Small optimization in SingleByteBuff

We do read from this using Unsafe based reads on underlying BB. The UnsafeAccess getters having 2 branches of code for HBB and DBB and exact memory offset calculation varies. We can do an optimize here. We can initialize the reference object and exact memory offset for Unsafe reads while creating the SBB. We will do doing the reads on this SBB many a times. Each time when we do read we can use
Unsafe.getXXX(Object, long)
I am able to get a slight adv of 2% on this change. Small change and worth getting this slight gain.