This fixes a double-counting in the reduction cost when vectorizing
the reduction through the regular vectorizable_* functions.
Bootstrapped / tested on x86_64-unknown-linux-gnu, pushed.
2021-01-11 Richard Biener <rguent...@suse.de>
PR tree-optimization/98526
* tree-vect-loop.c (vect_model_reduction_cost): Remove costing
of the actual reduction op for the regular case.
(vectorizable_reduction): Cost the stmts
vect_transform_reduction produces here.
---
gcc/tree-vect-loop.c | 17 +++++++++++------
1 file changed, 11 insertions(+), 6 deletions(-)
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 965cc164f6e..acfd1952e3b 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -4452,8 +4452,8 @@ have_whole_vector_shift (machine_mode mode)
/* Function vect_model_reduction_cost.
Models cost for a reduction operation, including the vector ops
- generated within the strip-mine loop, the initial definition before
- the loop, and the epilogue code that must be generated. */
+ generated within the strip-mine loop in some cases, the initial
+ definition before the loop, and the epilogue code that must be generated.
*/
static void
vect_model_reduction_cost (loop_vec_info loop_vinfo,
@@ -4516,10 +4516,6 @@ vect_model_reduction_cost (loop_vec_info loop_vinfo,
prologue_cost += record_stmt_cost (cost_vec, prologue_stmts,
scalar_to_vec, stmt_info, 0,
vect_prologue);
-
- /* Cost of reduction op inside loop. */
- inside_cost = record_stmt_cost (cost_vec, ncopies, vector_stmt,
- stmt_info, 0, vect_body);
}
/* Determine cost of epilogue code.
@@ -7268,6 +7264,15 @@ vectorizable_reduction (loop_vec_info loop_vinfo,
vect_model_reduction_cost (loop_vinfo, stmt_info, reduc_fn,
reduction_type, ncopies, cost_vec);
+ /* Cost the reduction op inside the loop if transformed via
+ vect_transform_reduction. Otherwise this is costed by the
+ separate vectorizable_* routines. */
+ if (single_defuse_cycle
+ || code == DOT_PROD_EXPR
+ || code == WIDEN_SUM_EXPR
+ || code == SAD_EXPR)
+ record_stmt_cost (cost_vec, ncopies, vector_stmt, stmt_info, 0, vect_body);
+
if (dump_enabled_p ()
&& reduction_type == FOLD_LEFT_REDUCTION)
dump_printf_loc (MSG_NOTE, vect_location,
--
2.26.2
