Re: 1teraflops cell processor possible?

On Thu, 27 Nov 2003 06:08:12 -0500, Robert Myers wrote:
> Current microarchitectures have the following paradigm:
>
> Get something. Do something to it. Put it back.
>
> There is not a thing a compiler can do about that.  Between operations
> (except in the case of an FMAC, which is an example of streaming),
> operands have to sit in registers and they have to be ferried back and
> forth.

Not heard of forwarding?  One reason why the heavily
out-of-order CPUs of today get away with as few register ports
as they do.  Values flit from one FU to the next just fine.

-- 
Andrew