一种硬件缓存与预取的联合学习方法
A Joint Learning Approach to Hardware Caching and Prefetching
AI总结:
本文针对硬件缓存中缓存替换与预取策略孤立训练导致的次优问题,提出一种基于共享特征表示的联合学习方法,包含联合编码器和对比学习两种方案,并展示了初步成果与未来研究议程。
摘要:
现代系统中已提出多种学习策略来替代调度、缓存等系统组件的启发式方法。通过利用多样化特征、从历史趋势中学习并预测未来行为,这些模型有望跟上不断增加的工作负载动态变化和持续的硬件演进。然而,孤立训练的策略在组合使用时仍可能达到次优性能。在本文中,我们检查了硬件缓存领域中这样一个实例——针对缓存替换和预取策略。我们认为这两种策略是双向相互依赖的,并提出联合训练两者的理由。我们提出了一种基于开发两种策略所用特征的共享表示的联合学习方法。我们提出了两种开发这些共享表示的方法,一种基于联合编码器,另一种基于嵌入的对比学习,并展示了这两种方法的初步结果。最后,我们列出了该方向未来研究的议程。
英文摘要:
Several learned policies have been proposed to replace heuristics for scheduling, caching, and other system components in modern systems. By leveraging diverse features, learning from historical trends, and predicting future behaviors, such models promise to keep pace with ever-increasing workload dynamism and continuous hardware evolution. However, policies trained in isolation may still achieve suboptimal performance when placed together. In this paper, we inspect one such instance in the domain of hardware caching -- for the policies of cache replacement and prefetching. We argue that these two policies are bidirectionally interdependent and make the case for training the two jointly. We propose a joint learning approach based on developing shared representations for the features used by the two policies. We present two approaches to develop these shared representations, one based on a joint encoder and another based on contrastive learning of the embeddings, and demonstrate promising preliminary results for both of these. Finally, we lay down an agenda for future research in this direction.
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。