[ITK-dev] Integrating header-only boost::Compute for faster itkGPU development.

[Pablo Hernández]

Thanks a lot Matt, I will have a look at those sources.
Pablo

> Date: Tue, 5 Jan 2016 22:46:37 -0500
> Subject: Re: [ITK-dev] Integrating header-only boost::Compute for faster itkGPU development.
> From: matt.mccormick at kitware.com
> To: pablo.hernandez.cerdan at outlook.com
> CC: insight-developers at itk.org
> 
> Hi Pablo,
> 
> To make it easier to develop ITK-GPU filters with boost::Compute, an
> ITK Module should be created.  See the Modules in
> ITK/Modules/ThirdParty/ as examples. Documentation on how to create a
> Module can now be found in the ITK Software Guide:
> 
>   http://itk.org/ITKSoftwareGuide/html/Book1/ITKSoftwareGuide-Book1ch9.html#x50-1430009
> 
> If an Insight Journal article is submitted, the module can be merged
> into ITK as a Remote Module, and it can be dependency for modules that
> want to use boost::Compute in ITK.
> 
> 
> Other similar libraries that have been discussed include Cuda:
> 
>   http://www.insight-journal.org/browse/publication/802
>   https://code.google.com/p/cuda-insight-toolkit/
>   https://github.com/SimonRit/RTK/tree/1defcbdfe0bdcac6d0786f62ed8530e1b39204f9/code
> 
> and ArrayFire:
> 
>   http://arrayfire.com/
> 
> And similar Modules could be created for these. Each has its own
> advantages in terms of platform support and programability. It is
> recommended to reuse as much of the existing ITK OpenCL GPU
> infrastructure as possible or to use a similar design.
> 
> 
> To drive ITK-GPU computing forward in general, we need more software
> quality dashboard submissions. Instructions on how to set up a Nightly
> dashboard submission can be found here:
> 
>   http://www.itk.org/Wiki/ITK/Git/Dashboard
> 
> Thanks,
> Matt
> 
> 
> On Sat, Jan 2, 2016 at 9:04 AM, Pablo Hernández
> <pablo.hernandez.cerdan at outlook.com> wrote:
> > https://github.com/boostorg/compute
> > It is like cuda::Thrust library, functional oriented, but using opencl and
> > header-only. It implements quite a lot of STL algorithms to run in GPU's. It
> > requires c++11, and will be officially available in next boost release
> > (1.61)
> > I mention this, because I was creating a home-brewed itkGPU filters, and it
> > is painful to hand-write opencl code for every basic operation out there. I
> > can of course use it by my own, but I thought it could be helpful to boost::
> > the GPU developing in ITK.
> > I have no conflict of interests with this particular library, but wanted to
> > share it and hear what you think. Also any comment about the road map
> > involving GPU in ITK would be interesting.
> >
> > Regards,
> > Pablo
> >
> >
> >
> > _______________________________________________
> > Powered by www.kitware.com
> >
> > Visit other Kitware open-source projects at
> > http://www.kitware.com/opensource/opensource.html
> >
> > Kitware offers ITK Training Courses, for more information visit:
> > http://kitware.com/products/protraining.php
> >
> > Please keep messages on-topic and check the ITK FAQ at:
> > http://www.itk.org/Wiki/ITK_FAQ
> >
> > Follow this link to subscribe/unsubscribe:
> > http://public.kitware.com/mailman/listinfo/insight-developers
> >
 		 	   		  
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://public.kitware.com/pipermail/insight-developers/attachments/20160106/862679f5/attachment.html>