i386.md (*add<mode>_1): Split insn to lea.

	* config/i386/i386.md (*add<mode>_1) <TYPE_LEA>: Split insn to lea.
	<default>:  Swap operands 1 and 2 for alternative 2 to use existing
	code to output insn mnemonic.  Fix comment.
	(*addsi_1_zext): Add r-r-0 alternative 1.
	<TYPE_LEA>: Split insn to lea.
	<default>: Handle alternative 1.
	(*addhi_1_lea): Add r-r-0 alternative 2.  Use cond RTX instead of
	multi-level if_then_else RTX to set "type" attribute.
	<default>: Handle alternative 2.
	(*addqi_1_lea): Add q-q-0 alternative 2 and r-r-0 alternative 4.
	Use cond RTX instead of multi-level if_then_else RTX to set
	"type" attribute.
	<default>: Handle alternatives 2 and 4.
	(lea splitters): Update calls to ix86_lea_for_add_ok.

	* config/i386/i386.c (ix86_lea_for_add_ok): Remove unused "code"
	argument.
	* config/i386/i386-protos.h (ix86_lea_for_add_ok): Update prototype.

From-SVN: r163351

4 files changed, 91 insertions, 46 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 341820d..83ab94b 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,24 @@
+2010-08-18  Uros Bizjak  <ubizjak@gmail.com>
+
+	* config/i386/i386.md (*add<mode>_1) <TYPE_LEA>: Split insn to lea.
+	<default>:  Swap operands 1 and 2 for alternative 2 to use existing
+	code to output insn mnemonic.  Fix comment.
+	(*addsi_1_zext): Add r-r-0 alternative 1.
+	<TYPE_LEA>: Split insn to lea.
+	<default>: Handle alternative 1.
+	(*addhi_1_lea): Add r-r-0 alternative 2.  Use cond RTX instead of
+	multi-level if_then_else RTX to set "type" attribute.
+	<default>: Handle alternative 2.
+	(*addqi_1_lea): Add q-q-0 alternative 2 and r-r-0 alternative 4.
+	Use cond RTX instead of multi-level if_then_else RTX to set
+	"type" attribute.
+	<default>: Handle alternatives 2 and 4.
+	(lea splitters): Update calls to ix86_lea_for_add_ok.
+
+	* config/i386/i386.c (ix86_lea_for_add_ok): Remove unused "code"
+	argument.
+	* config/i386/i386-protos.h (ix86_lea_for_add_ok): Update prototype.
+
 2010-08-18  Richard Guenther  <rguenther@suse.de>
 
 	* tree-ssa-uninit.c (find_uninit_use): Disregard debug stmts,
@@ -12,7 +33,7 @@
 2010-08-18  Yao Qi  <yao@codesourcery.com>
 
 	PR target/45094
-	* config/arm/arm.c (output_move_double): Fix typo generating 
+	* config/arm/arm.c (output_move_double): Fix typo generating
 	instructions ('ldr'->'str').
 
 2010-08-18  Maxim Kuvyrkov  <maxim@codesourcery.com>
@@ -66,21 +87,19 @@
 	* config/i386/i386.c (ix86_lea_for_add_ok): For !TARGET_OPT_AGU
 	or optimizing for size, always avoid lea if possible.
 
-	* config/i386/i386.md (*add<mode>_1): Always avoid lea if
-	possible.
+	* config/i386/i386.md (*add<mode>_1): Always avoid lea if possible.
 
 2010-08-17  Iain Sandoe  <iains@gcc.gnu.org>
 
 	* unwind-dw2-fde-darwin.c (_darwin10_Unwind_FindEnclosingFunction):
-	Dunmmy function with NULL return unless the target is 
+	Dunmmy function with NULL return unless the target is
 	OSX >= 10.6 (Darwin10).
-	
+
 2010-08-17  Jack Howarth <howarth@bromo.med.uc.edu>
 
 	* gcc.c (spec_function): Add remove-outfile.
 	(remove_outfile_spec_function): New function.
-	* config/darwin.h (LINK_SPEC): Add removal of
-	-ldl, -lm and -lpthread.
+	* config/darwin.h (LINK_SPEC): Add removal of -ldl, -lm and -lpthread.
 	* invoke.texi (replace-outfile): Document.
 
 2010-08-17  Uros Bizjak  <ubizjak@gmail.com>
@@ -105,8 +124,7 @@
 
 2010-08-17  Richard Guenther  <rguenther@suse.de>
 
-	* fold-const.c (fold_comparison): Strip nops inside
-	POINTER_PLUS_EXPR.
+	* fold-const.c (fold_comparison): Strip nops inside POINTER_PLUS_EXPR.
 
 2010-08-17  Shujing Zhao  <pearly.zhao@oracle.com>
 
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index a72a432..de6b961 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -86,7 +86,7 @@ extern void ix86_fixup_binary_operands_no_copy (enum rtx_code,
 extern void ix86_expand_binary_operator (enum rtx_code,
 					 enum machine_mode, rtx[]);
 extern int ix86_binary_operator_ok (enum rtx_code, enum machine_mode, rtx[]);
-extern bool ix86_lea_for_add_ok (enum rtx_code, rtx, rtx[]);
+extern bool ix86_lea_for_add_ok (rtx, rtx[]);
 extern bool ix86_vec_interleave_v2df_operator_ok (rtx operands[3], bool high);
 extern bool ix86_dep_by_shift_count (const_rtx set_insn, const_rtx use_insn);
 extern bool ix86_agi_dependent (rtx set_insn, rtx use_insn);
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index f1d4402..c90d576 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -14808,8 +14808,7 @@ distance_agu_use (unsigned int regno0, rtx insn)
    used soon, LEA is better and otherwise ADD is better.  */
 
 bool
-ix86_lea_for_add_ok (enum rtx_code code ATTRIBUTE_UNUSED,
-                     rtx insn, rtx operands[])
+ix86_lea_for_add_ok (rtx insn, rtx operands[])
 {
   unsigned int regno0 = true_regnum (operands[0]);
   unsigned int regno1 = true_regnum (operands[1]);
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index f6ab0e2..8d61bb6 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -5799,8 +5799,7 @@
   switch (get_attr_type (insn))
     {
     case TYPE_LEA:
-      operands[2] = SET_SRC (XVECEXP (PATTERN (insn), 0, 0));
-      return "lea{<imodesuffix>}\t{%a2, %0|%0, %a2}";
+      return "#";
 
     case TYPE_INCDEC:
       gcc_assert (rtx_equal_p (operands[0], operands[1]));
@@ -5813,11 +5812,13 @@
 	}
 
     default:
-      /* This alternative was added for TARGET_OPT_AGU to use add as
-	 much as possible.  But add is also faster than lea for
-	 !TARGET_OPT_AGU.  */
+      /* For most processors, ADD is faster than LEA.  This alternative
+	 was added to use ADD as much as possible.  */
       if (which_alternative == 2)
-        return "add{<imodesuffix>}\t{%1, %0|%0, %1}";
+	{
+	  rtx tmp;
+	  tmp = operands[1], operands[1] = operands[2], operands[2] = tmp;
+	}
         
       gcc_assert (rtx_equal_p (operands[0], operands[1]));
       if (x86_maybe_negate_const_int (&operands[2], <MODE>mode))
@@ -5847,18 +5848,17 @@
 ;; patterns constructed from addsi_1 to match.
 
 (define_insn "*addsi_1_zext"
-  [(set (match_operand:DI 0 "register_operand" "=r,r")
+  [(set (match_operand:DI 0 "register_operand" "=r,r,r")
 	(zero_extend:DI
-	  (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,r")
-		   (match_operand:SI 2 "general_operand" "g,li"))))
+	  (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,r,r")
+		   (match_operand:SI 2 "general_operand" "g,0,li"))))
    (clobber (reg:CC FLAGS_REG))]
   "TARGET_64BIT && ix86_binary_operator_ok (PLUS, SImode, operands)"
 {
   switch (get_attr_type (insn))
     {
     case TYPE_LEA:
-      operands[2] = XEXP (SET_SRC (XVECEXP (PATTERN (insn), 0, 0)), 0);
-      return "lea{l}\t{%a2, %k0|%k0, %a2}";
+      return "#";
 
     case TYPE_INCDEC:
       if (operands[2] == const1_rtx)
@@ -5870,6 +5870,14 @@
 	}
 
     default:
+      /* For most processors, ADD is faster than LEA.  This alternative
+	 was added to use ADD as much as possible.  */
+      if (which_alternative == 1)
+	{
+	  rtx tmp;
+	  tmp = operands[1], operands[1] = operands[2], operands[2] = tmp;
+	}
+
       if (x86_maybe_negate_const_int (&operands[2], SImode))
         return "sub{l}\t{%2, %k0|%k0, %2}";
 
@@ -5877,7 +5885,7 @@
     }
 }
   [(set (attr "type")
-     (cond [(eq_attr "alternative" "1")
+     (cond [(eq_attr "alternative" "2")
 	      (const_string "lea")
 	    (match_operand:SI 2 "incdec_operand" "")
 	      (const_string "incdec")
@@ -5932,9 +5940,9 @@
 ;; for PII, and in fact harmful because of partial register stalls.
 
 (define_insn "*addhi_1_lea"
-  [(set (match_operand:HI 0 "nonimmediate_operand" "=rm,r,r")
-	(plus:HI (match_operand:HI 1 "nonimmediate_operand" "%0,0,r")
-		 (match_operand:HI 2 "general_operand" "rn,rm,ln")))
+  [(set (match_operand:HI 0 "nonimmediate_operand" "=r,rm,r,r")
+	(plus:HI (match_operand:HI 1 "nonimmediate_operand" "%0,0,r,r")
+		 (match_operand:HI 2 "general_operand" "rmn,rn,0,ln")))
    (clobber (reg:CC FLAGS_REG))]
   "!TARGET_PARTIAL_REG_STALL
    && ix86_binary_operator_ok (PLUS, HImode, operands)"
@@ -5955,6 +5963,14 @@
 	}
 
     default:
+      /* For most processors, ADD is faster than LEA.  This alternative
+	 was added to use ADD as much as possible.  */
+      if (which_alternative == 2)
+	{
+	  rtx tmp;
+	  tmp = operands[1], operands[1] = operands[2], operands[2] = tmp;
+	}
+
       gcc_assert (rtx_equal_p (operands[0], operands[1]));
       if (x86_maybe_negate_const_int (&operands[2], HImode))
 	return "sub{w}\t{%2, %0|%0, %2}";
@@ -5963,18 +5979,20 @@
     }
 }
   [(set (attr "type")
-     (if_then_else (eq_attr "alternative" "2")
-	(const_string "lea")
-	(if_then_else (match_operand:HI 2 "incdec_operand" "")
-	   (const_string "incdec")
-	   (const_string "alu"))))
+     (cond [(eq_attr "alternative" "3")
+              (const_string "lea")
+	    (match_operand:HI 2 "incdec_operand" "")
+	      (const_string "incdec")
+	   ]
+	   (const_string "alu")))
    (set (attr "length_immediate")
       (if_then_else
 	(and (eq_attr "type" "alu") (match_operand 2 "const128_operand" ""))
 	(const_string "1")
 	(const_string "*")))
-   (set_attr "mode" "HI,HI,SI")])
+   (set_attr "mode" "HI,HI,HI,SI")])
 
+;; %%% Potential partial reg stall on alternative 2.  What to do?
 (define_insn "*addqi_1"
   [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r")
 	(plus:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0")
@@ -6020,16 +6038,17 @@
 	(const_string "*")))
    (set_attr "mode" "QI,QI,SI")])
 
-;; %%% Potential partial reg stall on alternative 2.  What to do?
+;; %%% Potential partial reg stall on alternatives 3 and 4.  What to do?
 (define_insn "*addqi_1_lea"
-  [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,r")
-	(plus:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,r")
-		 (match_operand:QI 2 "general_operand" "qn,qmn,rn,ln")))
+  [(set (match_operand:QI 0 "nonimmediate_operand" "=q,qm,q,r,r,r")
+	(plus:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,q,0,r,r")
+		 (match_operand:QI 2 "general_operand" "qmn,qn,0,rn,0,ln")))
    (clobber (reg:CC FLAGS_REG))]
   "!TARGET_PARTIAL_REG_STALL
    && ix86_binary_operator_ok (PLUS, QImode, operands)"
 {
-  int widen = (which_alternative == 2);
+  int widen = (which_alternative == 3 || which_alternative == 4);
+
   switch (get_attr_type (insn))
     {
     case TYPE_LEA:
@@ -6046,6 +6065,14 @@
 	}
 
     default:
+      /* For most processors, ADD is faster than LEA.  These alternatives
+	 were added to use ADD as much as possible.  */
+      if (which_alternative == 2 || which_alternative == 4)
+	{
+	  rtx tmp;
+	  tmp = operands[1], operands[1] = operands[2], operands[2] = tmp;
+	}
+
       gcc_assert (rtx_equal_p (operands[0], operands[1]));
       if (x86_maybe_negate_const_int (&operands[2], QImode))
 	{
@@ -6061,17 +6088,18 @@
     }
 }
   [(set (attr "type")
-     (if_then_else (eq_attr "alternative" "3")
-	(const_string "lea")
-	(if_then_else (match_operand:QI 2 "incdec_operand" "")
-	   (const_string "incdec")
-	   (const_string "alu"))))
+     (cond [(eq_attr "alternative" "5")
+              (const_string "lea")
+	    (match_operand:QI 2 "incdec_operand" "")
+	      (const_string "incdec")
+	   ]
+	   (const_string "alu")))
    (set (attr "length_immediate")
       (if_then_else
 	(and (eq_attr "type" "alu") (match_operand 2 "const128_operand" ""))
 	(const_string "1")
 	(const_string "*")))
-   (set_attr "mode" "QI,QI,SI,SI")])
+   (set_attr "mode" "QI,QI,QI,SI,SI,SI")])
 
 (define_insn "*addqi_1_slp"
   [(set (strict_low_part (match_operand:QI 0 "nonimmediate_operand" "+qm,q"))
@@ -6658,7 +6686,7 @@
 		 (match_operand:DI 2 "x86_64_nonmemory_operand" "")))
    (clobber (reg:CC FLAGS_REG))]
   "TARGET_64BIT && reload_completed 
-   && ix86_lea_for_add_ok (PLUS, insn, operands)"
+   && ix86_lea_for_add_ok (insn, operands)"
   [(set (match_dup 0)
 	(plus:DI (match_dup 1)
 		 (match_dup 2)))]
@@ -6670,7 +6698,7 @@
 	(plus (match_operand 1 "register_operand" "")
               (match_operand 2 "nonmemory_operand" "")))
    (clobber (reg:CC FLAGS_REG))]
-  "reload_completed && ix86_lea_for_add_ok (PLUS, insn, operands)" 
+  "reload_completed && ix86_lea_for_add_ok (insn, operands)" 
   [(const_int 0)]
 {
   rtx pat;