re PR tree-optimization/43434 (Missed vectorization: "not vectorized: data ref…

re PR tree-optimization/43434 (Missed vectorization: "not vectorized: data ref analysis": pointer incremented by a parameter)

2016-04-18  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/43434
	* tree-ssa-structalias.c (struct vls_data): New.
	(visit_loadstore): Handle all pointer-based accesses.
	(compute_dependence_clique): Compute a bitmap of restrict tags
	assigned bases and pass it to visit_loadstore.

	* gcc.dg/vect/pr43434.c: New testcase.
	* c-c++-common/goacc/kernels-alias-3.c: Adjust.
	* c-c++-common/goacc/kernels-alias-4.c: Likewise.
	* c-c++-common/goacc/kernels-alias-5.c: Likewise.
	* c-c++-common/goacc/kernels-alias-6.c: Likewise.
	* c-c++-common/goacc/kernels-alias-7.c: Likewise.
	* c-c++-common/goacc/kernels-alias-8.c: Likewise.
	* gcc.dg/gomp/pr68640.c: Likewise.
	* gfortran.dg/goacc/kernels-alias-3.f95: Likewise.
	* gfortran.dg/goacc/kernels-alias-4.f95: Likewise.

From-SVN: r235147

gcc/ChangeLog

+2016-04-18  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/43434
+	* tree-ssa-structalias.c (struct vls_data): New.
+	(visit_loadstore): Handle all pointer-based accesses.
+	(compute_dependence_clique): Compute a bitmap of restrict tags
+	assigned bases and pass it to visit_loadstore.
+
 2016-04-18  Matthew Wahab  <matthew.wahab@arm.com>
 
 	PR target/70711

gcc/testsuite/ChangeLog

 2016-04-18  Richard Biener  <rguenther@suse.de>
 
+	PR tree-optimization/43434
+	* gcc.dg/vect/pr43434.c: New testcase.
+	* c-c++-common/goacc/kernels-alias-3.c: Adjust.
+	* c-c++-common/goacc/kernels-alias-4.c: Likewise.
+	* c-c++-common/goacc/kernels-alias-5.c: Likewise.
+	* c-c++-common/goacc/kernels-alias-6.c: Likewise.
+	* c-c++-common/goacc/kernels-alias-7.c: Likewise.
+	* c-c++-common/goacc/kernels-alias-8.c: Likewise.
+	* gcc.dg/gomp/pr68640.c: Likewise.
+	* gfortran.dg/goacc/kernels-alias-3.f95: Likewise.
+	* gfortran.dg/goacc/kernels-alias-4.f95: Likewise.
+
+2016-04-18  Richard Biener  <rguenther@suse.de>
+
 	PR tree-optimization/70701
 	* gcc.dg/tree-ssa/ssa-fre-53.c: New testcase.
 

gcc/testsuite/c-c++-common/goacc/kernels-alias-3.c

@@ -14,7 +14,8 @@ foo (void)
   }
 }
 
-/* Only the omp_data_i related loads should be annotated with cliques.  */
+/* Only the omp_data_i related loads should be annotated with
+   non-base 0 cliques.  */
 /* { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } } */
-/* { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } } */
+/* { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 3 "ealias" } } */
 

gcc/testsuite/c-c++-common/goacc/kernels-alias-4.c

@@ -16,7 +16,8 @@ foo (void)
   }
 }
 
-/* Only the omp_data_i related loads should be annotated with cliques.  */
+/* Only the omp_data_i related loads should be annotated with
+   non-base 0 cliques.  */
 /* { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } } */
-/* { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } } */
+/* { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 3 "ealias" } } */
 

gcc/testsuite/c-c++-common/goacc/kernels-alias-5.c

@@ -15,5 +15,5 @@ foo (int *a)
 
 /* Only the omp_data_i related loads should be annotated with cliques.  */
 /* { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } } */
-/* { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } } */
+/* { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 4 "ealias" } } */
 

gcc/testsuite/c-c++-common/goacc/kernels-alias-6.c

@@ -19,5 +19,5 @@ foo (void)
 
 /* Only the omp_data_i related loads should be annotated with cliques.  */
 /* { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } } */
-/* { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } } */
+/* { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 3 "ealias" } } */
 

gcc/testsuite/c-c++-common/goacc/kernels-alias-7.c

@@ -21,5 +21,5 @@ foo (void)
 
 /* Only the omp_data_i related loads should be annotated with cliques.  */
 /* { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } } */
-/* { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } } */
+/* { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 3 "ealias" } } */
 

gcc/testsuite/c-c++-common/goacc/kernels-alias-8.c

@@ -18,5 +18,5 @@ foo (int *a, size_t n)
 
 /* Only the omp_data_i related loads should be annotated with cliques.  */
 /* { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } } */
-/* { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } } */
+/* { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 3 "ealias" } } */
 

gcc/testsuite/gcc.dg/gomp/pr68640.c

@@ -13,4 +13,4 @@ foo (int *__restrict__ ap)
 }
 
 /* { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } } */
-/* { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } } */
+/* { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 2 "ealias" } } */

gcc/testsuite/gcc.dg/vect/pr43434.c

+/* { dg-do compile } */
+
+typedef short DCTELEM;
+typedef unsigned char uint8_t;
+
+void diff_pixels_c(DCTELEM *__restrict__ block, const uint8_t *s1,
+		   const uint8_t *s2, int stride)
+{
+  int i;
+
+  for(i=0;i<8;i++)
+    {
+      block[0] = s1[0] - s2[0];
+      block[1] = s1[1] - s2[1];
+      block[2] = s1[2] - s2[2];
+      block[3] = s1[3] - s2[3];
+      block[4] = s1[4] - s2[4];
+      block[5] = s1[5] - s2[5];
+      block[6] = s1[6] - s2[6];
+      block[7] = s1[7] - s2[7];
+      s1 += stride;
+      s2 += stride;
+      block += 8;
+    }
+}
+
+/* { dg-final { scan-tree-dump "vectorized 1 loops" "vect" { target { vect_int && { vect_unpack && vect_hw_misalign } } } } } */

gcc/testsuite/gfortran.dg/goacc/kernels-alias-3.f95

@@ -16,4 +16,4 @@ end program main
 
 ! Only the omp_data_i related loads should be annotated with cliques.
 ! { dg-final { scan-tree-dump-times "clique 1 base 1" 2 "ealias" } }
-! { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 2 "ealias" } }
+! { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 3 "ealias" } }

gcc/testsuite/gfortran.dg/goacc/kernels-alias-4.f95

@@ -17,4 +17,4 @@ end program main
 
 ! Only the omp_data_i related loads should be annotated with cliques.
 ! { dg-final { scan-tree-dump-times "clique 1 base 1" 3 "ealias" } }
-! { dg-final { scan-tree-dump-times "(?n)clique .* base .*" 3 "ealias" } }
+! { dg-final { scan-tree-dump-times "(?n)clique 1 base 0" 4 "ealias" } }

gcc/tree-ssa-structalias.c

@@ -7182,13 +7182,20 @@ delete_points_to_sets (void)
   obstack_free (&final_solutions_obstack, NULL);
 }
 
+struct vls_data
+{
+  unsigned short clique;
+  bitmap rvars;
+};
+
 /* Mark "other" loads and stores as belonging to CLIQUE and with
    base zero.  */
 
 static bool
-visit_loadstore (gimple *, tree base, tree ref, void *clique_)
+visit_loadstore (gimple *, tree base, tree ref, void *data)
 {
-  unsigned short clique = (uintptr_t)clique_;
+  unsigned short clique = ((vls_data *) data)->clique;
+  bitmap rvars = ((vls_data *) data)->rvars;
   if (TREE_CODE (base) == MEM_REF
       || TREE_CODE (base) == TARGET_MEM_REF)
     {
@@ -7196,12 +7203,16 @@ visit_loadstore (gimple *, tree base, tree ref, void *clique_)
       if (TREE_CODE (ptr) == SSA_NAME
 	  && ! SSA_NAME_IS_DEFAULT_DEF (ptr))
 	{
-	  /* ???  We need to make sure 'ptr' doesn't include any of
+	  /* We need to make sure 'ptr' doesn't include any of
 	     the restrict tags we added bases for in its points-to set.  */
-	  return false;
-	}
+	  varinfo_t vi = lookup_vi_for_tree (ptr);
+	  if (! vi)
+	    return false;
 
-      /* For now let decls through.  */
+	  vi = get_varinfo (find (vi->id));
+	  if (bitmap_intersect_p (rvars, vi->solution))
+	    return false;
+	}
 
       /* Do not overwrite existing cliques (that includes clique, base
          pairs we just set).  */
@@ -7275,6 +7286,7 @@ compute_dependence_clique (void)
 {
   unsigned short clique = 0;
   unsigned short last_ruid = 0;
+  bitmap rvars = BITMAP_ALLOC (NULL);
   for (unsigned i = 0; i < num_ssa_names; ++i)
     {
       tree ptr = ssa_name (i);
@@ -7330,38 +7342,46 @@ compute_dependence_clique (void)
 	  /* Now look at possible dereferences of ptr.  */
 	  imm_use_iterator ui;
 	  gimple *use_stmt;
+	  bool used = false;
 	  FOR_EACH_IMM_USE_STMT (use_stmt, ui, ptr)
 	    {
 	      /* ???  Calls and asms.  */
 	      if (!gimple_assign_single_p (use_stmt))
 		continue;
-	      maybe_set_dependence_info (gimple_assign_lhs (use_stmt), ptr,
-					 clique, restrict_var, last_ruid);
-	      maybe_set_dependence_info (gimple_assign_rhs1 (use_stmt), ptr,
-					 clique, restrict_var, last_ruid);
+	      used |= maybe_set_dependence_info (gimple_assign_lhs (use_stmt),
+						 ptr, clique, restrict_var,
+						 last_ruid);
+	      used |= maybe_set_dependence_info (gimple_assign_rhs1 (use_stmt),
+						 ptr, clique, restrict_var,
+						 last_ruid);
 	    }
+	  if (used)
+	    bitmap_set_bit (rvars, restrict_var->id);
 	}
     }
 
-  if (clique == 0)
-    return;
+  if (clique != 0)
+    {
+      /* Assign the BASE id zero to all accesses not based on a restrict
+	 pointer.  That way they get disambiguated against restrict
+	 accesses but not against each other.  */
+      /* ???  For restricts derived from globals (thus not incoming
+	 parameters) we can't restrict scoping properly thus the following
+	 is too aggressive there.  For now we have excluded those globals from
+	 getting into the MR_DEPENDENCE machinery.  */
+      vls_data data = { clique, rvars };
+      basic_block bb;
+      FOR_EACH_BB_FN (bb, cfun)
+	for (gimple_stmt_iterator gsi = gsi_start_bb (bb);
+	     !gsi_end_p (gsi); gsi_next (&gsi))
+	  {
+	    gimple *stmt = gsi_stmt (gsi);
+	    walk_stmt_load_store_ops (stmt, &data,
+				      visit_loadstore, visit_loadstore);
+	  }
+    }
 
-  /* Assign the BASE id zero to all accesses not based on a restrict
-     pointer.  That way they get disabiguated against restrict
-     accesses but not against each other.  */
-  /* ???  For restricts derived from globals (thus not incoming
-     parameters) we can't restrict scoping properly thus the following
-     is too aggressive there.  For now we have excluded those globals from
-     getting into the MR_DEPENDENCE machinery.  */
-  basic_block bb;
-  FOR_EACH_BB_FN (bb, cfun)
-    for (gimple_stmt_iterator gsi = gsi_start_bb (bb);
-	 !gsi_end_p (gsi); gsi_next (&gsi))
-      {
-	gimple *stmt = gsi_stmt (gsi);
-	walk_stmt_load_store_ops (stmt, (void *)(uintptr_t)clique,
-				  visit_loadstore, visit_loadstore);
-      }
+  BITMAP_FREE (rvars);
 }
 
 /* Compute points-to information for every SSA_NAME pointer in the