xtensa: Eliminate unwanted reg-reg moves during DFmode input reloads

When spilled DFmode registers are reloaded in, once loaded into a pair of
SImode regs and then copied from that regs.  Such unwanted reg-reg moves
seems not to be eliminated at the "cprop_hardreg" stage, despite no problem
in output reloads.

Luckily it is easy to resolve such inefficiencies, with the use of peephole2
pattern.

gcc/ChangeLog:

	* config/xtensa/predicates.md (reload_operand):
	New predicate.
	* config/xtensa/xtensa.md: New peephole2 pattern.

diff --git a/gcc/config/xtensa/predicates.md b/gcc/config/xtensa/predicates.md
index d63a6cf..edd13ae 100644 (file)
--- a/gcc/config/xtensa/predicates.md
+++ b/gcc/config/xtensa/predicates.md
@@ -165,6 +165,19 @@
   (and (match_code "const_int")
        (match_test "xtensa_mem_offset (INTVAL (op), SFmode)")))
 
+(define_predicate "reload_operand"
+  (match_code "mem")
+{
+  const_rtx addr = XEXP (op, 0);
+  if (REG_P (addr))
+    return REGNO (addr) == A1_REG;
+  if (GET_CODE (addr) == PLUS)
+    return REG_P (XEXP (addr, 0))
+          && REGNO (XEXP (addr, 0)) == A1_REG
+          && CONST_INT_P (XEXP (addr, 1));
+  return false;
+})
+
 (define_predicate "branch_operator"
   (match_code "eq,ne,lt,ge"))
 

diff --git a/gcc/config/xtensa/xtensa.md b/gcc/config/xtensa/xtensa.md
index fa2a4a0..8ed0ff5 100644 (file)
--- a/gcc/config/xtensa/xtensa.md
+++ b/gcc/config/xtensa/xtensa.md
@@ -2749,3 +2749,34 @@
        (if_then_else (match_test "TARGET_DENSITY")
                      (const_int 5)
                      (const_int 6)))])
+
+(define_peephole2
+  [(set (match_operand:SI 0 "register_operand")
+       (match_operand:SI 6 "reload_operand"))
+   (set (match_operand:SI 1 "register_operand")
+       (match_operand:SI 7 "reload_operand"))
+   (set (match_operand:SF 2 "register_operand")
+       (match_operand:SF 4 "register_operand"))
+   (set (match_operand:SF 3 "register_operand")
+       (match_operand:SF 5 "register_operand"))]
+  "REGNO (operands[0]) == REGNO (operands[4])
+   && REGNO (operands[1]) == REGNO (operands[5])
+   && peep2_reg_dead_p (4, operands[0])
+   && peep2_reg_dead_p (4, operands[1])"
+  [(set (match_dup 2)
+       (match_dup 6))
+   (set (match_dup 3)
+       (match_dup 7))]
+{
+  uint32_t check = 0;
+  int i;
+  for (i = 0; i <= 3; ++i)
+    {
+      uint32_t mask = (uint32_t)1 << REGNO (operands[i]);
+      if (check & mask)
+       FAIL;
+      check |= mask;
+    }
+  operands[6] = gen_rtx_MEM (SFmode, XEXP (operands[6], 0));
+  operands[7] = gen_rtx_MEM (SFmode, XEXP (operands[7], 0));
+})