[PATCH] Fix PR56787, missed vectorization with CLOBBERs

[Richard Biener]

The following fixes vectorization of loops with CLOBBER statements
in the way of ignoring them during analysis and removing them during
vectorization (because we ignored them for store/load placement
and do not handle them in case we need to unroll the loop body).

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

Do you see a better way of handling the CLOBBERs that is worthwhile?

Thanks,
Richard.

2013-05-28  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/56787
	* tree-vect-data-refs.c (vect_analyze_data_refs): Drop clobbers
	from the list of data references.
	* tree-vect-loop.c (vect_determine_vectorization_factor): Skip
	clobbers.
	(vect_analyze_loop_operations): Likewise.
	(vect_transform_loop): Remove clobbers.

	* gcc.dg/vect/pr56787.c: New testcase.

Index: gcc/tree-vect-data-refs.c
===================================================================
*** gcc/tree-vect-data-refs.c	(revision 199374)
--- gcc/tree-vect-data-refs.c	(working copy)
*************** vect_analyze_data_refs (loop_vec_info lo
*** 2861,2866 ****
--- 2861,2867 ----
        bool gather = false;
        int vf;
  
+ again:
        if (!dr || !DR_REF (dr))
          {
            if (dump_enabled_p ())
*************** vect_analyze_data_refs (loop_vec_info lo
*** 2872,2877 ****
--- 2873,2891 ----
        stmt = DR_STMT (dr);
        stmt_info = vinfo_for_stmt (stmt);
  
+       /* Discard clobbers from the dataref vector.  We will remove
+          clobber stmts during vectorization.  */
+       if (gimple_clobber_p (stmt))
+ 	{
+ 	  if (i == datarefs.length () - 1)
+ 	    {
+ 	      datarefs.pop ();
+ 	      break;
+ 	    }
+ 	  datarefs[i] = datarefs.pop ();
+ 	  goto again;
+ 	}
+ 
        /* Check that analysis of the data-ref succeeded.  */
        if (!DR_BASE_ADDRESS (dr) || !DR_OFFSET (dr) || !DR_INIT (dr)
  	  || !DR_STEP (dr))
Index: gcc/tree-vect-loop.c
===================================================================
*** gcc/tree-vect-loop.c	(revision 199374)
--- gcc/tree-vect-loop.c	(working copy)
*************** vect_determine_vectorization_factor (loo
*** 270,277 ****
  	  gcc_assert (stmt_info);
  
  	  /* Skip stmts which do not need to be vectorized.  */
! 	  if (!STMT_VINFO_RELEVANT_P (stmt_info)
! 	      && !STMT_VINFO_LIVE_P (stmt_info))
              {
                if (STMT_VINFO_IN_PATTERN_P (stmt_info)
                    && (pattern_stmt = STMT_VINFO_RELATED_STMT (stmt_info))
--- 270,278 ----
  	  gcc_assert (stmt_info);
  
  	  /* Skip stmts which do not need to be vectorized.  */
! 	  if ((!STMT_VINFO_RELEVANT_P (stmt_info)
! 	       && !STMT_VINFO_LIVE_P (stmt_info))
! 	      || gimple_clobber_p (stmt))
              {
                if (STMT_VINFO_IN_PATTERN_P (stmt_info)
                    && (pattern_stmt = STMT_VINFO_RELATED_STMT (stmt_info))
*************** vect_analyze_loop_operations (loop_vec_i
*** 1431,1437 ****
        for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
          {
            gimple stmt = gsi_stmt (si);
! 	  if (!vect_analyze_stmt (stmt, &need_to_vectorize, NULL))
  	    return false;
          }
      } /* bbs */
--- 1432,1439 ----
        for (si = gsi_start_bb (bb); !gsi_end_p (si); gsi_next (&si))
          {
            gimple stmt = gsi_stmt (si);
! 	  if (!gimple_clobber_p (stmt)
! 	      && !vect_analyze_stmt (stmt, &need_to_vectorize, NULL))
  	    return false;
          }
      } /* bbs */
*************** vect_transform_loop (loop_vec_info loop_
*** 5595,5601 ****
            if (transform_pattern_stmt)
  	    stmt = pattern_stmt;
            else
!             stmt = gsi_stmt (si);
  
  	  if (dump_enabled_p ())
  	    {
--- 5597,5613 ----
            if (transform_pattern_stmt)
  	    stmt = pattern_stmt;
            else
! 	    {
! 	      stmt = gsi_stmt (si);
! 	      /* During vectorization remove existing clobber stmts.  */
! 	      if (gimple_clobber_p (stmt))
! 		{
! 		  unlink_stmt_vdef (stmt);
! 		  gsi_remove (&si, true);
! 		  release_defs (stmt);
! 		  continue;
! 		}
! 	    }
  
  	  if (dump_enabled_p ())
  	    {
Index: gcc/testsuite/gcc.dg/vect/pr56787.c
===================================================================
*** gcc/testsuite/gcc.dg/vect/pr56787.c	(revision 0)
--- gcc/testsuite/gcc.dg/vect/pr56787.c	(working copy)
***************
*** 0 ****
--- 1,35 ----
+ /* { dg-do compile } */
+ /* { dg-require-effective-target vect_float } */
+ 
+ inline void
+ bar (const float s[5], float z[3][5])
+ {
+   float a = s[0], b = s[1], c = s[2], d = s[3], e = s[4];
+   float f = 1.0f / a;
+   float u = f * b, v = f * c, w = f * d;
+   float p = 0.4f * (e - 0.5f * (b * u + c * v + d * w));
+   z[0][3] = b * w;
+   z[1][3] = c * w;
+   z[2][3] = d * w + p;
+ }
+ 
+ void
+ foo (unsigned long n, const float *__restrict u0,
+      const float *__restrict u1, const float *__restrict u2,
+      const float *__restrict u3, const float *__restrict u4,
+      const float *__restrict s0, const float *__restrict s1,
+      const float *__restrict s2, float *__restrict t3,
+      float *__restrict t4)
+ {
+   unsigned long i;
+   for (i = 0; i < n; i++)
+     {
+       float u[5], f[3][5];
+       u[0] = u0[i]; u[1] = u1[i]; u[2] = u2[i]; u[3] = u3[i]; u[4] = u4[i];
+       bar (u, f);
+       t3[i] = s0[i] * f[0][3] + s1[i] * f[1][3] + s2[i] * f[2][3];
+     }
+ }
+ 
+ /* { dg-final { scan-tree-dump "vectorized 1 loops" "vect" } } */
+ /* { dg-final { cleanup-tree-dump "vect" } } */