re PR tree-optimization/90358 (526.blender_r train run does not finish after r270847 on znver1)

2019-05-06  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/90358
	* tree-vect-stmts.c (get_group_load_store_type): Properly
	detect unused upper half of load.
	(vectorizable_load): Likewise.

	* gcc.target/i386/pr90358.c: New testcase.

From-SVN: r270911

gcc/ChangeLog

 2019-05-06  Richard Biener  <rguenther@suse.de>
 
+	PR tree-optimization/90358
+	* tree-vect-stmts.c (get_group_load_store_type): Properly
+	detect unused upper half of load.
+	(vectorizable_load): Likewise.
+
+2019-05-06  Richard Biener  <rguenther@suse.de>
+
 	PR tree-optimization/88828
 	* tree-ssa-forwprop.c (get_bit_field_ref_def): Split out from...
 	(simplify_vector_constructor): ...here.  Handle constants in

gcc/testsuite/ChangeLog

 2019-05-06  Richard Biener  <rguenther@suse.de>
 
+	PR tree-optimization/90358
+	* gcc.target/i386/pr90358.c: New testcase.
+
+2019-05-06  Richard Biener  <rguenther@suse.de>
+
 	PR tree-optimization/88828
 	* gcc.target/i386/pr88828-0.c: New testcase.
 

gcc/testsuite/gcc.target/i386/pr90358.c

+/* PR target/90358 */
+/* { dg-do run { target { sse4_runtime } } } */
+/* { dg-options "-O3 -msse4" } */
+
+struct s { unsigned int a, b, c; };
+
+void __attribute__ ((noipa))
+foo (struct s *restrict s1, struct s *restrict s2, int n)
+{
+  for (int i = 0; i < n; ++i)
+    {
+      s1[i].b = s2[i].b;
+      s1[i].c = s2[i].c;
+      s2[i].c = 0;
+    }
+}
+                            
+#define N 12
+
+int
+main ()
+{
+  struct s s1[N], s2[N];
+  for (unsigned int j = 0; j < N; ++j)
+    {
+      s2[j].a = j * 5;
+      s2[j].b = j * 5 + 2;
+      s2[j].c = j * 5 + 4;
+    }
+  foo (s1, s2, N);
+  for (unsigned int j = 0; j < N; ++j)
+  if (s1[j].b != j * 5 + 2)
+    __builtin_abort ();
+  return 0;
+}

gcc/tree-vect-stmts.c

@@ -2273,6 +2273,7 @@ get_group_load_store_type (stmt_vec_info stmt_info, tree vectype, bool slp,
 		   == dr_aligned
 		  || alignment_support_scheme == dr_unaligned_supported)
 	      && known_eq (nunits, (group_size - gap) * 2)
+	      && known_eq (nunits, group_size)
 	      && mode_for_vector (elmode, (group_size - gap)).exists (&vmode)
 	      && VECTOR_MODE_P (vmode)
 	      && targetm.vector_mode_supported_p (vmode)
@@ -8550,7 +8551,8 @@ vectorizable_load (stmt_vec_info stmt_info, gimple_stmt_iterator *gsi,
 			    && DR_GROUP_GAP (first_stmt_info) != 0
 			    && known_eq (nunits,
 					 (group_size
-					  - DR_GROUP_GAP (first_stmt_info)) * 2))
+					  - DR_GROUP_GAP (first_stmt_info)) * 2)
+			    && known_eq (nunits, group_size))
 			  ltype = build_vector_type (TREE_TYPE (vectype),
 						     (group_size
 						      - DR_GROUP_GAP