Is it infeasible to use something other than floats for such computations? There are many schemes for dealing with bigintegers, bigdecimals and such with reasonable performance.
But yeah, afaik arbitrary precision on GPUs isn't possible with reasonable performance.
And to answer him: Some programs can use it, some can't. IMO every program that can should, not not all do.
In the current top 10, 5 are Intel, 4 are AMD (and 1 SPARC64). Many have Nvidia GPU co-processors.
The only slightly exotic architecture in the top 10 is number 10, which supplements its AMD CPUs with Cell co-processors.