Machine Learning-Driven Intelligent Memory System Design: From On-Chip Caches to Storage

TL;DR

This paper introduces machine learning-based adaptive policies for memory systems, demonstrating significant performance improvements over traditional heuristics in cache prefetching, prediction, and data placement.

Contribution

It presents three novel ML-guided memory policies—Pythia, Hermes, and Sibyl—that adaptively optimize cache prefetching, prediction, and data placement, outperforming prior heuristics.

Findings

Pythia improves cache prefetching efficiency.

Hermes enhances multi-level cache prediction accuracy.

Sibyl optimizes data placement in hybrid storage systems.

Abstract

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.