[ix86/gcc-4_5-branch] PATCH: Always avoid lea if possible on x86

["H.J. Lu" <hongjiu dot lu at intel dot com>]

On Tue, Aug 17, 2010 at 07:49:25AM -0700, H.J. Lu wrote:
> Hi,
> 
> We added ix86_lea_for_add_ok and modified *add<mode>_1 to make sure
> that we use LEA on address and ADD on non-address for TARGET_OPT_AGU.
> It turned out ADD is always faster than LEA on all processors, except for
> TARGET_OPT_AGU.  This patch changes *add<mode>_1 and ix86_lea_for_add_ok
> to avoid lea for !TARGET_OPT_AGU processors.  OK for trunk?
> 
> Thanks.
> 
> 
> H.J.
> ---
> 2010-08-17  H.J. Lu  <hongjiu.lu@intel.com>
> 
> 	* 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.
> 

I backported it to ix86/gcc-4_5-branch.


H.J.
---
diff --git a/gcc/ChangeLog.ix86 b/gcc/ChangeLog.ix86
index c5ba9c9..116f87a 100644
--- a/gcc/ChangeLog.ix86
+++ b/gcc/ChangeLog.ix86
@@ -1,3 +1,14 @@
+2010-08-19  H.J. Lu  <hongjiu.lu@intel.com>
+
+	Backport from mainline
+	2010-08-17  H.J. Lu  <hongjiu.lu@intel.com>
+
+	* 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.
+
 2010-08-12  H.J. Lu  <hongjiu.lu@intel.com>
 
 	Backport from mainline
diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 4b7a061..7265465 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -13902,10 +13902,10 @@ distance_agu_use (unsigned int regno0, rtx insn)
 #define IX86_LEA_PRIORITY 2
 
 /* Return true if it is ok to optimize an ADD operation to LEA
-   operation to avoid flag register consumation.  For the processors
-   like ATOM, if the destination register of LEA holds an actual
-   address which will be used soon, LEA is better and otherwise ADD
-   is better.  */
+   operation to avoid flag register consumation.  For most processors,
+   ADD is faster than LEA.  For the processors like ATOM, if the
+   destination register of LEA holds an actual address which will be
+   used soon, LEA is better and otherwise ADD is better.  */
 
 bool
 ix86_lea_for_add_ok (enum rtx_code code ATTRIBUTE_UNUSED,
@@ -13913,17 +13913,15 @@ ix86_lea_for_add_ok (enum rtx_code code ATTRIBUTE_UNUSED,
 {
   unsigned int regno0 = true_regnum (operands[0]);
   unsigned int regno1 = true_regnum (operands[1]);
-  unsigned int regno2;
-
-  if (!TARGET_OPT_AGU || optimize_function_for_size_p (cfun))
-    return regno0 != regno1;
-
-  regno2 = true_regnum (operands[2]);
+  unsigned int regno2 = true_regnum (operands[2]);
 
   /* If a = b + c, (a!=b && a!=c), must use lea form. */
   if (regno0 != regno1 && regno0 != regno2)
     return true;
-  else    
+
+  if (!TARGET_OPT_AGU || optimize_function_for_size_p (cfun))
+    return false;
+  else
     {
       int dist_define, dist_use;
       dist_define = distance_non_agu_define (regno1, regno2, insn);
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index d092a4a..2f1b25e 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -6015,8 +6015,10 @@
 	}
 
     default:
-      /* Use add as much as possible to replace lea for AGU optimization. */
-      if (which_alternative == 2 && TARGET_OPT_AGU)
+      /* 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.  */
+      if (which_alternative == 2)
         return "add{<imodesuffix>}\t{%1, %0|%0, %1}";
         
       gcc_assert (rtx_equal_p (operands[0], operands[1]));
@@ -6038,10 +6040,7 @@
     }
 }
   [(set (attr "type")
-     (cond [(and (eq_attr "alternative" "2") 
-                 (eq (symbol_ref "TARGET_OPT_AGU") (const_int 0)))
-	      (const_string "lea")
-            (eq_attr "alternative" "3")
+     (cond [(eq_attr "alternative" "3")
               (const_string "lea")
 	    ; Current assemblers are broken and do not allow @GOTOFF in
 	    ; ought but a memory context.