Design and Implementation of a General Purpose Neural Network Processor

摘要

The general-purpose neural network processor is designed for the most neural networks algorithm and is required for variable bit length data processing ability. This paper proposes a processor that is based on SIMD (Single Instruction Multiple Data) architecture with three data bit mode: 8-bit, 16-bit and 32-bit. It can use the memory and ALU sufficiently when the bit mode changes. The processor is designed basing on 0.25-micron process technology and it can be synthesized at 50MHz with PKS of Cadence Inc. The experiment result shows that the processor can implement the neural network in highly parallel.