Fastest way to calculate a 128-bit integer modulo a 64-bit integer

Question

I have a 128-bit unsigned integer A and a 64-bit unsigned integer B. What\'s the fastest way to calculate A % B - that is the (64-bit) remainder from dividing A

Answer 1

Perhaps you're looking for a finished program, but the basic algorithms for multi-precision arithmetic can be found in Knuth's Art of Computer Programming, Volume 2. You can find the division algorithm described online here. The algorithms deal with arbitrary multi-precision arithmetic, and so are more general than you need, but you should be able to simplify them for 128 bit arithmetic done on 64- or 32-bit digits. Be prepared for a reasonable amount of work (a) understanding the algorithm, and (b) converting it to C or assembler.

You might also want to check out Hacker's Delight, which is full of very clever assembler and other low-level hackery, including some multi-precision arithmetic.