* config/i386/i386.md (simple LEA peephole2s): Add zero-extend

	variants of PLUS and MULT simple LEA patterns.  Disable PLUS
	patterns for TARGET_OPT_AGU.



git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@190301 138bc75d-0d04-0410-961f-82ee72b054a4

2 files changed, 130 insertions, 36 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 0ba7d42cf25..6fe9b3671cc 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,9 @@
+2012-08-10  Uros Bizjak  <ubizjak@gmail.com>
+
+	* config/i386/i386.md (simple LEA peephole2s): Add zero-extend
+	variants of PLUS and MULT simple LEA patterns.  Disable PLUS
+	patterns for TARGET_OPT_AGU.
+
 2012-08-10  Richard Guenther  <rguenther@suse.de>
 
 	* Makefile.in (OBJS): Remove matrix-reorg.o.
@@ -124,8 +130,8 @@
 
 2012-08-10  Michael Zolotukhin  <michael.v.zolotukhin@intel.com>
 
-	* config/i386/i386.c (ix86_init_mmx_sse_builtins): Fix builtin
-	target mask of __builtin_ia32_rdseed_di_step.
+	* config/i386/i386.c (ix86_init_mmx_sse_builtins): Fix
+	target mask of __builtin_ia32_rdseed_di_step builtin.
 
 2012-08-10  Richard Guenther  <rguenther@suse.de>
 
@@ -377,10 +383,10 @@
 
 2012-08-09  Uros Bizjak  <ubizjak@gmail.com>
 
-        * config/alpha/alpha.c (alpha_pad_noreturn): Rename to ...
-        (alpha_pad_function_end): ... this.  Also insert NOP between
-        sibling call and GP load.
-        (alpha_reorg): Update call to alpha_pad_function_end.  Expand comment.
+	* config/alpha/alpha.c (alpha_pad_noreturn): Rename to ...
+	(alpha_pad_function_end): ... this.  Also insert NOP between
+	sibling call and GP load.
+	(alpha_reorg): Update call to alpha_pad_function_end.  Expand comment.
 
 2012-08-09  Michael Zolotukhin  <michael.v.zolotukhin@intel.com>
 
@@ -1843,25 +1849,25 @@
 
 2012-07-27  Segher Boessenkool  <segher@kernel.crashing.org>
 
-        * config/rs6000/constraints.md: Delete "q" constraint.
-        * config/rs6000/dfp.md (movsd_hardfloat, movsd_softfloat):
-        Delete the "q" alternative.
-        * config/rs6000/predicates.md (gpc_reg_operand): Adjust.
-        * config/rs6000/rs6000.c (rs6000_debug_reg_global,
-        rs6000_init_hard_regno_mode_ok, rs6000_dbx_register_number):
-        Adjust to MQ_REGNO removal.
-        * config/rs6000/rs6000.h (FIRST_PSEUDO_REGISTER): Adjust
-        comment.
-        (REG_ALLOC_ORDER): Adjust comment.  Remove MQ from alloc order.
-        (enum reg_class): Adjust comment.  Delete MQ_REGS.
-        (REG_CLASS_CONTENTS): Adjust.
-        (REGISTER_NAMES, ADDITIONAL_REGISTER_NAMES): Adjust comment.
-        * config/rs6000/rs6000.md: Delete MQ_REGNO.
-        (movsi_internal1, movsi_internal1_single, movhi_internal,
-        movqi_internal, movcc_internal1, movsf_hardfloat,
-        movsf_softfloat): Delete the "q" alternative.
-        (ctr<mode>_internal1, ctr<mode>_internal2, ctr<mode>_internal5,
-        ctr<mode>_internal6): Delete "q" constraint.
+	* config/rs6000/constraints.md: Delete "q" constraint.
+	* config/rs6000/dfp.md (movsd_hardfloat, movsd_softfloat):
+	Delete the "q" alternative.
+	* config/rs6000/predicates.md (gpc_reg_operand): Adjust.
+	* config/rs6000/rs6000.c (rs6000_debug_reg_global)
+	(rs6000_init_hard_regno_mode_ok, rs6000_dbx_register_number):
+	adjust to MQ_REGNO removal.
+	* config/rs6000/rs6000.h (FIRST_PSEUDO_REGISTER): Adjust
+	comment.
+	(REG_ALLOC_ORDER): Adjust comment.  Remove MQ from alloc order.
+	(enum reg_class): Adjust comment.  Delete MQ_REGS.
+	(REG_CLASS_CONTENTS): Adjust.
+	(REGISTER_NAMES, ADDITIONAL_REGISTER_NAMES): Adjust comment.
+	* config/rs6000/rs6000.md: Delete MQ_REGNO.
+	(movsi_internal1, movsi_internal1_single, movhi_internal,
+	movqi_internal, movcc_internal1, movsf_hardfloat,
+	movsf_softfloat): Delete the "q" alternative.
+	(ctr<mode>_internal1, ctr<mode>_internal2, ctr<mode>_internal5,
+	ctr<mode>_internal6): Delete "q" constraint.
 
 2012-07-27  Richard Guenther  <rguenther@suse.de>
 
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 6774ae279d6..837547e2d8a 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -17317,12 +17317,15 @@
 
 ;; Attempt to convert simple lea to add/shift.
 ;; These can be created by move expanders.
+;; Disable PLUS peepholes on TARGET_OPT_AGU, since all
+;; relevant lea instructions were already split.
 
 (define_peephole2
   [(set (match_operand:SWI48 0 "register_operand")
   	(plus:SWI48 (match_dup 0)
 		    (match_operand:SWI48 1 "<nonmemory_operand>")))]
-  "peep2_regno_dead_p (0, FLAGS_REG)"
+  "!TARGET_OPT_AGU
+   && peep2_regno_dead_p (0, FLAGS_REG)"
   [(parallel [(set (match_dup 0) (plus:SWI48 (match_dup 0) (match_dup 1)))
 	      (clobber (reg:CC FLAGS_REG))])])
 
@@ -17330,7 +17333,8 @@
   [(set (match_operand:SWI48 0 "register_operand")
   	(plus:SWI48 (match_operand:SWI48 1 "<nonmemory_operand>")
 		    (match_dup 0)))]
-  "peep2_regno_dead_p (0, FLAGS_REG)"
+  "!TARGET_OPT_AGU
+   && peep2_regno_dead_p (0, FLAGS_REG)"
   [(parallel [(set (match_dup 0) (plus:SWI48 (match_dup 0) (match_dup 1)))
 	      (clobber (reg:CC FLAGS_REG))])])
 
@@ -17338,9 +17342,9 @@
   [(set (match_operand:SI 0 "register_operand")
   	(subreg:SI (plus:DI (match_operand:DI 1 "register_operand")
 			    (match_operand:DI 2 "nonmemory_operand")) 0))]
-  "TARGET_64BIT
-   && peep2_regno_dead_p (0, FLAGS_REG)
-   && REGNO (operands[0]) == REGNO (operands[1])"
+  "TARGET_64BIT && !TARGET_OPT_AGU
+   && REGNO (operands[0]) == REGNO (operands[1])
+   && peep2_regno_dead_p (0, FLAGS_REG)"
   [(parallel [(set (match_dup 0) (plus:SI (match_dup 0) (match_dup 2)))
 	      (clobber (reg:CC FLAGS_REG))])]
   "operands[2] = gen_lowpart (SImode, operands[2]);")
@@ -17349,27 +17353,81 @@
   [(set (match_operand:SI 0 "register_operand")
   	(subreg:SI (plus:DI (match_operand:DI 1 "nonmemory_operand")
 			    (match_operand:DI 2 "register_operand")) 0))]
-  "TARGET_64BIT
-   && peep2_regno_dead_p (0, FLAGS_REG)
-   && REGNO (operands[0]) == REGNO (operands[2])"
+  "TARGET_64BIT && !TARGET_OPT_AGU
+   && REGNO (operands[0]) == REGNO (operands[2])
+   && peep2_regno_dead_p (0, FLAGS_REG)"
   [(parallel [(set (match_dup 0) (plus:SI (match_dup 0) (match_dup 1)))
 	      (clobber (reg:CC FLAGS_REG))])]
   "operands[1] = gen_lowpart (SImode, operands[1]);")
 
 (define_peephole2
+  [(set (match_operand:DI 0 "register_operand")
+  	(zero_extend:DI
+	  (plus:SI (match_operand:SI 1 "register_operand")
+		   (match_operand:SI 2 "nonmemory_operand"))))]
+  "TARGET_64BIT && !TARGET_OPT_AGU
+   && REGNO (operands[0]) == REGNO (operands[1])
+   && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(parallel [(set (match_dup 0)
+		   (zero_extend:DI (plus:SI (match_dup 1) (match_dup 2))))
+	      (clobber (reg:CC FLAGS_REG))])])
+
+(define_peephole2
+  [(set (match_operand:DI 0 "register_operand")
+  	(zero_extend:DI
+	  (plus:SI (match_operand:SI 1 "nonmemory_operand")
+		   (match_operand:SI 2 "register_operand"))))]
+  "TARGET_64BIT && !TARGET_OPT_AGU
+   && REGNO (operands[0]) == REGNO (operands[2])
+   && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(parallel [(set (match_dup 0)
+		   (zero_extend:DI (plus:SI (match_dup 2) (match_dup 1))))
+	      (clobber (reg:CC FLAGS_REG))])])
+
+(define_peephole2
+  [(set (match_operand:DI 0 "register_operand")
+  	(zero_extend:DI
+	  (subreg:SI (plus:DI (match_dup 0)
+			      (match_operand:DI 1 "nonmemory_operand")) 0)))]
+  "TARGET_64BIT && !TARGET_OPT_AGU
+   && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(parallel [(set (match_dup 0)
+		   (zero_extend:DI (plus:SI (match_dup 2) (match_dup 1))))
+	      (clobber (reg:CC FLAGS_REG))])]
+{
+  operands[1] = gen_lowpart (SImode, operands[1]);
+  operands[2] = gen_lowpart (SImode, operands[0]);
+})
+
+(define_peephole2
+  [(set (match_operand:DI 0 "register_operand")
+  	(zero_extend:DI
+	  (subreg:SI (plus:DI (match_operand:DI 1 "nonmemory_operand")
+		     	      (match_dup 0)) 0)))]
+  "TARGET_64BIT && !TARGET_OPT_AGU
+   && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(parallel [(set (match_dup 0)
+		   (zero_extend:DI (plus:SI (match_dup 2) (match_dup 1))))
+	      (clobber (reg:CC FLAGS_REG))])]
+{
+  operands[1] = gen_lowpart (SImode, operands[1]);
+  operands[2] = gen_lowpart (SImode, operands[0]);
+})
+
+(define_peephole2
   [(set (match_operand:SWI48 0 "register_operand")
   	(mult:SWI48 (match_dup 0)
 		    (match_operand:SWI48 1 "const_int_operand")))]
   "exact_log2 (INTVAL (operands[1])) >= 0
    && peep2_regno_dead_p (0, FLAGS_REG)"
-  [(parallel [(set (match_dup 0) (ashift:SWI48 (match_dup 0) (match_dup 2)))
+  [(parallel [(set (match_dup 0) (ashift:SWI48 (match_dup 0) (match_dup 1)))
 	      (clobber (reg:CC FLAGS_REG))])]
-  "operands[2] = GEN_INT (exact_log2 (INTVAL (operands[1])));")
+  "operands[1] = GEN_INT (exact_log2 (INTVAL (operands[1])));")
 
 (define_peephole2
   [(set (match_operand:SI 0 "register_operand")
   	(subreg:SI (mult:DI (match_operand:DI 1 "register_operand")
-		   (match_operand:DI 2 "const_int_operand")) 0))]
+			    (match_operand:DI 2 "const_int_operand")) 0))]
   "TARGET_64BIT
    && exact_log2 (INTVAL (operands[2])) >= 0
    && REGNO (operands[0]) == REGNO (operands[1])
@@ -17378,6 +17436,36 @@
 	      (clobber (reg:CC FLAGS_REG))])]
   "operands[2] = GEN_INT (exact_log2 (INTVAL (operands[2])));")
 
+(define_peephole2
+  [(set (match_operand:DI 0 "register_operand")
+  	(zero_extend:DI
+	  (mult:SI (match_operand:SI 1 "register_operand")
+		   (match_operand:SI 2 "const_int_operand"))))]
+  "TARGET_64BIT
+   && exact_log2 (INTVAL (operands[2])) >= 0
+   && REGNO (operands[0]) == REGNO (operands[1])
+   && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(parallel [(set (match_dup 0)
+		   (zero_extend (ashift:SI (match_dup 1) (match_dup 2))))
+	      (clobber (reg:CC FLAGS_REG))])]
+  "operands[2] = GEN_INT (exact_log2 (INTVAL (operands[2])));")
+
+(define_peephole2
+  [(set (match_operand:DI 0 "register_operand")
+  	(zero_extend:DI
+  	  (subreg:SI (mult:DI (match_dup 0)
+			      (match_operand:DI 1 "const_int_operand")) 0)))]
+  "TARGET_64BIT
+   && exact_log2 (INTVAL (operands[2])) >= 0
+   && peep2_regno_dead_p (0, FLAGS_REG)"
+  [(parallel [(set (match_dup 0)
+		   (zero_extend:DI (ashift:SI (match_dup 2) (match_dup 1))))
+	      (clobber (reg:CC FLAGS_REG))])]
+{
+  operands[1] = GEN_INT (exact_log2 (INTVAL (operands[1])));
+  operands[2] = gen_lowpart (SImode, operands[0]);
+})
+
 ;; The ESP adjustments can be done by the push and pop instructions.  Resulting
 ;; code is shorter, since push is only 1 byte, while add imm, %esp is 3 bytes.
 ;; On many CPUs it is also faster, since special hardware to avoid esp