[erlang-questions] Tilera 64-core chip - let's help them help us!

[Hugh Perkins]

On 9/7/07, Sean Hinde <sean.hinde@REDACTED> wrote:
> You don't need to care about how many cores you have to make a
> parallel map function in erlang, you only need to care about cores
> when you start the emulator.
>
> Parallel map is really really simple in erlang. No loss of
> abstraction at all. Just stick this function in a small library file
> and away you go (code lifted from Luke Gorries blog: http://
> lukego.livejournal.com/).
>
>    pmap(F,List) ->
>        [wait_result(Worker) || Worker <- [spawn_worker(self(),F,E) ||
> E <- List]].
>
>    spawn_worker(Parent, F, E) ->
>        erlang:spawn_monitor(fun() -> Parent ! {self(), F(E)} end).
>
>    wait_result({Pid,Ref}) ->
>        receive
>           {'DOWN', Ref, _, _, normal} -> receive {Pid,Result} -> Result end;
>           {'DOWN', Ref, _, _, Reason} -> exit(Reason)
>        end.
>
> The VM will take care of passing out the work around the cores as
> described by Kenneth a few posts ago.

Well... this will spawn a process for every item in the map.  How
efficient would that be if there are, say, 10 million elements in the
map and only 64 processor cores?