cmd/compile: add intrinsics for runtime/internal/math on 386 and amd64

Add generic, 386 and amd64 specific ops and SSA rules for multiplication
with overflow and branching based on overflow flags. Use these to intrinsify
runtime/internal/math.MulUinptr.

On amd64
  mul, overflow := math.MulUintptr(a, b)
  if overflow {
is lowered to two instructions:
  MULQ SI
  JO 0x10ee35c

No codegen tests as codegen can not currently test unexported internal runtime
functions.

amd64:
name              old time/op  new time/op  delta
MulUintptr/small  1.16ns ± 5%  0.88ns ± 6%  -24.36%  (p=0.000 n=19+20)
MulUintptr/large  10.7ns ± 1%   1.1ns ± 1%  -89.28%  (p=0.000 n=17+19)

Change-Id: If60739a86f820e5044d677276c21df90d3c7a86a
Reviewed-on: https://go-review.googlesource.com/c/141820
Run-TryBot: Martin Möhrmann <moehrmann@google.com>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Keith Randall <khr@golang.org>

1 files changed, 28 insertions, 0 deletions

diff --git a/src/runtime/internal/math/math_test.go b/src/runtime/internal/math/math_test.go
index 9447bd23f9..303eb63405 100644
--- a/src/runtime/internal/math/math_test.go
+++ b/src/runtime/internal/math/math_test.go
@@ -49,3 +49,31 @@ func TestMulUintptr(t *testing.T) {
 		}
 	}
 }
+
+var SinkUintptr uintptr
+var SinkBool bool
+
+var x, y uintptr
+
+func BenchmarkMulUintptr(b *testing.B) {
+	x, y = 1, 2
+	b.Run("small", func(b *testing.B) {
+		for i := 0; i < b.N; i++ {
+			var overflow bool
+			SinkUintptr, overflow = MulUintptr(x, y)
+			if overflow {
+				SinkUintptr = 0
+			}
+		}
+	})
+	x, y = MaxUintptr, MaxUintptr-1
+	b.Run("large", func(b *testing.B) {
+		for i := 0; i < b.N; i++ {
+			var overflow bool
+			SinkUintptr, overflow = MulUintptr(x, y)
+			if overflow {
+				SinkUintptr = 0
+			}
+		}
+	})
+}