We're making vector construction extra costly but too much
because we up to now do not know the actual vector composition
type used. This makes use of this now available information.
Bootstrapped and tested on x86_64-unknown-linux-gnu.
OK?
Thanks,
Richard.
* config/i386/i386.cc (ix86_vector_costs::add_stmt_cost):
Use vector construction scaling also for mult-lane
VMAT_STRIDED_SLP but use vector composition type recorded
to avoid excessive over-costing.
---
gcc/config/i386/i386.cc | 13 +++++++++----
1 file changed, 9 insertions(+), 4 deletions(-)
diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index bd0ecfddbbc..4aa57f08dce 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -26730,15 +26730,20 @@ ix86_vector_costs::add_stmt_cost (int count,
vect_cost_for_stmt kind,
if ((kind == vec_construct || kind == vec_to_scalar)
&& ((node
&& (((SLP_TREE_MEMORY_ACCESS_TYPE (node) == VMAT_ELEMENTWISE
- || (SLP_TREE_MEMORY_ACCESS_TYPE (node) == VMAT_STRIDED_SLP
- && SLP_TREE_LANES (node) == 1))
+ || SLP_TREE_MEMORY_ACCESS_TYPE (node) == VMAT_STRIDED_SLP)
&& (TREE_CODE (DR_STEP (STMT_VINFO_DATA_REF
(SLP_TREE_REPRESENTATIVE (node))))
!= INTEGER_CST))
|| mat_gather_scatter_p (SLP_TREE_MEMORY_ACCESS_TYPE (node))))))
{
- stmt_cost = ix86_default_vector_cost (kind, mode);
- stmt_cost *= (TYPE_VECTOR_SUBPARTS (vectype) + 1);
+ auto lsdata = static_cast<vect_load_store_data *> (node->data);
+ tree ls_type = lsdata->ls_type ? lsdata->ls_type : vectype;
+ tree ls_eltype
+ = lsdata->ls_eltype ? lsdata->ls_eltype : TREE_TYPE (ls_type);
+ stmt_cost = ix86_vector_cd_cost (TYPE_MODE (ls_type),
+ TYPE_MODE (ls_eltype));
+ stmt_cost *= (GET_MODE_BITSIZE (TYPE_MODE (ls_type))
+ / GET_MODE_BITSIZE (TYPE_MODE (ls_eltype)) + 1);
}
else if ((kind == vec_construct || kind == scalar_to_vec)
&& node
--
2.51.0
