Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storage
This work addresses inefficiencies in memory system design for computing platforms, offering a novel approach that could lead to performance and efficiency gains, though it appears incremental as it builds on existing ML techniques applied to specific architectural components.
The paper tackles the problem of static, human-designed heuristics in memory systems by proposing machine learning methods for adaptive control, resulting in three ML-guided policies that significantly outperform prior approaches with modest hardware overheads.
Despite the data-rich environment in which memory systems of modern computing platforms operate, many state-of-the-art architectural policies employed in the memory system rely on static, human-designed heuristics that fail to truly adapt to the workload and system behavior via principled learning methodologies. In this article, we propose a fundamentally different design approach: using lightweight and practical machine learning (ML) methods to enable adaptive, data-driven control throughout the memory hierarchy. We present three ML-guided architectural policies: (1) Pythia, a reinforcement learning-based data prefetcher for on-chip caches, (2) Hermes, a perceptron learning-based off-chip predictor for multi-level cache hierarchies, and (3) Sibyl, a reinforcement learning-based data placement policy for hybrid storage systems. Our evaluation shows that Pythia, Hermes, and Sibyl significantly outperform the best-prior human-designed policies, while incurring modest hardware overheads. Collectively, this article demonstrates that integrating adaptive learning into memory subsystems can lead to intelligent, self-optimizing architectures that unlock performance and efficiency gains beyond what is possible with traditional human-designed approaches.