diff mbox

Fix PR61680

Message ID alpine.LSU.2.11.1407071621170.5753@zhemvz.fhfr.qr
State New
Headers show

Commit Message

Richard Biener July 7, 2014, 2:22 p.m. UTC 
The following fixes PR61680.

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

Richard.

2014-07-07  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/61680
	* tree-vect-data-refs.c (vect_analyze_data_ref_dependence):
	Handle properly all read-write dependences with group accesses.

	* gcc.dg/vect/pr61680.c: New testcase.
diff mbox

Patch

Index: gcc/tree-vect-data-refs.c
===================================================================
--- gcc/tree-vect-data-refs.c	(revision 212323)
+++ gcc/tree-vect-data-refs.c	(working copy)
@@ -375,11 +397,14 @@  vect_analyze_data_ref_dependence (struct
 		.. = a[i+1];
 	     where we will end up loading { a[i], a[i+1] } once, make
 	     sure that inserting group loads before the first load and
-	     stores after the last store will do the right thing.  */
-	  if ((STMT_VINFO_GROUPED_ACCESS (stmtinfo_a)
-	       && GROUP_SAME_DR_STMT (stmtinfo_a))
-	      || (STMT_VINFO_GROUPED_ACCESS (stmtinfo_b)
-		  && GROUP_SAME_DR_STMT (stmtinfo_b)))
+	     stores after the last store will do the right thing.
+	     Similar for groups like
+	        a[i] = ...;
+		... = a[i];
+		a[i+1] = ...;
+	     where loads from the group interleave with the store.  */
+	  if (STMT_VINFO_GROUPED_ACCESS (stmtinfo_a)
+	      || STMT_VINFO_GROUPED_ACCESS (stmtinfo_b))
 	    {
 	      gimple earlier_stmt;
 	      earlier_stmt = get_earlier_stmt (DR_STMT (dra), DR_STMT (drb));
Index: gcc/testsuite/gcc.dg/vect/pr61680.c
===================================================================
--- gcc/testsuite/gcc.dg/vect/pr61680.c	(revision 0)
+++ gcc/testsuite/gcc.dg/vect/pr61680.c	(working copy)
@@ -0,0 +1,51 @@ 
+/* { dg-do run } */
+
+#include "tree-vect.h"
+
+double v[4096][4];
+
+__attribute__((noinline, noclone)) void
+bar (double p[][4])
+{
+  int i;
+  double d = 172.0;
+  for (i = 0; i < 4096; i++)
+    {
+      if (p[i][0] != 6.0 || p[i][1] != 6.0 || p[i][2] != 10.0)
+	__builtin_abort ();
+      if (__builtin_fabs (p[i][3] - d) > 0.25)
+	__builtin_abort ();
+    }
+}
+
+__attribute__((noinline, noclone)) void
+foo (void)
+{
+  int i;
+  double w[4096][4], t;
+  for (i = 0; i < 4096; i++)
+    {
+      w[i][0] = v[i][0] + 2.0;
+      w[i][1] = v[i][1] + 1.0;
+      w[i][2] = v[i][2] + 4.0;
+      w[i][3] = (w[i][0] * w[i][0] + w[i][1] * w[i][1] + w[i][2] * w[i][2]);
+    }
+  bar (w);
+}
+
+int
+main ()
+{
+  int i;
+
+  check_vect ();
+
+  for (i = 0; i < 4096; i++)
+    {
+      v[i][0] = 4.0;
+      v[i][1] = 5.0;
+      v[i][2] = 6.0;
+    }
+  foo ();
+  return 0;
+}