Data processing method and device, electronic equipment and storage medium

By introducing multi-layer integration units and computing units into the data processing array, and based on preset rules and enabled signal processing calculation results, the problem of wasted computing power of the computing unit is solved, and efficient data processing and resource utilization are achieved.

CN119721152APending Publication Date: 2025-03-28HUNAN GOKE MICROELECTRONICS CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202411947662.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-27
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

In hardware devices that require a large amount of calculation of parallelism, there is a problem of wasting computing power of the computing unit, especially in multiple output results scenarios, resulting in low computing efficiency.

Method used

By introducing N-layer integration units and M computing units into the data processing array, the data to be processed is calculated according to preset rules, and the calculation results are progressively integrated or directly output according to the enable signals of each layer of integration unit, ensuring that as many computing units as possible participate in the calculation and reducing waste of computing power.

Benefits of technology

It realizes the output of multiple output results simultaneously through a single calculation, which improves data processing efficiency, reduces the vacancy of computing units and waste of computing power, and improves resource utilization.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a data processing method and device, electronic equipment and a computer readable storage medium, the method is applied to a data processing array, the data processing array comprises N layers of integration units, N is a natural number greater than or equal to 1, the method comprises the following steps: calculating to-be-processed data according to a preset rule, obtaining a plurality of operation results; and according to the enable signal of each layer of integration unit, carrying out progressive integration processing or direct output on the plurality of operation results layer by layer. According to the invention, the vacancy of the arithmetic units is reduced, the computing power waste of the arithmetic units is reduced, the resource utilization rate of the data processing array is improved, and the data processing efficiency is improved.
Need to check novelty before this filing date? Find Prior Art