diff mbox series

[1/4] Fix SLP of masked loads

Message ID 20231108150254.8F9F9133F5@imap2.suse-dmz.suse.de
State New
Headers show
Series [1/4] Fix SLP of masked loads | expand

Commit Message

Richard Biener Nov. 8, 2023, 3:02 p.m. UTC 
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.

Bootstrap and regtest running on x86_64-unknown-linux-gnu.

	* tree-vect-stmts.cc (vectorizable_load): Use the correct
	vectorized mask operand.
---
 gcc/tree-vect-stmts.cc | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)
diff mbox series

Patch

diff --git a/gcc/tree-vect-stmts.cc b/gcc/tree-vect-stmts.cc
index 65883e04ad7..096a857f2dd 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,