|
From: | Steven H. Rogers |
Subject: | Re: [Swarm-Modelling] ABMs on Graphical Processor Units |
Date: | Fri, 28 Dec 2007 21:31:21 -0700 |
User-agent: | Thunderbird 1.5.0.10 (X11/20070302) |
Russell Standish wrote:
The Cell is not SMP at all. It's really asymmetrical and MPI is unlikely to be a good fit. One of the SPUs may be reserved for OS use. IIRC, each SPU has an MMU to coordinate DMA transfers between local and shared memory, so data can be streamed in and out efficiently. The SPUs shouldn't need to keep much data local for workloads that can be structured to take advantage of this.It sounds to me that the Cell is basically equivalent to a 9 core conventional SMP setup, with "local memory" being essentially the same as the L2 cache. 256KB is a little on the measely side these days, as even commodity IA can stump up a couple MB of cache, but its certainly possible to be used, as pevious generations of IA only had this much cache. Then it doesn't matter if MPI is kept in local store - only the bits of the program heavily used will matter, and typically MPI is at its most successful when communication costs are much less than computation costs.
# Steve
[Prev in Thread] | Current Thread | [Next in Thread] |