Brain-like computing system based on multi-neural network fusion and execution method of instruction set

Abstract

The invention belongs to the field of brain-like computing, particularly relates to a brain-like computing system based on multi-neural-network fusion and an execution method of an instruction set, and aims to solve the problem that an existing brain-like computing system cannot realize parallel fusion computing of a deep neural network and an impulsive neural network. The system is used for carrying out parallel operation on a deep neural network and a pulse neural network, and comprises a local tight coupling calculation cluster, a PCIE interface and an internal data bus, wherein the local tight coupling calculation clusters are electrically connected through an internal data bus, are used for calculating a deep neural network or a pulse neural network and consist of N * N neuron enginesNE, and each NE shares one neuron buffer area; the NE is used for carrying out matrix operation and vector operation on the neuron model data; and the PCIE interface is matched with a PCIE slot of acomputer mainboard and is used for data interaction between the brain-like computing system and external equipment. According to the invention, parallel operation of the deep neural network and the spiking neural network is realized.

Description

technical field [0001] The invention belongs to the technical field of brain-inspired computing, and in particular relates to a brain-inspired computing system based on fusion of multiple neural networks and an execution method of an instruction set. Background technique [0002] The evolution of artificial intelligence algorithms has accelerated the demand for high computing power and low power consumption of chips, and new architectures, new devices and new solutions for artificial intelligence are constantly emerging. Among them, a class of brain-like chips has attracted widespread attention, such as the TrueNorth chip with millions of neurons released by IBM in 2014, the Loihi chip with 131,000 neurons released by Intel in 2017, and the Manches SpiNNaker from the University of Stuttgart and BrainScaleS from the University of Heidelberg. However, this type of chip basically does not have online learning capabilities, and has not yet shown performance and application scen...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above-mentioned problems in the prior art, that is, in order to solve the problem that the existing brain-like computing system cannot realize the parallel fusion calculation of the deep neural network and the pulse neural network, the first aspect of the present invention proposes a multi-neural network fusion based Brain-like computing system, the system is used for parallel computing of deep neural network and pulse neural network, which includes local tightly coupled computing cluster, PCIE interface, internal data bus; each local tightly coupled computing cluster passes through the internal data bus electrical connection;

Images