Global Shared Memory and SCI/Dolphin

Joachim Worringen joachim at ccrl-nece.de
Wed Jul 16 09:16:09 EDT 2003


Franz Marini:
>   being in the process of deciding which net infrastructure to use for our
> next cluster (Myrinet, SCI/Dolphin or Quadrics), I was looking at the
> specs for the different types of hw.
>
>   Provided that SCI/Dolphin implements RDMA, I was wondering why so little
> effort seems to be put into implementing a GSM solution for x86 clusters.

Because MPI is what most people want to achieve code- and 
peformance-portability.

> The only (maybe big, maybe not) problem I see in the Dolphin hw is the
> lack of support for cache coherency.
>
>   I think that having GSM support in (almost) commodity clusters would be
> a really-nice-thing(tm).

Martin Schulz (formerly TU München, now Cornell Theory Center) has developed 
exactly the thing you are looking for. See 
http://wwwbode.cs.tum.edu/Par/arch/smile/software/shmem/ . You will also find 
his PhD thesis there which describes the complete software.

I do not know about the exact status of the SW right now (his approach 
required some patches to the SCI driver, and it will probably be necessary to 
apply them to the current drivers). Very interesting approach, though.

Other, non SCI approaches like MOSIX and the various DSM/SVM libraries also 
offer you some sort of global shared memory - but most do only use TCP/IP for 
communication.

 Joachim

-- 
Joachim Worringen - NEC C&C research lab St.Augustin
fon +49-2241-9252.20 - fax .99 - http://www.ccrl-nece.de

_______________________________________________
Beowulf mailing list, Beowulf at beowulf.org
To change your subscription (digest mode or unsubscribe) visit http://www.beowulf.org/mailman/listinfo/beowulf



More information about the Beowulf mailing list