The adjusted vector costs give Falkor a reasonable boost in performance for FP
benchmarks (both CPU2017 and CPU2006) and doesn't change INT benchmarks that
much. About 0.7% for CPU2017 FP and 1.54% for CPU2006 FP.
OK for trunk?
gcc/ChangeLog:
2018-07-25 Luis Machado <luis.mach...@linaro.org>
* config/aarch64/aarch64.c (qdf24xx_vector_cost): New.
(qdf24xx_tunings) <vec_costs>: Set to qdf24xx_vector_cost.
---
gcc/config/aarch64/aarch64.c | 22 +++++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index fa01475..d443aee 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -430,6 +430,26 @@ static const struct cpu_vector_cost generic_vector_cost =
1 /* cond_not_taken_branch_cost */
};
+/* Qualcomm QDF24xx costs for vector insn classes. */
+static const struct cpu_vector_cost qdf24xx_vector_cost =
+{
+ 1, /* scalar_int_stmt_cost */
+ 1, /* scalar_fp_stmt_cost */
+ 1, /* scalar_load_cost */
+ 1, /* scalar_store_cost */
+ 1, /* vec_int_stmt_cost */
+ 3, /* vec_fp_stmt_cost */
+ 2, /* vec_permute_cost */
+ 1, /* vec_to_scalar_cost */
+ 1, /* scalar_to_vec_cost */
+ 1, /* vec_align_load_cost */
+ 1, /* vec_unalign_load_cost */
+ 1, /* vec_unalign_store_cost */
+ 1, /* vec_store_cost */
+ 3, /* cond_taken_branch_cost */
+ 1 /* cond_not_taken_branch_cost */
+};
+
/* ThunderX costs for vector insn classes. */
static const struct cpu_vector_cost thunderx_vector_cost =
{
@@ -890,7 +910,7 @@ static const struct tune_params qdf24xx_tunings =
&qdf24xx_extra_costs,
&qdf24xx_addrcost_table,
&qdf24xx_regmove_cost,
- &generic_vector_cost,
+ &qdf24xx_vector_cost,
&generic_branch_cost,
&generic_approx_modes,
4, /* memmov_cost */
--
2.7.4
