Nice video. Thank you for uploading these Smiley

 

You know the OpenCL 1.1 HelloWorld example from "OpenCL Programming Guide" by Aftab Munshi (editor of the OpenCL specification) -after removing all the comments- is around 260+ lines plus a 10-line kernel, and it exactly does the same thing: adding the corresponding elements of two arrays and putting the results in a third array. After watching this video, I'm really questioning the OpenCL's execution model and the need for all that explicit context creation, command queue creation, program object and memory object creation and alike in OpenCL! If we can do the same thing with ~50 lines of code, and with the simplicity we see in this video, why should we even bother using an execution model like OpenCL's? a performance comparison between C++ AMP, OpenCL and CUDA would be great to answer that question (I haven't seen any yet) it will defenitely tell us if we really need a complicated execution model like OpenCL's (or may be where do we need such a model)