Fix PR45948: add ssa defs from builtin partitions to the last partition.

2010-12-14  Sebastian Pop  <sebastian.pop@amd.com>

	PR tree-optimization/45948
	* tree-loop-distribution.c (ssa_name_has_uses_outside_loop_p): New.
	(stmt_has_scalar_dependences_outside_loop): New.
	(stmt_generated_in_another_partition): New.
	(add_scalar_computations_to_partition): New.
	(rdg_build_partitions): Call add_scalar_computations_to_partition.

	* gcc.dg/tree-ssa/ldist-pr45948.c: New.

From-SVN: r167842

1 files changed, 98 insertions, 0 deletions

diff --git a/gcc/tree-loop-distribution.c b/gcc/tree-loop-distribution.c
index b603209..a9ee67f 100644
--- a/gcc/tree-loop-distribution.c
+++ b/gcc/tree-loop-distribution.c
@@ -808,6 +808,102 @@ fuse_partitions_with_similar_memory_accesses (struct graph *rdg,
 	  }
 }
 
+/* Returns true when DEF is an SSA_NAME defined in LOOP and used after
+   the LOOP.  */
+
+static bool
+ssa_name_has_uses_outside_loop_p (tree def, loop_p loop)
+{
+  imm_use_iterator imm_iter;
+  use_operand_p use_p;
+
+  FOR_EACH_IMM_USE_FAST (use_p, imm_iter, def)
+    if (loop != loop_containing_stmt (USE_STMT (use_p)))
+      return true;
+
+  return false;
+}
+
+/* Returns true when STMT defines a scalar variable used after the
+   loop.  */
+
+static bool
+stmt_has_scalar_dependences_outside_loop (gimple stmt)
+{
+  tree name;
+
+  switch (gimple_code (stmt))
+    {
+    case GIMPLE_ASSIGN:
+      name = gimple_assign_lhs (stmt);
+      break;
+
+    case GIMPLE_PHI:
+      name = gimple_phi_result (stmt);
+      break;
+
+    default:
+      return false;
+    }
+
+  return TREE_CODE (name) == SSA_NAME
+    && ssa_name_has_uses_outside_loop_p (name, loop_containing_stmt (stmt));
+}
+
+/* Returns true when STMT will be code generated in a partition of RDG
+   different than PART and that will not be code generated as a
+   builtin.  */
+
+static bool
+stmt_generated_in_another_partition (struct graph *rdg, gimple stmt, int part,
+				     VEC (bitmap, heap) *partitions)
+{
+  int p;
+  bitmap pp;
+  unsigned i;
+  bitmap_iterator bi;
+
+  FOR_EACH_VEC_ELT (bitmap, partitions, p, pp)
+    if (p != part
+	&& !can_generate_builtin (rdg, pp))
+      EXECUTE_IF_SET_IN_BITMAP (pp, 0, i, bi)
+	if (stmt == RDG_STMT (rdg, i))
+	  return true;
+
+  return false;
+}
+
+/* For each partition in PARTITIONS that will be code generated using
+   a builtin, add its scalar computations used after the loop to
+   PARTITION.  */
+
+static void
+add_scalar_computations_to_partition (struct graph *rdg,
+				      VEC (bitmap, heap) *partitions,
+				      bitmap partition)
+{
+  int p;
+  bitmap pp;
+  unsigned i;
+  bitmap_iterator bi;
+  bitmap l = BITMAP_ALLOC (NULL);
+  bitmap pr = BITMAP_ALLOC (NULL);
+  bool f = false;
+
+  FOR_EACH_VEC_ELT (bitmap, partitions, p, pp)
+    if (can_generate_builtin (rdg, pp))
+      EXECUTE_IF_SET_IN_BITMAP (pp, 0, i, bi)
+	if (stmt_has_scalar_dependences_outside_loop (RDG_STMT (rdg, i))
+	    && !stmt_generated_in_another_partition (rdg, RDG_STMT (rdg, i), p,
+						     partitions))
+	  rdg_flag_vertex_and_dependent (rdg, i, partition, l, pr, &f);
+
+  rdg_flag_loop_exits (rdg, l, partition, pr, &f);
+
+  BITMAP_FREE (pr);
+  BITMAP_FREE (l);
+}
+
 /* Aggregate several components into a useful partition that is
    registered in the PARTITIONS vector.  Partitions will be
    distributed in different loops.  */
@@ -871,6 +967,8 @@ rdg_build_partitions (struct graph *rdg, VEC (rdgc, heap) *components,
       free_rdg_components (comps);
     }
 
+  add_scalar_computations_to_partition (rdg, *partitions, partition);
+
   /* If there is something left in the last partition, save it.  */
   if (bitmap_count_bits (partition) > 0)
     VEC_safe_push (bitmap, heap, *partitions, partition);