re PR tree-optimization/56118 (Piecewise vector / complex initialization from constants not combined)

2015-11-09  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/56118
	* tree-vectorizer.h (vect_find_last_scalar_stmt_in_slp): Declare.
	* tree-vect-slp.c (vect_find_last_scalar_stmt_in_slp): Export.
	* tree-vect-data-refs.c (vect_slp_analyze_node_dependences): New
	function.
	(vect_slp_analyze_data_ref_dependences): Instead of computing
	all dependences of the region DRs just analyze the code motions
	SLP vectorization will perform.  Remove SLP instances that
	cannot have their store/load motions applied.
	(vect_analyze_data_refs): Allow DRs without a vectype
	in BB vectorization.

	* gcc.dg/vect/no-tree-sra-bb-slp-pr50730.c: Adjust.

From-SVN: r230020

6 files changed, 105 insertions, 13 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index eb6acd5..56c609f 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,17 @@
+2015-11-09  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/56118
+	* tree-vectorizer.h (vect_find_last_scalar_stmt_in_slp): Declare.
+	* tree-vect-slp.c (vect_find_last_scalar_stmt_in_slp): Export.
+	* tree-vect-data-refs.c (vect_slp_analyze_node_dependences): New
+	function.
+	(vect_slp_analyze_data_ref_dependences): Instead of computing
+	all dependences of the region DRs just analyze the code motions
+	SLP vectorization will perform.  Remove SLP instances that
+	cannot have their store/load motions applied.
+	(vect_analyze_data_refs): Allow DRs without a vectype
+	in BB vectorization.
+
 2015-11-09  Julian Brown  <julian@codesourcery.com>
 
 	* final.c (output_asm_insn): Pass VOIDmode to output_address.
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index 4cd50cd..3809a72 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,8 @@
+2015-11-09  Richard Biener  <rguenther@suse.de>
+
+	PR tree-optimization/56118
+	* gcc.dg/vect/no-tree-sra-bb-slp-pr50730.c: Adjust.
+
 2015-11-09  Thomas Preud'homme  <thomas.preudhomme@arm.com>
 
 	* gcc.target/arm/thumb2-slow-flash-data.c: Add missing typespec for
diff --git a/gcc/testsuite/gcc.dg/vect/no-tree-sra-bb-slp-pr50730.c b/gcc/testsuite/gcc.dg/vect/no-tree-sra-bb-slp-pr50730.c
index e7328fc..8fe67f4 100644
--- a/gcc/testsuite/gcc.dg/vect/no-tree-sra-bb-slp-pr50730.c
+++ b/gcc/testsuite/gcc.dg/vect/no-tree-sra-bb-slp-pr50730.c
@@ -13,4 +13,4 @@ A sum(A a,A b)
   return a;
 }
 
-/* { dg-final { scan-tree-dump-times "not vectorized: more than one data ref in stmt" 0 "slp2" } } */
+/* { dg-final { scan-tree-dump-times "basic block vectorized" 1 "slp2" } } */
diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
index 11bce79..6e32391 100644
--- a/gcc/tree-vect-data-refs.c
+++ b/gcc/tree-vect-data-refs.c
@@ -559,6 +559,49 @@ vect_slp_analyze_data_ref_dependence (struct data_dependence_relation *ddr)
 }
 
 
+/* Analyze dependences involved in the transform of SLP NODE.  */
+
+static bool
+vect_slp_analyze_node_dependences (slp_instance instance, slp_tree node)
+{
+  /* This walks over all stmts involved in the SLP load/store done
+     in NODE verifying we can sink them up to the last stmt in the
+     group.  */
+  gimple *last_access = vect_find_last_scalar_stmt_in_slp (node);
+  for (unsigned k = 0; k < SLP_INSTANCE_GROUP_SIZE (instance); ++k)
+    {
+      gimple *access = SLP_TREE_SCALAR_STMTS (node)[k];
+      if (access == last_access)
+	continue;
+      stmt_vec_info access_stmt_info = vinfo_for_stmt (access);
+      gimple_stmt_iterator gsi = gsi_for_stmt (access);
+      gsi_next (&gsi);
+      for (; gsi_stmt (gsi) != last_access; gsi_next (&gsi))
+	{
+	  gimple *stmt = gsi_stmt (gsi);
+	  stmt_vec_info stmt_info = vinfo_for_stmt (stmt);
+	  if (!STMT_VINFO_DATA_REF (stmt_info)
+	      || (DR_IS_READ (STMT_VINFO_DATA_REF (stmt_info))
+		  && DR_IS_READ (STMT_VINFO_DATA_REF (access_stmt_info))))
+	    continue;
+
+	  ddr_p ddr = initialize_data_dependence_relation
+	      (STMT_VINFO_DATA_REF (access_stmt_info),
+	       STMT_VINFO_DATA_REF (stmt_info), vNULL);
+	  if (vect_slp_analyze_data_ref_dependence (ddr))
+	    {
+	      /* ???  If the dependence analysis failed we can resort to the
+		 alias oracle which can handle more kinds of stmts.  */
+	      free_dependence_relation (ddr);
+	      return false;
+	    }
+	  free_dependence_relation (ddr);
+	}
+    }
+  return true;
+}
+
+
 /* Function vect_analyze_data_ref_dependences.
 
    Examine all the data references in the basic-block, and make sure there
@@ -568,21 +611,45 @@ vect_slp_analyze_data_ref_dependence (struct data_dependence_relation *ddr)
 bool
 vect_slp_analyze_data_ref_dependences (bb_vec_info bb_vinfo)
 {
-  struct data_dependence_relation *ddr;
-  unsigned int i;
-
   if (dump_enabled_p ())
     dump_printf_loc (MSG_NOTE, vect_location,
                      "=== vect_slp_analyze_data_ref_dependences ===\n");
 
-  if (!compute_all_dependences (BB_VINFO_DATAREFS (bb_vinfo),
-				&BB_VINFO_DDRS (bb_vinfo),
-				vNULL, true))
-    return false;
+  slp_instance instance;
+  slp_tree load;
+  unsigned int i, j;
+  for (i = 0; BB_VINFO_SLP_INSTANCES (bb_vinfo).iterate (i, &instance); )
+    {
+      bool remove = false;
+      /* Verify we can sink loads to the vectorized stmt insert location.  */
+      FOR_EACH_VEC_ELT (SLP_INSTANCE_LOADS (instance), j, load)
+	if (! vect_slp_analyze_node_dependences (instance, load))
+	  {
+	    remove = true;
+	    break;
+	  }
+      /* Verify we can sink stores to the vectorized stmt insert location.  */
+      slp_tree store = SLP_INSTANCE_TREE (instance);
+      if (!remove
+	  && STMT_VINFO_DATA_REF
+		(vinfo_for_stmt (SLP_TREE_SCALAR_STMTS (store)[0]))
+	  && ! vect_slp_analyze_node_dependences (instance, store))
+	remove = true;
+      if (remove)
+	{
+	  dump_printf_loc (MSG_NOTE, vect_location,
+			   "removing SLP instance operations starting from: ");
+	  dump_gimple_stmt (MSG_NOTE, TDF_SLIM,
+			    SLP_TREE_SCALAR_STMTS
+			      (SLP_INSTANCE_TREE (instance))[0], 0);
+	  vect_free_slp_instance (instance);
+	  BB_VINFO_SLP_INSTANCES (bb_vinfo).ordered_remove (i);
+	}
+      i++;
+    }
 
-  FOR_EACH_VEC_ELT (BB_VINFO_DDRS (bb_vinfo), i, ddr)
-    if (vect_slp_analyze_data_ref_dependence (ddr))
-      return false;
+  if (!BB_VINFO_SLP_INSTANCES (bb_vinfo).length ())
+    return false;
 
   return true;
 }
@@ -3674,7 +3741,12 @@ again:
             }
 
           if (is_a <bb_vec_info> (vinfo))
-	    break;
+	    {
+	      /* No vector type is fine, the ref can still participate
+	         in dependence analysis, we just can't vectorize it.  */
+	      STMT_VINFO_VECTORIZABLE (stmt_info) = false;
+	      continue;
+	    }
 
 	  if (gatherscatter != SG_NONE || simd_lane_access)
 	    {
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index cfdfc29..954b85e 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -1426,7 +1426,7 @@ vect_supported_load_permutation_p (slp_instance slp_instn)
 
 /* Find the last store in SLP INSTANCE.  */
 
-static gimple *
+gimple *
 vect_find_last_scalar_stmt_in_slp (slp_tree node)
 {
   gimple *last = NULL, *stmt;
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 9cde091..fed80c8 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -1075,6 +1075,7 @@ extern void vect_detect_hybrid_slp (loop_vec_info);
 extern void vect_get_slp_defs (vec<tree> , slp_tree,
 			       vec<vec<tree> > *, int);
 extern bool vect_slp_bb (basic_block);
+extern gimple *vect_find_last_scalar_stmt_in_slp (slp_tree);
 
 /* In tree-vect-patterns.c.  */
 /* Pattern recognition functions.