Convolutional Neural Network On Programmable Two Dimensional Image Processor

A machine readable storage medium having stored thereon program code that when processed by an image processor having an array of execution lanes and a two-dimensional shift register that provides local respective register space to the executional lanes causes a method to be performed, the method comprising:

• executing a convolutional neural network by performing the following:
• a) loading a plane of image data of a three-dimensional block of image data into the two-dimensional shift register;
• b) performing a two-dimensional convolution of the plane of image data with an array of coefficient values by sequentially:
• concurrently multiplying within the execution lanes respective pixel and coefficient values to produce an array of partial products;
• concurrently summing within the execution lanes the partial products with respective accumulations of partial products being kept within the two dimensional register for different stencils within the image data;
• and,
• effecting alignment of values for the two-dimensional convolution within the execution lanes by shifting content within the two-dimensional shift register array.

An apparatus, comprising:

• i) an image processor comprising an array of execution lanes and a two dimensional shift register, said two dimensional shift register to provide respective local register space for the execution lanes;
• ii) a machine readable storage medium containing stored program code that when executed by the array of execution lanes causes a method to be performed comprising:
• executing a convolutional neural network by performing the following:
• a) loading a plane of image data of a three-dimensional block of image data into the two-dimensional shift register;
• b) performing a two-dimensional convolution of the plane of image data with an array of coefficient values by sequentially:
• concurrently multiplying within the execution lanes respective pixel and coefficient values to produce an array of partial products;
• concurrently summing within the execution lanes the partial products with respective accumulations of partial products being kept within the two dimensional register for different stencils within the image data;
• and,
• effecting alignment of values for the two-dimensional convolution within the execution lanes by shifting content within the two-dimensional shift register array.