Beowulf: A theorical approach
jcownie at etnus.com
Sat Jun 24 05:44:38 PDT 2000
> > Personally I always called it a "cache-coherent explicit remote store
> > access" model,
> But it isn't actually cache coherent. Remember Cray shmem(): To use
> data, you fetch it to be close to you, and then it isn't cache
> coherent while it's local. It IS cache coherent in that the fetch
> gets you the right data.
Wrong. In the CS2 it _was_ cache coherent both locally and remotely.
Transfers could be made from anywhere in the user address space (with
no special allocation or lock-down requirement), and were fully cache
That's why I added "cache coherent" to the description, explicitly to
distinguish it from the Cray shmem which I would call "non-cache
coherent explicit remote store access".
Another of the reasons I don't like the SALC description is precisely
this confusion about what the "local consistency" is intended to mean.
Making the NIC properly cache coherent is one of the main reasons to
be on the processor bus, appearing as a second CPU. It allows the NIC
to implement the full coherency protocol when accessing data (either
bringing it in, or sending it out).
James Cownie <jcownie at etnus.com>
Etnus, Inc. +44 117 9071438
More information about the Beowulf