Hi, I try to adapt C++ project on OMAP and want to take advantage of the DSP. The project is a big one (multiview video codec), and I thought of discriminating the functions that are most often called and do their processing on DSP (filtering type of operations, with for loops). When I tried to do this on a single function, unexpectedly the total run time of the code increased considerably. I was using streaming to communicate with the DSP and thought this might be the reason. So, I will try the same with Direct Memory Mapping but I'm not very optimistic that this will increase my runtime either. So my question is, what would be the best approach to follow for using the DSP to make my code more efficient? In what cases DSP is advantageous over ARM? Thanks a lot. Best regards, Can -- To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
