Exploiting input data sparsity in neural network compute units

摘要

Receiving, by a computing device, a plurality of input activations, the input activations being provided, at least in part, from a source external to the computing device; determining, by a controller of the computing device, whether each of the plurality of input activations has one of a zero value or a non-zero value; storing, in a memory bank of the computing device, at least one of the input activations; generating, by the controller, an index comprising one or more memory address locations having input activation values that are non-zero values; and providing, by the controller and from the memory bank, at least one input activation onto a data bus that is accessible by one or more units of a computational array, wherein the activations are provided, at least in part, from a memory address location associated with the index.