arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.23945cs.PFcs.DCcs.OS
收藏

LMS-AR:基于LMS预测的多核系统内存带宽自适应调节器

LMS-AR: LMS Prediction-based Adaptive Regulator for Memory Bandwidth in Multicore Systems

IIIT Hyderabad(印度理工学院海德拉巴分校);Eindhoven University of Technology (TU/e)(埃因霍温理工大学)

Sudarshan Srinivasan, Deepak Gangadharan, Dip Goswami

AI总结:

提出LMS-AR机制,通过主核外部监控与自适应滤波预测,调节多核系统内存带宽分配,显著降低内存争用导致的性能下降。

摘要:

多核系统中的内存带宽争用严重影响应用程序性能和服务质量(QoS)保证。调节共享内存带宽可减轻内存性能不确定性,从而使其成为可管理的资源,并提高多核系统的可信度。在这项工作中,我们提出了一种内存带宽调节机制LMS-AR,即基于LMS预测的自适应调节器,作为Linux内核模块,将内存带宽作为资源分配给CPU核心。我们描述了一种设计,其中监控和调节均由主核从外部强制执行——该主核并非专用的调节控制器。这允许插入计算量大的预测和调节算法,而不会干扰被调节的核心。采用自适应滤波技术预测每个核心的带宽需求。我们使用分布在多个核心上的SPEC CPU 2017基准测试进行了多项实验。与Memguard相比,我们提出的方法在内存争用导致的减速比方面表现出显著改进。我们的解决方案公开托管在$\href{这个URL}{这个URL}$。

英文摘要:

Memory bandwidth contention in multi-core systems severely impacts application performance and quality-of-service (QoS) guarantees. Regulating the shared memory bandwidth mitigates the memory performance uncertainty thereby making it a manageable resource and improving trustworthiness of multi-core systems. In this work we propose a memory bandwidth regulation mechanism LMS-AR, i.e., LMS Prediction-based Adaptive Regulator within a Linux kernel module to distribute the memory bandwidth as a resource among the CPU cores. We describe a design in which both monitoring and regulation is enforced from outside by a master core - which is not a dedicated controller for regulation. This allows for plugging in computationally heavy prediction and regulation algorithms without interfering with the regulated core. An adaptive filtering technique was employed for prediction of per-core bandwidth requirement. We conducted several experiments with SPEC CPU 2017 benchmarks distributed across multiple cores. Our proposed approach demonstrated significant improvement over Memguard with respect to slowdown ratios caused due to memory contention. Our solution is hosted publicly at $\href{https://github.com/ss22ongithub/LMSAdaptiveRegulator}{https://github.com/ss22ongithub/LMSAdaptiveRegulator}$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑