[Paraview] Parallel MB reader

Paul Edwards paul.m.edwards at gmail.com
Tue Jun 28 12:25:15 EDT 2011


Adriano,

I'm not totally sure I understand your question but this thread might be of
use where I was asking about multi block data sets in parallel:

      http://markmail.org/message/skb653xqwa4hvs4c

Regards,
Paul


On 28 June 2011 16:24, Andy Bauer <andy.bauer at kitware.com> wrote:

> If I understand you correctly I think you need to do 2.  Each process
> should have the same multiblock structure and will just not contain a data
> set for the leaves that are assigned to a different process.  Check out
> http://www.vtk.org/doc/nightly/html/classvtkMultiBlockDataSet.html#details
>
> HTH,
> Andy
>
>
> On Tue, Jun 28, 2011 at 5:38 AM, Adriano Gagliardi <agagliardi at ara.co.uk>wrote:
>
>>
>> I've run into an issue when writing a parallel reader for partitioned
>> files
>> containing multi-block data. All data reads in fine on each process and
>> works as expected, except for one thing. Since each partition only knows
>> about the blocks it contains (and not the global blocks), I've not been
>> able
>> to have all the blocks available in the entire data-set available to the
>> user. What I get instead is the list of blocks read in by the last data
>> reader. I've got a couple of ideas to resolve this issue.
>>
>> (1) Have some sort of communication between each of the PV processes to
>> ascertain which process has which data
>>
>> (2) Have the number of blocks stored on each process the same as the
>> global
>> number of blocks, but just allocate data to the blocks that each
>> partition/process has data of.
>>
>> So, my questions are:
>>
>> (1) Is item (1) possible and, if so, what class(es) should I be looking at
>> to do it
>>
>> (2) Will item (2) alone solve my issue, or will I run into problems
>> whereby
>> if block 0 has 50% of its data on partition 0 and the rest on partition 1
>> that, after reading in, I will only ever see 50% of block 0 being
>> whichever
>> of partition 0 or 1 is read in last.
>>
>> Thanks again,
>>
>> Adriano
>>
>> ===================================
>>
>> Adriano Gagliardi MEng PhD
>> Business Sector Leader
>> Computational Aerodynamics
>> Aircraft Research Association Ltd.
>> Manton Lane
>> Bedford
>>
>> Tel: 01234 32 4644
>> E-mail: agagliardi at ara.co.uk
>> Url: www.ara.co.uk
>>
>>
>> **********************************************************************
>> This email contains information that is private and confidential and is
>> intended only for the addressee.
>> If you are not the intended recipient please delete it and notify us
>> immediately by e-mailing the sender.
>> Note: All email sent to or from this address may be accessed by someone
>> other than the recipient, for
>> system management and security reasons.
>> Aircraft Research Association Ltd.  Registered in England, Registration No
>> 503668 Registered Office:
>> Manton Lane, Bedford MK41 7PF England VAT No GB 196351245
>>
>> **********************************************************************
>> _______________________________________________
>> Powered by www.kitware.com
>>
>> Visit other Kitware open-source projects at
>> http://www.kitware.com/opensource/opensource.html
>>
>> Please keep messages on-topic and check the ParaView Wiki at:
>> http://paraview.org/Wiki/ParaView
>>
>> Follow this link to subscribe/unsubscribe:
>> http://www.paraview.org/mailman/listinfo/paraview
>>
>
>
> _______________________________________________
> Powered by www.kitware.com
>
> Visit other Kitware open-source projects at
> http://www.kitware.com/opensource/opensource.html
>
> Please keep messages on-topic and check the ParaView Wiki at:
> http://paraview.org/Wiki/ParaView
>
> Follow this link to subscribe/unsubscribe:
> http://www.paraview.org/mailman/listinfo/paraview
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.paraview.org/pipermail/paraview/attachments/20110628/c11f56d3/attachment.htm>


More information about the ParaView mailing list