Re: Asymmetric multiprocessing?

Alan Cox (alan@lxorguk.ukuu.org.uk)
Sun, 3 May 1998 13:52:48 +0100 (BST)


> Now as an alternative I suggested putting one REAL processor on each
> node (P-II/400) and one that does all the nasty side-tasks (say a
> P-II/200)

Way overkill. A much more interesting model is to use something like
a strongarm on a PCI card (eg the EBSA285) to do the I/O and U-NET
message passing stuff you want help with. With the Digital 21285 bridge
your ARM board runs in its own memory space but can hit all of PCI space

Alan

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu