[patch, vectorizer] Fix PR tree-optimization/36648

[Ira Rosen <IRAR at il dot ibm dot com>]

Hi,

This patch fixes a bug in calculation of number of prolog loop iterations
(used to align data accesses) in case of non-unit-stride access.

Bootstrapped with vectorization enabled and tested on x86_64-linux. O.K.
for 4.3 branch and mainline?

Thanks,
Ira

ChangeLogs:

      PR tree-optimization/36648
      * tree-vect-transform.c (vect_do_peeling_for_loop_bound): Divide
number
      of prolog iterations by step. Fix the comment.


      PR tree-optimization/36648
      * g++.dg/vect/pr36648.cc: New testcase.

Index: tree-vect-transform.c
===================================================================
--- tree-vect-transform.c       (revision 137251)
+++ tree-vect-transform.c       (working copy)
@@ -6725,16 +6725,14 @@ vect_do_peeling_for_loop_bound (loop_vec
    Else, compute address misalignment in bytes:
      addr_mis = addr & (vectype_size - 1)

-   prolog_niters = min ( LOOP_NITERS , (VF - addr_mis/elem_size)&(VF-1) )
-
-   (elem_size = element type size; an element is the scalar element
-       whose type is the inner type of the vectype)
-
-   For interleaving,
-
-   prolog_niters = min ( LOOP_NITERS ,
-                        (VF/group_size -
addr_mis/elem_size)&(VF/group_size-1) )
-        where group_size is the size of the interleaved group.
+   prolog_niters = min (LOOP_NITERS, ((VF -
addr_mis/elem_size)&(VF-1))/step))
+
+   (elem_size = element type size; an element is the scalar element whose
type
+   is the inner type of the vectype)
+
+   When the step of the data-ref in the loop is not 1 (as in interleaved
data
+   and SLP), the number of iterations of the prolog must be divided by the
step)
+   (which is equal to the size of interleaved group).

    The above formulas assume that VF == number of elements in the vector.
This
    may not hold when there are multiple-types in the loop.
@@ -6756,18 +6754,12 @@ vect_gen_niters_for_prolog_loop (loop_ve
   tree vectype = STMT_VINFO_VECTYPE (stmt_info);
   int vectype_align = TYPE_ALIGN (vectype) / BITS_PER_UNIT;
   tree niters_type = TREE_TYPE (loop_niters);
-  int group_size = 1;
+  int step = 1;
   int element_size = GET_MODE_SIZE (TYPE_MODE (TREE_TYPE (DR_REF (dr))));
   int nelements = TYPE_VECTOR_SUBPARTS (vectype);

   if (STMT_VINFO_STRIDED_ACCESS (stmt_info))
-    {
-      /* For interleaved access element size must be multiplied by the
size of
-        the interleaved group.  */
-      group_size = DR_GROUP_SIZE (vinfo_for_stmt (
-                                              DR_GROUP_FIRST_DR
(stmt_info)));
-      element_size *= group_size;
-    }
+    step = DR_GROUP_SIZE (vinfo_for_stmt (DR_GROUP_FIRST_DR
(stmt_info)));)));

   pe = loop_preheader_edge (loop);
@@ -6778,8 +6770,9 @@ vect_gen_niters_for_prolog_loop (loop_ve

       if (vect_print_dump_info (REPORT_DETAILS))
         fprintf (vect_dump, "known alignment = %d.", byte_misalign);
-      iters = build_int_cst (niters_type,
-                            (nelements -
elem_misalign)&(nelements/group_size-1));
+
+      iters = build_int_cst (niters_type,
+                     (((nelements - elem_misalign) & (nelements - 1)) /
step));));
     }
   else
     {
Index: testsuite/g++.dg/vect/pr36648.cc
===================================================================
--- testsuite/g++.dg/vect/pr36648.cc    (revision 0)
+++ testsuite/g++.dg/vect/pr36648.cc    (revision 0)
@@ -0,0 +1,24 @@
+/* { dg-require-effective-target vect_float } */
+
+struct vector
+{
+  vector() : x(0), y(0), z(0) { }
+  float x,y,z;
+};
+};
+struct Foo
+{
+  int dummy;
+  /* Misaligned access.  */
+  vector array_of_vectors[4];
+};
+};
+Foo foo;
+
+int main() { }
+
+/* { dg-final { scan-tree-dump-times "vectorized 1 loops" 1 "vect" } }*/
+/* { dg-final { scan-tree-dump-times "vectorizing stmts using SLP" 1
"vect" } } */
+/* { dg-final { cleanup-tree-dump "vect" } } */
+
+