cmd/compile: optimize slice bounds checking with SUB/SUBconst comparisons

Optimize ARM64 code generation for slice bounds checking by recognizing
patterns where comparisons to zero involve SUB or SUBconst operations.
This change adds SSA opt rules to simplify:
 (CMPconst [0] (SUB x y)) => (CMP x y)

The optimizations apply to EQ, NE, ULE, and UGT comparisons, enabling
more efficient bounds checking for slice operations.

Code size improvement:
compile: .text:    9088004  ->  9065988 (-0.24%)
etcd:    .text:    10500276 -> 10497092 (-0.03%)
Change-Id: I467cb27674351652bcacc52b87e1f19677bd46a8
Reviewed-on: https://go-review.googlesource.com/c/go/+/679915
LUCI-TryBot-Result: Go LUCI <[email protected]>
Reviewed-by: Keith Randall <[email protected]>
Reviewed-by: Keith Randall <[email protected]>
Reviewed-by: Michael Knyszek <[email protected]>
Auto-Submit: Keith Randall <[email protected]>

Author: amusman

src/cmd/compile/internal/ssa/_gen/ARM64.rules

@@ -683,6 +683,14 @@
 ((EQ|NE) (CMPconst  [0] x) yes no) => ((Z|NZ)   x yes no)
 ((EQ|NE) (CMPWconst [0] x) yes no) => ((ZW|NZW) x yes no)
 
+((ULE|UGT) (CMPconst  [0] x)) => ((EQ|NE) (CMPconst  [0] x))
+((ULE|UGT) (CMPWconst [0] x)) => ((EQ|NE) (CMPWconst [0] x))
+
+((Z|NZ)   sub:(SUB        x y)) && sub.Uses == 1 => ((EQ|NE) (CMP                x y))
+((ZW|NZW) sub:(SUB        x y)) && sub.Uses == 1 => ((EQ|NE) (CMPW               x y))
+((Z|NZ)   sub:(SUBconst [c] y)) && sub.Uses == 1 => ((EQ|NE) (CMPconst         [c] y))
+((ZW|NZW) sub:(SUBconst [c] y)) && sub.Uses == 1 => ((EQ|NE) (CMPWconst [int32(c)] y))
+
 ((EQ|NE|LT|LE|GT|GE) (CMPconst  [0] z:(MADD a x y))  yes no) && z.Uses==1 => ((EQ|NE|LTnoov|LEnoov|GTnoov|GEnoov) (CMN  a (MUL  <x.Type> x y)) yes no)
 ((EQ|NE|LT|LE|GT|GE) (CMPconst  [0] z:(MSUB a x y))  yes no) && z.Uses==1 => ((EQ|NE|LTnoov|LEnoov|GTnoov|GEnoov) (CMP  a (MUL  <x.Type> x y)) yes no)
 ((EQ|NE|LT|LE|GT|GE) (CMPWconst [0] z:(MADDW a x y)) yes no) && z.Uses==1 => ((EQ|NE|LTnoov|LEnoov|GTnoov|GEnoov) (CMNW a (MULW <x.Type> x y)) yes no)

src/cmd/compile/internal/ssa/rewriteARM64.go

@@ -429,3 +429,21 @@ func Slice0(p *struct{}, i int) []struct{} {
 	// amd64:-"MULQ"
 	return unsafe.Slice(p, i)
 }
+
+// --------------------------------------- //
+//   Code generation for slice bounds      //
+//   checking comparison                   //
+// --------------------------------------- //
+
+func SlicePut(a []byte, c uint8) []byte {
+	// arm64:`CBZ\tR1`
+	a[0] = c
+	// arm64:`CMP\t\$1, R1`
+	a = a[1:]
+	a[0] = c
+	// arm64:`CMP\t\$2, R1`
+	a = a[1:]
+	a[0] = c
+	a = a[1:]
+	return a
+}