Stackless/microthreads merge news

[Will Ware]

Christian Tismer (tismer at tismer.com) wrote:
> But I'm thinking of some more. It should be possible to have
> microthreads that don't block with a real thread switch.
> They would just move into another thread that is micro-enabled
> and continue there. It isn't that easy, needs more care about
> switching and recursions, but well :-)
> nomad-thread-ly y'rs - chris

It might be possible to pickle a thread and ship it over an IP socket
to another processor, as a means of load-balancing in a parallel
machine. This would start to address some of the things Konrad is
looking for, except for the part about filling his Fortran code with
context switches.
-- 
 - - - - - - - - - - - - - - - - - - - - - - - -
Resistance is futile. Capacitance is efficacious.
Will Ware	email:    wware @ world.std.com