Probably I’ll choose openCL. It means that I must learn a new
language,but it’s
not bad…
le to do either for this project. Have you
checked the mailing list archives? Getting GPU-based processing into a
GNU Radio flowgraph is quite hard, given the structure of the
scheduler. Also, which elements are you hoping to accelerate?
Do you speak about the fact that in cuda memory can be used only in the
thread
which instantiated it?
There is the gr-gpu project (it’s a CGRAN project) that is based on
using CUDA for the development of the signal processing blocks.
Mostly, this was done because OpenCL was too new at the time and was
not really usable for this purpose.
I’ve already seen it,but thank you!!
And, an aside on co-processor projects like gr-gpu. My opinion on this
is that we wouldn’t carry gr_block’s that are written for
co-processors in GNU Radio, anyways. So the license doesn’t matter so
much for that
I’ve not considered this aspect…is it for GSOC rules,in your opinion?