The testcases shows single-element interleaving of size three
being exempted from permutation lowering via heuristics
(see also PR116973). But it wasn't supposed to apply to
non-power-of-two sizes so this amends the check to ensure
the sub-group is aligned even when the number of lanes is one.
Bootstrap and regtest running on x86_64-unknown-linux-gnu.
* tree-vect-slp.cc (vect_lower_load_permutations): Avoid
exempting non-power-of-two group sizes from lowering.
---
gcc/tree-vect-slp.cc | 1 +
1 file changed, 1 insertion(+)
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc
index 629c4b433ab..d35c2ea02dc 100644
--- a/gcc/tree-vect-slp.cc
+++ b/gcc/tree-vect-slp.cc
@@ -4427,6 +4427,7 @@ vect_lower_load_permutations (loop_vec_info loop_vinfo,
&& contiguous
&& (SLP_TREE_LANES (load) > 1 || loads.size () == 1)
&& pow2p_hwi (SLP_TREE_LANES (load))
+ && pow2p_hwi (group_lanes)
&& SLP_TREE_LOAD_PERMUTATION (load)[0] % SLP_TREE_LANES (load) == 0
&& group_lanes % SLP_TREE_LANES (load) == 0)
{
--
2.43.0
