CPU/Hardware optimized for Erlang
Thu Jul 28 12:55:55 CEST 2005
--- James Hague <> wrote:
> Thomas Lindgren wrote:
> Good points. I had forgotten about the ECOMP
> numbers being relative to JAM.
Hrrm, yes ... Well, er :-)
> >As someone whose name I can't remember liked to ask
> >situations like this, "what has changed?" Why is it
> >going to be different this time?
> Three things:
> [no clock speed increase => more work/instr good]
> [power concerns]
How should the complex instructions be implemented?
Longer pipelines? Slower clock + more work per stage?
More internal parallelism?
I'd say the main use for a complex instruction is that
it is a compact representation of "some work", in
particular in memory/cache. While actually executing,
resource requirements for any given instruction can
vary widely. (Cue that infamous VAX instruction.)
FPGAs are very interesting, definitely. I think the
manufacturers now offer simple migration paths from
FPGA to ASIC too, if you find you have a winner.
Start your day with Yahoo! - make it your home page
More information about the erlang-questions