re PR tree-optimization/70354 (Wrong code with -O3 -march=broadwell and -march=skylake-avx512.)

	PR tree-optimization/70354
	* tree-vect-patterns.c (vect_recog_vector_vector_shift_pattern): If
	oprnd0 is wider than oprnd1 and there is a cast from the wider
	type to oprnd1, mask it with the mask of the narrower type.

	* gcc.dg/vect/pr70354-1.c: New test.
	* gcc.dg/vect/pr70354-2.c: New test.
	* gcc.target/i386/avx2-pr70354-1.c: New test.
	* gcc.target/i386/avx2-pr70354-2.c: New test.

From-SVN: r234417

gcc/ChangeLog

 2016-03-23  Jakub Jelinek  <jakub@redhat.com>
 
+	PR tree-optimization/70354
+	* tree-vect-patterns.c (vect_recog_vector_vector_shift_pattern): If
+	oprnd0 is wider than oprnd1 and there is a cast from the wider
+	type to oprnd1, mask it with the mask of the narrower type.
+
 	PR target/70321
 	* config/i386/i386.md (*anddi3_doubleword, *<code>di3_doubleword):
 	Optimize TARGET_STV splitters, if high or low word of last argument

gcc/testsuite/ChangeLog

+2016-03-23  Jakub Jelinek  <jakub@redhat.com>
+
+	PR tree-optimization/70354
+	* gcc.dg/vect/pr70354-1.c: New test.
+	* gcc.dg/vect/pr70354-2.c: New test.
+	* gcc.target/i386/avx2-pr70354-1.c: New test.
+	* gcc.target/i386/avx2-pr70354-2.c: New test.
+
 2016-03-22  Jeff Law  <law@redhat.com>
 
 	PR target/70232

gcc/testsuite/gcc.dg/vect/pr70354-1.c

+/* PR tree-optimization/70354 */
+/* { dg-do run } */
+
+#ifndef main
+#include "tree-vect.h"
+#endif
+
+long long int b[64], c[64], g[64];
+unsigned long long int a[64], d[64], e[64], f[64], h[64];
+
+__attribute__ ((noinline, noclone)) void
+foo (void)
+{
+  int i;
+  for (i = 0; i < 64; i++)
+    {
+      d[i] = h[i] << (((((unsigned long long int) b[i] * e[i])
+			<< (-a[i] - 3752448776177690134ULL))
+		       - 8214565720323784703ULL) - 1ULL);
+      e[i] = (_Bool) (f[i] + (unsigned long long int) g[i]);
+      g[i] = c[i];
+    }
+}
+
+int
+main ()
+{
+  int i;
+#ifndef main
+  check_vect ();
+#endif
+  if (__CHAR_BIT__ != 8 || sizeof (long long int) != 8)
+    return 0;
+  for (i = 0; i < 64; ++i)
+    {
+      a[i] = 14694295297531861425ULL;
+      b[i] = -1725558902283030715LL;
+      c[i] = 4402992416302558097LL;
+      e[i] = 6297173129107286501ULL;
+      f[i] = 13865724171235650855ULL;
+      g[i] = 982871027473857427LL;
+      h[i] = 8193845517487445944ULL;
+    }
+  foo ();
+  for (i = 0; i < 64; i++)
+    if (d[i] != 8193845517487445944ULL || e[i] != 1
+	|| g[i] != 4402992416302558097ULL)
+      abort ();
+  return 0;
+}

gcc/testsuite/gcc.dg/vect/pr70354-2.c

+/* PR tree-optimization/70354 */
+/* { dg-do run } */
+
+#ifndef main
+#include "tree-vect.h"
+#endif
+
+unsigned long long a[64], b[64];
+
+__attribute__((noinline, noclone)) void
+foo (void)
+{
+  int i;
+  for (i = 0; i < 64; i++)
+    a[i] <<= (b[i] - 0x1200000000ULL);
+}
+
+int
+main ()
+{
+  int i;
+#ifndef main
+  check_vect ();
+#endif
+  if (__CHAR_BIT__ != 8 || sizeof (long long int) != 8)
+    return 0;
+  for (i = 0; i < 64; i++)
+    {
+      a[i] = 0x1234ULL;
+      b[i] = 0x1200000000ULL + (i % 54);
+    }
+  foo ();
+  for (i = 0; i < 64; i++)
+    if (a[i] != (0x1234ULL << (i % 54)))
+      abort ();
+  return 0;
+}

gcc/testsuite/gcc.target/i386/avx2-pr70354-1.c

+/* PR tree-optimization/70354 */
+/* { dg-do run } */
+/* { dg-options "-O2 -ftree-vectorize -mavx2" } */
+/* { dg-require-effective-target avx2 } */
+
+#include "avx2-check.h"
+
+#define main() do_main ()
+
+#include "../../gcc.dg/vect/pr70354-1.c"
+
+static void
+avx2_test (void)
+{
+  do_main ();
+}

gcc/testsuite/gcc.target/i386/avx2-pr70354-2.c

+/* PR tree-optimization/70354 */
+/* { dg-do run } */
+/* { dg-options "-O2 -ftree-vectorize -mavx2" } */
+/* { dg-require-effective-target avx2 } */
+
+#include "avx2-check.h"
+
+#define main() do_main ()
+
+#include "../../gcc.dg/vect/pr70354-2.c"
+
+static void
+avx2_test (void)
+{
+  do_main ();
+}

gcc/tree-vect-patterns.c

@@ -2097,7 +2097,20 @@ vect_recog_vector_vector_shift_pattern (vec<gimple *> *stmts,
       if (TYPE_MODE (TREE_TYPE (rhs1)) == TYPE_MODE (TREE_TYPE (oprnd0))
 	  && TYPE_PRECISION (TREE_TYPE (rhs1))
 	     == TYPE_PRECISION (TREE_TYPE (oprnd0)))
-	def = rhs1;
+	{
+	  if (TYPE_PRECISION (TREE_TYPE (oprnd1))
+	      >= TYPE_PRECISION (TREE_TYPE (rhs1)))
+	    def = rhs1;
+	  else
+	    {
+	      tree mask
+		= build_low_bits_mask (TREE_TYPE (rhs1),
+				       TYPE_PRECISION (TREE_TYPE (oprnd1)));
+	      def = vect_recog_temp_ssa_var (TREE_TYPE (rhs1), NULL);
+	      def_stmt = gimple_build_assign (def, BIT_AND_EXPR, rhs1, mask);
+	      new_pattern_def_seq (stmt_vinfo, def_stmt);
+	    }
+	}
     }
 
   if (def == NULL_TREE)