[GRASS-dev] Re: [SoC] Parallelization of RST modules of GRASS GIS

[Markus Neteler]

On Tue, Mar 16, 2010 at 6:45 AM, Abhishek Shukla
<abhishek_shukla at students.iiit.ac.in> wrote:
> Dr. Helena
> I was wondering about which platform to consider for parallelization of
> v.surf.rst , v.vol.rst etc.  Till now I was thinking to do it for GPU and
> Cell BE.  If doing it in OpenCL or OpenMP will increase its usability ,
> doing it on those platforms makes more sense.  Currently I am planning to do
> this on CUDA before gsoc starts in May.

@all: Please consider to add material as relevant here:
http://grass.osgeo.org/wiki/GPU

>  My plan for gsoc is to this in
> OpenCL, so the project may be titled  something like "Rewriting RST modules
> of GRASS GIS in OpenCL" .

Maybe, to increase the possibility to be accepted (suggestion):

"Parallelization of GRASS GIS in OpenCL: The  RST modules case"

or so...?

> Has anyone signed up already for mentoring this project ?

Not that at know besides Helena's offer.

> I am starting to do system of linear equations now on CUDA (for GPU) .
> Please keep me posted about any information on other time consuming part of
> RST modules.

(I take liberty to cross-post Helena's answer from the SOC list here,
for the record):

On Mon, Mar 15, 2010 at 8:31 PM, Helena Mitasova <hmitaso at unity.ncsu.edu> wrote:
> Do the system of linear equations first - it should help on several levels
> because it will also make it possible to run the interpolation with fewer larger segments
> and larger neighborhood reducing the instances when segments may be visible
> in the resulting grid.
>
> Computing grid may be time consuming for certain values of tension - I would have to look at it.
> Checking the interpolating function at given points should be made optional - it depends on how
> many points there are - it could take as much time as computing the grid.
>
> Finding points should not take too much time unless the spatial distribution of points
> is very heterogeneous, but I would have to look at it.
>
> you can write me off-this list (maybe cc to GRASS dev list) as SoC list is mostly
> to organize GSoC (at least that is how I understand its purpose),
>
> Helena
>
>
> Helena Mitasova
> Associate Professor
> Department of Marine, Earth and Atmospheric Sciences
> North Carolina State University
> Raleigh, NC 27695
> hmitaso at unity.ncsu.edu

Best,
Markus