re PR rtl-optimization/37948 (IRA generates slower code)

2008-11-07  Vladimir Makarov  <vmakarov@redhat.com>
	    
	PR rtl-optimizations/37948
	* ira-int.h (struct ira_allocno_copy): New member constraint_p.
	(ira_create_copy, ira_add_allocno_copy): New parameter.

	* ira-conflicts.c (process_regs_for_copy): New parameter.  Pass it
	to ira_add_allocno_copy.
	(process_reg_shuffles, add_insn_allocno_copies): Pass a new
	parameter to process_regs_for_copy.
	(propagate_copies): Pass a new parameter to ira_add_allocno_copy.
	Fix typo in passing second allocno to ira_add_allocno_copy.

	* ira-color.c (update_conflict_hard_regno_costs): Use head of
	coalesced allocnos list.
	(assign_hard_reg): Ditto.  Check that assigned allocnos are not in
	the graph.
	(add_ira_allocno_to_bucket): Rename to add_allocno_to_bucket.
	(add_ira_allocno_to_ordered_bucket): Rename to
	add_allocno_to_ordered_bucket.
	(push_ira_allocno_to_stack): Rename to push_allocno_to_stack.  Use
	head of coalesced allocnos list.
	(push_allocnos_to_stack): Remove calculation of ALLOCNO_TEMP.
	Check that it is aready calculated.
	(push_ira_allocno_to_spill): Rename to push_ira_allocno_to_spill.
	(setup_allocno_left_conflicts_num): Use head of coalesced allocnos
	list.
	(coalesce_allocnos): Do extended coalescing too.

	* ira-emit.c (add_range_and_copies_from_move_list): Pass a new
	parameter to ira_add_allocno_copy.

	* ira-build.c (ira_create_copy, ira_add_allocno_copy): Add a new
	parameter.
	(print_copy): Print copy origination too.

	* ira-costs.c (scan_one_insn): Use alloc_pref for load from
	equivalent memory.

From-SVN: r141753

1 files changed, 10 insertions, 7 deletions

diff --git a/gcc/ira-conflicts.c b/gcc/ira-conflicts.c
index 01ba907..66376b6 100644
--- a/gcc/ira-conflicts.c
+++ b/gcc/ira-conflicts.c
@@ -329,7 +329,8 @@ go_through_subreg (rtx x, int *offset)
    registers.  When nothing is changed, the function returns
    FALSE.  */
 static bool
-process_regs_for_copy (rtx reg1, rtx reg2, rtx insn, int freq)
+process_regs_for_copy (rtx reg1, rtx reg2, bool constraint_p,
+		       rtx insn, int freq)
 {
   int allocno_preferenced_hard_regno, cost, index, offset1, offset2;
   bool only_regs_p;
@@ -363,7 +364,8 @@ process_regs_for_copy (rtx reg1, rtx reg2, rtx insn, int freq)
     {
       cp = ira_add_allocno_copy (ira_curr_regno_allocno_map[REGNO (reg1)],
 				 ira_curr_regno_allocno_map[REGNO (reg2)],
-				 freq, insn, ira_curr_loop_tree_node);
+				 freq, constraint_p, insn,
+				 ira_curr_loop_tree_node);
       bitmap_set_bit (ira_curr_loop_tree_node->local_copies, cp->num); 
       return true;
     }
@@ -426,7 +428,7 @@ process_reg_shuffles (rtx reg, int op_num, int freq)
 	  || recog_data.operand_type[i] != OP_OUT)
 	continue;
       
-      process_regs_for_copy (reg, another_reg, NULL_RTX, freq);
+      process_regs_for_copy (reg, another_reg, false, NULL_RTX, freq);
     }
 }
 
@@ -451,7 +453,7 @@ add_insn_allocno_copies (rtx insn)
 			REG_P (SET_SRC (set))
 			? SET_SRC (set)
 			: SUBREG_REG (SET_SRC (set))) != NULL_RTX)
-    process_regs_for_copy (SET_DEST (set), SET_SRC (set), insn, freq);
+    process_regs_for_copy (SET_DEST (set), SET_SRC (set), false, insn, freq);
   else
     {
       extract_insn (insn);
@@ -470,7 +472,8 @@ add_insn_allocno_copies (rtx insn)
 	      for (j = 0, commut_p = false; j < 2; j++, commut_p = true)
 		if ((dup = get_dup (i, commut_p)) != NULL_RTX
 		    && REG_SUBREG_P (dup)
-		    && process_regs_for_copy (operand, dup, NULL_RTX, freq))
+		    && process_regs_for_copy (operand, dup, true,
+					      NULL_RTX, freq))
 		  bound_p = true;
 	      if (bound_p)
 		continue;
@@ -524,8 +527,8 @@ propagate_copies (void)
 	parent_a2 = parent->regno_allocno_map[ALLOCNO_REGNO (a2)];
       ira_assert (parent_a1 != NULL && parent_a2 != NULL);
       if (! CONFLICT_ALLOCNO_P (parent_a1, parent_a2))
-	ira_add_allocno_copy (parent_a1, parent_a1, cp->freq,
-			      cp->insn, cp->loop_tree_node);
+	ira_add_allocno_copy (parent_a1, parent_a2, cp->freq,
+			      cp->constraint_p, cp->insn, cp->loop_tree_node);
     }
 }