Data processing method and device, processor, electronic equipment and storage medium

By obtaining the processor's calculation time model and the search space of the target parameters, traversing the target parameters to determine the optimal computing scale, the problem of low configuration efficiency of processor computing cores in the prior art is solved, and efficient computing time optimization is achieved.

CN119718429APending Publication Date: 2025-03-28BEIJING ZITIAO NETWORK TECH CO LTD
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202311259402.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-09-27
Publication Date
2025-03-28

AI Technical Summary

Technical Problem

It is difficult to efficiently configure processor computing cores to optimize computing time in prior art, especially in parallel computing tasks in the field of deep learning of artificial intelligence.

Method used

By obtaining the search space of the target parameters and the processor's calculation time model, the target parameters are traversed to calculate the corresponding calculation time, and the target parameters are determined based on the minimum calculation time to configure the calculation scale of the calculation core.

Benefits of technology

It realizes that the processor's computing time is optimized without running on real hardware, makes full use of processor performance, improves computing efficiency, and is suitable for different types of operators and computing modes.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119718429A_ABST
    Figure CN119718429A_ABST
Patent Text Reader

Abstract

The embodiment of the invention provides a data processing method and device for a processor, the processor, electronic equipment and a storage medium. The processor comprises at least one computing core. The data processing method comprises the steps that a search space of a target parameter is obtained, and the search space comprises a first parameter to an nth parameter; a calculation time model of the processor is obtained, and the calculation time model is a function of the target parameter and the number of calculation cores of the processor; traversing the target parameter in the search space, and calculating the calculation time corresponding to the selected target parameter based on a calculation time model; in response to the minimum calculation time when the target parameter is the kth parameter, determining the target parameter as the kth parameter; the calculation scale of each of the at least one calculation core is configured using the kth parameter. The data processing method does not need to be operated on real hardware, the performance of a processor is fully utilized, and the calculation efficiency is greatly improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Cited By

  • Processor core number determination method and device, electronic equipment and storage medium

    CN120745376A

  • Data processing method and apparatus, processor, electronic device and storage medium

    EP4530873A1