Fix GROUP_GAP for single-element interleaving

vectorizable_load had a curious "force_peeling" variable, with no
comment explaining why we need it for single-element interleaving
but not for other cases.  I think it's simply because we weren't
initialising the GROUP_GAP correctly for single loads.

Tested on aarch64-linux-gnu and x86_64-linux-gnu.

gcc/
	* tree-vect-data-refs.c (vect_analyze_group_access_1): Set
	GROUP_GAP for single-element interleaving.
	* tree-vect-stmts.c (vectorizable_load): Remove force_peeling
	variable.

From-SVN: r236631

gcc/ChangeLog

+2016-05-24  Richard Sandiford  <richard.sandiford@arm.com>
+
+	* tree-vect-data-refs.c (vect_analyze_group_access_1): Set
+	GROUP_GAP for single-element interleaving.
+	* tree-vect-stmts.c (vectorizable_load): Remove force_peeling
+	variable.
+
 2016-05-24  Richard Biener  <rguenther@suse.de>
 
 	PR middle-end/70434

gcc/tree-vect-data-refs.c

@@ -2233,6 +2233,7 @@ vect_analyze_group_access_1 (struct data_reference *dr)
 	{
 	  GROUP_FIRST_ELEMENT (vinfo_for_stmt (stmt)) = stmt;
 	  GROUP_SIZE (vinfo_for_stmt (stmt)) = groupsize;
+	  GROUP_GAP (stmt_info) = groupsize - 1;
 	  if (dump_enabled_p ())
 	    {
 	      dump_printf_loc (MSG_NOTE, vect_location,

gcc/tree-vect-stmts.c

@@ -6308,7 +6308,6 @@ vectorizable_load (gimple *stmt, gimple_stmt_iterator *gsi, gimple **vec_stmt,
          that leaves unused vector loads around punt - we at least create
 	 very sub-optimal code in that case (and blow up memory,
 	 see PR65518).  */
-      bool force_peeling = false;
       if (first_stmt == stmt
 	  && !GROUP_NEXT_ELEMENT (stmt_info))
 	{
@@ -6322,7 +6321,7 @@ vectorizable_load (gimple *stmt, gimple_stmt_iterator *gsi, gimple **vec_stmt,
 	    }
 
 	  /* Single-element interleaving requires peeling for gaps.  */
-	  force_peeling = true;
+	  gcc_assert (GROUP_GAP (stmt_info));
 	}
 
       /* If there is a gap in the end of the group or the group size cannot
@@ -6330,8 +6329,7 @@ vectorizable_load (gimple *stmt, gimple_stmt_iterator *gsi, gimple **vec_stmt,
 	 elements in the last iteration and thus need to peel that off.  */
       if (loop_vinfo
 	  && ! STMT_VINFO_STRIDED_P (stmt_info)
-	  && (force_peeling
-	      || GROUP_GAP (vinfo_for_stmt (first_stmt)) != 0
+	  && (GROUP_GAP (vinfo_for_stmt (first_stmt)) != 0
 	      || (!slp && vf % GROUP_SIZE (vinfo_for_stmt (first_stmt)) != 0)))
 	{
 	  if (dump_enabled_p ())