NUMA系统运行状态检测方法、电子设备和介质

By automatically acquiring and binding the nodes of GPU, CPU, memory, and dynamic link libraries in the NUMA system, the problems of low efficiency and poor accuracy in NUMA system operation status detection are solved, thereby improving system performance and stability.

CN122132253BActive Publication Date: 2026-07-17MU XI LING ZHI KE JI (HANG ZHOU) YOU XIAN GONG SI
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
MU XI LING ZHI KE JI (HANG ZHOU) YOU XIAN GONG SI
Filing Date
2026-05-08
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing technologies are inefficient and inaccurate in detecting the operational status of NUMA systems, and cannot effectively improve the computing performance and operational stability of NUMA systems.

Method used

By automatically obtaining the NUMA nodes to which the GPU, CPU, memory, and dynamic link libraries used by the process to be processed belong and their loading ratios, binding and optimization are performed to ensure that these resources are on the same NUMA node, reducing cross-node access.

Benefits of technology

This improves the efficiency and accuracy of NUMA system status detection, and enhances the system's computing performance and stability.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122132253B_ABST
    Figure CN122132253B_ABST
Patent Text Reader

Abstract

本发明涉及计算机技术领域，尤其涉及一种NUMA系统运行状态检测方法、电子设备和介质，包括获取待处理进程使用的GPU归属的NUMA节点，运行的CPU、内存绑定的NUMA节点及动态链接库加载至的NUMA节点和比例；将GPU归属的NUMA节点设置为目标NUMA节点；若CPU绑定的NUMA节点不是目标NUMA节点，则将CPU绑定至目标NUMA节点上；若内存绑定的NUMA节点是目标NUMA节点，则限制内存分配在目标NUMA节点上；若动态链接库未百分百加载在目标NUMA节点上，则清除内存缓后重新启动待处理进程，将动态链接库百分百加载在目标NUMA节点上。本发明提高了NUMA系统运行状态检测的效率和准确性。
Need to check novelty before this filing date? Find Prior Art