PR target/23303 (worse instruction choice)

[Jan Hubicka]

Hi,
here is updated patch I am testing now.  It also adds
reg_overlap_mentioned_p test I think I missed in original patch.

OK, assuming it passes?
Honza

/* { dg-do assemble { target i?86-*-* x86_64-*-* } } */
/* { dg-require-effective-target ilp32 } */
/* { dg-options "-O2 -march=i686" } */
/* { dg-final { scan-assembler "leal" } } */
typedef struct {
  char **visbuf;
  char **allbuf;
} TScreen;

void
VTallocbuf(TScreen *screen, unsigned long savelines)
{
  screen->visbuf = &screen->allbuf[savelines];
}
2005-10-31  Jan Hubicka  <jh@suse.cz>
	PR target/23303
	* i386.md: Add peep2 for simplyfing array accesses.
Index: config/i386/i386.md
===================================================================
--- config/i386/i386.md	(revision 106395)
+++ config/i386/i386.md	(working copy)
@@ -19785,6 +19785,64 @@
   if (!rtx_equal_p (operands[0], operands[1]))
     emit_move_insn (operands[0], operands[1]);
 })
+
+;; After splitting up read-modify operations, array accesses with memory
+;; operands might end up in form:
+;;  sall    $2, %eax
+;;  movl    4(%esp), %edx
+;;  addl    %edx, %eax
+;; instead of pre-splitting:
+;;  sall    $2, %eax
+;;  addl    4(%esp), %eax
+;; Turn it into:
+;;  movl    4(%esp), %edx
+;;  leal    (%edx,%eax,4), %eax
+
+(define_peephole2
+  [(parallel [(set (match_operand 0 "register_operand" "")
+		   (ashift (match_operand 1 "register_operand" "")
+			   (match_operand 2 "const_int_operand" "")))
+	       (clobber (reg:CC FLAGS_REG))])
+   (set (match_operand 3 "register_operand")
+        (match_operand 4 "x86_64_general_operand" ""))
+   (parallel [(set (match_operand 5 "register_operand" "")
+		   (plus (match_operand 6 "register_operand" "")
+			 (match_operand 7 "register_operand" "")))
+		   (clobber (reg:CC FLAGS_REG))])]
+  "INTVAL (operands[2]) >= 0 && INTVAL (operands[2]) <= 3
+   /* Validate MODE for lea.  */
+   && ((!TARGET_PARTIAL_REG_STALL
+	&& (GET_MODE (operands[0]) == QImode
+	    || GET_MODE (operands[0]) == HImode))
+       || GET_MODE (operands[0]) == SImode 
+       || (TARGET_64BIT && GET_MODE (operands[0]) == DImode))
+   /* We reorder load and the shift.  */
+   && !rtx_equal_p (operands[1], operands[3])
+   && !reg_overlap_mentioned_p (operands[0], operands[4])
+   /* Last PLUS must consist of operand 0 and 3.  */
+   && !rtx_equal_p (operands[0], operands[3])
+   && (rtx_equal_p (operands[3], operands[6])
+       || rtx_equal_p (operands[3], operands[7]))
+   && (rtx_equal_p (operands[0], operands[6])
+       || rtx_equal_p (operands[0], operands[7]))
+   /* The intermediate operand 0 must die or be same as output.  */
+   && (rtx_equal_p (operands[0], operands[5])
+       || peep2_reg_dead_p (3, operands[0]))"
+  [(set (match_dup 3) (match_dup 4))
+   (set (match_dup 0) (match_dup 1))]
+{
+  enum machine_mode mode = GET_MODE (operands[5]) == DImode ? DImode : SImode;
+  int scale = 1 << INTVAL (operands[2]);
+  rtx index = gen_lowpart (mode, operands[1]);
+  rtx base = gen_lowpart (mode, operands[3]);
+  rtx dest = gen_lowpart (Pmode, operands[5]);
+
+  operands[1] = gen_rtx_PLUS (Pmode, base,
+  			      gen_rtx_MULT (Pmode, index, GEN_INT (scale)));
+  if (mode != Pmode)
+    operands[1] = gen_rtx_ZERO_EXTEND (Pmode, operands[1]);
+  operands[0] = dest;
+})
 
 ;; Call-value patterns last so that the wildcard operand does not
 ;; disrupt insn-recog's switch tables.