Jano wrote:

> I'm about to finish simulations going up to 28 as the load parameter. I'm
> using the phase7 version, without modifications. I'll post my results late
> today.

Here are the results. Load is increased in steps of two (2,4,..28).
The 'nothing' line stops at 14 because I run out of memory, but I find
strange that until that point is the best performing one, specially since
the others seem to reach a plateau of throughput before that point. However
my understanding of these mechanisms is very superficial so I leave the
interpretation to you.

Note that this is with the version without slow nodes.

_______________________________________________
Tech mailing list
Tech@...
http://emu.freenetproject.org/cgi-bin/mailman/listinfo/tech