aarch64: update ampere1 vectorization cost

The original submission of AmpereOne (-mcpu=ampere1) costs occurred
prior to exhaustive testing of vectorizable workloads against
hardware.

Adjust the vector costs to achieve the best results and more closely
match the underlying hardware.

gcc/ChangeLog:

	* config/aarch64/aarch64.cc: Update vector costs for ampere1.

Co-Authored-By: Jiangning Liu <jiangning.liu@amperecomputing.com>
Co-Authored-By: Manolis Tsamis <manolis.tsamis@vrull.eu>
(cherry picked from commit ff1f2f2412bda118f7ddc10e69bd4284d9b24b9e)

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index a49618ac0ead4d2951b457748022586cfdcc1800..ce3dcdcd754ce327094af2b30ae1b766f50240c4 100644 (file)
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -1137,7 +1137,7 @@ static const struct cpu_vector_cost thunderx3t110_vector_cost =
 
 static const advsimd_vec_cost ampere1_advsimd_vector_cost =
 {
-  3, /* int_stmt_cost  */
+  1, /* int_stmt_cost  */
   3, /* fp_stmt_cost  */
   0, /* ld2_st2_permute_cost  */
   0, /* ld3_st3_permute_cost  */
@@ -1153,17 +1153,17 @@ static const advsimd_vec_cost ampere1_advsimd_vector_cost =
   8, /* store_elt_extra_cost  */
   6, /* vec_to_scalar_cost  */
   7, /* scalar_to_vec_cost  */
-  5, /* align_load_cost  */
-  5, /* unalign_load_cost  */
-  2, /* unalign_store_cost  */
-  2  /* store_cost  */
+  4, /* align_load_cost  */
+  4, /* unalign_load_cost  */
+  1, /* unalign_store_cost  */
+  1  /* store_cost  */
 };
 
 /* Ampere-1 costs for vector insn classes.  */
 static const struct cpu_vector_cost ampere1_vector_cost =
 {
   1, /* scalar_int_stmt_cost  */
-  1, /* scalar_fp_stmt_cost  */
+  3, /* scalar_fp_stmt_cost  */
   4, /* scalar_load_cost  */
   1, /* scalar_store_cost  */
   1, /* cond_taken_branch_cost  */