Intel acquiring Pallas

Jeffrey B. Layton laytonjb at bellsouth.net
Thu Aug 28 11:50:41 EDT 2003


Robert G. Brown wrote:

>On Thu, 28 Aug 2003, Jeffrey B. Layton wrote:
>  
>
>>Good morning!
>>
>>   I though I would post this for those who haven't seen it yet:
>>
>>http://www.theregister.co.uk/content/4/32522.html
>>
>>"Intel has signed on to acquire German software maker Pallas,
>>hoping the company's performance tools can give it an edge in
>>the compute cluster arena."
>>    
>>
>
>Interesting.  I'm trying to understand where and how this will help them
>-- more often than not it is a Bad Thing when hardware mfrs start
>dabbling in something higher than firmware or compilers -- Apple (and
>Next in its day) stands at one end of that path.
>
>It's especially curious given that Intel is already overwhelmingly
>dominant in the compute cluster arena (with only AMD a meaningful
>cluster competitor, and with apple and the PPC perhas a distant third).
>Not to mention the fact that if they REALLY wanted to get an edge in the
>compute cluster arena, they'd acquire somebody like Dolphin or Myricom.
>
>Monitoring is lovely and even important for application tuning, but it
>is an application layer on TOP of both systems software and the network.
>Or perhaps they are buying them so they can instrument their compilers?
>
>   rgb
>

Bob,

   Very interesting observation. I wonder if Intel doesn't have something
else up their sleeve? Could they be trying to get back into Supercomputer
game (not likely, but didn't they get some DoD money recently?). Could
they be helping with networking stuff (Intel has been discussing the next
generation networking stuff lately). Maybe some sort of TCP Offload
Engine? Maybe something with their new bus ( PCI Express?) They have also
created CSA (Communication Streaming Architecture) in their new chipset
to bypass the PCI bottleneck. Of course they could also be after the Pallas
parallel debuggers to integrate into their compilers (like you mentioned)
or perhaps to help with debugging threaded code in the hyperthreaded chips.
   Not that you mention it, this is a somewhat interesting development.
I wonder what they're up to?

>Robert G. Brown	                       http://www.phy.duke.edu/~rgb/
>Duke University Dept. of Physics, Box 90305
>Durham, N.C. 27708-0305
>Phone: 1-919-660-2567  Fax: 919-660-2525     email:rgb at phy.duke.edu
>
>  
>

Jeff


_______________________________________________
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