Single AIE vector sum example
These are two examples for using a single AI Engine kernel. I adapted and extended the given vec_sum example to get:
- One version with PLIO data transfer to the AIE (vec_sum)
- One version with GMIO data transfer to the AIE (vec_sum_gmio) Both versions come with two kernels to choose from, once the "normal" kernel where the result is calculated value by value, and one "vectorised" version of it (fpadd). Also both versions should be selfcontained, i.e. by following the steps of the README.md you should be able to run both of them in x86simulation, aiesimulation, sw_emulation, hw_emulation and in hardware it self.
One might have to extend the README.md a bit, depending on the audience which it is meant for (e.g. by explanations of the single files). And also the code documentation in the code itself might not be sufficient.