-Re: building a department GPU cluster
Roberto Nunnari 2013-01-18, 09:01
Thiago Vieira wrote:
> I've seen some academic researches on this direction, with good results.
> Some computations can be expressed by GPGPU, but it is still a restrict
> number of cases. If is not easy to solve problems using MapReduce, solve
> some problems with SIMD is harder.
Ok.. Thank you all for your time.. I'll keep searching.
> Thiago Vieira
> On Thu, Jan 17, 2013 at 9:24 PM, Russell Jurney
> <[EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]>> wrote:
> Hadoop streaming can do this, and there's been some discussion in
> the past, but it's not a core use case. Check the list archives.
> Russell Jurney http://datasyndrome.com
> On Jan 17, 2013, at 9:25 AM, Jeremy Lewi <[EMAIL PROTECTED]
> <mailto:[EMAIL PROTECTED]>> wrote:
>> I don't think running hadoop on a GPU cluster is a common use
>> case; the types of workloads for a hadoop vs. gpu cluster are very
>> different although a quick google search did turn up some. So this
>> is probably not the best mailing list for your question.
>> On Thu, Jan 17, 2013 at 5:18 AM, Roberto Nunnari
>> <[EMAIL PROTECTED] <mailto:[EMAIL PROTECTED]>> wrote:
>> Roberto Nunnari wrote:
>> Hi all.
>> I'm writing to you to ask for advice or a hint to the
>> right direction.
>> In our department, more and more researchers ask us (IT
>> administrators) to assemble (or to buy) GPGPU powered
>> workstations to do parallel computing.
>> As I already manage a small CPU cluster (resources managed
>> using SGE), with my boss we talked about building a new
>> GPU cluster. The problem is that I have no experience at
>> all with GPU clusters.
>> Apart from the already running GPU workstations, we
>> already have some new HW that looks promising to me as a
>> starting point for a GPU cluster.
>> - 1x Dell PowerEdge R720
>> - 1x Dell PowerEdge C410x
>> - 1x NVIDIA M2090 PCIe x16
>> - 1x NVIDIA iPASS Cable Kit
>> (Dell forgot to include the iPASS adapter for the R720!! :-D)
>> I'd be grateful if you could kindly give me some advice
>> and/or hint to the right direction.
>> In particular I'm interested on your opinion on:
>> 1) is the above HW suitable for a small (2 to 4/6 GPUs)
>> GPU cluster?
>> 2) is apache adhoop suitable (or what could we use?) as a
>> queuing and resource management system? We would like the
>> cluster to be usable by many users at once in a way that
>> no user has to worry about resources, just like we do on
>> the CPU cluster with SGE.
>> 3) What distribution of linux would be more appropriate?
>> 4) necessary stack of sw? (cuda, hadoop, other?)
>> Thank you very much for your valuable insight!
>> Best regards.
>> Anybody on this, please?