var x [512]uint8 // give byte its own cache line
	sink = &x
	b.RunParallel(func(pb *testing.PB) {
		i := uint8(0)
		for pb.Next() {
			atomic.And8(&x[255], i)
			i++
		}
	})
}

func BenchmarkAndParallel(b *testing.B) {
	var x [128]uint32 // give x its own cache line
	sink = &x
	b.RunParallel(func(pb *testing.PB) {
		i := uint32(0)
		for pb.Next() {
			atomic.And(&x[63], i)
			i++
		}
	})
}