[PATCH][AArch64] Enable AUTOPREFETCHER

public inbox for gcc-patches@gcc.gnu.org
 help / color / mirror / Atom feed

* [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic
@ 2017-04-05 12:38 Wilco Dijkstra
  2017-04-05 16:17 ` Andrew Pinski
                   ` (3 more replies)
  0 siblings, 4 replies; 5+ messages in thread
From: Wilco Dijkstra @ 2017-04-05 12:38 UTC (permalink / raw)
  To: GCC Patches
  Cc: nd, James Greenhalgh, Andrew.pinski, Evandro Menezes, jim.wilson

Many supported cores use the AUTOPREFETCHER_WEAK setting which tries
to order loads and stores to improve streaming performance.  Since significant
gains were reported in http://patchwork.ozlabs.org/patch/534469/ it seems
like a good idea to enable this setting too for -mcpu=generic.  Since the
weak model only keeps the order if it doesn't make the schedule worse, it
should not impact performance adversely on cores that don't show a gain.
Any objections?

ChangeLog:
2017-04-05  Wilco Dijkstra  <wdijkstr@arm.com>

	* gcc/config/aarch64/aarch64.c (generic_tunings): Update prefetch model.

--
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 8b729b1b1f87316e940d7fc657f235a935ffa93e..b249ce2b310707c7ded2827d505ce2ddfcfbf976 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -547,7 +547,7 @@ static const struct tune_params generic_tunings =
   2,	/* min_div_recip_mul_df.  */
   0,	/* max_case_values.  */
   0,	/* cache_line_size.  */
-  tune_params::AUTOPREFETCHER_OFF,	/* autoprefetcher_model.  */
+  tune_params::AUTOPREFETCHER_WEAK,	/* autoprefetcher_model.  */
   (AARCH64_EXTRA_TUNE_NONE)	/* tune_flags.  */
 };

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic
  2017-04-05 12:38 [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic Wilco Dijkstra
@ 2017-04-05 16:17 ` Andrew Pinski
  2017-04-05 16:44 ` Jim Wilson
                   ` (2 subsequent siblings)
  3 siblings, 0 replies; 5+ messages in thread
From: Andrew Pinski @ 2017-04-05 16:17 UTC (permalink / raw)
  To: Wilco Dijkstra
  Cc: GCC Patches, nd, James Greenhalgh, Andrew.pinski,
	Evandro Menezes, jim.wilson

On Wed, Apr 5, 2017 at 5:38 AM, Wilco Dijkstra <Wilco.Dijkstra@arm.com> wrote:
> Many supported cores use the AUTOPREFETCHER_WEAK setting which tries
> to order loads and stores to improve streaming performance.  Since significant
> gains were reported in http://patchwork.ozlabs.org/patch/534469/ it seems
> like a good idea to enable this setting too for -mcpu=generic.  Since the
> weak model only keeps the order if it doesn't make the schedule worse, it
> should not impact performance adversely on cores that don't show a gain.
> Any objections?

This is ok with me.

Thanks,
Andrew

>
> ChangeLog:
> 2017-04-05  Wilco Dijkstra  <wdijkstr@arm.com>
>
>         * gcc/config/aarch64/aarch64.c (generic_tunings): Update prefetch model.
>
> --
> diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
> index 8b729b1b1f87316e940d7fc657f235a935ffa93e..b249ce2b310707c7ded2827d505ce2ddfcfbf976 100644
> --- a/gcc/config/aarch64/aarch64.c
> +++ b/gcc/config/aarch64/aarch64.c
> @@ -547,7 +547,7 @@ static const struct tune_params generic_tunings =
>    2,   /* min_div_recip_mul_df.  */
>    0,   /* max_case_values.  */
>    0,   /* cache_line_size.  */
> -  tune_params::AUTOPREFETCHER_OFF,     /* autoprefetcher_model.  */
> +  tune_params::AUTOPREFETCHER_WEAK,    /* autoprefetcher_model.  */
>    (AARCH64_EXTRA_TUNE_NONE)    /* tune_flags.  */
>  };

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic
  2017-04-05 12:38 [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic Wilco Dijkstra
  2017-04-05 16:17 ` Andrew Pinski
@ 2017-04-05 16:44 ` Jim Wilson
  2017-04-20 15:53 ` Wilco Dijkstra
  2017-05-04 10:29 ` Richard Earnshaw (lists)
  3 siblings, 0 replies; 5+ messages in thread
From: Jim Wilson @ 2017-04-05 16:44 UTC (permalink / raw)
  To: Wilco Dijkstra
  Cc: GCC Patches, nd, James Greenhalgh, Andrew.pinski, Evandro Menezes

On Wed, Apr 5, 2017 at 5:38 AM, Wilco Dijkstra <Wilco.Dijkstra@arm.com> wrote:
> Many supported cores use the AUTOPREFETCHER_WEAK setting which tries
> to order loads and stores to improve streaming performance.  Since significant
> gains were reported in http://patchwork.ozlabs.org/patch/534469/ it seems
> like a good idea to enable this setting too for -mcpu=generic.  Since the
> weak model only keeps the order if it doesn't make the schedule worse, it
> should not impact performance adversely on cores that don't show a gain.
> Any objections?

This is fine with me also.

Jim

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic
  2017-04-05 12:38 [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic Wilco Dijkstra
  2017-04-05 16:17 ` Andrew Pinski
  2017-04-05 16:44 ` Jim Wilson
@ 2017-04-20 15:53 ` Wilco Dijkstra
  2017-05-04 10:29 ` Richard Earnshaw (lists)
  3 siblings, 0 replies; 5+ messages in thread
From: Wilco Dijkstra @ 2017-04-20 15:53 UTC (permalink / raw)
  To: GCC Patches, James Greenhalgh; +Cc: nd


ping


From: Wilco Dijkstra
Sent: 05 April 2017 13:38
To: GCC Patches
Cc: nd; James Greenhalgh; Andrew.pinski@cavium.com; Evandro Menezes; jim.wilson@linaro.org
Subject: [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic
    
Many supported cores use the AUTOPREFETCHER_WEAK setting which tries
to order loads and stores to improve streaming performance.  Since significant
gains were reported in http://patchwork.ozlabs.org/patch/534469/ it seems
like a good idea to enable this setting too for -mcpu=generic.  Since the
weak model only keeps the order if it doesn't make the schedule worse, it
should not impact performance adversely on cores that don't show a gain.
Any objections?

ChangeLog:
2017-04-05  Wilco Dijkstra  <wdijkstr@arm.com>

        * gcc/config/aarch64/aarch64.c (generic_tunings): Update prefetch model.

--
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 8b729b1b1f87316e940d7fc657f235a935ffa93e..b249ce2b310707c7ded2827d505ce2ddfcfbf976 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -547,7 +547,7 @@ static const struct tune_params generic_tunings =
   2,   /* min_div_recip_mul_df.  */
   0,   /* max_case_values.  */
   0,   /* cache_line_size.  */
-  tune_params::AUTOPREFETCHER_OFF,     /* autoprefetcher_model.  */
+  tune_params::AUTOPREFETCHER_WEAK,    /* autoprefetcher_model.  */
   (AARCH64_EXTRA_TUNE_NONE)    /* tune_flags.  */
 };    

^ permalink raw reply	[flat|nested] 5+ messages in thread

* Re: [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic
  2017-04-05 12:38 [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic Wilco Dijkstra
                   ` (2 preceding siblings ...)
  2017-04-20 15:53 ` Wilco Dijkstra
@ 2017-05-04 10:29 ` Richard Earnshaw (lists)
  3 siblings, 0 replies; 5+ messages in thread
From: Richard Earnshaw (lists) @ 2017-05-04 10:29 UTC (permalink / raw)
  To: Wilco Dijkstra, GCC Patches
  Cc: nd, James Greenhalgh, Andrew.pinski, Evandro Menezes, jim.wilson

On 05/04/17 13:38, Wilco Dijkstra wrote:
> Many supported cores use the AUTOPREFETCHER_WEAK setting which tries
> to order loads and stores to improve streaming performance.  Since significant
> gains were reported in http://patchwork.ozlabs.org/patch/534469/ it seems
> like a good idea to enable this setting too for -mcpu=generic.  Since the
> weak model only keeps the order if it doesn't make the schedule worse, it
> should not impact performance adversely on cores that don't show a gain.
> Any objections?
> 
> ChangeLog:
> 2017-04-05  Wilco Dijkstra  <wdijkstr@arm.com>
> 
> 	* gcc/config/aarch64/aarch64.c (generic_tunings): Update prefetch model.
> 

OK.  The consensus seems to be in favour of this.

R.

> --
> diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
> index 8b729b1b1f87316e940d7fc657f235a935ffa93e..b249ce2b310707c7ded2827d505ce2ddfcfbf976 100644
> --- a/gcc/config/aarch64/aarch64.c
> +++ b/gcc/config/aarch64/aarch64.c
> @@ -547,7 +547,7 @@ static const struct tune_params generic_tunings =
>    2,	/* min_div_recip_mul_df.  */
>    0,	/* max_case_values.  */
>    0,	/* cache_line_size.  */
> -  tune_params::AUTOPREFETCHER_OFF,	/* autoprefetcher_model.  */
> +  tune_params::AUTOPREFETCHER_WEAK,	/* autoprefetcher_model.  */
>    (AARCH64_EXTRA_TUNE_NONE)	/* tune_flags.  */
>  };
> 

^ permalink raw reply	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2017-05-04 10:28 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-04-05 12:38 [PATCH][AArch64] Enable AUTOPREFETCHER_WEAK with -mcpu=generic Wilco Dijkstra
2017-04-05 16:17 ` Andrew Pinski
2017-04-05 16:44 ` Jim Wilson
2017-04-20 15:53 ` Wilco Dijkstra
2017-05-04 10:29 ` Richard Earnshaw (lists)

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).