[hpx-users] Some more study regarding proposed Map/Reduce Framework [GSOC-2016]

[Aalekh Nigam]

Hello Everyone,

For past few days I have been working on improving some of the idea's in my
proposal regarding Implementing Map/Reduce Framework and have come up some
more points mentioned here, thus I would request you all to please spare
some of your time and give your advise over it:

https://docs.google.com/document/d/1z-sdDoEoaGn6N-0Sk2ZIEb-BuKt7dFpfYKCsxn57pu8/edit?usp=sharing

Further, I am also in the process of implementing a sample dataflow
pipeline based framework with minimal windowing(fixed windowing only)
support to gather a better idea about how our *C++ API* would look like,
you can keep track and share your advise over my work here:
https://github.com/AALEKH/DataflowExperiment

Thanks,
Aalekh
___
hpx-users mailing list
hpx-users@stellar.cct.lsu.edu
https://mail.cct.lsu.edu/mailman/listinfo/hpx-users

Re: [hpx-users] Your interest in HPX

[Patrick Diehl]

Hi,

we have a bachelor thesis for the validation of HPX for a two
dimensional fluid dynamics solver. The student is evaluating how HPX is
feasible for this numerical task. A large part of the computational
effort is the solving of a linear equation system and matric vector
operations.

Best,

Patrick

Am 03/30/2016 um 01:58 AM schrieb Hartmut Kaiser:
> Ashwin,
> 
> (cc'ing hpx-users for others to chime in as well)
> 
>> My work has focused on developing multi-GPU tridiagonal solvers, and I'm
>> excited about upcoming GPU support in HPX. However, I am interested in
>> seeing a library comparable to PETSc built on the HPX framework.
>> LibGeoDecomp has a significant amount of the functionality, and there is
>> effort in a related direction with hpxla. The PETSc developers themselves
>> had this discussion a long time ago - although maybe it left a bad taste
>> in everyone's mouths :-)
> 
> HPX has come a long way since 2012. I'm sure people would like to have 
> another look.
> 
>> I am new to HPX, and by no means an expert in numerical analysis. But I'm
>> wondering what the HPX group thinks about a solid library for large scale
>> scientific computation using HPX.
> 
> There is definitely interest! Andy (the author of LibGeoDecomp) may chime in 
> on his behalf, but from HPX's standpoint this would be a wonderful addition 
> to the toolbox. Please let us know what we can do to support such an endeavor.
> 
> You might want to join the hpx-users mailing list and drop by in the IRC 
> channel (our main means of communication). For details see here: 
> http://stellar.cct.lsu.edu/contact-us/.
> 
> Thanks!
> Regards Hartmut
> ---
> http://boost-spirit.com
> http://stellar.cct.lsu.edu
> 
> 
>>
>> Thanks,
>> Ashwin
>>
>> On Tue, Mar 29, 2016 at 1:46 PM, Hartmut Kaiser 
>> wrote:
>> Ashwin,
>>
>> Dr. Feltus brought to our attention that you're interested in HPX and in
>> getting in contact with our group. Could you please let us know more
>> concretely what you're planning to do or what you're looking for?
>>
>> We are generally very interested in collaborating with interested people,
>> so
>> I'd be excited if we could find some project which would be interesting
>> for
>> everybody.
>>
>> Thanks!
>> Regards Hartmut
>> ---
>> http://boost-spirit.com
>> http://stellar.cct.lsu.edu
>>
>>
> 
> 
> ___
> hpx-users mailing list
> hpx-users@stellar.cct.lsu.edu
> https://mail.cct.lsu.edu/mailman/listinfo/hpx-users
> 

-- 
Patrick Diehl
Institut für Numerische Simulation
Rheinische Friedrich-Wilhelms Universität Bonn
Wegelerstrasse 4 , Room 0.001
D-53115 Bonn Germany
Tel : +49 228 733846
Mail: di...@ins.uni-bonn.de



signature.asc
Description: OpenPGP digital signature
___
hpx-users mailing list
hpx-users@stellar.cct.lsu.edu
https://mail.cct.lsu.edu/mailman/listinfo/hpx-users