Monad:面向基于芯粒的空间加速器的高性价比专业化实现
Monad: Towards Cost-effective Specialization for Chiplet-based Spatial Accelerators
AI总结:
本研究针对芯粒基空间加速器的架构与集成设计空间未被充分开发的问题,提出成本感知的专业化方法Monad,结合统一编码与ML方法探索设计权衡,相较现有最优方案实现16%-30%的EDP降低。
摘要:
先进封装为后摩尔时代提供了一种全新的设计范式,可将众多小型芯粒组装为大型系统。基于异构集成的芯粒基加速器能够针对特定工作负载实现高度专业化,展现出极致效率与成本降低的优势。为充分挖掘这一潜力,需同时探索单个芯粒的架构设计空间以及组装这些芯粒的不同集成方案,而现有研究尚未充分开发这一领域。本文提出Monad——一种面向芯粒基空间加速器的成本感知专业化方法,旨在探索性能、功耗与面积(PPA)和制造成本之间的权衡关系。为评估专业化系统,我们引入了一个建模框架,该框架考虑了在不同芯粒上执行多种张量工作负载时,数据流、流水线和通信过程中的非均匀性。我们提出将架构与集成设计空间相结合,通过对两类空间的设计维度进行统一编码,并采用系统化的基于机器学习的方法开展探索。实验结果表明,与当前最先进的芯粒基加速器Simba和NN-Baton相比,Monad分别实现了平均16%和30%的能耗延迟积(EDP)降低。
英文摘要:
Advanced packaging offers a new design paradigm in the post-Moore era, where many small chiplets can be assembled into a large system. Based on heterogeneous integration, a chiplet-based accelerator can be highly specialized for a specific workload, demonstrating extreme efficiency and cost reduction. To fully leverage this potential, it is critical to explore both the architectural design space for individual chiplets and different integration options to assemble these chiplets, which have yet to be fully exploited by existing proposals. This paper proposes Monad, a cost-aware specialization approach for chiplet-based spatial accelerators that explores the tradeoffs between PPA and fabrication costs. To evaluate a specialized system, we introduce a modeling framework considering the non-uniformity in dataflow, pipelining, and communications when executing multiple tensor workloads on different chiplets. We propose to combine the architecture and integration design space by uniformly encoding the design aspects for both spaces and exploring them with a systematic ML-based approach. The experiments demonstrate that Monad can achieve an average of 16% and 30% EDP reduction compared with the state-of-the-art chiplet-based accelerators, Simba and NN-Baton, respectively.
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。