Makefile.in (tree-ssa-copy.o): Add $(CFGLOOP_H) dependency.

2009-04-04  Richard Guenther  <rguenther@suse.de>

	* Makefile.in (tree-ssa-copy.o): Add $(CFGLOOP_H) dependency.
	* tree-ssa-copy.c (init_copy_prop): Do not propagate through
	single-argument PHIs if we are in loop-closed SSA form.
	* tree-vect-loop-manip.c (slpeel_add_loop_guard): Pass extra guards
	for the pre-condition.
	(slpeel_tree_peel_loop_to_edge): Likewise.
	(vect_build_loop_niters): Take an optional sequence to append stmts.
	(vect_generate_tmps_on_preheader): Likewise.
	(vect_do_peeling_for_loop_bound): Take extra guards for the
	pre-condition.
	(vect_do_peeling_for_alignment): Adjust.  Unconditionally apply
	the cost model check.
	(vect_loop_versioning): Take stmt and stmt list to put pre-condition
	guards if we are going to peel.  Do not apply versioning in that
	case.
	* tree-vectorizer.h (vect_loop_versioning): Adjust declaration.
	(vect_do_peeling_for_loop_bound): Likewise.
	* tree-vect-loop.c (vect_transform_loop): If we are peeling for
	loop bound only record extra pre-conditions, do not apply loop
	versioning.

From-SVN: r145551

gcc/ChangeLog

 2009-04-04  Richard Guenther  <rguenther@suse.de>
 
+	* Makefile.in (tree-ssa-copy.o): Add $(CFGLOOP_H) dependency.
+	* tree-ssa-copy.c (init_copy_prop): Do not propagate through
+	single-argument PHIs if we are in loop-closed SSA form.
+	* tree-vect-loop-manip.c (slpeel_add_loop_guard): Pass extra guards
+	for the pre-condition.
+	(slpeel_tree_peel_loop_to_edge): Likewise.
+	(vect_build_loop_niters): Take an optional sequence to append stmts.
+	(vect_generate_tmps_on_preheader): Likewise.
+	(vect_do_peeling_for_loop_bound): Take extra guards for the
+	pre-condition.
+	(vect_do_peeling_for_alignment): Adjust.  Unconditionally apply
+	the cost model check.
+	(vect_loop_versioning): Take stmt and stmt list to put pre-condition
+	guards if we are going to peel.  Do not apply versioning in that
+	case.
+	* tree-vectorizer.h (vect_loop_versioning): Adjust declaration.
+	(vect_do_peeling_for_loop_bound): Likewise.
+	* tree-vect-loop.c (vect_transform_loop): If we are peeling for
+	loop bound only record extra pre-conditions, do not apply loop
+	versioning.
+
+2009-04-04  Richard Guenther  <rguenther@suse.de>
+
 	* tree-ssa-operands.c (pop_stmt_changes): Remove automatic
 	renaming code.
 

gcc/Makefile.in

@@ -2124,7 +2124,8 @@ tree-nrv.o : tree-nrv.c $(CONFIG_H) $(SYSTEM_H) coretypes.h \
 tree-ssa-copy.o : tree-ssa-copy.c $(TREE_FLOW_H) $(CONFIG_H) $(SYSTEM_H) \
    $(RTL_H) $(TREE_H) $(TM_P_H) $(EXPR_H) $(GGC_H) output.h $(DIAGNOSTIC_H) \
    $(FUNCTION_H) $(TIMEVAR_H) $(TM_H) coretypes.h $(TREE_DUMP_H) \
-   $(BASIC_BLOCK_H) tree-pass.h langhooks.h tree-ssa-propagate.h $(FLAGS_H)
+   $(BASIC_BLOCK_H) tree-pass.h langhooks.h tree-ssa-propagate.h $(FLAGS_H) \
+   $(CFGLOOP_H)
 tree-ssa-propagate.o : tree-ssa-propagate.c $(TREE_FLOW_H) $(CONFIG_H) \
    $(SYSTEM_H) $(RTL_H) $(TREE_H) $(TM_P_H) $(EXPR_H) $(GGC_H) output.h \
    $(DIAGNOSTIC_H) $(FUNCTION_H) $(TIMEVAR_H) $(TM_H) coretypes.h \

gcc/tree-ssa-copy.c

@@ -37,6 +37,7 @@ along with GCC; see the file COPYING3.  If not see
 #include "tree-pass.h"
 #include "tree-ssa-propagate.h"
 #include "langhooks.h"
+#include "cfgloop.h"
 
 /* This file implements the copy propagation pass and provides a
    handful of interfaces for performing const/copy propagation and
@@ -885,7 +886,13 @@ init_copy_prop (void)
           tree def;
 
 	  def = gimple_phi_result (phi);
-	  if (!is_gimple_reg (def))
+	  if (!is_gimple_reg (def)
+	      /* In loop-closed SSA form do not copy-propagate through
+	         PHI nodes.  Technically this is only needed for loop
+		 exit PHIs, but this is difficult to query.  */
+	      || (current_loops
+		  && gimple_phi_num_args (phi) == 1
+		  && loops_state_satisfies_p (LOOP_CLOSED_SSA)))
             prop_set_simulate_again (phi, false);
 	  else
             prop_set_simulate_again (phi, true);

gcc/tree-vect-loop.c

@@ -3388,23 +3388,33 @@ vect_transform_loop (loop_vec_info loop_vinfo)
   bool strided_store;
   bool slp_scheduled = false;
   unsigned int nunits;
+  tree cond_expr = NULL_TREE;
+  gimple_seq cond_expr_stmt_list = NULL;
+  bool do_peeling_for_loop_bound;
 
   if (vect_print_dump_info (REPORT_DETAILS))
     fprintf (vect_dump, "=== vec_transform_loop ===");
 
+  /* Peel the loop if there are data refs with unknown alignment.
+     Only one data ref with unknown store is allowed.  */
+
+  if (LOOP_PEELING_FOR_ALIGNMENT (loop_vinfo))
+    vect_do_peeling_for_alignment (loop_vinfo);
+
+  do_peeling_for_loop_bound
+    = (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+       || (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
+	   && LOOP_VINFO_INT_NITERS (loop_vinfo) % vectorization_factor != 0));
+
   if (VEC_length (gimple, LOOP_VINFO_MAY_MISALIGN_STMTS (loop_vinfo))
       || VEC_length (ddr_p, LOOP_VINFO_MAY_ALIAS_DDRS (loop_vinfo)))
-    vect_loop_versioning (loop_vinfo);
+    vect_loop_versioning (loop_vinfo,
+			  !do_peeling_for_loop_bound,
+			  &cond_expr, &cond_expr_stmt_list);
 
   /* CHECKME: we wouldn't need this if we called update_ssa once
      for all loops.  */
   bitmap_zero (vect_memsyms_to_rename);
-
-  /* Peel the loop if there are data refs with unknown alignment.
-     Only one data ref with unknown store is allowed.  */
-
-  if (LOOP_PEELING_FOR_ALIGNMENT (loop_vinfo))
-    vect_do_peeling_for_alignment (loop_vinfo);
   
   /* If the loop has a symbolic number of iterations 'n' (i.e. it's not a
      compile time constant), or it is a constant that doesn't divide by the
@@ -3414,10 +3424,9 @@ vect_transform_loop (loop_vec_info loop_vinfo)
      will remain scalar and will compute the remaining (n%VF) iterations.
      (VF is the vectorization factor).  */
 
-  if (!LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
-      || (LOOP_VINFO_NITERS_KNOWN_P (loop_vinfo)
-          && LOOP_VINFO_INT_NITERS (loop_vinfo) % vectorization_factor != 0))
-    vect_do_peeling_for_loop_bound (loop_vinfo, &ratio);
+  if (do_peeling_for_loop_bound)
+    vect_do_peeling_for_loop_bound (loop_vinfo, &ratio,
+				    cond_expr, cond_expr_stmt_list);
   else
     ratio = build_int_cst (TREE_TYPE (LOOP_VINFO_NITERS (loop_vinfo)),
 		LOOP_VINFO_INT_NITERS (loop_vinfo) / vectorization_factor);

gcc/tree-vectorizer.h

@@ -706,8 +706,9 @@ extern bitmap vect_memsyms_to_rename;
    in tree-vect-loop-manip.c.  */
 extern void slpeel_make_loop_iterate_ntimes (struct loop *, tree);
 extern bool slpeel_can_duplicate_loop_p (const struct loop *, const_edge);
-extern void vect_loop_versioning (loop_vec_info);
-extern void vect_do_peeling_for_loop_bound (loop_vec_info, tree *);
+extern void vect_loop_versioning (loop_vec_info, bool, tree *, gimple_seq *);
+extern void vect_do_peeling_for_loop_bound (loop_vec_info, tree *,
+					    tree, gimple_seq);
 extern void vect_do_peeling_for_alignment (loop_vec_info);
 extern LOC find_loop_location (struct loop *);
 extern bool vect_can_advance_ivs_p (loop_vec_info);