[Beowulf] massive parallel processing application required

Mitchell Wisidagamage 06002352 at brookes.ac.uk
Tue Jan 30 16:23:27 PST 2007


Thank you for the reply. what I mean by massively parallel processing is 
"compute intensive" problem where I will be able to process on many 
hosts independently in parallel (by parallelizing the algorithms). 
Apologies if I'm repeating what you already know. Currently there are 9 
hosts on Beowulf cluster in Lab running on UltraSPARC 5 (yes, very old 
machines!).

"raw data" I'm looking for are the input files required for the 
application, so I can "process" them. I do not have any specific 
application in mind. I will be developing the different components of 
the application such as job scheduling, fault tolerance, fault recovery, 
etc for my dissertation. I will be useing PVM or MPI for message passing 
and programming in c.

But I do have any specific application in mind and I don't mind any 
application. I can come up with say, "data mining" but it's pointless 
unless I have the "raw data" files to process and know the patterns I'm 
looking for.

Application design and programming model all depends on the type of 
application I get my hands on. I'm quite desperate for a "problem" since 
I have to submit my proposal end of next week. Any help would he greatly 
appreciated. I'm sure everyone here has lot of experience in distributed 
processing and hopefully can be of some help. Sorry for the long post.


Thanks,
  Mitchell


Douglas Eadline wrote:
> You may want to quantify "massively parallel"
> and define "raw data" (i.e. how many
> processors and data for which specific application?)
> 
> 
>   --
>   Doug
> 
> 
>> Hi all,
>>   As part of my dissertation, I'm looking for "raw data" which will be
>> used for massive parallel processing using Beuwulf cluster (with the use
>> of PVM or MPI). I tried looking for e-science raw data (and the
>> computations required on it) such as bioinformatics, fluid dynamics,
>> etc. but without any luck.
>>
>> Anyone has any idea of getting some raw data so I can give compute
>> intensive "work" to the nodes?
>>
>> Any pointers/hints/tips would be very much appriciated.
>>
>> Best wishes,
>>   Mitchell
>>
>>
>>
>> _______________________________________________
>> Beowulf mailing list, Beowulf at beowulf.org
>> To change your subscription (digest mode or unsubscribe) visit
>> http://www.beowulf.org/mailman/listinfo/beowulf
>>
>> !DSPAM:45bf9f33277683326710967!
>>
> 
> 
> --
> Doug





More information about the Beowulf mailing list