re PR tree-optimization/59591 (ICE in vect_get_vec_def_for_stmt_copy, at tree-vect-stmts.c:156 for -march=core-avx2)

	PR tree-optimization/59591
	* tree-vect-stmts.c (vectorizable_mask_load_store): Fix up handling
	of modifier = NARROW masked gathers.
	(permute_vec_elements): Use gimple_get_lhs instead of
	gimple_assign_lhs.

	* gcc.dg/vect/pr59591-1.c: New test.
	* gcc.dg/vect/pr59591-2.c: New test.
	* gcc.target/i386/pr59591-1.c: New test.
	* gcc.target/i386/pr59591-2.c: New test.

From-SVN: r206248

7 files changed, 201 insertions, 30 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 1a6ae5e..09e0ad2 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2013-12-30  Jakub Jelinek  <jakub@redhat.com>
+
+	PR tree-optimization/59591
+	* tree-vect-stmts.c (vectorizable_mask_load_store): Fix up handling
+	of modifier = NARROW masked gathers.
+	(permute_vec_elements): Use gimple_get_lhs instead of
+	gimple_assign_lhs.
+
 2013-12-30  Nick Clifton  <nickc@redhat.com>
 
 	* config/msp430/msp430.c (msp430_print_operand): Rename %B to %b
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e5f1a82..3d68675 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,11 @@
 2013-12-30  Jakub Jelinek  <jakub@redhat.com>
 
+	PR tree-optimization/59591
+	* gcc.dg/vect/pr59591-1.c: New test.
+	* gcc.dg/vect/pr59591-2.c: New test.
+	* gcc.target/i386/pr59591-1.c: New test.
+	* gcc.target/i386/pr59591-2.c: New test.
+
 	PR target/59501
 	* gcc.target/i386/pr59501-1.c: New test.
 	* gcc.target/i386/pr59501-1a.c: New test.
diff --git a/gcc/testsuite/gcc.dg/vect/pr59591-1.c b/gcc/testsuite/gcc.dg/vect/pr59591-1.c
new file mode 100644
index 0000000..b216dee
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr59591-1.c
@@ -0,0 +1,55 @@
+/* PR tree-optimization/59591 */
+/* { dg-do run } */
+/* { dg-additional-options "-fopenmp-simd" } */
+
+#ifndef CHECK_H
+#include "tree-vect.h"
+#endif
+
+extern void abort (void);
+
+int p[256], q[256], r[256], t[256];
+
+__attribute__((noinline, noclone)) void
+foo (void)
+{
+  int i;
+  #pragma omp simd safelen(64)
+  for (i = 0; i < 256; i++)
+    if (r[i] > 32)
+      t[i] = p[q[i] * 3L + 2L];
+}
+
+__attribute__((noinline, noclone)) void
+bar (void)
+{
+  int i;
+  for (i = 0; i < 256; i++)
+    {
+      r[i] = ((i >> 2) & (1 << (i & 3))) ? 32 + i : 32 - i;
+      q[i] = r[i] > 32 ? ((i * 7) % 84) : 99 + i;
+      p[i] = i * 11;
+      t[i] = i * 13;
+    }
+  foo ();
+  for (i = 0; i < 256; i++)
+    if ((i >> 2) & (1 << (i & 3)))
+      {
+	if (t[i] != (((i * 7) % 84) * 3 + 2) * 11)
+	  abort ();
+      }
+    else if (t[i] != i * 13)
+      abort ();
+}
+
+#ifndef CHECK_H
+int
+main ()
+{
+  check_vect ();
+  bar ();
+  return 0;
+}
+#endif
+
+/* { dg-final { cleanup-tree-dump "vect" } } */
diff --git a/gcc/testsuite/gcc.dg/vect/pr59591-2.c b/gcc/testsuite/gcc.dg/vect/pr59591-2.c
new file mode 100644
index 0000000..429b187
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr59591-2.c
@@ -0,0 +1,56 @@
+/* PR tree-optimization/59591 */
+/* { dg-do run } */
+/* { dg-additional-options "-fopenmp-simd" } */
+
+#ifndef CHECK_H
+#include "tree-vect.h"
+#endif
+
+extern void abort (void);
+
+long long int p[256], r[256], t[256];
+int q[256];
+
+__attribute__((noinline, noclone)) void
+foo (void)
+{
+  int i;
+  #pragma omp simd safelen(64)
+  for (i = 0; i < 256; i++)
+    if (r[i] > 32LL)
+      t[i] = p[q[i]];
+}
+
+__attribute__((noinline, noclone)) void
+bar (void)
+{
+  int i;
+  for (i = 0; i < 256; i++)
+    {
+      r[i] = ((i >> 2) & (1 << (i & 3))) ? 32 + i : 32 - i;
+      q[i] = r[i] > 32 ? ((i * 7) % 256) : 258 + i;
+      p[i] = i * 11;
+      t[i] = i * 13;
+    }
+  foo ();
+  for (i = 0; i < 256; i++)
+    if ((i >> 2) & (1 << (i & 3)))
+      {
+	if (t[i] != ((i * 7) % 256) * 11)
+	  abort ();
+      }
+    else if (t[i] != i * 13)
+      abort ();
+}
+
+#ifndef CHECK_H
+int
+main ()
+{
+  check_vect ();
+  bar ();
+  return 0;
+}
+#endif
+
+/* { dg-final { cleanup-tree-dump "vect" } } */
diff --git a/gcc/testsuite/gcc.target/i386/pr59591-1.c b/gcc/testsuite/gcc.target/i386/pr59591-1.c
new file mode 100644
index 0000000..a88c6fd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr59591-1.c
@@ -0,0 +1,17 @@
+/* PR tree-optimization/59591 */
+/* { dg-do run } */
+/* { dg-options "-O2 -fopenmp-simd -mavx2 -fno-vect-cost-model" } */
+/* { dg-require-effective-target avx2 } */
+
+#define CHECK_H "avx2-check.h"
+#define TEST avx2_test
+
+#include "../../gcc.dg/vect/pr59591-1.c"
+
+#include CHECK_H
+
+static void
+TEST (void)
+{
+  bar ();
+}
diff --git a/gcc/testsuite/gcc.target/i386/pr59591-2.c b/gcc/testsuite/gcc.target/i386/pr59591-2.c
new file mode 100644
index 0000000..c032364
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr59591-2.c
@@ -0,0 +1,17 @@
+/* PR tree-optimization/59591 */
+/* { dg-do run } */
+/* { dg-options "-O2 -fopenmp-simd -mavx2 -fno-vect-cost-model" } */
+/* { dg-require-effective-target avx2 } */
+
+#define CHECK_H "avx2-check.h"
+#define TEST avx2_test
+
+#include "../../gcc.dg/vect/pr59591-2.c"
+
+#include CHECK_H
+
+static void
+TEST (void)
+{
+  bar ();
+}
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index e3009d9..a07c14d 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -1855,14 +1855,24 @@ vectorizable_mask_load_store (gimple stmt, gimple_stmt_iterator *gsi,
       tree vec_oprnd0 = NULL_TREE, op;
       tree arglist = TYPE_ARG_TYPES (TREE_TYPE (gather_decl));
       tree rettype, srctype, ptrtype, idxtype, masktype, scaletype;
-      tree ptr, vec_mask = NULL_TREE, mask_op, var, scale;
+      tree ptr, vec_mask = NULL_TREE, mask_op = NULL_TREE, var, scale;
       tree perm_mask = NULL_TREE, prev_res = NULL_TREE;
+      tree mask_perm_mask = NULL_TREE;
       edge pe = loop_preheader_edge (loop);
       gimple_seq seq;
       basic_block new_bb;
       enum { NARROW, NONE, WIDEN } modifier;
       int gather_off_nunits = TYPE_VECTOR_SUBPARTS (gather_off_vectype);
 
+      rettype = TREE_TYPE (TREE_TYPE (gather_decl));
+      srctype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
+      ptrtype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
+      idxtype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
+      masktype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
+      scaletype = TREE_VALUE (arglist);
+      gcc_checking_assert (types_compatible_p (srctype, rettype)
+			   && types_compatible_p (srctype, masktype));
+
       if (nunits == gather_off_nunits)
 	modifier = NONE;
       else if (nunits == gather_off_nunits / 2)
@@ -1888,19 +1898,14 @@ vectorizable_mask_load_store (gimple stmt, gimple_stmt_iterator *gsi,
 	  perm_mask = vect_gen_perm_mask (vectype, sel);
 	  gcc_assert (perm_mask != NULL_TREE);
 	  ncopies *= 2;
+	  for (i = 0; i < nunits; ++i)
+	    sel[i] = i | gather_off_nunits;
+	  mask_perm_mask = vect_gen_perm_mask (masktype, sel);
+	  gcc_assert (mask_perm_mask != NULL_TREE);
 	}
       else
 	gcc_unreachable ();
 
-      rettype = TREE_TYPE (TREE_TYPE (gather_decl));
-      srctype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
-      ptrtype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
-      idxtype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
-      masktype = TREE_VALUE (arglist); arglist = TREE_CHAIN (arglist);
-      scaletype = TREE_VALUE (arglist);
-      gcc_checking_assert (types_compatible_p (srctype, rettype)
-			   && types_compatible_p (srctype, masktype));
-
       vec_dest = vect_create_destination_var (gimple_call_lhs (stmt), vectype);
 
       ptr = fold_convert (ptrtype, gather_base);
@@ -1940,28 +1945,35 @@ vectorizable_mask_load_store (gimple stmt, gimple_stmt_iterator *gsi,
 	      op = var;
 	    }
 
-	  if (j == 0)
-	    vec_mask = vect_get_vec_def_for_operand (mask, stmt, NULL);
+	  if (mask_perm_mask && (j & 1))
+	    mask_op = permute_vec_elements (mask_op, mask_op,
+					    mask_perm_mask, stmt, gsi);
 	  else
 	    {
-	      vect_is_simple_use (vec_mask, NULL, loop_vinfo, NULL, &def_stmt,
-				  &def, &dt);
-	      vec_mask = vect_get_vec_def_for_stmt_copy (dt, vec_mask);
-	    }
+	      if (j == 0)
+		vec_mask = vect_get_vec_def_for_operand (mask, stmt, NULL);
+	      else
+		{
+		  vect_is_simple_use (vec_mask, NULL, loop_vinfo, NULL,
+				      &def_stmt, &def, &dt);
+		  vec_mask = vect_get_vec_def_for_stmt_copy (dt, vec_mask);
+		}
 
-	  mask_op = vec_mask;
-	  if (!useless_type_conversion_p (masktype, TREE_TYPE (vec_mask)))
-	    {
-	      gcc_assert (TYPE_VECTOR_SUBPARTS (TREE_TYPE (mask_op))
-			  == TYPE_VECTOR_SUBPARTS (masktype));
-	      var = vect_get_new_vect_var (masktype, vect_simple_var, NULL);
-	      var = make_ssa_name (var, NULL);
-	      mask_op = build1 (VIEW_CONVERT_EXPR, masktype, mask_op);
-	      new_stmt
-		= gimple_build_assign_with_ops (VIEW_CONVERT_EXPR, var,
-						mask_op, NULL_TREE);
-	      vect_finish_stmt_generation (stmt, new_stmt, gsi);
-	      mask_op = var;
+	      mask_op = vec_mask;
+	      if (!useless_type_conversion_p (masktype, TREE_TYPE (vec_mask)))
+		{
+		  gcc_assert (TYPE_VECTOR_SUBPARTS (TREE_TYPE (mask_op))
+			      == TYPE_VECTOR_SUBPARTS (masktype));
+		  var = vect_get_new_vect_var (masktype, vect_simple_var,
+					       NULL);
+		  var = make_ssa_name (var, NULL);
+		  mask_op = build1 (VIEW_CONVERT_EXPR, masktype, mask_op);
+		  new_stmt
+		    = gimple_build_assign_with_ops (VIEW_CONVERT_EXPR, var,
+						    mask_op, NULL_TREE);
+		  vect_finish_stmt_generation (stmt, new_stmt, gsi);
+		  mask_op = var;
+		}
 	    }
 
 	  new_stmt
@@ -5446,7 +5458,7 @@ permute_vec_elements (tree x, tree y, tree mask_vec, gimple stmt,
   tree perm_dest, data_ref;
   gimple perm_stmt;
 
-  perm_dest = vect_create_destination_var (gimple_assign_lhs (stmt), vectype);
+  perm_dest = vect_create_destination_var (gimple_get_lhs (stmt), vectype);
   data_ref = make_ssa_name (perm_dest, NULL);
 
   /* Generate the permute statement.  */