> From: Jud McCranie[SMTP:[EMAIL PROTECTED]]
> At 11:36 PM 6/16/99 -0700, John R Pierce wrote:
> >*If* the IA64 has a fast pipelineable 64 bit * 64 bit -> 128 bit integer
> >multiply capability, perhaps the FPU is no longer needed?
>
> You still need floating point numbers and that's probably better handled
> with
> FPU hardware.
>
>
No, no, no, no. :) Georges code uses the FPU of intel chips because the
early ones had very poor integer processing capabilities--small number of
small registers, non-pipelined multiply, darn *slow* multiply, etc. There
was the FPU sitting right next to it with 8 80 bit registers, nice multiply
instruction, etc... When the pentium came along, it pipelines the FPU and
things really got fun. Didn't hurt that the C&F DWT paper came out about
that time.
But, you can do it in integer if you have a processor with 1) enough integer
registers 2) wide registers and 3) fast/pipelined multiply--which IA-64 is
supposed to have. The floating point version was a cluge to make up for an,
uhhh, *interesting* processor archetecture. It shouldn't make everyone
think that it's always the best way to do things.
Well, keep in mind I'm wrong frequently, but I think this sums up the
development of the arguement--four or six years ago. It's been a while and
I don't remember all that well.
Cheers,
David
> +----------------------------------------------+
> | Jud "program first and think later" McCranie |
> +----------------------------------------------+
>
*laugh* Uh, hmmm, think now? :)
________________________________________________________________
Unsubscribe & list info -- http://www.scruz.net/~luke/signup.htm
