diff options
| author | Richard Biener <rguenther@suse.de> | 2024-10-10 11:02:47 +0200 |
|---|---|---|
| committer | Richard Biener <rguenth@gcc.gnu.org> | 2024-10-16 13:02:53 +0200 |
| commit | ae224de0631a7fcac37ac1384f457f1dc1a487b2 (patch) | |
| tree | b9d1110455844444547b4285ac3d1e36393cabbe | |
| parent | 962a994d57f5b39c92d26b0446dbe6de9aa8910a (diff) | |
| download | gcc-ae224de0631a7fcac37ac1384f457f1dc1a487b2.zip gcc-ae224de0631a7fcac37ac1384f457f1dc1a487b2.tar.gz gcc-ae224de0631a7fcac37ac1384f457f1dc1a487b2.tar.bz2 | |
tree-optimization/117050 - fix ICE with non-grouped .MASK_LOAD SLP
The following is a more complete fix for PR117050, restoring the
ability to permute non-grouped .MASK_LOAD with.
PR tree-optimization/117050
* tree-vect-slp.cc (vect_build_slp_tree_2): Properly handle
non-grouped masked loads when handling permutations.
| -rw-r--r-- | gcc/tree-vect-slp.cc | 18 |
1 files changed, 9 insertions, 9 deletions
diff --git a/gcc/tree-vect-slp.cc b/gcc/tree-vect-slp.cc index f053198..629c4b4 100644 --- a/gcc/tree-vect-slp.cc +++ b/gcc/tree-vect-slp.cc @@ -1991,7 +1991,8 @@ vect_build_slp_tree_2 (vec_info *vinfo, slp_tree node, stmt_vec_info load_info; load_permutation.create (group_size); stmt_vec_info first_stmt_info - = DR_GROUP_FIRST_ELEMENT (SLP_TREE_SCALAR_STMTS (node)[0]); + = STMT_VINFO_GROUPED_ACCESS (stmt_info) + ? DR_GROUP_FIRST_ELEMENT (stmt_info) : stmt_info; bool any_permute = false; bool any_null = false; FOR_EACH_VEC_ELT (SLP_TREE_SCALAR_STMTS (node), j, load_info) @@ -2035,8 +2036,7 @@ vect_build_slp_tree_2 (vec_info *vinfo, slp_tree node, loads with gaps. */ if ((STMT_VINFO_GROUPED_ACCESS (stmt_info) && (DR_GROUP_GAP (first_stmt_info) != 0 || has_gaps)) - || STMT_VINFO_STRIDED_P (stmt_info) - || (!STMT_VINFO_GROUPED_ACCESS (stmt_info) && any_permute)) + || STMT_VINFO_STRIDED_P (stmt_info)) { load_permutation.release (); matches[0] = false; @@ -2051,17 +2051,17 @@ vect_build_slp_tree_2 (vec_info *vinfo, slp_tree node, { /* Discover the whole unpermuted load. */ vec<stmt_vec_info> stmts2; - stmts2.create (DR_GROUP_SIZE (first_stmt_info)); - stmts2.quick_grow_cleared (DR_GROUP_SIZE (first_stmt_info)); + unsigned dr_group_size = STMT_VINFO_GROUPED_ACCESS (stmt_info) + ? DR_GROUP_SIZE (first_stmt_info) : 1; + stmts2.create (dr_group_size); + stmts2.quick_grow_cleared (dr_group_size); unsigned i = 0; for (stmt_vec_info si = first_stmt_info; si; si = DR_GROUP_NEXT_ELEMENT (si)) stmts2[i++] = si; - bool *matches2 - = XALLOCAVEC (bool, DR_GROUP_SIZE (first_stmt_info)); + bool *matches2 = XALLOCAVEC (bool, dr_group_size); slp_tree unperm_load - = vect_build_slp_tree (vinfo, stmts2, - DR_GROUP_SIZE (first_stmt_info), + = vect_build_slp_tree (vinfo, stmts2, dr_group_size, &this_max_nunits, matches2, limit, &this_tree_size, bst_map); /* When we are able to do the full masked load emit that |