flags.
Ah, yes. I see your point now. Reverted to the original change with
condition profile_arc_flag and flag_branch_probabilities.
Mark
>
> David
>
>
> On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
>> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
>> wrote:
>>>
>>> To make consistent inline decisions between profile-gen and
>>> profile-use, probably better to check these two:
>>>
>>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>>> enables profile-arcs, and value profiling is enabled only when
>>> edge/branch profiling is enabled (so no need to be checked).
>>
>> I changed the location where these parameters are set to someplace more
>> appropriate (to where the flags are set when profile gen/use is indicated).
>> Verified identical binaries are generated.
>> OK as updated?
>>
>> Mark
>> 2011-05-18 Mark Heffernan <meheff@google.com>
>> * opts.c (set_profile_parameters): New function.
>> Index: opts.c
>> ===================================================================
>> --- opts.c (revision 173666)
>> +++ opts.c (working copy)
>> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
>> opts->x_help_columns, opts, lang_mask);
>> }
>>
>> +
>> +/* Set parameters to more appropriate values when profile information
>> + is available. */
>> +static void
>> +set_profile_parameters (struct gcc_options *opts,
>> + struct gcc_options *opts_set)
>> +{
>> + /* With accurate profile information, inlining is much more
>> + selective and makes better decisions, so increase the
>> + inlining function size limits. */
>> + maybe_set_param_value
>> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
>> + opts->x_param_values, opts_set->x_param_values);
>> + maybe_set_param_value
>> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
>> + opts->x_param_values, opts_set->x_param_values);
>> +}
>> +
>> +
>> /* Handle target- and language-independent options. Return zero to
>> generate an "unknown option" message. Only options that need
>> extra handling need to be listed here; if you simply want
>> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
>> opts->x_flag_unswitch_loops = value;
>> if (!opts_set->x_flag_gcse_after_reload)
>> opts->x_flag_gcse_after_reload = value;
>> + set_profile_parameters (opts, opts_set);
>> break;
>>
>> case OPT_fprofile_generate_:
>> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
>> is done. */
>> if (!opts_set->x_flag_ipa_reference && in_lto_p)
>> opts->x_flag_ipa_reference = false;
>> + set_profile_parameters (opts, opts_set);
>> break;
>>
>> case OPT_fshow_column:
>>
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-18 19:41 ` Mark Heffernan
@ 2011-05-18 19:53 ` Xinliang David Li
2011-05-18 20:36 ` Mark Heffernan
0 siblings, 1 reply; 11+ messages in thread
From: Xinliang David Li @ 2011-05-18 19:53 UTC (permalink / raw)
To: Mark Heffernan; +Cc: gcc-patches
Ok with that change to google/main with some retesting.
David
On Wed, May 18, 2011 at 11:34 AM, Mark Heffernan <meheff@google.com> wrote:
> On Wed, May 18, 2011 at 10:52 AM, Xinliang David Li <davidxl@google.com> wrote:
>> The new change won't help those. Your original place will be ok if you
>> test profile_arcs and branch_probability flags.
>
> Ah, yes. I see your point now. Reverted to the original change with
> condition profile_arc_flag and flag_branch_probabilities.
>
> Mark
>
>>
>> David
>>
>>
>> On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
>>> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
>>> wrote:
>>>>
>>>> To make consistent inline decisions between profile-gen and
>>>> profile-use, probably better to check these two:
>>>>
>>>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>>>> enables profile-arcs, and value profiling is enabled only when
>>>> edge/branch profiling is enabled (so no need to be checked).
>>>
>>> I changed the location where these parameters are set to someplace more
>>> appropriate (to where the flags are set when profile gen/use is indicated).
>>> Verified identical binaries are generated.
>>> OK as updated?
>>>
>>> Mark
>>> 2011-05-18 Mark Heffernan <meheff@google.com>
>>> * opts.c (set_profile_parameters): New function.
>>> Index: opts.c
>>> ===================================================================
>>> --- opts.c (revision 173666)
>>> +++ opts.c (working copy)
>>> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
>>> opts->x_help_columns, opts, lang_mask);
>>> }
>>>
>>> +
>>> +/* Set parameters to more appropriate values when profile information
>>> + is available. */
>>> +static void
>>> +set_profile_parameters (struct gcc_options *opts,
>>> + struct gcc_options *opts_set)
>>> +{
>>> + /* With accurate profile information, inlining is much more
>>> + selective and makes better decisions, so increase the
>>> + inlining function size limits. */
>>> + maybe_set_param_value
>>> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
>>> + opts->x_param_values, opts_set->x_param_values);
>>> + maybe_set_param_value
>>> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
>>> + opts->x_param_values, opts_set->x_param_values);
>>> +}
>>> +
>>> +
>>> /* Handle target- and language-independent options. Return zero to
>>> generate an "unknown option" message. Only options that need
>>> extra handling need to be listed here; if you simply want
>>> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
>>> opts->x_flag_unswitch_loops = value;
>>> if (!opts_set->x_flag_gcse_after_reload)
>>> opts->x_flag_gcse_after_reload = value;
>>> + set_profile_parameters (opts, opts_set);
>>> break;
>>>
>>> case OPT_fprofile_generate_:
>>> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
>>> is done. */
>>> if (!opts_set->x_flag_ipa_reference && in_lto_p)
>>> opts->x_flag_ipa_reference = false;
>>> + set_profile_parameters (opts, opts_set);
>>> break;
>>>
>>> case OPT_fshow_column:
>>>
>>
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-18 19:53 ` Xinliang David Li
@ 2011-05-18 20:36 ` Mark Heffernan
2011-05-19 20:50 ` Xinliang David Li
0 siblings, 1 reply; 11+ messages in thread
From: Mark Heffernan @ 2011-05-18 20:36 UTC (permalink / raw)
To: Xinliang David Li; +Cc: gcc-patches
Verified identical binaries created and submitted.
Mark
On Wed, May 18, 2011 at 11:37 AM, Xinliang David Li <davidxl@google.com> wrote:
> Ok with that change to google/main with some retesting.
>
> David
>
> On Wed, May 18, 2011 at 11:34 AM, Mark Heffernan <meheff@google.com> wrote:
>> On Wed, May 18, 2011 at 10:52 AM, Xinliang David Li <davidxl@google.com> wrote:
>>> The new change won't help those. Your original place will be ok if you
>>> test profile_arcs and branch_probability flags.
>>
>> Ah, yes. I see your point now. Reverted to the original change with
>> condition profile_arc_flag and flag_branch_probabilities.
>>
>> Mark
>>
>>>
>>> David
>>>
>>>
>>> On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
>>>> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
>>>> wrote:
>>>>>
>>>>> To make consistent inline decisions between profile-gen and
>>>>> profile-use, probably better to check these two:
>>>>>
>>>>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>>>>> enables profile-arcs, and value profiling is enabled only when
>>>>> edge/branch profiling is enabled (so no need to be checked).
>>>>
>>>> I changed the location where these parameters are set to someplace more
>>>> appropriate (to where the flags are set when profile gen/use is indicated).
>>>> Verified identical binaries are generated.
>>>> OK as updated?
>>>>
>>>> Mark
>>>> 2011-05-18 Mark Heffernan <meheff@google.com>
>>>> * opts.c (set_profile_parameters): New function.
>>>> Index: opts.c
>>>> ===================================================================
>>>> --- opts.c (revision 173666)
>>>> +++ opts.c (working copy)
>>>> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
>>>> opts->x_help_columns, opts, lang_mask);
>>>> }
>>>>
>>>> +
>>>> +/* Set parameters to more appropriate values when profile information
>>>> + is available. */
>>>> +static void
>>>> +set_profile_parameters (struct gcc_options *opts,
>>>> + struct gcc_options *opts_set)
>>>> +{
>>>> + /* With accurate profile information, inlining is much more
>>>> + selective and makes better decisions, so increase the
>>>> + inlining function size limits. */
>>>> + maybe_set_param_value
>>>> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
>>>> + opts->x_param_values, opts_set->x_param_values);
>>>> + maybe_set_param_value
>>>> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
>>>> + opts->x_param_values, opts_set->x_param_values);
>>>> +}
>>>> +
>>>> +
>>>> /* Handle target- and language-independent options. Return zero to
>>>> generate an "unknown option" message. Only options that need
>>>> extra handling need to be listed here; if you simply want
>>>> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
>>>> opts->x_flag_unswitch_loops = value;
>>>> if (!opts_set->x_flag_gcse_after_reload)
>>>> opts->x_flag_gcse_after_reload = value;
>>>> + set_profile_parameters (opts, opts_set);
>>>> break;
>>>>
>>>> case OPT_fprofile_generate_:
>>>> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
>>>> is done. */
>>>> if (!opts_set->x_flag_ipa_reference && in_lto_p)
>>>> opts->x_flag_ipa_reference = false;
>>>> + set_profile_parameters (opts, opts_set);
>>>> break;
>>>>
>>>> case OPT_fshow_column:
>>>>
>>>
>>
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-18 20:36 ` Mark Heffernan
@ 2011-05-19 20:50 ` Xinliang David Li
2011-05-20 10:15 ` Richard Guenther
0 siblings, 1 reply; 11+ messages in thread
From: Xinliang David Li @ 2011-05-19 20:50 UTC (permalink / raw)
To: Mark Heffernan; +Cc: gcc-patches
I have done some SPEC testing evaluating the performance impact of
your patch. They look very positive. LIPO got helped even more than
FDO (I only did SPEC2k LIPO testing).
Thanks,
David
1. SPEC06 (C/C++) with FDO
before after Improvement
---------------------------------------------------------------------------------
400.perlbench 27.4 28.2 2.89% <---
401.bzip2 18.1 18.2 0.28%
403.gcc 25.5 26.3 3.26% <---
429.mcf 26.0 26.0 0.08%
445.gobmk 22.6 23.2 2.30% <----
456.hmmer 20.1 19.8 -1.25%
458.sjeng 23.6 23.6 -0.42%
462.libquantum 57.1 56.9 -0.40%
464.h264ref 34.4 34.1 -0.70%
471.omnetpp 18.8 18.9 0.53%
473.astar 16.6 17.0 2.53% <---
483.xalancbmk 27.4 28.5 3.79% <---
999.specrand 94.9 98.4 3.71% <---
450.soplex 34.5 33.8 -2.00%
447.dealII 32.0 31.9 -0.34%
453.povray 25.9 28.3 9.02% <---
482.sphinx3 32.6 31.4 -3.50%
2. SPEC2k FDO
before after
Improvement
--------------------------------------------------------------------------------------------------
164.gzip 1308 1372 4.95%
175.vpr 1723 1805 4.76%
176.gcc 2407 2504 4.01%
181.mcf 1724 1748 1.38%
186.crafty 2292 2349 2.47%
197.parser 1457 1601 9.88%
252.eon 2557 2588 1.22%
253.perlbmk 2479 2574 3.83%
254.gap 1996 2013 0.84%
255.vortex 2683 2798 4.31%
256.bzip2 1833 1829 -0.26%
300.twolf 2321 2359 1.63%
188.ammp 771 766 -0.72%
183.equake 1071 1071 0.05%
179.art 2954 2979 0.85%
3. SPEC2k LIPO:
before after
Improvement
-------------------------------------------------------------------------------------------------
164.gzip 1311 1405 7.18%
175.vpr 1732 1772 2.35%
176.gcc 2462 2559 3.96%
181.mcf 1723 1731 0.50%
186.crafty 2552 2662 4.33%
197.parser 1468 1671 13.78%
252.eon 2690 3000 11.49%
253.perlbmk 2545 2611 2.60%
254.gap 2097 2152 2.60%
255.vortex 2949 3719 26.11%
256.bzip2 1864 1935 3.78%
300.twolf 2371 2471 4.22%
188.ammp 771 774 0.41%
183.equake 1081 1081 -0.04%
179.art 2878 2884 0.24%
4. SPEC2k LIPO vs FDO before the change:
FDO(before) LIPO(before) Improvement
-----------------------------------------------------------------------------------------------------
164.gzip 1308 1311 0.22%
175.vpr 1723 1732 0.53%
176.gcc 2407 2462 2.27%
181.mcf 1724 1723 -0.07%
186.crafty 2292 2552 11.32%
197.parser 1457 1468 0.81%
252.eon 2557 2690 5.20%
253.perlbmk 2479 2545 2.66%
254.gap 1996 2097 5.04%
255.vortex 2683 2949 9.91%
256.bzip2 1833 1864 1.67%
300.twolf 2321 2371 2.15%
188.ammp 771 771 -0.04%
183.equake 1071 1081 1.02%
179.art 2954 2878 -2.59%
5. SPEC2k LIPO vs FDO after the change:
FDO(after) LIPO(after) Improvement
------------------------------------------------------------------------------------------------
164.gzip 1372 1405 2.36%
175.vpr 1805 1772 -1.79%
176.gcc 2504 2559 2.21%
181.mcf 1748 1731 -0.94%
186.crafty 2349 2662 13.35%
197.parser 1601 1671 4.38%
252.eon 2588 3000 15.88%
253.perlbmk 2574 2611 1.44%
254.gap 2013 2152 6.87%
255.vortex 2798 3719 32.88%
256.bzip2 1829 1935 5.79%
300.twolf 2359 2471 4.75%
188.ammp 766 774 1.10%
183.equake 1071 1081 0.92%
179.art 2979 2884 -3.18%
On Wed, May 18, 2011 at 12:53 PM, Mark Heffernan <meheff@google.com> wrote:
> Verified identical binaries created and submitted.
>
> Mark
>
> On Wed, May 18, 2011 at 11:37 AM, Xinliang David Li <davidxl@google.com> wrote:
>> Ok with that change to google/main with some retesting.
>>
>> David
>>
>> On Wed, May 18, 2011 at 11:34 AM, Mark Heffernan <meheff@google.com> wrote:
>>> On Wed, May 18, 2011 at 10:52 AM, Xinliang David Li <davidxl@google.com> wrote:
>>>> The new change won't help those. Your original place will be ok if you
>>>> test profile_arcs and branch_probability flags.
>>>
>>> Ah, yes. I see your point now. Reverted to the original change with
>>> condition profile_arc_flag and flag_branch_probabilities.
>>>
>>> Mark
>>>
>>>>
>>>> David
>>>>
>>>>
>>>> On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
>>>>> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
>>>>> wrote:
>>>>>>
>>>>>> To make consistent inline decisions between profile-gen and
>>>>>> profile-use, probably better to check these two:
>>>>>>
>>>>>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>>>>>> enables profile-arcs, and value profiling is enabled only when
>>>>>> edge/branch profiling is enabled (so no need to be checked).
>>>>>
>>>>> I changed the location where these parameters are set to someplace more
>>>>> appropriate (to where the flags are set when profile gen/use is indicated).
>>>>> Verified identical binaries are generated.
>>>>> OK as updated?
>>>>>
>>>>> Mark
>>>>> 2011-05-18 Mark Heffernan <meheff@google.com>
>>>>> * opts.c (set_profile_parameters): New function.
>>>>> Index: opts.c
>>>>> ===================================================================
>>>>> --- opts.c (revision 173666)
>>>>> +++ opts.c (working copy)
>>>>> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
>>>>> opts->x_help_columns, opts, lang_mask);
>>>>> }
>>>>>
>>>>> +
>>>>> +/* Set parameters to more appropriate values when profile information
>>>>> + is available. */
>>>>> +static void
>>>>> +set_profile_parameters (struct gcc_options *opts,
>>>>> + struct gcc_options *opts_set)
>>>>> +{
>>>>> + /* With accurate profile information, inlining is much more
>>>>> + selective and makes better decisions, so increase the
>>>>> + inlining function size limits. */
>>>>> + maybe_set_param_value
>>>>> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>> + maybe_set_param_value
>>>>> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>> +}
>>>>> +
>>>>> +
>>>>> /* Handle target- and language-independent options. Return zero to
>>>>> generate an "unknown option" message. Only options that need
>>>>> extra handling need to be listed here; if you simply want
>>>>> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
>>>>> opts->x_flag_unswitch_loops = value;
>>>>> if (!opts_set->x_flag_gcse_after_reload)
>>>>> opts->x_flag_gcse_after_reload = value;
>>>>> + set_profile_parameters (opts, opts_set);
>>>>> break;
>>>>>
>>>>> case OPT_fprofile_generate_:
>>>>> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
>>>>> is done. */
>>>>> if (!opts_set->x_flag_ipa_reference && in_lto_p)
>>>>> opts->x_flag_ipa_reference = false;
>>>>> + set_profile_parameters (opts, opts_set);
>>>>> break;
>>>>>
>>>>> case OPT_fshow_column:
>>>>>
>>>>
>>>
>>
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-19 20:50 ` Xinliang David Li
@ 2011-05-20 10:15 ` Richard Guenther
2011-05-20 16:37 ` Xinliang David Li
0 siblings, 1 reply; 11+ messages in thread
From: Richard Guenther @ 2011-05-20 10:15 UTC (permalink / raw)
To: Xinliang David Li; +Cc: Mark Heffernan, gcc-patches
On Thu, May 19, 2011 at 8:26 PM, Xinliang David Li <davidxl@google.com> wrote:
> I have done some SPEC testing evaluating the performance impact of
> your patch. They look very positive. LIPO got helped even more than
> FDO (I only did SPEC2k LIPO testing).
Did you also check impact on compile-time and code-size?
> Thanks,
>
> David
>
> 1. SPEC06 (C/C++) with FDO
>
> before after Improvement
> ---------------------------------------------------------------------------------
> 400.perlbench 27.4 28.2 2.89% <---
> 401.bzip2 18.1 18.2 0.28%
> 403.gcc 25.5 26.3 3.26% <---
> 429.mcf 26.0 26.0 0.08%
> 445.gobmk 22.6 23.2 2.30% <----
> 456.hmmer 20.1 19.8 -1.25%
> 458.sjeng 23.6 23.6 -0.42%
> 462.libquantum 57.1 56.9 -0.40%
> 464.h264ref 34.4 34.1 -0.70%
> 471.omnetpp 18.8 18.9 0.53%
> 473.astar 16.6 17.0 2.53% <---
> 483.xalancbmk 27.4 28.5 3.79% <---
> 999.specrand 94.9 98.4 3.71% <---
> 450.soplex 34.5 33.8 -2.00%
> 447.dealII 32.0 31.9 -0.34%
> 453.povray 25.9 28.3 9.02% <---
> 482.sphinx3 32.6 31.4 -3.50%
>
>
> 2. SPEC2k FDO
>
> before after
> Improvement
> --------------------------------------------------------------------------------------------------
> 164.gzip 1308 1372 4.95%
> 175.vpr 1723 1805 4.76%
> 176.gcc 2407 2504 4.01%
> 181.mcf 1724 1748 1.38%
> 186.crafty 2292 2349 2.47%
> 197.parser 1457 1601 9.88%
> 252.eon 2557 2588 1.22%
> 253.perlbmk 2479 2574 3.83%
> 254.gap 1996 2013 0.84%
> 255.vortex 2683 2798 4.31%
> 256.bzip2 1833 1829 -0.26%
> 300.twolf 2321 2359 1.63%
> 188.ammp 771 766 -0.72%
> 183.equake 1071 1071 0.05%
> 179.art 2954 2979 0.85%
>
>
> 3. SPEC2k LIPO:
>
> before after
> Improvement
> -------------------------------------------------------------------------------------------------
> 164.gzip 1311 1405 7.18%
> 175.vpr 1732 1772 2.35%
> 176.gcc 2462 2559 3.96%
> 181.mcf 1723 1731 0.50%
> 186.crafty 2552 2662 4.33%
> 197.parser 1468 1671 13.78%
> 252.eon 2690 3000 11.49%
> 253.perlbmk 2545 2611 2.60%
> 254.gap 2097 2152 2.60%
> 255.vortex 2949 3719 26.11%
> 256.bzip2 1864 1935 3.78%
> 300.twolf 2371 2471 4.22%
> 188.ammp 771 774 0.41%
> 183.equake 1081 1081 -0.04%
> 179.art 2878 2884 0.24%
>
>
> 4. SPEC2k LIPO vs FDO before the change:
>
> FDO(before) LIPO(before) Improvement
> -----------------------------------------------------------------------------------------------------
> 164.gzip 1308 1311 0.22%
> 175.vpr 1723 1732 0.53%
> 176.gcc 2407 2462 2.27%
> 181.mcf 1724 1723 -0.07%
> 186.crafty 2292 2552 11.32%
> 197.parser 1457 1468 0.81%
> 252.eon 2557 2690 5.20%
> 253.perlbmk 2479 2545 2.66%
> 254.gap 1996 2097 5.04%
> 255.vortex 2683 2949 9.91%
> 256.bzip2 1833 1864 1.67%
> 300.twolf 2321 2371 2.15%
> 188.ammp 771 771 -0.04%
> 183.equake 1071 1081 1.02%
> 179.art 2954 2878 -2.59%
>
>
>
> 5. SPEC2k LIPO vs FDO after the change:
> FDO(after) LIPO(after) Improvement
> ------------------------------------------------------------------------------------------------
> 164.gzip 1372 1405 2.36%
> 175.vpr 1805 1772 -1.79%
> 176.gcc 2504 2559 2.21%
> 181.mcf 1748 1731 -0.94%
> 186.crafty 2349 2662 13.35%
> 197.parser 1601 1671 4.38%
> 252.eon 2588 3000 15.88%
> 253.perlbmk 2574 2611 1.44%
> 254.gap 2013 2152 6.87%
> 255.vortex 2798 3719 32.88%
> 256.bzip2 1829 1935 5.79%
> 300.twolf 2359 2471 4.75%
> 188.ammp 766 774 1.10%
> 183.equake 1071 1081 0.92%
> 179.art 2979 2884 -3.18%
>
>
>
> On Wed, May 18, 2011 at 12:53 PM, Mark Heffernan <meheff@google.com> wrote:
>> Verified identical binaries created and submitted.
>>
>> Mark
>>
>> On Wed, May 18, 2011 at 11:37 AM, Xinliang David Li <davidxl@google.com> wrote:
>>> Ok with that change to google/main with some retesting.
>>>
>>> David
>>>
>>> On Wed, May 18, 2011 at 11:34 AM, Mark Heffernan <meheff@google.com> wrote:
>>>> On Wed, May 18, 2011 at 10:52 AM, Xinliang David Li <davidxl@google.com> wrote:
>>>>> The new change won't help those. Your original place will be ok if you
>>>>> test profile_arcs and branch_probability flags.
>>>>
>>>> Ah, yes. I see your point now. Reverted to the original change with
>>>> condition profile_arc_flag and flag_branch_probabilities.
>>>>
>>>> Mark
>>>>
>>>>>
>>>>> David
>>>>>
>>>>>
>>>>> On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
>>>>>> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
>>>>>> wrote:
>>>>>>>
>>>>>>> To make consistent inline decisions between profile-gen and
>>>>>>> profile-use, probably better to check these two:
>>>>>>>
>>>>>>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>>>>>>> enables profile-arcs, and value profiling is enabled only when
>>>>>>> edge/branch profiling is enabled (so no need to be checked).
>>>>>>
>>>>>> I changed the location where these parameters are set to someplace more
>>>>>> appropriate (to where the flags are set when profile gen/use is indicated).
>>>>>> Verified identical binaries are generated.
>>>>>> OK as updated?
>>>>>>
>>>>>> Mark
>>>>>> 2011-05-18 Mark Heffernan <meheff@google.com>
>>>>>> * opts.c (set_profile_parameters): New function.
>>>>>> Index: opts.c
>>>>>> ===================================================================
>>>>>> --- opts.c (revision 173666)
>>>>>> +++ opts.c (working copy)
>>>>>> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
>>>>>> opts->x_help_columns, opts, lang_mask);
>>>>>> }
>>>>>>
>>>>>> +
>>>>>> +/* Set parameters to more appropriate values when profile information
>>>>>> + is available. */
>>>>>> +static void
>>>>>> +set_profile_parameters (struct gcc_options *opts,
>>>>>> + struct gcc_options *opts_set)
>>>>>> +{
>>>>>> + /* With accurate profile information, inlining is much more
>>>>>> + selective and makes better decisions, so increase the
>>>>>> + inlining function size limits. */
>>>>>> + maybe_set_param_value
>>>>>> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
>>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>>> + maybe_set_param_value
>>>>>> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
>>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>>> +}
>>>>>> +
>>>>>> +
>>>>>> /* Handle target- and language-independent options. Return zero to
>>>>>> generate an "unknown option" message. Only options that need
>>>>>> extra handling need to be listed here; if you simply want
>>>>>> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
>>>>>> opts->x_flag_unswitch_loops = value;
>>>>>> if (!opts_set->x_flag_gcse_after_reload)
>>>>>> opts->x_flag_gcse_after_reload = value;
>>>>>> + set_profile_parameters (opts, opts_set);
>>>>>> break;
>>>>>>
>>>>>> case OPT_fprofile_generate_:
>>>>>> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
>>>>>> is done. */
>>>>>> if (!opts_set->x_flag_ipa_reference && in_lto_p)
>>>>>> opts->x_flag_ipa_reference = false;
>>>>>> + set_profile_parameters (opts, opts_set);
>>>>>> break;
>>>>>>
>>>>>> case OPT_fshow_column:
>>>>>>
>>>>>
>>>>
>>>
>>
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-20 10:15 ` Richard Guenther
@ 2011-05-20 16:37 ` Xinliang David Li
2011-05-20 21:52 ` Xinliang David Li
0 siblings, 1 reply; 11+ messages in thread
From: Xinliang David Li @ 2011-05-20 16:37 UTC (permalink / raw)
To: Richard Guenther; +Cc: Mark Heffernan, GCC Patches
On Fri, May 20, 2011 at 2:12 AM, Richard Guenther
<richard.guenther@gmail.com> wrote:
> On Thu, May 19, 2011 at 8:26 PM, Xinliang David Li <davidxl@google.com> wrote:
>> I have done some SPEC testing evaluating the performance impact of
>> your patch. They look very positive. LIPO got helped even more than
>> FDO (I only did SPEC2k LIPO testing).
>
> Did you also check impact on compile-time and code-size?
Not yet for SPEC -- will pick some benchmarks and take a look.
David
>
>> Thanks,
>>
>> David
>>
>> 1. SPEC06 (C/C++) with FDO
>>
>> before after Improvement
>> ---------------------------------------------------------------------------------
>> 400.perlbench 27.4 28.2 2.89% <---
>> 401.bzip2 18.1 18.2 0.28%
>> 403.gcc 25.5 26.3 3.26% <---
>> 429.mcf 26.0 26.0 0.08%
>> 445.gobmk 22.6 23.2 2.30% <----
>> 456.hmmer 20.1 19.8 -1.25%
>> 458.sjeng 23.6 23.6 -0.42%
>> 462.libquantum 57.1 56.9 -0.40%
>> 464.h264ref 34.4 34.1 -0.70%
>> 471.omnetpp 18.8 18.9 0.53%
>> 473.astar 16.6 17.0 2.53% <---
>> 483.xalancbmk 27.4 28.5 3.79% <---
>> 999.specrand 94.9 98.4 3.71% <---
>> 450.soplex 34.5 33.8 -2.00%
>> 447.dealII 32.0 31.9 -0.34%
>> 453.povray 25.9 28.3 9.02% <---
>> 482.sphinx3 32.6 31.4 -3.50%
>>
>>
>> 2. SPEC2k FDO
>>
>> before after
>> Improvement
>> --------------------------------------------------------------------------------------------------
>> 164.gzip 1308 1372 4.95%
>> 175.vpr 1723 1805 4.76%
>> 176.gcc 2407 2504 4.01%
>> 181.mcf 1724 1748 1.38%
>> 186.crafty 2292 2349 2.47%
>> 197.parser 1457 1601 9.88%
>> 252.eon 2557 2588 1.22%
>> 253.perlbmk 2479 2574 3.83%
>> 254.gap 1996 2013 0.84%
>> 255.vortex 2683 2798 4.31%
>> 256.bzip2 1833 1829 -0.26%
>> 300.twolf 2321 2359 1.63%
>> 188.ammp 771 766 -0.72%
>> 183.equake 1071 1071 0.05%
>> 179.art 2954 2979 0.85%
>>
>>
>> 3. SPEC2k LIPO:
>>
>> before after
>> Improvement
>> -------------------------------------------------------------------------------------------------
>> 164.gzip 1311 1405 7.18%
>> 175.vpr 1732 1772 2.35%
>> 176.gcc 2462 2559 3.96%
>> 181.mcf 1723 1731 0.50%
>> 186.crafty 2552 2662 4.33%
>> 197.parser 1468 1671 13.78%
>> 252.eon 2690 3000 11.49%
>> 253.perlbmk 2545 2611 2.60%
>> 254.gap 2097 2152 2.60%
>> 255.vortex 2949 3719 26.11%
>> 256.bzip2 1864 1935 3.78%
>> 300.twolf 2371 2471 4.22%
>> 188.ammp 771 774 0.41%
>> 183.equake 1081 1081 -0.04%
>> 179.art 2878 2884 0.24%
>>
>>
>> 4. SPEC2k LIPO vs FDO before the change:
>>
>> FDO(before) LIPO(before) Improvement
>> -----------------------------------------------------------------------------------------------------
>> 164.gzip 1308 1311 0.22%
>> 175.vpr 1723 1732 0.53%
>> 176.gcc 2407 2462 2.27%
>> 181.mcf 1724 1723 -0.07%
>> 186.crafty 2292 2552 11.32%
>> 197.parser 1457 1468 0.81%
>> 252.eon 2557 2690 5.20%
>> 253.perlbmk 2479 2545 2.66%
>> 254.gap 1996 2097 5.04%
>> 255.vortex 2683 2949 9.91%
>> 256.bzip2 1833 1864 1.67%
>> 300.twolf 2321 2371 2.15%
>> 188.ammp 771 771 -0.04%
>> 183.equake 1071 1081 1.02%
>> 179.art 2954 2878 -2.59%
>>
>>
>>
>> 5. SPEC2k LIPO vs FDO after the change:
>> FDO(after) LIPO(after) Improvement
>> ------------------------------------------------------------------------------------------------
>> 164.gzip 1372 1405 2.36%
>> 175.vpr 1805 1772 -1.79%
>> 176.gcc 2504 2559 2.21%
>> 181.mcf 1748 1731 -0.94%
>> 186.crafty 2349 2662 13.35%
>> 197.parser 1601 1671 4.38%
>> 252.eon 2588 3000 15.88%
>> 253.perlbmk 2574 2611 1.44%
>> 254.gap 2013 2152 6.87%
>> 255.vortex 2798 3719 32.88%
>> 256.bzip2 1829 1935 5.79%
>> 300.twolf 2359 2471 4.75%
>> 188.ammp 766 774 1.10%
>> 183.equake 1071 1081 0.92%
>> 179.art 2979 2884 -3.18%
>>
>>
>>
>> On Wed, May 18, 2011 at 12:53 PM, Mark Heffernan <meheff@google.com> wrote:
>>> Verified identical binaries created and submitted.
>>>
>>> Mark
>>>
>>> On Wed, May 18, 2011 at 11:37 AM, Xinliang David Li <davidxl@google.com> wrote:
>>>> Ok with that change to google/main with some retesting.
>>>>
>>>> David
>>>>
>>>> On Wed, May 18, 2011 at 11:34 AM, Mark Heffernan <meheff@google.com> wrote:
>>>>> On Wed, May 18, 2011 at 10:52 AM, Xinliang David Li <davidxl@google.com> wrote:
>>>>>> The new change won't help those. Your original place will be ok if you
>>>>>> test profile_arcs and branch_probability flags.
>>>>>
>>>>> Ah, yes. I see your point now. Reverted to the original change with
>>>>> condition profile_arc_flag and flag_branch_probabilities.
>>>>>
>>>>> Mark
>>>>>
>>>>>>
>>>>>> David
>>>>>>
>>>>>>
>>>>>> On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
>>>>>>> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
>>>>>>> wrote:
>>>>>>>>
>>>>>>>> To make consistent inline decisions between profile-gen and
>>>>>>>> profile-use, probably better to check these two:
>>>>>>>>
>>>>>>>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>>>>>>>> enables profile-arcs, and value profiling is enabled only when
>>>>>>>> edge/branch profiling is enabled (so no need to be checked).
>>>>>>>
>>>>>>> I changed the location where these parameters are set to someplace more
>>>>>>> appropriate (to where the flags are set when profile gen/use is indicated).
>>>>>>> Verified identical binaries are generated.
>>>>>>> OK as updated?
>>>>>>>
>>>>>>> Mark
>>>>>>> 2011-05-18 Mark Heffernan <meheff@google.com>
>>>>>>> * opts.c (set_profile_parameters): New function.
>>>>>>> Index: opts.c
>>>>>>> ===================================================================
>>>>>>> --- opts.c (revision 173666)
>>>>>>> +++ opts.c (working copy)
>>>>>>> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
>>>>>>> opts->x_help_columns, opts, lang_mask);
>>>>>>> }
>>>>>>>
>>>>>>> +
>>>>>>> +/* Set parameters to more appropriate values when profile information
>>>>>>> + is available. */
>>>>>>> +static void
>>>>>>> +set_profile_parameters (struct gcc_options *opts,
>>>>>>> + struct gcc_options *opts_set)
>>>>>>> +{
>>>>>>> + /* With accurate profile information, inlining is much more
>>>>>>> + selective and makes better decisions, so increase the
>>>>>>> + inlining function size limits. */
>>>>>>> + maybe_set_param_value
>>>>>>> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
>>>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>>>> + maybe_set_param_value
>>>>>>> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
>>>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>>>> +}
>>>>>>> +
>>>>>>> +
>>>>>>> /* Handle target- and language-independent options. Return zero to
>>>>>>> generate an "unknown option" message. Only options that need
>>>>>>> extra handling need to be listed here; if you simply want
>>>>>>> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
>>>>>>> opts->x_flag_unswitch_loops = value;
>>>>>>> if (!opts_set->x_flag_gcse_after_reload)
>>>>>>> opts->x_flag_gcse_after_reload = value;
>>>>>>> + set_profile_parameters (opts, opts_set);
>>>>>>> break;
>>>>>>>
>>>>>>> case OPT_fprofile_generate_:
>>>>>>> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
>>>>>>> is done. */
>>>>>>> if (!opts_set->x_flag_ipa_reference && in_lto_p)
>>>>>>> opts->x_flag_ipa_reference = false;
>>>>>>> + set_profile_parameters (opts, opts_set);
>>>>>>> break;
>>>>>>>
>>>>>>> case OPT_fshow_column:
>>>>>>>
>>>>>>
>>>>>
>>>>
>>>
>>
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* Re: [google] Increase inlining limits with FDO/LIPO
2011-05-20 16:37 ` Xinliang David Li
@ 2011-05-20 21:52 ` Xinliang David Li
0 siblings, 0 replies; 11+ messages in thread
From: Xinliang David Li @ 2011-05-20 21:52 UTC (permalink / raw)
To: Richard Guenther; +Cc: Mark Heffernan, GCC Patches
Some code size and timing number (profile use compile) are collected. Summary:
Compile time for profile-use compilation increase for all cases --
this is probably not a big issue as this is for peak performance.
It is more interesting to look at the size numbers. C++ program size
actually decrease in many cases (which match the results from our
internal benchmarks). For some benchmark such as povray, it reduce
quite a bit (either due to more DFE, or better cleanups -- have not
looked at details). For C programs, especially smaller ones, the
size increase (some significantly).
David
1. xalancbmk:
Size (total size of object files, not text size which is correlated)
Before: 17,801,488
After : 17,252,032
Change: -3%
Time (make all with -j1)
Before: 248 seconds
After : 286 seconds
Change: 15%
2. povray:
Size
Before: 2,855,690
After: 2,113,754
Change: -25%
Time:
Before: 36.5s
After: 43.2 s
Change: +18%
3. eon
Size
Before: 3,988,460
After : 4,099,108
Change: +2.8%
Time
Before: 53.1s
After: 56.8s
Change: +6.9%
4. gcc
Size
Before: 14,162,908
After: 15,089,106
Change: +6.5%
Time
Before: 57.3s
After: 60.7s
Change: +5.9%
5. Parser:
Size
Before: 1,175,509
After: 1,568,135
Change: +33.4%
Time
Before: 5.3s
After: 12.9s
Change: +143%
On Fri, May 20, 2011 at 8:53 AM, Xinliang David Li <davidxl@google.com> wrote:
> On Fri, May 20, 2011 at 2:12 AM, Richard Guenther
> <richard.guenther@gmail.com> wrote:
>> On Thu, May 19, 2011 at 8:26 PM, Xinliang David Li <davidxl@google.com> wrote:
>>> I have done some SPEC testing evaluating the performance impact of
>>> your patch. They look very positive. LIPO got helped even more than
>>> FDO (I only did SPEC2k LIPO testing).
>>
>> Did you also check impact on compile-time and code-size?
>
> Not yet for SPEC -- will pick some benchmarks and take a look.
>
> David
>
>>
>>> Thanks,
>>>
>>> David
>>>
>>> 1. SPEC06 (C/C++) with FDO
>>>
>>> before after Improvement
>>> ---------------------------------------------------------------------------------
>>> 400.perlbench 27.4 28.2 2.89% <---
>>> 401.bzip2 18.1 18.2 0.28%
>>> 403.gcc 25.5 26.3 3.26% <---
>>> 429.mcf 26.0 26.0 0.08%
>>> 445.gobmk 22.6 23.2 2.30% <----
>>> 456.hmmer 20.1 19.8 -1.25%
>>> 458.sjeng 23.6 23.6 -0.42%
>>> 462.libquantum 57.1 56.9 -0.40%
>>> 464.h264ref 34.4 34.1 -0.70%
>>> 471.omnetpp 18.8 18.9 0.53%
>>> 473.astar 16.6 17.0 2.53% <---
>>> 483.xalancbmk 27.4 28.5 3.79% <---
>>> 999.specrand 94.9 98.4 3.71% <---
>>> 450.soplex 34.5 33.8 -2.00%
>>> 447.dealII 32.0 31.9 -0.34%
>>> 453.povray 25.9 28.3 9.02% <---
>>> 482.sphinx3 32.6 31.4 -3.50%
>>>
>>>
>>> 2. SPEC2k FDO
>>>
>>> before after
>>> Improvement
>>> --------------------------------------------------------------------------------------------------
>>> 164.gzip 1308 1372 4.95%
>>> 175.vpr 1723 1805 4.76%
>>> 176.gcc 2407 2504 4.01%
>>> 181.mcf 1724 1748 1.38%
>>> 186.crafty 2292 2349 2.47%
>>> 197.parser 1457 1601 9.88%
>>> 252.eon 2557 2588 1.22%
>>> 253.perlbmk 2479 2574 3.83%
>>> 254.gap 1996 2013 0.84%
>>> 255.vortex 2683 2798 4.31%
>>> 256.bzip2 1833 1829 -0.26%
>>> 300.twolf 2321 2359 1.63%
>>> 188.ammp 771 766 -0.72%
>>> 183.equake 1071 1071 0.05%
>>> 179.art 2954 2979 0.85%
>>>
>>>
>>> 3. SPEC2k LIPO:
>>>
>>> before after
>>> Improvement
>>> -------------------------------------------------------------------------------------------------
>>> 164.gzip 1311 1405 7.18%
>>> 175.vpr 1732 1772 2.35%
>>> 176.gcc 2462 2559 3.96%
>>> 181.mcf 1723 1731 0.50%
>>> 186.crafty 2552 2662 4.33%
>>> 197.parser 1468 1671 13.78%
>>> 252.eon 2690 3000 11.49%
>>> 253.perlbmk 2545 2611 2.60%
>>> 254.gap 2097 2152 2.60%
>>> 255.vortex 2949 3719 26.11%
>>> 256.bzip2 1864 1935 3.78%
>>> 300.twolf 2371 2471 4.22%
>>> 188.ammp 771 774 0.41%
>>> 183.equake 1081 1081 -0.04%
>>> 179.art 2878 2884 0.24%
>>>
>>>
>>> 4. SPEC2k LIPO vs FDO before the change:
>>>
>>> FDO(before) LIPO(before) Improvement
>>> -----------------------------------------------------------------------------------------------------
>>> 164.gzip 1308 1311 0.22%
>>> 175.vpr 1723 1732 0.53%
>>> 176.gcc 2407 2462 2.27%
>>> 181.mcf 1724 1723 -0.07%
>>> 186.crafty 2292 2552 11.32%
>>> 197.parser 1457 1468 0.81%
>>> 252.eon 2557 2690 5.20%
>>> 253.perlbmk 2479 2545 2.66%
>>> 254.gap 1996 2097 5.04%
>>> 255.vortex 2683 2949 9.91%
>>> 256.bzip2 1833 1864 1.67%
>>> 300.twolf 2321 2371 2.15%
>>> 188.ammp 771 771 -0.04%
>>> 183.equake 1071 1081 1.02%
>>> 179.art 2954 2878 -2.59%
>>>
>>>
>>>
>>> 5. SPEC2k LIPO vs FDO after the change:
>>> FDO(after) LIPO(after) Improvement
>>> ------------------------------------------------------------------------------------------------
>>> 164.gzip 1372 1405 2.36%
>>> 175.vpr 1805 1772 -1.79%
>>> 176.gcc 2504 2559 2.21%
>>> 181.mcf 1748 1731 -0.94%
>>> 186.crafty 2349 2662 13.35%
>>> 197.parser 1601 1671 4.38%
>>> 252.eon 2588 3000 15.88%
>>> 253.perlbmk 2574 2611 1.44%
>>> 254.gap 2013 2152 6.87%
>>> 255.vortex 2798 3719 32.88%
>>> 256.bzip2 1829 1935 5.79%
>>> 300.twolf 2359 2471 4.75%
>>> 188.ammp 766 774 1.10%
>>> 183.equake 1071 1081 0.92%
>>> 179.art 2979 2884 -3.18%
>>>
>>>
>>>
>>> On Wed, May 18, 2011 at 12:53 PM, Mark Heffernan <meheff@google.com> wrote:
>>>> Verified identical binaries created and submitted.
>>>>
>>>> Mark
>>>>
>>>> On Wed, May 18, 2011 at 11:37 AM, Xinliang David Li <davidxl@google.com> wrote:
>>>>> Ok with that change to google/main with some retesting.
>>>>>
>>>>> David
>>>>>
>>>>> On Wed, May 18, 2011 at 11:34 AM, Mark Heffernan <meheff@google.com> wrote:
>>>>>> On Wed, May 18, 2011 at 10:52 AM, Xinliang David Li <davidxl@google.com> wrote:
>>>>>>> The new change won't help those. Your original place will be ok if you
>>>>>>> test profile_arcs and branch_probability flags.
>>>>>>
>>>>>> Ah, yes. I see your point now. Reverted to the original change with
>>>>>> condition profile_arc_flag and flag_branch_probabilities.
>>>>>>
>>>>>> Mark
>>>>>>
>>>>>>>
>>>>>>> David
>>>>>>>
>>>>>>>
>>>>>>> On Wed, May 18, 2011 at 10:39 AM, Mark Heffernan <meheff@google.com> wrote:
>>>>>>>> On Tue, May 17, 2011 at 11:34 PM, Xinliang David Li <davidxl@google.com>
>>>>>>>> wrote:
>>>>>>>>>
>>>>>>>>> To make consistent inline decisions between profile-gen and
>>>>>>>>> profile-use, probably better to check these two:
>>>>>>>>>
>>>>>>>>> flag_profile_arcs and flag_branch_probabilities. -fprofile-use
>>>>>>>>> enables profile-arcs, and value profiling is enabled only when
>>>>>>>>> edge/branch profiling is enabled (so no need to be checked).
>>>>>>>>
>>>>>>>> I changed the location where these parameters are set to someplace more
>>>>>>>> appropriate (to where the flags are set when profile gen/use is indicated).
>>>>>>>> Verified identical binaries are generated.
>>>>>>>> OK as updated?
>>>>>>>>
>>>>>>>> Mark
>>>>>>>> 2011-05-18 Mark Heffernan <meheff@google.com>
>>>>>>>> * opts.c (set_profile_parameters): New function.
>>>>>>>> Index: opts.c
>>>>>>>> ===================================================================
>>>>>>>> --- opts.c (revision 173666)
>>>>>>>> +++ opts.c (working copy)
>>>>>>>> @@ -1209,6 +1209,25 @@ print_specific_help (unsigned int includ
>>>>>>>> opts->x_help_columns, opts, lang_mask);
>>>>>>>> }
>>>>>>>>
>>>>>>>> +
>>>>>>>> +/* Set parameters to more appropriate values when profile information
>>>>>>>> + is available. */
>>>>>>>> +static void
>>>>>>>> +set_profile_parameters (struct gcc_options *opts,
>>>>>>>> + struct gcc_options *opts_set)
>>>>>>>> +{
>>>>>>>> + /* With accurate profile information, inlining is much more
>>>>>>>> + selective and makes better decisions, so increase the
>>>>>>>> + inlining function size limits. */
>>>>>>>> + maybe_set_param_value
>>>>>>>> + (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
>>>>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>>>>> + maybe_set_param_value
>>>>>>>> + (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
>>>>>>>> + opts->x_param_values, opts_set->x_param_values);
>>>>>>>> +}
>>>>>>>> +
>>>>>>>> +
>>>>>>>> /* Handle target- and language-independent options. Return zero to
>>>>>>>> generate an "unknown option" message. Only options that need
>>>>>>>> extra handling need to be listed here; if you simply want
>>>>>>>> @@ -1560,6 +1579,7 @@ common_handle_option (struct gcc_options
>>>>>>>> opts->x_flag_unswitch_loops = value;
>>>>>>>> if (!opts_set->x_flag_gcse_after_reload)
>>>>>>>> opts->x_flag_gcse_after_reload = value;
>>>>>>>> + set_profile_parameters (opts, opts_set);
>>>>>>>> break;
>>>>>>>>
>>>>>>>> case OPT_fprofile_generate_:
>>>>>>>> @@ -1580,6 +1600,7 @@ common_handle_option (struct gcc_options
>>>>>>>> is done. */
>>>>>>>> if (!opts_set->x_flag_ipa_reference && in_lto_p)
>>>>>>>> opts->x_flag_ipa_reference = false;
>>>>>>>> + set_profile_parameters (opts, opts_set);
>>>>>>>> break;
>>>>>>>>
>>>>>>>> case OPT_fshow_column:
>>>>>>>>
>>>>>>>
>>>>>>
>>>>>
>>>>
>>>
>>
>
^ permalink raw reply [flat|nested] 11+ messages in thread
* [google] Increase inlining limits with FDO/LIPO
@ 2011-05-18 7:50 Mark Heffernan
0 siblings, 0 replies; 11+ messages in thread
From: Mark Heffernan @ 2011-05-18 7:50 UTC (permalink / raw)
To: Xinliang David Li, gcc-patches
This small patch greatly expands the function size limits for inlining
with FDO/LIPO. With profile information, the inliner is much more
selective and precise and so the limits can be increased with less
worry that functions and total code size will blow up. This speeds up
x86-64 internal benchmarks by about geomean 1.5% to 3% with LIPO
(depending on microarch), and 1% to 1.5% with FDO. Size increase is
negligible (0.1% mean).
Bootstrapped and regression tested on x86-64.
Trunk testing to follow.
Ok for google/main?
Mark
2011-05-17 Mark Heffernan <meheff@google.com>
* opts.c (finish_options): Increase inlining limits with profile
generate and use.
Index: opts.c
===================================================================
--- opts.c (revision 173666)
+++ opts.c (working copy)
@@ -828,6 +828,22 @@ finish_options (struct gcc_options *opts
opts->x_flag_split_stack = 0;
}
}
+
+ if (opts->x_flag_profile_use
+ || opts->x_profile_arc_flag
+ || opts->x_flag_profile_values)
+ {
+ /* With accurate profile information, inlining is much more
+ selective and makes better decisions, so increase the
+ inlining function size limits. Changes must be added to both
+ the generate and use builds to avoid profile mismatches. */
+ maybe_set_param_value
+ (PARAM_MAX_INLINE_INSNS_SINGLE, 1000,
+ opts->x_param_values, opts_set->x_param_values);
+ maybe_set_param_value
+ (PARAM_MAX_INLINE_INSNS_AUTO, 1000,
+ opts->x_param_values, opts_set->x_param_values);
+ }
}
^ permalink raw reply [flat|nested] 11+ messages in thread
end of thread, other threads:[~2011-05-20 18:20 UTC | newest]
Thread overview: 11+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
[not found] <BANLkTimYA_0zYxj12z3_Tu1Dz7BayRxW-Q@mail.gmail.com>
2011-05-18 9:01 ` [google] Increase inlining limits with FDO/LIPO Xinliang David Li
2011-05-18 18:37 ` Mark Heffernan
[not found] ` <BANLkTimta+uCqZW8RX1wDoJ2GQb=GFGZ1Q@mail.gmail.com>
2011-05-18 19:00 ` Xinliang David Li
2011-05-18 19:41 ` Mark Heffernan
2011-05-18 19:53 ` Xinliang David Li
2011-05-18 20:36 ` Mark Heffernan
2011-05-19 20:50 ` Xinliang David Li
2011-05-20 10:15 ` Richard Guenther
2011-05-20 16:37 ` Xinliang David Li
2011-05-20 21:52 ` Xinliang David Li
2011-05-18 7:50 Mark Heffernan
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).