[rescue] SGI, Origin 200, and speed?

[Dave McGuire]

On Apr 30, 2004, at 11:00 AM, Charles Shannon Hendrix wrote:
>>> At NASA, Craylink was a bottleneck and the SGI rep said there would
>>> be a replacement at some point.
>>
>>   A bottleneck...?  As I understand it, it's a direct port off of one
>> of the crossbar switches.  It runs at memory speed.  How was it a
>> bottleneck?
>
> It is always faster to access memory that is physically on the local
> node.  Irix tries to make sure that threads are very close to their
> memory addresses.  It isn't perfect.  It is also harder to make this
> happen with a single-threaded application than a parallel application.
> The performance papers from SGI say to keep memory access local 
> whenever
> possible and this is true of most any network memory interconnect
> system.
>
> The Origin will function as a big SMP box, but that isn't the best way
> to use it.  The SGI code performance papers say to minimize Craylink
> traffic and give guidelines on how to optimize.  You also have library
> routines like dplace() which let's you bind memory accesses to the same
> node the thread runs on, etc.
>
> NASA insisted on code not being changed to make it optimized for SGI,
> and SAIC claimed that the application could not be made parallel.  So
> it ran as a big SMP application.  Fragmented memory accesses across the
> cluster are much slower than keeping them local.

   Ahhhhhh yes...this makes sense now that I think about it.  Reading 
through the Origin architecture theoretical documentation, they 
specifically state this as well.  The hardware dynamically moves data 
around from node to node to keep things local, but it doesn't always 
succeed.  Visualizing this, I'd imagine, that it'd be possible for the 
compiler to arrange its output's memory references to help this (or at 
least give the hardware "hints") but I don't know if SGI's compilers do 
this or not.

   Thanks for the explanation.

> Unlike their O2000 pages which lists the memory bandwidth, the O3000
> site only lists the aggregate bandwidth.
>
> Need more info.
>
> Man, I'd like to work on one of these.

   An O3000, you mean?  Yeah.

        -Dave

--
Dave McGuire          "PC users only know two 'solutions'...
Cape Coral, FL          reboot and upgrade."    -Jonathan Patschke