Re: [Swarm-Modelling] SWARM on Clusters

[Marcus G. Daniels]

Sunwoo Park wrote:

> But, for example, 
> (1) if models perform considerable amount of computation in a single
> simulation phase (or cycle) with minimum communication between agents
> (2) if the size and/or scalability of simulation models is much important
> than performance (or execution time)
> do you still think multi-threading approach is better than message passing
> because of the nature of SWARM even in above cases ?
>  
Well, in say Java/Swarm you could use RMI to distribute agents onto 
different computers and just block on the calls.  That's not a feature 
of Swarm, but something a person could do without much work.

In general, processor count and memory being equal, I think big fast 
parallel machines NUMA shared memory systems are more useful than 
independent machines running independent operating systems (e.g. Beowulf 
clusters).

> Also, could you give me some information (or link) on SWARM models/projects
> that are already done or planned for 'large-scale' simulation  ?
> For example, is there any SWARM project that uses more than 256 (or 512)
> nodes in MPP machines ?
>  
I'm not aware of any, but maybe someone else has done that with Swarm or 
another toolkit.