[ODE] Particle/cloth/skeleton (was: Re: Choleski factorization)

[Gary R. Van Sickle]

> SIMD: I wasn't considering rewriting all of the code with SIMD
> alternatives, but just rewriting Vector and Matrix multiplication and dot
> product functions with a SIMD alternative.

I've always wondered if it would make any sense to use Windows' Direct3D vector
and matrix operations on Win32 platforms.  If they by chance use SIMD
instructions etc, you'd get that for free, and in the distant future, when the
Pentium XXIV has single-cycle matrix multiplies, you'd get that for free with no
code changes.

Just a thought.  I'm giddy with anticipation wrt the iterated solver!  Thanks
for the hard work David!

--
Gary R. Van Sickle
Brewer.  Patriot.