re PR tree-optimization/58453 (Revision 202431 results in miscompare for CPU2006 434.zeusmp)

2013-09-20  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/58453
	* tree-loop-distribution.c (distribute_loop): Apply the cost
	model for -ftree-loop-distribute-patterns, too.

	* gcc.dg/tree-ssa/ldist-23.c: New testcase.

From-SVN: r202775

4 files changed, 86 insertions, 40 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 14c3016..e4e4a69 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,11 @@
 2013-09-20  Richard Biener  <rguenther@suse.de>
 
+	PR tree-optimization/58453
+	* tree-loop-distribution.c (distribute_loop): Apply the cost
+	model for -ftree-loop-distribute-patterns, too.
+
+2013-09-20  Richard Biener  <rguenther@suse.de>
+
 	PR middle-end/58473
 	* tree-chrec.h (build_polynomial_chrec): Use gcc_checking_assert,
 	make type comparison less strict.
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 203fd13..8d287f1 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2013-09-20  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/58453
+	* gcc.dg/tree-ssa/ldist-23.c: New testcase.
+
 2013-09-20  Janus Weil  <janus@gcc.gnu.org>
 
 	PR fortran/58099
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ldist-23.c b/gcc/testsuite/gcc.dg/tree-ssa/ldist-23.c
new file mode 100644
index 0000000..22b82d9
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ldist-23.c
@@ -0,0 +1,34 @@
+/* { dg-do run } */
+/* { dg-options "-O3 -fdump-tree-ldist-details" } */
+
+extern void abort (void);
+
+int a[128], b[128], c[128], d[128];
+
+void __attribute__((noinline,noclone))
+foo (void)
+{
+  int i;
+  for (i = 0; i < 128; ++i)
+    {
+      a[i] = a[i] + 1;
+      b[i] = d[i];
+      c[i] = a[i] / d[i];
+    }
+}
+int main()
+{
+  int i;
+  for (i = 0; i < 128; ++i)
+    a[i] = i;
+  for (i = 0; i < 128; ++i)
+    d[i] = 1;
+  foo ();
+  if (c[0] != 1)
+    abort ();
+  return 0;
+}
+
+/* { dg-final { scan-tree-dump "split to 2 loops" "ldist" } } */
+/* { dg-final { scan-tree-dump "generated memcpy" "ldist" } } */
+/* { dg-final { cleanup-tree-dump "ldist" } } */
diff --git a/gcc/tree-loop-distribution.c b/gcc/tree-loop-distribution.c
index 7482d8c..51b6ef0 100644
--- a/gcc/tree-loop-distribution.c
+++ b/gcc/tree-loop-distribution.c
@@ -1514,18 +1514,51 @@ distribute_loop (struct loop *loop, vec<gimple> stmts,
       any_builtin |= partition_builtin_p (partition);
     }
 
+  /* If we did not detect any builtin but are not asked to apply
+     regular loop distribution simply bail out.  */
+  if (!flag_tree_loop_distribution
+      && !any_builtin)
+    {
+      nbp = 0;
+      goto ldist_done;
+    }
+
+  /* Apply our simple cost model - fuse partitions with similar
+     memory accesses.  */
+  partition_t into;
+  for (i = 0; partitions.iterate (i, &into); ++i)
+    {
+      if (partition_builtin_p (into))
+	continue;
+      for (int j = i + 1;
+	   partitions.iterate (j, &partition); ++j)
+	{
+	  if (!partition_builtin_p (partition)
+	      && similar_memory_accesses (rdg, into, partition))
+	    {
+	      if (dump_file && (dump_flags & TDF_DETAILS))
+		{
+		  fprintf (dump_file, "fusing partitions\n");
+		  dump_bitmap (dump_file, into->stmts);
+		  dump_bitmap (dump_file, partition->stmts);
+		  fprintf (dump_file, "because they have similar "
+			   "memory accesses\n");
+		}
+	      bitmap_ior_into (into->stmts, partition->stmts);
+	      if (partition->kind == PKIND_REDUCTION)
+		into->kind = PKIND_REDUCTION;
+	      partitions.ordered_remove (j);
+	      partition_free (partition);
+	      j--;
+	    }
+	}
+    }
+
   /* If we are only distributing patterns fuse all partitions that
-     were not properly classified as builtins.  Else fuse partitions
-     with similar memory accesses.  */
+     were not properly classified as builtins.  */
   if (!flag_tree_loop_distribution)
     {
       partition_t into;
-      /* If we did not detect any builtin simply bail out.  */
-      if (!any_builtin)
-	{
-	  nbp = 0;
-	  goto ldist_done;
-	}
       /* Only fuse adjacent non-builtin partitions, see PR53616.
          ???  Use dependence information to improve partition ordering.  */
       i = 0;
@@ -1549,38 +1582,6 @@ distribute_loop (struct loop *loop, vec<gimple> stmts,
 	}
       while ((unsigned) i < partitions.length ());
     }
-  else
-    {
-      partition_t into;
-      int j;
-      for (i = 0; partitions.iterate (i, &into); ++i)
-	{
-	  if (partition_builtin_p (into))
-	    continue;
-	  for (j = i + 1;
-	       partitions.iterate (j, &partition); ++j)
-	    {
-	      if (!partition_builtin_p (partition)
-		  && similar_memory_accesses (rdg, into, partition))
-		{
-		  if (dump_file && (dump_flags & TDF_DETAILS))
-		    {
-		      fprintf (dump_file, "fusing partitions\n");
-		      dump_bitmap (dump_file, into->stmts);
-		      dump_bitmap (dump_file, partition->stmts);
-		      fprintf (dump_file, "because they have similar "
-			       "memory accesses\n");
-		    }
-		  bitmap_ior_into (into->stmts, partition->stmts);
-		  if (partition->kind == PKIND_REDUCTION)
-		    into->kind = PKIND_REDUCTION;
-		  partitions.ordered_remove (j);
-		  partition_free (partition);
-		  j--;
-		}
-	    }
-	}
-    }
 
   /* Fuse all reduction partitions into the last.  */
   if (partitions.length () > 1)