arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.00858cs.AR
收藏

Chiplet-Gym:利用强化学习优化基于Chiplet的AI加速器设计

Chiplet-Gym: Optimizing Chiplet-based AI Accelerator Design with Reinforcement Learning

Kaniz Mishty, Mehdi Sadi

AI总结:

针对基于Chiplet的AI加速器设计空间巨大且缺乏协同设计方法的问题,提出基于强化学习的优化框架Chiplet-Gym,结合PPAC分析建模与非RL方法,在等面积下实现高吞吐、低能耗与低成本的最优设计点。

摘要:

现代人工智能(AI)工作负载需要大面积硅片的计算系统来维持吞吐量和有竞争力的性能。然而,先进工艺节点下高昂的制造成本和良率限制,以及晶粒尺寸达到光罩极限,阻碍了我们实现这一目标。随着先进封装技术的最新创新,基于Chiplet的架构在AI硬件领域受到了广泛关注。然而,基于Chiplet的AI加速器设计空间巨大,且缺乏系统与封装级的协同设计方法,使得设计者难以在功耗、性能、面积和制造成本(PPAC)方面找到最优设计点。本文提出了Chiplet-Gym,一个基于强化学习(RL)的优化框架,用于探索基于Chiplet的AI加速器的广阔设计空间,涵盖资源分配、放置和封装架构。我们对基于Chiplet的AI加速器的PPAC进行了分析建模,并将其集成到OpenAI gym环境中以评估设计点。我们还探索了非RL的优化方法,并将这两种方法结合以确保优化器的鲁棒性。在等面积条件下,优化器建议的设计点实现了1.52倍的吞吐量、0.27倍的能耗和0.01倍的晶粒成本,同时其封装成本仅为单片对应方案的1.62倍。

英文摘要:

Modern Artificial Intelligence (AI) workloads demand computing systems with large silicon area to sustain throughput and competitive performance. However, prohibitive manufacturing costs and yield limitations at advanced tech nodes and die-size reaching the reticle limit restrain us from achieving this. With the recent innovations in advanced packaging technologies, chiplet-based architectures have gained significant attention in the AI hardware domain. However, the vast design space of chiplet-based AI accelerator design and the absence of system and package-level co-design methodology make it difficult for the designer to find the optimum design point regarding Power, Performance, Area, and manufacturing Cost (PPAC). This paper presents Chiplet-Gym, a Reinforcement Learning (RL)-based optimization framework to explore the vast design space of chiplet-based AI accelerators, encompassing the resource allocation, placement, and packaging architecture. We analytically model the PPAC of the chiplet-based AI accelerator and integrate it into an OpenAI gym environment to evaluate the design points. We also explore non-RL-based optimization approaches and combine these two approaches to ensure the robustness of the optimizer. The optimizer-suggested design point achieves 1.52X throughput, 0.27X energy, and 0.01X die cost while incurring only 1.62X package cost of its monolithic counterpart at iso-area.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑