2008-01-08 Jan Sjodin <jan.sjodin@amd.com>

       * config/i386/i386.c:
        (k8_cost, amdfam10_cost): Branch costs for vectorization tuned.

From-SVN: r131401

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3bf8fb163375cf961b8c9dc200831eb5f6154517..d163f6ac4047dcf2ea12649312b2a541acb61f8c 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2008-01-08  Jan Sjodin  <jan.sjodin@amd.com>
+       
+       * config/i386/i386.c:
+       (k8_cost, amdfam10_cost): Branch costs for vectorization tuned.
+       
 2008-01-08  Richard Guenther  <rguenther@suse.de>
 
        PR tree-optimization/34683

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 0f827a6de9b2909f0bb3fda36bbe99696c9723a9..599f8646e1bca218c522939bbd034084d0ac9940 100644 (file)
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -701,7 +701,7 @@ struct processor_costs k8_cost = {
      to limit number of prefetches at all, as their execution also takes some
      time).  */
   100,                                 /* number of parallel prefetches */
-  5,                                   /* Branch cost */
+  3,                                   /* Branch cost */
   COSTS_N_INSNS (4),                   /* cost of FADD and FSUB insns.  */
   COSTS_N_INSNS (4),                   /* cost of FMUL instruction.  */
   COSTS_N_INSNS (19),                  /* cost of FDIV instruction.  */
@@ -725,8 +725,8 @@ struct processor_costs k8_cost = {
   2,                                    /* vec_align_load_cost.  */
   3,                                    /* vec_unalign_load_cost.  */
   3,                                    /* vec_store_cost.  */
-  6,                                    /* cond_taken_branch_cost.  */
-  1,                                    /* cond_not_taken_branch_cost.  */
+  3,                                    /* cond_taken_branch_cost.  */
+  2,                                    /* cond_not_taken_branch_cost.  */
 };
 
 struct processor_costs amdfam10_cost = {
@@ -787,7 +787,7 @@ struct processor_costs amdfam10_cost = {
      to limit number of prefetches at all, as their execution also takes some
      time).  */
   100,                                 /* number of parallel prefetches */
-  5,                                   /* Branch cost */
+  2,                                   /* Branch cost */
   COSTS_N_INSNS (4),                   /* cost of FADD and FSUB insns.  */
   COSTS_N_INSNS (4),                   /* cost of FMUL instruction.  */
   COSTS_N_INSNS (19),                  /* cost of FDIV instruction.  */
@@ -812,7 +812,7 @@ struct processor_costs amdfam10_cost = {
   2,                                    /* vec_align_load_cost.  */
   2,                                    /* vec_unalign_load_cost.  */
   2,                                    /* vec_store_cost.  */
-  6,                                    /* cond_taken_branch_cost.  */
+  2,                                    /* cond_taken_branch_cost.  */
   1,                                    /* cond_not_taken_branch_cost.  */
 };