ARC: Use rlc r0,0 to implement scc_ltu (i.e. carry_flag ? 1 : 0)

This patch teaches the ARC backend that the contents of the carry flag
can be placed in an integer register conveniently using the "rlc rX,0"
instruction, which is a rotate-left-through-carry using zero as a source.
This is a convenient special case for the LTU form of the scc pattern.

unsigned int foo(unsigned int x, unsigned int y)
{
  return (x+y) < x;
}

With -O2 -mcpu=em this is currently compiled to:

foo:    add.f 0,r0,r1
        mov_s   r0,1    ;3
        j_s.d   [blink]
        mov.hs r0,0

[which after an addition to set the carry flag, sets r0 to 1,
followed by a conditional assignment of r0 to zero if the
carry flag is clear].  With the new define_insn/optimization
in this patch, this becomes:

foo:    add.f 0,r0,r1
        j_s.d   [blink]
        rlc     r0,0

This define_insn is also a useful building block for implementing
shifts and rotates.

2023-10-03  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	* config/arc/arc.md (CC_ltu): New mode iterator for CC and CC_C.
	(scc_ltu_<mode>): New define_insn to handle LTU form of scc_insn.
	(*scc_insn): Don't split to a conditional move sequence for LTU.

gcc/testsuite/ChangeLog
	* gcc.target/arc/scc-ltu.c: New test case.

diff --git a/gcc/config/arc/arc.md b/gcc/config/arc/arc.md
index d37ecbf4292e4dd52f6b80c5ef4555ace4e04e37..fe2e7fb366255d26410a337f54c517845e3680c1 100644 (file)
--- a/gcc/config/arc/arc.md
+++ b/gcc/config/arc/arc.md
@@ -3658,12 +3658,24 @@ archs4x, archs4xd"
 (define_expand "scc_insn"
   [(set (match_operand:SI 0 "dest_reg_operand" "=w") (match_operand:SI 1 ""))])
 
+(define_mode_iterator CC_ltu [CC_C CC])
+
+(define_insn "scc_ltu_<mode>"
+  [(set (match_operand:SI 0 "dest_reg_operand" "=w")
+        (ltu:SI (reg:CC_ltu CC_REG) (const_int 0)))]
+  ""
+  "rlc\\t%0,0"
+  [(set_attr "type" "shift")
+   (set_attr "predicable" "no")
+   (set_attr "length" "4")])
+
 (define_insn_and_split "*scc_insn"
   [(set (match_operand:SI 0 "dest_reg_operand" "=w")
        (match_operator:SI 1 "proper_comparison_operator" [(reg CC_REG) (const_int 0)]))]
   ""
   "#"
-  "reload_completed"
+  "reload_completed
+   && GET_CODE (operands[1]) != LTU"
   [(set (match_dup 0) (const_int 1))
    (cond_exec
      (match_dup 1)

diff --git a/gcc/testsuite/gcc.target/arc/scc-ltu.c b/gcc/testsuite/gcc.target/arc/scc-ltu.c
new file mode 100644 (file)
index 0000000..653c55d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arc/scc-ltu.c
@@ -0,0 +1,12 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mcpu=em" } */
+
+unsigned int foo(unsigned int x, unsigned int y)
+{
+  return (x+y) < x;
+}
+
+/* { dg-final { scan-assembler "rlc\\s+r0,0" } } */
+/* { dg-final { scan-assembler "add.f\\s+0,r0,r1" } } */
+/* { dg-final { scan-assembler-not "mov_s\\s+r0,1" } } */
+/* { dg-final { scan-assembler-not "mov\.hs\\s+r0,0" } } */