[vtk-developers] Shared Memory Parallelism in VTK

[Berk Geveci]

Dear Jianwei,

The VTK SMP infrastructure abstracts the backend so you don't have to worry
about which backend to write for. See the PDF document reference in

http://www.vtk.org/Wiki/VTK/VTK_SMP

It is up to the students to make a decision on which filters they want to
implement using this infrastructure. Once the proposals are in, we may come
back and make some suggestions for other algorithms. Also, note that the
project may include the VTK imaging pipeline as stating in "this will
include modernization of the old multi-threading code in the imaging
pipeline".

David: Is there a reference describing the VTK threaded image algorithm
infrastructure or do we just point to the code?

Best,
-berk

On Mon, Mar 16, 2015 at 2:25 PM, jianwei li <ljianweiyx at gmail.com> wrote:

> Hi
>      I have read the paper 'VtkSMP: Task-based Parallel Operators for VTK
> Filters'.Based on the paper,kaapi is better than other two methods.So,do
> you want to use kaapi to implement some VTK filters.And,which processor
> want to be,such as the number of core.And do you only want to implement the
> filter listed in the paper.
> Best regard
>      Jianwei
>
> 2015-03-17 1:48 GMT+08:00 Berk Geveci <berk.geveci at kitware.com>:
>
>> Dear Jianwei,
>>
>> Please take a look at these references:
>>
>> * http://www.vtk.org/Wiki/VTK/VTK_SMP
>> * https://hal.inria.fr/hal-00789814/document
>> *
>> http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.396.4673&rep=rep1&type=pdf
>>
>> This particular project refer to the CPU based SMP parallelism currently
>> in VTK as explained in the references above. For reference, I included
>> these in the topic page as well.
>>
>> Best,
>> -berk
>>
>> On Mon, Mar 16, 2015 at 1:33 PM, jianwei li <ljianweiyx at gmail.com> wrote:
>>
>>> Hi
>>>    I'm a graduate student in NorthWestern Polytenical University.I have
>>> been study Parelism promraming,especially GPU programming for two year.So I
>>> want to accept task Shared Memory Paralism in VTK.
>>>    But now,I don't know if you want implement the parallelism on GPU or
>>> CPU,and do you hace some other demand,such as efficiency,coefficeent of
>>> utilization of processor.
>>>    Watting for your answer!
>>>    Than you!
>>> Best Regard
>>>
>>>
>>> _______________________________________________
>>> Powered by www.kitware.com
>>>
>>> Visit other Kitware open-source projects at
>>> http://www.kitware.com/opensource/opensource.html
>>>
>>> Search the list archives at:
>>> http://markmail.org/search/?q=vtk-developers
>>>
>>> Follow this link to subscribe/unsubscribe:
>>> http://public.kitware.com/mailman/listinfo/vtk-developers
>>>
>>>
>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/vtk-developers/attachments/20150316/af40a982/attachment.html>