用强化学习动态优化内存控制器，兼顾能效与延迟。
ReLMXEL: Adaptive RL-Based Memory Controller with Explainable Energy and Latency Optimization
- 多智能体强化学习分解奖励，实时调整内存参数。
- 跨多种工作负载，延迟和能耗均显著降低。
- 决策过程可解释，适合对可靠性要求高的系统设计。
降低延迟和能耗是提升现代计算中内存系统效率的关键。本文提出ReLMXEL（基于可解释能效与延迟优化的强化学习内存控制器），一个可解释的多智能体在线强化学习框架，通过奖励分解动态优化内存控制器参数。ReLMXEL在内存控制器内部运行，利用详细的内存行为指标指导决策。在多种工作负载上的实验表明，相比基线配置性能持续提升，优化效果由工作负载特异的内存访问行为驱动。通过将可解释性融入学习过程，ReLMXEL不仅提升性能，还增强控制决策的透明度，为更可问责、自适应的内存系统设计铺平道路。
原文摘要 · Abstract (English)
Reducing latency and energy consumption is critical to improving the efficiency of memory systems in modern computing. This work introduces ReLMXEL (Reinforcement Learning for Memory Controller with Explainable Energy and Latency Optimization), a explainable multi-agent online reinforcement learning framework that dynamically optimizes memory controller parameters using reward decomposition. ReLMXEL operates within the memory controller, leveraging detailed memory behavior metrics to guide decision-making. Experimental evaluations across diverse workloads demonstrate consistent performance gains over baseline configurations, with refinements driven by workload-specific memory access behaviour. By incorporating explainability into the learning process, ReLMXEL not only enhances performance but also increases the transparency of control decisions, paving the way for more accountable and adaptive memory system designs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。