On Wed, 11 Feb 1998, Matthew Jacob wrote:
> >Right.   And the effect isn't the same - in one case, you're getting
> >speed and reliability.   In the other case, you're only getting speed.
> >BTW, if the PrestoServe support was implemented the right way, it
> >would speed up local as well as remote disk access.
> 
> Yes, this is true. But also note that PrestoServe memory cards
> are slave only devices. Assuming a TurboChannel or SBus or PCI
> memory card you're stashing data in you pay for not only the
> CPU cycles of moving the data, but moving it in a really undesirable
> manner (across several bus bridges, little help from a cache
> prefetch, and also providing massive interference for other I/O
> that may be occurring). The tradeoffs are not always obvious.

True enough.  But in this case, I *think* the card is on whatever bus the
machine uses for memory.  It goes into a memory module slot, at any rate.
I have no idea how you'd want to implement this for other machines, where
(I'm assuming) a presto memory card would be impractical.

Chris

-------------------------------------------------------------------------------
Chris Jones                                      cjones@rupert.oscs.montana.edu
           Mad scientist in training...
"Is this going to be a stand-up programming session, sir, or another bug hunt?"