Changes

As usual, before implementing any optimization, a profiling was carried out in order to detect the portion of code that made sense to optimize. In addition to traditional , well-know techniques, the specific NPU-related tools were usedas well. For instance, the following dump shows the detailed report referring to the execution of a Convolutional Neural Network on the accelerator. {| class="wikitable"|+Example of NPU profiling report!LAYER ID!LAYER NAME!OPERATION ID!OPERATION TYPE!TARGET!CYCLES!READ BW [MByte]!WRITE BW [MByte]!AXI READ BW [MByte]!AXI WRITE BW [MByte]!DDR READ BW [MByte]!DDR WRITE BW [MByte]!TIME [μs]|-|0|TensorTranspose|0|TENSOR_TRANS|TP|482613|0.491743|0.445310|0.000000|0.000000|0.491743|0.445310|631|-|20|ConvolutionReluPoolingLayer2|0|RESHUFFLE|TP|1822|0.002380|0.000000|0.000000|0.000000|0.002380|0.000000|136|-|20|ConvolutionReluPoolingLayer2|0|RESHUFFLE|TP|402743|0.251754|0.000000|0.000000|0.000000|0.251754|0.000000|539|-|...|...|...|...|...|...|...|...|...|...|...|...|...|}