[PATCH][AArch64] Update alignment for -mcpu=generic

[PATCH][AArch64] Update alignment for -mcpu=generic

[Wilco Dijkstra]

With -mcpu=generic the loop alignment is currently 4.  All but one of the
supported cores use 8 or higher.  Since using 8 provides performance gains
on several cores, it is best to use that by default.  As discussed in [1],
the jump alignment has no effect on performance, yet has a relatively high
codesize cost [2], so setting it to 4 is best.  This gives a 0.2% overall 
codesize improvement as well as performance gains in several benchmarks.
Any objections?

Bootstrap OK on AArch64, OK for stage 1?

ChangeLog:
2017-04-12  Wilco Dijkstra  <wdijkstr@arm.com>

	* config/aarch64/aarch64.c (generic_tunings): Set jump alignment to 4.
	Set loop alignment to 8.

[1] https://gcc.gnu.org/ml/gcc-patches/2017-04/msg00574.html
[2] https://gcc.gnu.org/ml/gcc-patches/2016-06/msg02075.html

---
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index c8cf7169a5d387de336920b50c83761dc0c96f3a..8b729b1b1f87316e940d7fc657f235a935ffa93e 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -538,8 +538,8 @@ static const struct tune_params generic_tunings =
   2, /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC), /* fusible_ops  */
   8,	/* function_align.  */
-  8,	/* jump_align.  */
-  4,	/* loop_align.  */
+  4,	/* jump_align.  */
+  8,	/* loop_align.  */
   2,	/* int_reassoc_width.  */
   4,	/* fp_reassoc_width.  */
   1,	/* vec_reassoc_width.  */
    

Re: [PATCH][AArch64] Update alignment for -mcpu=generic

[Wilco Dijkstra]

ping


From: Wilco Dijkstra
Sent: 12 April 2017 13:58
To: GCC Patches
Cc: nd; James Greenhalgh; jim.wilson@linaro.org; Evandro Menezes; Andrew.pinski@cavium.com
Subject: [PATCH][AArch64] Update alignment for -mcpu=generic
    
With -mcpu=generic the loop alignment is currently 4.  All but one of the
supported cores use 8 or higher.  Since using 8 provides performance gains
on several cores, it is best to use that by default.  As discussed in [1],
the jump alignment has no effect on performance, yet has a relatively high
codesize cost [2], so setting it to 4 is best.  This gives a 0.2% overall 
codesize improvement as well as performance gains in several benchmarks.
Any objections?

Bootstrap OK on AArch64, OK for stage 1?

ChangeLog:
2017-04-12  Wilco Dijkstra  <wdijkstr@arm.com>

        * config/aarch64/aarch64.c (generic_tunings): Set jump alignment to 4.
        Set loop alignment to 8.

[1] https://gcc.gnu.org/ml/gcc-patches/2017-04/msg00574.html
[2] https://gcc.gnu.org/ml/gcc-patches/2016-06/msg02075.html

---
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index c8cf7169a5d387de336920b50c83761dc0c96f3a..8b729b1b1f87316e940d7fc657f235a935ffa93e 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -538,8 +538,8 @@ static const struct tune_params generic_tunings =
   2, /* issue_rate  */
   (AARCH64_FUSE_AES_AESMC), /* fusible_ops  */
   8,   /* function_align.  */
-  8,   /* jump_align.  */
-  4,   /* loop_align.  */
+  4,   /* jump_align.  */
+  8,   /* loop_align.  */
   2,   /* int_reassoc_width.  */
   4,   /* fp_reassoc_width.  */
   1,   /* vec_reassoc_width.  */
        

Re: [PATCH][AArch64] Update alignment for -mcpu=generic

[Richard Earnshaw (lists)]

On 12/04/17 13:58, Wilco Dijkstra wrote:
> With -mcpu=generic the loop alignment is currently 4.  All but one of the
> supported cores use 8 or higher.  Since using 8 provides performance gains
> on several cores, it is best to use that by default.  As discussed in [1],
> the jump alignment has no effect on performance, yet has a relatively high
> codesize cost [2], so setting it to 4 is best.  This gives a 0.2% overall 
> codesize improvement as well as performance gains in several benchmarks.
> Any objections?
> 
> Bootstrap OK on AArch64, OK for stage 1?
> 
> ChangeLog:
> 2017-04-12  Wilco Dijkstra  <wdijkstr@arm.com>
> 
> 	* config/aarch64/aarch64.c (generic_tunings): Set jump alignment to 4.
> 	Set loop alignment to 8.
> 

OK.  It looks to me as though these two values were back-to-front.
Having loop align lower than jump align sounds just perverse.

R.

> [1] https://gcc.gnu.org/ml/gcc-patches/2017-04/msg00574.html
> [2] https://gcc.gnu.org/ml/gcc-patches/2016-06/msg02075.html
> 
> ---
> diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
> index c8cf7169a5d387de336920b50c83761dc0c96f3a..8b729b1b1f87316e940d7fc657f235a935ffa93e 100644
> --- a/gcc/config/aarch64/aarch64.c
> +++ b/gcc/config/aarch64/aarch64.c
> @@ -538,8 +538,8 @@ static const struct tune_params generic_tunings =
>    2, /* issue_rate  */
>    (AARCH64_FUSE_AES_AESMC), /* fusible_ops  */
>    8,	/* function_align.  */
> -  8,	/* jump_align.  */
> -  4,	/* loop_align.  */
> +  4,	/* jump_align.  */
> +  8,	/* loop_align.  */
>    2,	/* int_reassoc_width.  */
>    4,	/* fp_reassoc_width.  */
>    1,	/* vec_reassoc_width.  */
>     
>