OpenCL Group in Linkedin

I find important sharing information among people using OpenCL. Recently, I joined to OpenCL group in Linkedin. Some discussions and points of view that you'll find there:

1. the lack of domain specific libraries compared to CUDA, for instance. However, AMD has released stuff like http://developer.amd.com/libraries/appmathlibs/Pages/default.aspx. Anyway, we should have always in mind that OpenCL is younger than CUDA.
2. questions about why use OpenCL in environments without GPUs were answered by people arguing about the unknown user space (where your app will run) and stuff like http://www.khronos.org/developers/library/2010_siggraph_bof_opencl/OpenCL-BOF-Intel-SIGGRAPH-Jul10.pdf that points the direction of applications implemented on Intel's SDK.

The group is open and some helpful and qualified helpful members are creating interesting discussions.

Parallel Primitives Library

Lets try to improve OpenCL libraries for everything...

Libs like this:

clpp is an OpenCL Data Parallel Primitives Library. It is a library of data-parallel algorithm primitives such as parallel-prefix-sum ("scan"), parallel sort and parallel reduction. Primitives such as these are important building blocks for a wide variety of data-parallel algorithms, including sorting, stream compaction, and building data structures such as trees and summed-area tables.

If you want to join the project, please simply send a message to our mailing list: http://groups.google.com/group/cl-pp

Thanks to Polar Lights?? initiative. ;)

Profiling your application

I was away for a time, but I'm coming back. In my recent projects, I had taken a few results from profiling tools. For a better understanding, I grabbed some resources from Marcus Bannerman's website. Putting the link...

Profiling in Linux

I didn't ask no authorization to publish it in this blog, but I'm sure that he will not be upset about that.

Take a look at other articles from his website. There are a lot of stuff about OpenCL http://www.marcusbannerman.co.uk