runtime: add Benchmark[Clear|Copy]Fat[8|12]

These correspond to 2 and 3 word fat copies/clears on 8g, which dominate usage in the stdlib. (70% of copies and 46% of clears are for 2 or 3 words.) I missed these in CL 111350043, which added 2 and 3 word benchmarks for 6g. A follow-up CL will optimize these cases.

LGTM=khr
R=khr
CC=golang-codereviews
https://golang.org/cl/115160043

diff --git a/src/pkg/runtime/memmove_test.go b/src/pkg/runtime/memmove_test.go
index 8dea1f9e7a8f511108f09dcd565eb8aef5a93fa9..ffda4fe6c535e3ef13456e678e01e1c841071737 100644 (file)
--- a/src/pkg/runtime/memmove_test.go
+++ b/src/pkg/runtime/memmove_test.go
@@ -162,6 +162,18 @@ 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 BenchmarkClearFat8(b *testing.B) {
+       for i := 0; i < b.N; i++ {
+               var x [8 / 4]uint32
+               _ = x
+       }
+}
+func BenchmarkClearFat12(b *testing.B) {
+       for i := 0; i < b.N; i++ {
+               var x [12 / 4]uint32
+               _ = x
+       }
+}
 func BenchmarkClearFat16(b *testing.B) {
        for i := 0; i < b.N; i++ {
                var x [16 / 4]uint32
@@ -211,6 +223,20 @@ func BenchmarkClearFat1024(b *testing.B) {
        }
 }
 
+func BenchmarkCopyFat8(b *testing.B) {
+       var x [8 / 4]uint32
+       for i := 0; i < b.N; i++ {
+               y := x
+               _ = y
+       }
+}
+func BenchmarkCopyFat12(b *testing.B) {
+       var x [12 / 4]uint32
+       for i := 0; i < b.N; i++ {
+               y := x
+               _ = y
+       }
+}
 func BenchmarkCopyFat16(b *testing.B) {
        var x [16 / 4]uint32
        for i := 0; i < b.N; i++ {