Messages in this thread |  | | | Date | Mon, 06 Mar 2000 11:36:06 -0800 | | From | Aman Singla <> | | Subject | Re: Help in DSM design |
| |
> That turns out not to be the case. It was exactly this granularity > problem which killed the only machine I'm aware of which did DSM in > hardware (the Kendall Square boxes --- and how many people here have > heard of that one? :)
The KSR boxes aren't the only h/w DSM systems - NUMA boxes today (Origin for one) also do DSM. Both add that additional level of locality that a performance conscious application needs to exploit; agreed that KSR was the only one to have caching at the remote memory to local memory level (with a page size granularity). A DSM system could look very much like the current NUMA h/w with an added remote-local memory caching happening at application specific granularity. The main issue there is getting access control at the desired granularity for the s/w DSM layer - which in a way the current OS dictates to be a page size; and yeah! unfortunately there are many smart solutions around that one that I'm aware of :-)
:a
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/
|  |