Development and Design of Reconfigurable and Scalable Optical Interconnection Architectures for Next Generation High-Performance Computing Systems

下一代高性能计算系统的可重构和可扩展光互连架构的开发和设计

• 批准号: 0538945
• 负责人: Glenn Schrader
• 金额: --
• 依托单位: University of Arizona
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2006
• 资助国家: 美国
• 起止时间: 2006-03-01 至 2011-02-28
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0538945&HistoricalAwards=false
• 关键词: Development; Design; Reconfigurable; Scalable; Optical

This research explores the application of optical technology to the communication problems of future high-performance computing (HPC) systems. The goal is to develop flexible and dynamically reconfigurable optical interconnection architectures that will scale to a large number of processors while delivering scalable bandwidth, low communication latency, low power consumption, and low cost. The proposed approach is an organized effort combining architecture, technology, simulation and physical demonstration. The proposed research consists of three inter-related tasks: (1) Development and design of reconfigurable and scalable optical interconnection architectures for HPCs, (2) Identification and characterization of possible optical components necessary for the implementation of the proposed architectures, and (3) Development of analytic modeling and simulation tools for the precise physical modeling of the optical implementation techniques, as well as end-to-end system modeling of the proposed architectures. As feature sizes in CMOS chips decrease to the sub-micron regime, and clock rates increase to the multi-GHz range, electrical interconnects are predicted to reach their fundamental limits and become the ultimate bottleneck for performance. This limitation will result in major bandwidth imbalances in future high-performance computers, and significantly affect their performance and scalability. One of the technologies that has been recognized to have the potential to solve communication problems of HPC systems is optical interconnects.

本研究探讨了光学技术在未来高性能计算（HPC）系统通信问题中的应用。其目标是开发灵活且可动态重构的光互连架构，该架构将扩展到大量处理器，同时提供可扩展的带宽、低通信延迟、低功耗和低成本。所提出的方法是一个有组织的努力相结合的架构，技术，仿真和物理演示。 拟议的研究包括三个相互关联的任务：（1）开发和设计用于HPC的可重新配置和可扩展的光互连架构，（2）识别和表征实现所提出的架构所需的可能的光组件，以及（3）开发用于光实现技术的精确物理建模的分析建模和仿真工具，以及所提出的体系结构的端到端系统建模。随着CMOS芯片中的特征尺寸减小到亚微米范围，并且时钟速率增加到几GHz范围，预计电互连将达到其基本极限并成为性能的最终瓶颈。这种限制将导致未来高性能计算机的主要带宽不平衡，并显着影响其性能和可扩展性。光互连技术是被认为有潜力解决HPC系统通信问题的技术之一。