[MPFR] Re: Is there a platform optimized version of gmp for INTEL?

[Michael]

No, the optimization problem is to speed up for a given set of parameters,
one single expression involving log/exp,
addition/subtraction/multiplication/division with huge numbers.

That's all I need. Once the critical single expression has been optimized,
then I can vary the parameters. The current focus is that single expression.


On 1/2/07, Jürgen Kahrs <Juergen.Kahrs at vr-web.de> wrote:
>
> Patrick Pelissier wrote:
>
> >> (2) We
> >> have to optimize the code and make it faster by a speedup of hundreds
> to
> >> thousands times.
> >
> > Such a speedup can only be reached by an algorithm optimization (if
> > possible).
>
> That's right. When reading Michael's messages, I always
> wonder why he insists on speeding up GMP and MPFR.
> I bet that GMP and MPFR are those parts of his software
> that already _are_ near the optimum run-time efficiency.
>
> As you (Patrick) suggested, Michael should concentrate on
> speeding up the algorithm that makes use of MPFR. It sounds
> like his algorithm follows a brute-force approach of trying
> all possible combinations of values of some variables.
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://gmplib.org/list-archives/gmp-discuss/attachments/20070102/94349981/attachment.html