# A Joint Learning Approach to Hardware Caching and Prefetching

arXiv: https://arxiv.org/abs/2510.10862 · HTML: https://mlsanity.com/paper/2510.10862/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 21 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Builds on (most cited first, 11 of 11)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [Keystroke Dynamics as Part of Lifelogging](https://mlsanity.com/paper/2010.10144/) (2020)
- [CLAR: Contrastive Learning of Auditory Representations](https://mlsanity.com/paper/2010.09542/) (2020)
- [Learning Memory Access Patterns](https://mlsanity.com/paper/1803.02329/) (2018)
- [Pythia: A Customizable Hardware Prefetching Framework Using Online Reinforcement Learning](https://mlsanity.com/paper/2109.12021/) (2021)
- [A neural network memory prefetcher using semantic locality](https://mlsanity.com/paper/1804.00478/) (2018)

## Built on by (most cited first, 1 of 1)

- [ArchAgent: Agentic AI-driven Computer Architecture Discovery](https://mlsanity.com/paper/2602.22425/) (2026)

## Abstract (arXiv)

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.