This is a small adjustment to the work done for PR108752 and
better reflects the cost of the generated sequence.
Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed.
PR tree-optimization/108752
* tree-vect-stmts.cc (vectorizable_operation): For bit
operations with generic word_mode vectors do not cost
an extra stmt. For plus, minus and negate also cost the
constant materialization.
---
gcc/tree-vect-stmts.cc | 19 +++++++++++++++----
1 file changed, 15 insertions(+), 4 deletions(-)
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 0022b878767..127b987cd62 100644
--- a/gcc/tree-vect-stmts.cc
+++ b/gcc/tree-vect-stmts.cc
@@ -6466,8 +6466,8 @@ vectorizable_operation (vec_info *vinfo,
{
/* The above vect_model_simple_cost call handles constants
in the prologue and (mis-)costs one of the stmts as
- vector stmt. See tree-vect-generic.cc:do_plus_minus/do_negate
- for the actual lowering that will be applied. */
+ vector stmt. See below for the actual lowering that will
+ be applied. */
unsigned n
= slp_node ? SLP_TREE_NUMBER_OF_VEC_STMTS (slp_node) : ncopies;
switch (code)
@@ -6481,9 +6481,20 @@ vectorizable_operation (vec_info *vinfo,
case NEGATE_EXPR:
n *= 4;
break;
- default:;
+ default:
+ /* Bit operations do not have extra cost and are accounted
+ as vector stmt by vect_model_simple_cost. */
+ n = 0;
+ break;
+ }
+ if (n != 0)
+ {
+ /* We also need to materialize two large constants. */
+ record_stmt_cost (cost_vec, 2, scalar_stmt, stmt_info,
+ 0, vect_prologue);
+ record_stmt_cost (cost_vec, n, scalar_stmt, stmt_info,
+ 0, vect_body);
}
- record_stmt_cost (cost_vec, n, scalar_stmt, stmt_info, 0, vect_body);
}
return true;
}
--
2.35.3
