cmd/gc: optimize memclr of slices and arrays

Recognize loops of the form

for i := range a {
	a[i] = zero
}

in which the evaluation of a is free from side effects.
Replace these loops with calls to memclr.
This occurs in the stdlib in 18 places.

The motivating example is clearing a byte slice:

benchmark                old ns/op     new ns/op     delta
BenchmarkGoMemclr5       3.31          3.26          -1.51%
BenchmarkGoMemclr16      13.7          3.28          -76.06%
BenchmarkGoMemclr64      50.8          4.14          -91.85%
BenchmarkGoMemclr256     157           6.02          -96.17%

Update #5373.

Change-Id: I99d3e6f5f268e8c6499b7e661df46403e5eb83e4
Reviewed-on: https://go-review.googlesource.com/2520
Reviewed-by: Keith Randall <khr@golang.org>

1 files changed, 14 insertions, 0 deletions

diff --git a/src/runtime/memmove_test.go b/src/runtime/memmove_test.go
index ffda4fe6c5..29c62cc37d 100644
--- a/src/runtime/memmove_test.go
+++ b/src/runtime/memmove_test.go
@@ -162,6 +162,20 @@ func BenchmarkMemclr256(b *testing.B)   { bmMemclr(b, 256) }
 func BenchmarkMemclr4096(b *testing.B)  { bmMemclr(b, 4096) }
 func BenchmarkMemclr65536(b *testing.B) { bmMemclr(b, 65536) }
 
+func bmGoMemclr(b *testing.B, n int) {
+	x := make([]byte, n)
+	b.SetBytes(int64(n))
+	for i := 0; i < b.N; i++ {
+		for j := range x {
+			x[j] = 0
+		}
+	}
+}
+func BenchmarkGoMemclr5(b *testing.B)   { bmGoMemclr(b, 5) }
+func BenchmarkGoMemclr16(b *testing.B)  { bmGoMemclr(b, 16) }
+func BenchmarkGoMemclr64(b *testing.B)  { bmGoMemclr(b, 64) }
+func BenchmarkGoMemclr256(b *testing.B) { bmGoMemclr(b, 256) }
+
 func BenchmarkClearFat8(b *testing.B) {
 	for i := 0; i < b.N; i++ {
 		var x [8 / 4]uint32