i386: Fix up replacement of registers in certain peephole2s [PR108832]

As mentioned in the PR, replace_rtx has 2 modes, one that only replaces
x == from with to, the other which i386.md uses which also replaces
REGNO (x) == REGNO (from) with to if both are REGs, but assert they have
the same mode.  This is reasonable behavior if one replaces from with
some other expression, say constant etc., but ICEs whenever the register
appears in a different mode, which happens e.g. on the following testcase,
where from/to has DImode but inside of the operands we have SImode of
the from register.  replace_rtx also does some limited simplifications
(though far less than simplify_replace_fn_rtx), which is needed if
from a REG is replaced say with CONST_INT, but the peephole2s that use
this only replace one REG with another one.

The following patch introduces a new backend function for this, avoids doing
any simplifications and just replaces the REGs, for safety on a copy of
the expression if any changes will be needed.

2023-02-18  Jakub Jelinek  <jakub@redhat.com>

	PR target/108832
	* config/i386/i386-protos.h (ix86_replace_reg_with_reg): Declare.
	* config/i386/i386-expand.cc (ix86_replace_reg_with_reg): New
	function.
	* config/i386/i386.md: Replace replace_rtx calls in all peephole2s
	with ix86_replace_reg_with_reg.

	* gcc.target/i386/pr108832.c: New test.

4 files changed, 63 insertions, 5 deletions

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc
index e59c7b0..1094ece 100644
--- a/gcc/config/i386/i386-expand.cc
+++ b/gcc/config/i386/i386-expand.cc
@@ -7093,6 +7093,37 @@ ix86_expand_v1ti_ashiftrt (rtx operands[])
     }
 }
 
+/* Replace all occurrences of REG FROM with REG TO in X, including
+   occurrences with different modes.  */
+
+rtx
+ix86_replace_reg_with_reg (rtx x, rtx from, rtx to)
+{
+  gcc_checking_assert (REG_P (from)
+		       && REG_P (to)
+		       && GET_MODE (from) == GET_MODE (to));
+  if (!reg_overlap_mentioned_p (from, x))
+    return x;
+  rtx ret = copy_rtx (x);
+  subrtx_ptr_iterator::array_type array;
+  FOR_EACH_SUBRTX_PTR (iter, array, &ret, NONCONST)
+    {
+      rtx *loc = *iter;
+      x = *loc;
+      if (REG_P (x) && REGNO (x) == REGNO (from))
+	{
+	  if (x == from)
+	    *loc = to;
+	  else
+	    {
+	      gcc_checking_assert (REG_NREGS (x) == 1);
+	      *loc = gen_rtx_REG (GET_MODE (x), REGNO (to));
+	    }
+	}
+    }
+  return ret;
+}
+
 /* Return mode for the memcpy/memset loop counter.  Prefer SImode over
    DImode for constant loop counts.  */
 
diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h
index e4037dc..bfb2198 100644
--- a/gcc/config/i386/i386-protos.h
+++ b/gcc/config/i386/i386-protos.h
@@ -168,6 +168,7 @@ extern void ix86_split_lshr (rtx *, rtx, machine_mode);
 extern void ix86_expand_v1ti_shift (enum rtx_code, rtx[]);
 extern void ix86_expand_v1ti_rotate (enum rtx_code, rtx[]);
 extern void ix86_expand_v1ti_ashiftrt (rtx[]);
+extern rtx ix86_replace_reg_with_reg (rtx, rtx, rtx);
 extern rtx ix86_find_base_term (rtx);
 extern bool ix86_check_movabs (rtx, int);
 extern bool ix86_check_no_addr_space (rtx);
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index 55042e7..6382cfb 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -22101,8 +22101,10 @@
 					  (match_dup 0)))]
 {
   operands[7] = SET_DEST (XVECEXP (PATTERN (peep2_next_insn (1)), 0, 0));
-  operands[8] = replace_rtx (operands[5], operands[0], operands[1], true);
-  operands[9] = replace_rtx (operands[6], operands[0], operands[1], true);
+  operands[8]
+    = ix86_replace_reg_with_reg (operands[5], operands[0], operands[1]);
+  operands[9]
+    = ix86_replace_reg_with_reg (operands[6], operands[0], operands[1]);
 })
 
 ;; Eliminate a reg-reg mov by inverting the condition of a cmov (#2).
@@ -22134,8 +22136,10 @@
 					  (match_dup 0)))]
 {
   operands[7] = SET_DEST (XVECEXP (PATTERN (peep2_next_insn (2)), 0, 0));
-  operands[8] = replace_rtx (operands[5], operands[0], operands[1], true);
-  operands[9] = replace_rtx (operands[6], operands[0], operands[1], true);
+  operands[8]
+    = ix86_replace_reg_with_reg (operands[5], operands[0], operands[1]);
+  operands[9]
+    = ix86_replace_reg_with_reg (operands[6], operands[0], operands[1]);
 })
 
 (define_insn "movhf_mask"
@@ -23274,7 +23278,10 @@
    (parallel [(set (match_dup 0)
 		   (match_op_dup 3 [(match_dup 0) (match_dup 1)]))
 	      (clobber (reg:CC FLAGS_REG))])]
-  "operands[4] = replace_rtx (operands[2], operands[0], operands[1], true);")
+{
+  operands[4]
+    = ix86_replace_reg_with_reg (operands[2], operands[0], operands[1]);
+})
 
 (define_peephole2
   [(set (match_operand 0 "mmx_reg_operand")
diff --git a/gcc/testsuite/gcc.target/i386/pr108832.c b/gcc/testsuite/gcc.target/i386/pr108832.c
new file mode 100644
index 0000000..b6d4731
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr108832.c
@@ -0,0 +1,19 @@
+/* PR target/108832 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -funroll-loops" } */
+
+unsigned int m;
+short int n;
+
+long int
+bar (unsigned int x)
+{
+  return x ? x : 1;
+}
+
+__attribute__ ((simd)) void
+foo (void)
+{
+  int a = m / bar (3);
+  n = 1 % bar (a << 1);
+}