allow ffs & co. a binary search

[Ian Lepore]

On Thu, 2015-06-11 at 10:49 -0400, Richard Yao wrote:
> On 06/06/2015 08:13 PM, Erich Dollansky wrote:
[...]
> 
> The fastest portable way of calculating highest bit set is to use a
> debrujin sequence:
> 
> https://graphics.stanford.edu/~seander/bithacks.html#IntegerLogDeBruijn
> 
> The binary approach is inferior, especially on Pentium 4 processors.

And of course it's crucial that we optimize for Pentium 4 processors in
2015.

-- Ian