Next programming paradigm for CBE/GPU in the next years

Question

Hi,

in the last five years, there has been a rise in the use of GPU and CBE for parallelization of applications. Around 2005-2007 verything seemed to be programmed by hand, C, etc. Afterwards new unifying alternatives emerged like CUDA for GPU and lastly OpenCL.

What do you think will be the programming paradigm for GPU/CBE in the forthcoming years? My vote goes for OpenCL

Thanks

Answer 1

Low level GPU libraries won't be mainstream. Instead we'll have high level abstractions built on top of them, such as map-reduce, etc.