This paper presents ARCO, an adaptive Multi-Agent Reinforcement Learning (MARL)-based co-optimizing compilation framework designed to enhance the efficiency of mapping machine learning (ML) models - such as Deep Neural Networks (DNNs) - onto diverse hardware platforms. The framework incorporates three specialized actor-critic agents within MARL, each dedicated to a distinct aspect of compilation/optimization at an abstract level: one agent focuses on hardware, while two agents focus on software optimizations. This integration results in a collaborative hardware/software co-optimization strategy that improves the precision and speed of DNN deployments. Concentrating on high-confidence configurations simplifies the search space and delivers superior performance compared to current optimization methods. The ARCO framework surpasses existing leading frameworks, achieving a throughput increase of up to 37.95% while reducing the optimization time by up to 42.2% across various DNNs.

翻译：本文提出ARCO，一种基于自适应多智能体强化学习（MARL）的协同优化编译框架，旨在提升机器学习（ML）模型（如深度神经网络DNN）在多样化硬件平台上的映射效率。该框架在MARL中集成了三个专用的行动者-评论家智能体，每个智能体在抽象层面专注于编译/优化的不同方面：一个智能体专注于硬件优化，另外两个智能体专注于软件优化。这种集成形成了一种协作式软硬件协同优化策略，从而提升了DNN部署的精度与速度。通过聚焦于高置信度配置，该框架简化了搜索空间，并相较于现有优化方法实现了更优的性能。ARCO框架超越了当前主流框架，在多种DNN上实现了高达37.95%的吞吐量提升，同时将优化时间降低了高达42.2%。