[PATCH] Fix PR56826

[Richard Biener]

This fixes the testcase in PR56826, the underlying issue being
that a SLP group load with a gap is detected as supported while
it is not because we compute ncopies incorrectly.  The following
patch makes us compute ncopies more correctly.

Bootstrap and regtest pending on x86_64-unknown-linux-gnu.

Richard.

2013-04-04  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/56826
	* tree-vect-slp.c (vect_build_slp_tree): Compute ncopies
	more accurately.

	* gcc.dg/vect/pr56826.c: New testcase.

Index: gcc/tree-vect-slp.c
===================================================================
*** gcc/tree-vect-slp.c	(revision 197475)
--- gcc/tree-vect-slp.c	(working copy)
*************** vect_build_slp_tree (loop_vec_info loop_
*** 470,476 ****
    tree lhs;
    bool stop_recursion = false, need_same_oprnds = false;
    tree vectype, scalar_type, first_op1 = NULL_TREE;
-   unsigned int ncopies;
    optab optab;
    int icode;
    enum machine_mode optab_op2_mode;
--- 470,475 ----
*************** vect_build_slp_tree (loop_vec_info loop_
*** 577,584 ****
              vectorization_factor = *max_nunits;
          }
  
-       ncopies = vectorization_factor / TYPE_VECTOR_SUBPARTS (vectype);
- 
        if (is_gimple_call (stmt))
  	{
  	  rhs_code = CALL_EXPR;
--- 576,581 ----
*************** vect_build_slp_tree (loop_vec_info loop_
*** 741,746 ****
--- 738,746 ----
  	  else
  	    {
  	      /* Load.  */
+ 	      unsigned ncopies
+ 		= least_common_multiple
+ 		    (vectorization_factor, group_size) / group_size;
                /* FORNOW: Check that there is no gap between the loads
  		 and no gap between the groups when we need to load
  		 multiple groups at once.
Index: gcc/testsuite/gcc.dg/vect/pr56826.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/pr56826.c	(revision 0)
--- gcc/testsuite/gcc.dg/vect/pr56826.c	(working copy)
***************
*** 0 ****
--- 1,41 ----
+ extern void abort (void);
+ 
+ typedef struct {
+     int a[3];
+     int num;
+ } t1;
+ t1 B[100];
+ int A[300];
+ 
+ void __attribute__((noinline,noclone))
+ bar (int *A, t1 *B, int n)
+ {
+   int i;
+   int *a = A;
+   for (i=0; i<n; i++, a+=3)
+     {
+       a[0] = B[i].a[0];
+       a[1] = B[i].a[1];
+       a[2] = B[i].a[2];
+     }
+ }
+ 
+ int main()
+ {
+   int i;
+   for (i=0; i<100; i++) 
+     {
+       B[i].num = i;
+       B[i].a[0] = i * 3;
+       B[i].a[1] = i * 3 + 1;
+       B[i].a[2] = i * 3 + 2;
+       __asm__ volatile ("");
+     }
+   bar (&A[0], &B[0], 100);
+   for (i=0; i<300; i++)
+     if (A[i] != i)
+       abort ();
+   return 0;
+ } 
+ 
+ /* { dg-final { cleanup-tree-dump "vect" } } */

Property changes on: gcc/testsuite/gcc.dg/vect/pr56826.c
___________________________________________________________________
Added: svn:executable
## -0,0 +1 ##
+*
\ No newline at end of property