Scalable neural network processing engine

A method for processing input data, comprising:

• selectively activating a plurality of neural engine circuits of a neural processor circuit, each of the neural engine circuits configured to perform convolution operations on input data and kernel coefficients to generate output data, at least two of the neural engine circuits each comprising a plurality of multiply-add (MAD) circuits and a post-processor configured to apply nonlinear function to processed values from the MAD circuits;
• storing the input data in a data buffer of the neural engine circuit, for sending to the neural engine circuits and the output data received from different post-processors of the neural engine circuits, the data buffer shared among the plurality of neural engine circuits, the data buffer in communication with a memory external to the neural processor circuit;
• and
• sending a corresponding kernel coefficient extracted from kernel data to neural engine circuits selected for activation.

An integrated circuit (IC) system comprising a neural processor circuit, the neural processor circuit comprising:

• a plurality of neural engine circuits that are selectively activated, each of the neural engine circuits configured to perform convolution operations on input data and kernel coefficients to generate output data, at least two of the neural engine circuits each comprising a plurality of multiply-add (MAD) circuits and a post-processor configured to apply nonlinear function to processed values from the MAD circuits;
• a data buffer shared among the plurality of neural engine circuits, the data buffer in communication with a memory external to the neural processor circuit, the data buffer configured to store the input data from the memory for sending to the neural engine circuits and the output data received from different post-processors of the neural engine circuits;
• and
• a kernel extract circuit configured to receive kernel data from the memory external to the neural processor circuit, the kernel extract circuit configured to send a corresponding kernel coefficient extracted from the kernel data to neural engine circuits selected for activation.