Modern Electronics (was Re: List charter mods & headcount... ;

From: Paul Koning <pkoning_at_equallogic.com>
Date: Tue Jun 29 08:33:51 2004

>>>>> "William" == William Donzelli <aw288_at_osfn.org> writes:

>> Then there are special cases: the Cray and Alpha integer units,
>> which don't offer divide at all. Instead, you're supposed to
>> multiply by the reciprocal of the divisor. This works well,
>> because you can actually do that faster than the straightforward
>> one bit at a time division even if you have to calculate the
>> reciprocal at runtime.

 William> Do you know how this is done (at least the fancy ways of
 William> doing it)? I assume there are shortcuts, as the Cray 1/x
 William> pipes were not hugely long compared with the other pipes
 William> (there has to be some magic somewhere).

Only in outline. The instruction is called "reciprocal approximation"
-- I believe it's a Newton's method iterative method for finding the
reciprocal of a given number. Apparently Newton's method converges
faster (when you throw the right number of gates at the inner loop)
than a divide would for the Cray's 64 bit word length.

     paul
Received on Tue Jun 29 2004 - 08:33:51 BST