Abstract: Using a buffer sized according to the size of the filters of a convolutional neural network (CNN), a processor may use a read pointer to generate a two-dimensional virtual matrix of inputs. The number of inputs in each row in the two-dimensional virtual matrix of inputs may match the one-dimensional filter size of the cubic filters. The processor may collapse each of the cubic filters to one-dimensional linear arrays and generate a two-dimensional filter matrix from the one-dimensional linear arrays. The convolution computations for a corresponding layer of the CNN therefore reduce to a single matrix multiplication without any memory movement operations. When the buffer is refreshed using a new input frame, the processor may increment the initial read address of each read pointer by one and increment the final read address by one, circling back to the corresponding initial read address.

Abstract: An integrated circuit includes electronic components, a voltage regulator for generating a control voltage, and a power consumption measurement module. The power consumption measurement module is connected to the voltage regulator and includes an analog-to-digital converter (ADC) for converting the control voltage to multiple digital control voltage samples, an averaging module for averaging the digital control voltage samples, and a current profiling module for receiving the averaged control voltage data and determining an average current from averaged control voltage data. The average current represents power consumption of the integrated circuit.