Systems and methods for reducing power consumption of convolution operations for artificial neural networks

摘要

A computer-implemented method may include maintaining, within a local memory device (LMD) in a hardware accelerator (1) a filter matrix that may include a set of filter vectors corresponding to a filter location in each of a set of filters of a convolutional layer of an artificial neural network, and (2) an activation matrix that may include a primary and a secondary set of activation vectors, each activation vector included in an activation volume. The method may also include (1) directing a matrix multiplication unit (MMU) in the hardware accelerator to execute a matrix multiplication operation (MMO) using the filter matrix and the activation matrix, (2) replacing (i) the filter matrix with an additional filter matrix, and (ii) the secondary set of activation vectors with an additional set of activation vectors, and (3) directing the MMU to execute an additional MMO using the additional filter matrix and the activation matrix.