Abstract: Neural network inference may be performed by configuration of a device including an accumulation memory, a plurality of convolution modules configured to perform mathematical operations on input values, a plurality of adder modules configured to sum values output from the plurality of convolution modules, and a plurality of convolution output interconnects connecting the plurality of convolution modules, the plurality of adder modules, and the accumulation memory. The accumulation memory is an accumulation memory allocation of a writable memory block having a reconfigurable bank width, and each bank of the accumulation memory allocation is a virtual combination of consecutive banks of the writable memory block.

Abstract: Neural network inference may be performed by configuration of a device including an accumulation memory, a plurality of convolution modules configured to perform mathematical operations on input values, a plurality of adder modules configured to sum values output from the plurality of convolution modules, and a plurality of convolution output interconnects connecting the plurality of convolution modules, the plurality of adder modules, and the accumulation memory. The accumulation memory is an accumulation memory allocation of a writable memory block having a reconfigurable bank width, and each bank of the accumulation memory allocation is a virtual combination of consecutive banks of the writable memory block.

Abstract: Neural network inference may be performed by an apparatus or integrated circuit configured to perform mathematical operations on activation data stored in an activation data memory and weight values stored in a weight memory, to store values resulting from the mathematical operations onto an accumulation memory, to perform activation operations on the values stored in the accumulation memory, to store resulting activation data onto the activation data memory, and to perform inference of a neural network by feeding and synchronizing instructions from an external memory.

Abstract: Preparation and execution of quantized scaling may be performed by operations including obtaining an original array and a scaling factor representing a ratio of a size of the original array to a size of a scaled array, determining, for each column of the scaled array, a horizontal coordinate of each of two nearest elements in the horizontal dimension of the original array, and, for each row of the scaled array, a vertical coordinate of each of two nearest elements in the vertical dimension of the original array, calculating, for each row of the scaled array and each column of the scaled array, a linear interpolation coefficient, converting each value of the original array from a floating point number into a quantized number, converting each linear interpolation coefficient from a floating point number into a fixed point number, storing, in a memory, the horizontal coordinates and vertical coordinates as integers, the values as quantized numbers, and the linear interpolation coefficients as fixed point numbers

Abstract: Neural network accelerator hardware-specific division of inference may be performed by operations including obtaining a computational graph and a hardware chip configuration. The operations also include dividing inference of the plurality of layers into a plurality of groups. Each group includes a number of sequential layers based on an estimate of duration and energy consumption by the hardware chip to perform inference of the neural network by performing the mathematical operations on activation data, sequentially by layer, of corresponding portions of layers of each group. The operations further include generating instructions for the hardware chip to perform inference of the neural network, sequentially by group, of the plurality of groups.

Abstract: Neural network accelerator hardware-specific division of inference may be performed by operations including obtaining a computational graph and a hardware chip configuration. The operations also include dividing inference of the plurality of layers into a plurality of groups. Each group includes a number of sequential layers based on an estimate of duration and energy consumption by the hardware chip to perform inference of the neural network by performing the mathematical operations on activation data, sequentially by layer, of corresponding portions of layers of each group. The operations further include generating instructions for the hardware chip to perform inference of the neural network, sequentially by group, of the plurality of groups.

Abstract: Neural network inference may be performed by configuration of a device including a plurality of convolution modules, a plurality of adder modules, an accumulation memory, and a convolution output interconnect control module configured to open and close convolution output interconnects among a plurality of convolution output interconnects connecting the plurality of convolution modules, the plurality of adder modules, and the accumulation memory. Inference may be performed while the device is configured according to at least one convolution output connection scheme whereby each convolution module has no more than one open direct connection through the plurality of convolution output interconnects to the accumulation memory or one of the plurality of adder modules. The device includes a convolution output interconnect control module to configure the plurality of convolution output interconnects according to the at least one convolution output connection scheme.

Abstract: A CNN processing apparatus (1) includes an input buffer (10) configured to store an input signal A given to a CNN, a weight buffer (11) configured to store weights U, a convolutional operation unit (12) configured to perform a convolutional operation including a product-sum operation of the input signal A and the weights U, a storage unit 16 configured to store a table (160) which is configured to associate an input and an output of conversion-quantization processing with each other, wherein the input is an operation result of the convolutional operation, and the output is a result of the conversion-quantization processing of converting the input value based on a predetermined condition and quantizing the converted value by reducing a bit accuracy of the converted data, and a processing unit (14) configured to acquire the output of the conversion-quantization processing corresponding to the operation result by the operation unit by referring to the table (160).