Better tabselect

[Torbjorn Granlund]

I think my original tabselect methid is not the best, at least not of we
implement it in assembly.

The current method takes one full table vector entry at a time, and need
to perform two loads and one store per entry in the large table of
vectors.

It seems better two work in the opposite direction, i.e., to load and
select first element 0 of each vector, and store the result, then do the
same with all element 1, etc.

This will require more logops or select ops (where they don't leak) but
all-in-all it should be faster in most cases.

-- 
Torbjörn