互连性
光子学
中间层
计算机科学
高效能源利用
模块化设计
加速度
宽带
带宽(计算)
硅光子学
电子工程
电信
材料科学
工程类
电气工程
光电子学
纳米技术
人工智能
蚀刻(微加工)
图层(电子)
物理
经典力学
操作系统
作者
Ebadollah Taheri,Mohammad Amin Mahdian,Sudeep Pasricha,Mahdi Nikdast
出处
期刊:
日期:2023-10-12
卷期号:: 15-20
被引量:10
标识
DOI:10.1145/3610396.3618091
摘要
2.5D chiplet systems have showcased low manufacturing costs and modular designs for machine learning (ML) acceleration. Nevertheless, communication challenges arise from chiplet interconnectivity and high-bandwidth demands among chiplets. To address these challenges, we present TRINE, a novel tree-based silicon photonic interposer network for energy-efficient ML acceleration. Leveraging silicon photonics and broadband optical switching, TRINE enables efficient inter-chiplet communication with reduced latency and improved energy efficiency. Considering several ML workloads, our simulation results demonstrate significant improvements in the average energy efficiency by 61.7% and 40% when comparing TRINE with two recently proposed silicon photonic interposer networks. By overcoming communication limitations in 2.5D ML accelerators, this work is a promising step towards advancing 2.5D photonic-based ML accelerator design.
科研通智能强力驱动
Strongly Powered by AbleSci AI