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

[David Miller]

From: Torbjorn Granlund <tg at gmplib.org>
Date: Fri, 04 Jan 2013 14:54:15 +0100

> 1:      umulxhi %g5, %g5, %g1
>         mulx    %g5, %g5, %g2
>         umulxhi %g5, %g5, %g3
>         mulx    %g5, %g5, %g4
>         umulxhi %g5, %g5, %i1
>         mulx    %g5, %g5, %i2
>         umulxhi %g5, %g5, %i3
>         mulx    %g5, %g5, %i4
>         brnz,a  %i0, 1b
>         addx    %i0, -1, %i0
> 
>         ret

This runs in 9 seconds with a suitably initialized %i0
for this processor (2.8GHZ)