A Method of Using Cell Array Computing System to Realize Neural Network Computing

A technology of cell array and neural network, which is applied in the field of computer and computer application, can solve the problems of unfavorable neural network calculation efficient implementation and affecting the overall performance of the computer, so as to achieve the effect of speeding up the calculation, improving the overall performance, and increasing the speed

Active Publication Date: 2019-02-12
SHANGHAI CIYU INFORMATION TECH CO LTD
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0010] The problem to be solved by the present invention is that the computer architecture in the prior art affects the overall performance of the computer due to the communication bottleneck between the CPU, memory and storage, which is not conducive to the efficient realization of neural network calculations

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Method of Using Cell Array Computing System to Realize Neural Network Computing
  • A Method of Using Cell Array Computing System to Realize Neural Network Computing
  • A Method of Using Cell Array Computing System to Realize Neural Network Computing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] Due to the communication bottleneck between the CPU, the memory and the storage in the computer architecture of the prior art, the improvement of the overall performance of the computer is affected, and the cost-effectiveness is relatively poor.

[0044] After research, the inventor of the present application considers that if the three functions of memory, storage and calculation are integrated into one chip, a relatively simple unit with independent calculation and storage functions will be formed, and a large number of such units will form a dense network. Communication network, in order to realize the function of data broadcasting / group sending and the internal network capable of large-scale parallel transmission of data, a computing architecture similar to the human brain can be developed, which is equivalent to building a large number of microcomputers in one on chip.

[0045] To this end, the technical solution of the present invention provides a computing archit...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a method for realizing neural network calculation by using a cell array calculation system. The cell array calculation system includes a main control CPU, a cell array and a cell array bus; the cell array is a two-dimensional array composed of more than one cell with a calculation function and a storage function; the main control CPU communicates with each cell in the cell array through the cell array bus; and communication interfaces are arranged between adjacent cells and can transmit data to each other. The method includes the following steps that: each cell in the cell array, which participates in neural network calculation, stores the code of one or more than one neuronal function; any cell in the cell array, which participates in neural network calculation, receives execution results for the codes of the neuronal functions which are outputted by other cells and adopts the execution results as input data of the cell so as to execute the codes of the neuronal functions stored by the cell, and outputs an execution result, or stores the execution result into a preset address. With the method of the invention adopted, communication bottlenecks between the CPU and memory as well as between the CPU and storage of an existing computer architecture can be eliminated, and the overall performance of the system can be improved.

Description

technical field [0001] The invention relates to the technical field of computers and computer applications, in particular to a method for realizing neural network calculations using a cell array computing system. Background technique [0002] Generally speaking, a computer mainly includes three core parts: a central processing unit (CPU, Central Processing Unit), memory and storage. [0003] Through the unremitting efforts of some of the world's top companies, the CPU has evolved into an extremely complex semiconductor chip. The number of MOS tubes inside the top CPU core can exceed 100 million. The current industry trend is that it is difficult to increase the operating frequency of the CPU due to power consumption constraints. It is also difficult to improve the operating efficiency of the already extremely complex modern CPU. New CPU products are increasingly evolving towards multi-core. [0004] In terms of memory, the current dominant technology is Dynamic Random Ac...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06N3/00G06F15/163
Inventor 戴瑾郭一民王践识
Owner SHANGHAI CIYU INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products