Abstract: A method comprises accessing a flattened input stream that includes a set of parallel vectors representing a set of input values of a kernel-sized tile of an input tensor that is to be convolved with a kernel. An expanded kernel is received that is generated by permuting values from the kernel. A control pattern is received that includes a set of vectors each corresponding to the output value position for the kernel-sized tile of the output and indicating a vector of the flattened input stream to access input values. The method further comprises generating, for each output position of each kernel-sized tile of the output, a dot product between a first vector that includes values of the flattened input stream as selected by the control pattern, and a second vector corresponding to a vector in the expanded kernel corresponding to the output position.

Abstract: A computational array is implemented in which all operands and results are loaded or output from a single side of the array. The computational array comprises a plurality of cells arranged in n rows and m columns, each configured to produce a processed value based upon a weight value and an activation value. The cells receive weight and activation values via colinear weight and activation transmission channels that each extend across a first side edge of the computational array to provide weight values and activation values to the cells of the array. In addition, result values produced at a top cell of each of the m columns of the array are routed through the array to be output from the same first side edge of the array at a same relative timing at which the result values were produced.

Abstract: A method comprises receiving a kernel used to convolve with an input tensor. For a first dimension of the kernel, a square block of values for each single dimensional vector of the kernel that includes all rotations of that single dimensional vector is generated. For each additional dimension of the kernel, group blocks of an immediately preceding dimension into sets of blocks, each set of blocks including blocks of the immediately preceding dimension that are aligned along a vector that is parallel to the axis of the dimension; and generate, for the additional dimension, one or more blocks of values, each block including all rotations of blocks within each of the sets of blocks of the immediately preceding dimension. The block of values corresponding to the last dimension in the additional dimensions of the kernel is output as the expanded kernel.

Abstract: A computational array is implemented in which all operands and results are loaded or output from a single side of the array. The computational array comprises a plurality of cells arranged in n rows and m columns, each configured to produce a processed value based upon a weight value and an activation value. The cells receive weight and activation values are received via colinear weight and activation transmission channels that each extend across a first side edge of the computational array to provide weight values and activations values to the cells of the array. In addition, result values produced at a top cell of each of the m columns of the array are routed through the array to be output from the same first side edge of the array at a same relative timing at which the result values were produced.

Abstract: A method comprises receiving an input tensor for convolution with a kernel, dividing the input tensor into one or more tiles with each tile having a size equal to the kernel, flattening the values in the one or more tiles into vectors to generate the flattened input stream.

Abstract: A method comprises receiving a kernel used to convolve with an input tensor. For a first dimension of the kernel, a square block of values for each single dimensional vector of the kernel that includes all rotations of that single dimensional vector is generated. For each additional dimension of the kernel, group blocks of an immediately preceding dimension into sets of blocks, each set of blocks including blocks of the immediately preceding dimension that are aligned along a vector that is parallel to the axis of the dimension; and generate, for the additional dimension, one or more blocks of values, each block including all rotations of blocks within each of the sets of blocks of the immediately preceding dimension. The block of values corresponding to the last dimension in the additional dimensions of the kernel is output as the expanded kernel.

Abstract: A method comprises receiving one or more sizes for each of the dimensions of a kernel that is convolved with an input tensor to generate an output activation, generating a control pattern used to compute output values for the convolution of the input tensor, with the control pattern being a square matrix with each dimension being a size equal to the product of the width and the height of the kernel. The control pattern is generated by generating a value for each position of the control pattern that is based on a location of the position in the control pattern and the one or more sizes of each of the dimensions of the kernel, the value indicating a location from which to access values from a flattened input tensor for the convolution with the kernel.

Abstract: A method comprises accessing a flattened input stream that includes a set of parallel vectors representing a set of input values of a kernel-sized tile of an input tensor that is to be convolved with a kernel. An expanded kernel is received that is generated by permuting values from the kernel. A control pattern is received that includes a set of vectors each corresponding to the output value position for the kernel-sized tile of the output and indicating a vector of the flattened input stream to access input values. The method further comprises generating, for each output position of each kernel-sized tile of the output, a dot product between a first vector that includes values of the flattened input stream as selected by the control pattern, and a second vector corresponding to a vector in the expanded kernel corresponding to the output position.