diff options
| author | Richard Biener <rguenther@suse.de> | 2023-11-08 15:18:21 +0100 |
|---|---|---|
| committer | Richard Biener <rguenther@suse.de> | 2023-11-08 16:35:36 +0100 |
| commit | c49e0c57b22e68e1aa89204f300dc5d61b42d812 (patch) | |
| tree | b6fe02eb184806bfbc7ebd6dbd1c14230e8c5c16 | |
| parent | 8cf7b936d44c37558b518cbbea4b21ed502b651e (diff) | |
| download | gcc-c49e0c57b22e68e1aa89204f300dc5d61b42d812.zip gcc-c49e0c57b22e68e1aa89204f300dc5d61b42d812.tar.gz gcc-c49e0c57b22e68e1aa89204f300dc5d61b42d812.tar.bz2 | |
Fix SLP of masked loads
The following adjusts things to use the correct mask operand for
the SLP of masked loads and gathers. Test coverage is from
runtime fails of i386 specific AVX512 tests when enabling single-lane
SLP.
* tree-vect-stmts.cc (vectorizable_load): Use the correct
vectorized mask operand.
| -rw-r--r-- | gcc/tree-vect-stmts.cc | 11 |
1 files changed, 4 insertions, 7 deletions
diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc index 65883e0..096a857 100644 --- a/gcc/tree-vect-stmts.cc +++ b/gcc/tree-vect-stmts.cc @@ -10920,9 +10920,6 @@ vectorizable_load (vec_info *vinfo, gsi, stmt_info, bump); } - if (mask && !costing_p) - vec_mask = vec_masks[j]; - gimple *new_stmt = NULL; for (i = 0; i < vec_num; i++) { @@ -10931,6 +10928,8 @@ vectorizable_load (vec_info *vinfo, tree bias = NULL_TREE; if (!costing_p) { + if (mask) + vec_mask = vec_masks[vec_num * j + i]; if (loop_masks) final_mask = vect_get_loop_mask (loop_vinfo, gsi, loop_masks, @@ -11285,8 +11284,6 @@ vectorizable_load (vec_info *vinfo, at_loop, offset, &dummy, gsi, &ptr_incr, simd_lane_access_p, bump); - if (mask) - vec_mask = vec_masks[0]; } else if (!costing_p) { @@ -11297,8 +11294,6 @@ vectorizable_load (vec_info *vinfo, else dataref_ptr = bump_vector_ptr (vinfo, dataref_ptr, ptr_incr, gsi, stmt_info, bump); - if (mask) - vec_mask = vec_masks[j]; } if (grouped_load || slp_perm) @@ -11312,6 +11307,8 @@ vectorizable_load (vec_info *vinfo, tree bias = NULL_TREE; if (!costing_p) { + if (mask) + vec_mask = vec_masks[vec_num * j + i]; if (loop_masks) final_mask = vect_get_loop_mask (loop_vinfo, gsi, loop_masks, vec_num * ncopies, vectype, |