A multi-task scheduling method of a heterogeneous processor

By creating task parsers and Stream objects in heterogeneous processors and adopting reasonable task scheduling strategies, the problem of multi-task parallel processing in memory-constrained environments is solved, achieving efficient utilization of computing resources and task scheduling.

CN122111692BActive Publication Date: 2026-06-2658TH RES INST OF CETC
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
58TH RES INST OF CETC
Filing Date
2026-04-29
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing heterogeneous processors cannot effectively process multiple tasks in parallel in memory-constrained edge environments, resulting in wasted computing resources and low processing efficiency, especially lacking advantages in scenarios such as parallel analysis of video frame data and model priority scheduling.

Method used

By creating task parsers and Model objects in main memory, constructing Stream objects to manage tasks, adopting serial, parallel, priority, and cascading scheduling strategies, rationally allocating global IDs and video memory for Tasks, and utilizing the Kernel scheduler to optimize task distribution, multi-task parallel execution is achieved.

Benefits of technology

It improves task scheduling efficiency, reduces computing resource waste, enhances resource utilization, supports multi-task parallel and cascaded processing, and optimizes the use of memory and video memory.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122111692B_ABST
    Figure CN122111692B_ABST
Patent Text Reader

Abstract

The application discloses a multi-task scheduling method of a heterogeneous processor and belongs to the computer field. In the case that the storage resource of an end side is insufficient, the user cannot use a single model to parallel infer different frame data, and the existing resources are reused as much as possible to improve the inference efficiency in the scene that the camera data / frame data needs to be processed in parallel. Meanwhile, different priorities are set for different inference tasks and different inference tasks of the same model, multiple models exist in cascade, and the multiple model cascades return in the middle, and the multi-task scheduling method is provided, which can effectively improve the efficiency of the end side inference task and significantly reduce the waste of the computing resource.
Need to check novelty before this filing date? Find Prior Art