[PATCH] Optimize 32-bit sparc T1 multiply routines.

David Miller davem at davemloft.net
Fri Jan 4 01:49:35 CET 2013

From: David Miller <davem at davemloft.net>
Date: Thu, 03 Jan 2013 13:01:28 -0800 (PST)

> From: Torbjorn Granlund <tg at gmplib.org>
> Date: Thu, 03 Jan 2013 15:54:22 +0100
>> Would you be willing to assign copyrights to the FSF, so that we can
>> include them?
> Of course.

Just FYI, I'm also working on an mpn_mul_basecase that makes use of
the T4 'mpmul' instruction which can do NxN 64-bit limb multiplies
for values of N from 1 to 32.

It's an instruction that seems like it was designed specifically for
libgmp :-)

I guess the ideal implementation would be to have gmp-mparam.h setup
so that basecase only gets invoked for N <= 32.

More information about the gmp-devel mailing list