II-NEW: BOLD: Big Data and Optical Lightpaths-Driven Networked Systems Research Infrastructure

II-新：大胆：大数据和光路驱动的网络系统研究基础设施

• 批准号: 1305379
• 负责人: T. S. Eugene Ng
• 金额: $ 90万
• 依托单位: William Marsh Rice University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-09-01 至 2017-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1305379&HistoricalAwards=false
• 关键词: II; NEW; BOLD; Big; Data

This project will deploy an optically networked systems research infrastructure named BOLD that integrates high-performance, low-power, optical networking devices and programmable packet switches to enable transformative and inter-disciplinary research. It enables experimental exploration of different architectural design choices and it will potentially suggest new approaches to integrated hardware-software designs. At the hardware level, it enables research on novel optical network devices that can provide powerful communication capabilities, possibly tailored to the specific needs of big data applications, as well as experimentation with the device prototypes under real application traffic. BOLD enables a broad range of transformative big data-driven research. At the system software level, it enables research on storage, network, and application control software that are designed from the ground up to coordinate for optimal performance. At the application level, BOLD motivates research on how fundamental algorithms for big data applications should be designed to leverage the new network capabilities. BOLD has the unique potential to bridge the gap between nano-photonics researchers, networked systems researchers, and big data application researchers, creating inter-disciplinary research opportunities. Furthermore, because BOLD is designed to operate alongside Rice?s existing NSF-funded computing infrastructures BOLD can support big data experiments at a substantial scale.Results from the inter-disciplinary research enabled by BOLD will lead to future big data processing system architectures that dramatically speed up a wide range of computational scientific discoveries. Because optical networking devices are unique in that they consume very little power, yet can support enormous data rates, BOLD will inspire a new class of high performance, high energy efficiency system architectures. Research enabled by BOLD could inform the design of future nation-wide networking infrastructures by showing how optical networks can be harnessed as shared ?cloud? resources. BOLD will serve as a platform for the training and education of numerous undergraduate and graduate students, including under-represented groups, in cutting edge big data-driven research.

该项目将部署一个名为BOLD的光网络系统研究基础设施，该基础设施集成了高性能、低功耗的光网络设备和可编程分组交换机，以实现变革性和跨学科的研究。 它使实验探索不同的架构设计选择，它可能会建议新的方法来集成硬件软件设计。 在硬件层面，它可以研究新型光网络设备，这些设备可以提供强大的通信功能，可能适合大数据应用的特定需求，以及在真实的应用流量下对设备原型进行实验。BOLD支持广泛的变革性大数据驱动研究。在系统软件级别，它支持对存储、网络和应用程序控制软件的研究，这些软件是从头开始设计的，以协调实现最佳性能。在应用层面，BOLD激励研究如何设计大数据应用的基础算法，以利用新的网络功能。BOLD具有弥合纳米光子学研究人员、网络系统研究人员和大数据应用研究人员之间差距的独特潜力，创造了跨学科研究的机会。此外，由于BOLD的设计是与大米一起运作的？现有的NSF资助的计算基础设施BOLD可以支持大规模的大数据实验。BOLD支持的跨学科研究的结果将导致未来的大数据处理系统架构，从而显着加速广泛的计算科学发现。由于光网络设备的独特之处在于它们消耗很少的功率，但可以支持巨大的数据速率，BOLD将激发一类新的高性能，高能效系统架构。BOLD支持的研究可以通过展示如何利用光网络来共享，为未来全国范围的网络基础设施的设计提供信息。云？资源BOLD将作为众多本科生和研究生（包括代表性不足的群体）在尖端大数据驱动研究中的培训和教育平台。