This patch sets the branch cost to the same most optimal setting for all Cortex cores...

This patch sets the branch cost to the same most optimal setting for all Cortex
cores, reducing codesize and improving performance due to using more CSEL
instructions.  Set the autoprefetcher model in Cortex-A72 to weak like the
others.  Enable AES fusion in Cortex-A35.  As a result generated code is now
more similar as well as more optimal across Cortex cores.

    gcc/
	* config/aarch64/aarch64.c (cortexa35_tunings):
	Enable AES fusion.  Use cortexa57_branch_cost.
	(cortexa53_tunings): Use cortexa57_branch_cost.
	(cortexa72_tunings): Use cortexa57_branch_cost.
	Use AUTOPREFETCHER_WEAK.
	(cortexa73_tunings): Use cortexa57_branch_cost.

From-SVN: r237884

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index da6956aafc9abcfae9f14fe815ac896a37a97dbc..88cab9847da939446a5fe883b4db2c6f463c115f 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,12 @@
+2016-06-30  Wilco Dijkstra  <wdijkstr@arm.com>
+
+       * config/aarch64/aarch64.c (cortexa35_tunings):
+       Enable AES fusion.  Use cortexa57_branch_cost.
+       (cortexa53_tunings): Use cortexa57_branch_cost.
+       (cortexa72_tunings): Use cortexa57_branch_cost.
+       Use AUTOPREFETCHER_WEAK.
+       (cortexa73_tunings): Use cortexa57_branch_cost.
+
 2016-06-30  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
             James Greenhalgh  <james.greenhalgh@arm.com>
 

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 356cb7ec6b8d01bec2c641ed9f49b7795b138d31..062899fbcc8840769cc09bef6194e546bc813e86 100644 (file)
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -473,11 +473,11 @@ static const struct tune_params cortexa35_tunings =
   &generic_addrcost_table,
   &cortexa53_regmove_cost,
   &generic_vector_cost,
-  &generic_branch_cost,
+  &cortexa57_branch_cost,
   &generic_approx_modes,
   4, /* memmov_cost  */
   1, /* issue_rate  */
-  (AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
+  (AARCH64_FUSE_AES_AESMC | AARCH64_FUSE_MOV_MOVK | AARCH64_FUSE_ADRP_ADD
    | AARCH64_FUSE_MOVK_MOVK | AARCH64_FUSE_ADRP_LDR), /* fusible_ops  */
   16,  /* function_align.  */
   8,   /* jump_align.  */
@@ -499,7 +499,7 @@ static const struct tune_params cortexa53_tunings =
   &generic_addrcost_table,
   &cortexa53_regmove_cost,
   &generic_vector_cost,
-  &generic_branch_cost,
+  &cortexa57_branch_cost,
   &generic_approx_modes,
   4, /* memmov_cost  */
   2, /* issue_rate  */
@@ -551,7 +551,7 @@ static const struct tune_params cortexa72_tunings =
   &cortexa57_addrcost_table,
   &cortexa57_regmove_cost,
   &cortexa57_vector_cost,
-  &generic_branch_cost,
+  &cortexa57_branch_cost,
   &generic_approx_modes,
   4, /* memmov_cost  */
   3, /* issue_rate  */
@@ -567,7 +567,7 @@ static const struct tune_params cortexa72_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.  */
 };
 
@@ -577,7 +577,7 @@ static const struct tune_params cortexa73_tunings =
   &cortexa57_addrcost_table,
   &cortexa57_regmove_cost,
   &cortexa57_vector_cost,
-  &generic_branch_cost,
+  &cortexa57_branch_cost,
   &generic_approx_modes,
   4, /* memmov_cost.  */
   2, /* issue_rate.  */