re PR tree-optimization/53366 (wrong code generation by tree vectorizer using AVX)

	PR tree-optimization/53366
	* tree-vect-slp.c (vect_supported_load_permutation_p): Don't shortcut
	tests if complex_numbers == 2, but there are non-complex number loads
	too.

	* gcc.dg/torture/pr53366-1.c: New test.
	* gcc.dg/torture/pr53366-2.c: New test.
	* gcc.target/i386/pr53366-1.c: New test.
	* gcc.target/i386/pr53366-2.c: New test.

From-SVN: r187717

7 files changed, 136 insertions, 1 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 080975c..d7bdb99 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,10 @@
 2012-05-21  Jakub Jelinek  <jakub@redhat.com>
 
+	PR tree-optimization/53366
+	* tree-vect-slp.c (vect_supported_load_permutation_p): Don't shortcut
+	tests if complex_numbers == 2, but there are non-complex number loads
+	too.
+
 	PR tree-optimization/53409
 	* tree-vect-loop.c (vect_analyze_loop_operations): Don't check
 	vinfo_for_stmt (op_def_stmt) if op_def_stmt isn't inside loop.
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index a9ba222..1f1bcb4 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,11 @@
 2012-05-21  Jakub Jelinek  <jakub@redhat.com>
 
+	PR tree-optimization/53366
+	* gcc.dg/torture/pr53366-1.c: New test.
+	* gcc.dg/torture/pr53366-2.c: New test.
+	* gcc.target/i386/pr53366-1.c: New test.
+	* gcc.target/i386/pr53366-2.c: New test.
+
 	PR tree-optimization/53409
 	* gcc.c-torture/compile/pr53409.c: New test.
 
diff --git a/gcc/testsuite/gcc.dg/torture/pr53366-1.c b/gcc/testsuite/gcc.dg/torture/pr53366-1.c
new file mode 100644
index 0000000..ca9997e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr53366-1.c
@@ -0,0 +1,70 @@
+/* PR tree-optimization/53366 */
+/* { dg-do run } */
+
+extern void abort (void);
+
+struct S { double v[3]; };
+struct T { struct S r, i; };
+struct U { struct T j[5]; };
+
+void
+foo (struct U *__restrict p1, struct U *__restrict p2,
+     struct S l1, struct S l2, struct S l3, struct S l4,
+     const double _Complex * __restrict x, int y, int z)
+{
+  int i, j;
+  while (y < z - 2)
+    {
+      for (j = 0; j < 5; ++j)
+	{
+	  double a = __real__ x[5 * y + j];
+	  double b = __imag__ x[5 * y + j];
+	  double c = __real__ x[5 * (y + 2) + j];
+	  double d = __imag__ x[5 * (y + 2) + j];
+	  double e = __real__ x[5 * (y + 1) + j];
+	  double f = __imag__ x[5 * (y + 1) + j];
+	  double g = __real__ x[5 * (y + 3) + j];
+	  double h = __imag__ x[5 * (y + 3) + j];
+	  for (i = 0; i < 3; ++i)
+	    {
+	      p1->j[j].r.v[i] += l2.v[i] * a;
+	      p1->j[j].r.v[i] += l4.v[i] * c;
+	      p1->j[j].i.v[i] += l2.v[i] * b;
+	      p1->j[j].i.v[i] += l4.v[i] * d;
+	      p2->j[j].r.v[i] += l3.v[i] * e;
+	      p2->j[j].r.v[i] += l1.v[i] * g;
+	      p2->j[j].i.v[i] += l3.v[i] * f;
+	      p2->j[j].i.v[i] += l1.v[i] * h;
+	    }
+	}
+      y += 4;
+    }
+}
+
+_Complex double x[5005];
+struct U p1, p2;
+
+int
+main ()
+{
+  int i, j;
+  struct S l1, l2, l3, l4;
+  for (i = 0; i < 5005; ++i)
+    x[i] = i + 1.0iF * (2 * i);
+  for (i = 0; i < 3; ++i)
+    {
+      l1.v[i] = 1;
+      l2.v[i] = 2;
+      l3.v[i] = 3;
+      l4.v[i] = 4;
+    }
+  foo (&p1, &p2, l1, l2, l3, l4, x, 5, 1000);
+  for (j = 0; j < 5; ++j)
+    for (i = 0; i < 3; ++i)
+      if (p1.j[j].r.v[i] != 3752430 + j * 1494.0
+	  || p1.j[j].i.v[i] != p1.j[j].r.v[i] * 2
+	  || p2.j[j].r.v[i] != 2502450 + j * 996.0
+	  || p2.j[j].i.v[i] != p2.j[j].r.v[i] * 2)
+	abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.dg/torture/pr53366-2.c b/gcc/testsuite/gcc.dg/torture/pr53366-2.c
new file mode 100644
index 0000000..6be6a56
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr53366-2.c
@@ -0,0 +1,43 @@
+/* PR tree-optimization/53366 */
+/* { dg-do run } */
+
+extern void abort (void);
+
+struct T { float r[3], i[3]; };
+struct U { struct T j[2]; };
+
+void __attribute__ ((noinline))
+foo (struct U *__restrict y, const float _Complex *__restrict x)
+{
+  int i, j;
+  for (j = 0; j < 2; ++j)
+    {
+      float a = __real__ x[j];
+      float b = __imag__ x[j];
+      float c = __real__ x[j + 2];
+      float d = __imag__ x[j + 2];
+      for (i = 0; i < 3; ++i)
+        {
+          y->j[j].r[i] = y->j[j].r[i] + a + c;
+          y->j[j].i[i] = y->j[j].i[i] + b + d;
+        }
+    }
+}
+
+_Complex float x[4];
+struct U y;
+
+int
+main ()
+{
+  int i, j;
+  for (i = 0; i < 4; ++i)
+    x[i] = i + 1.0iF * (2 * i);
+  foo (&y, x);
+  for (j = 0; j < 2; ++j)
+    for (i = 0; i < 3; ++i)
+      if (y.j[j].r[i] != __real__ (x[j] + x[j + 2])
+          || y.j[j].i[i] != __imag__ (x[j] + x[j + 2]))
+        __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr53366-1.c b/gcc/testsuite/gcc.target/i386/pr53366-1.c
new file mode 100644
index 0000000..c24a594
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr53366-1.c
@@ -0,0 +1,5 @@
+/* PR tree-optimization/53366 */
+/* { dg-do run { target avx_runtime } } */
+/* { dg-options "-O3 -mavx" } */
+
+#include "../../gcc.dg/torture/pr53366-1.c"
diff --git a/gcc/testsuite/gcc.target/i386/pr53366-2.c b/gcc/testsuite/gcc.target/i386/pr53366-2.c
new file mode 100644
index 0000000..77270a0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr53366-2.c
@@ -0,0 +1,5 @@
+/* PR tree-optimization/53366 */
+/* { dg-do run { target avx_runtime } } */
+/* { dg-options "-O3 -mavx" } */
+
+#include "../../gcc.dg/torture/pr53366-2.c"
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index e189c50..4690a4e 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -1199,7 +1199,8 @@ vect_supported_load_permutation_p (slp_instance slp_instn, int group_size,
 
   /* We checked that this case ok, so there is no need to proceed with 
      permutation tests.  */
-  if (complex_numbers == 2)
+  if (complex_numbers == 2
+      && VEC_length (slp_tree, SLP_INSTANCE_LOADS (slp_instn)) == 2)
     {
       VEC_free (slp_tree, heap, SLP_INSTANCE_LOADS (slp_instn));
       VEC_free (int, heap, SLP_INSTANCE_LOAD_PERMUTATION (slp_instn));