[gcc r12-1769] Fix SLP permute propagation error
Richard Biener
rguenth@gcc.gnu.org
Thu Jun 24 09:42:18 GMT 2021
https://gcc.gnu.org/g:82ab14927651e0eaf0f6d6964396048bb5471f23
commit r12-1769-g82ab14927651e0eaf0f6d6964396048bb5471f23
Author: Richard Biener <rguenther@suse.de>
Date: Thu Jun 24 10:47:18 2021 +0200
Fix SLP permute propagation error
This fixes SLP permute propagation to not propagate across operations
that have different semantics on different lanes like for example
the recently added COMPLEX_ADD_ROT90.
2021-06-24 Richard Biener <rguenther@suse.de>
* tree-vect-slp.c (vect_optimize_slp): Do not propagate
across operations that have different semantics on different
lanes.
Diff:
---
gcc/tree-vect-slp.c | 30 +++++++++++++++++++++++-------
1 file changed, 23 insertions(+), 7 deletions(-)
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index 29db56ed532..69ee8faed09 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -3680,18 +3680,34 @@ vect_optimize_slp (vec_info *vinfo)
{
int idx = ipo[i-1];
slp_tree node = vertices[idx].node;
- /* For leafs there's nothing to do - we've seeded permutes
- on those above. */
- if (SLP_TREE_DEF_TYPE (node) != vect_internal_def)
+
+ /* Handle externals and constants optimistically throughout the
+ iteration. */
+ if (SLP_TREE_DEF_TYPE (node) == vect_external_def
+ || SLP_TREE_DEF_TYPE (node) == vect_constant_def)
continue;
vertices[idx].visited = 1;
- /* We cannot move a permute across a store. */
- if (STMT_VINFO_DATA_REF (SLP_TREE_REPRESENTATIVE (node))
- && DR_IS_WRITE
- (STMT_VINFO_DATA_REF (SLP_TREE_REPRESENTATIVE (node))))
+ /* We do not handle stores with a permutation. */
+ stmt_vec_info rep = SLP_TREE_REPRESENTATIVE (node);
+ if (STMT_VINFO_DATA_REF (rep)
+ && DR_IS_WRITE (STMT_VINFO_DATA_REF (rep)))
continue;
+ /* We cannot move a permute across an operation that is
+ not independent on lanes. Note this is an explicit
+ negative list since that's much shorter than the respective
+ positive one but it's critical to keep maintaining it. */
+ if (is_gimple_call (STMT_VINFO_STMT (rep)))
+ switch (gimple_call_combined_fn (STMT_VINFO_STMT (rep)))
+ {
+ case CFN_COMPLEX_ADD_ROT90:
+ case CFN_COMPLEX_ADD_ROT270:
+ case CFN_COMPLEX_MUL:
+ case CFN_COMPLEX_MUL_CONJ:
+ continue;
+ default:;
+ }
int perm = -1;
for (graph_edge *succ = slpg->vertices[idx].succ;
More information about the Gcc-cvs
mailing list