CAREER: Energy-Efficient Datacenters with Wireless Interconnection Networks
职业:具有无线互连网络的节能数据中心
基本信息
- 批准号:1553264
- 负责人:
- 金额:$ 59.65万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2016
- 资助国家:美国
- 起止时间:2016-02-01 至 2024-01-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The principal aim of this CAREER: Energy-Efficient Datacenters with Wireless Interconnection Networks project is to establish design principals of a wireless datacenter by integrating intra- and inter-chip wireless networks. Computing machinery around the world consumes staggering amounts of energy. According to the NY Times in September 2012, digital warehouses like datacenters use thirty billion watts of electricity, which is equivalent to the output of thirty nuclear power plants. Networked computing elements are omnipresent in all computing machinery like datacenters, servers and High Performance Computing (HPC). Tens to thousands of multicore chips are interconnected to form an entire datacenter making the role of the network paramount in the performance and energy efficiency of the entire system. Data transfer between cores or memory components in different chips in large computing machinery need to traverse various interconnection technologies at the different levels of the network, often requiring change of switching protocols thus resulting in overheads. More importantly, according to the International Technology Roadmap for Semiconductors (ITRS), the pitch of the interchip interconnects is not scaling as fast as the pitch of on-chip interconnects, resulting in a performance gap in the future. Additionally, the wiring complexity of both on-chip and off-chip interconnects exacerbates the problem by posing design challenges, crosstalk and signal integrity issues. Recent research envisions on-chip wireless interconnects using millimeter-wave (mm-wave) technologies for designing Network-on-Chips, which are significantly more energy-efficient compared to traditional architectures. On the other hand in recent years considerable research has been done to develop wireless datacenters using the same 60GHz unlicensed wireless spectrum. The integrated architecture proposed in this work will be capable of establishing wireless routes between communicating processing cores in a datacenter. This highly interdisciplinary project will engage experts from the disciplines of computer engineering, computer science and electrical engineering from both academia and industry. Using concepts and technologies from various domains like computer architecture, communication, integrated circuit packaging and datacenters, the project will establish methodologies for wireless interconnections in large-scale computing warehouses to decrease their energy consumption and carbon footprint, ultimately resulting in a green and sustainable computing paradigm.
这个CAREER的主要目的:节能数据中心与无线互连网络项目是建立一个无线数据中心的设计原则,通过集成芯片内和芯片间的无线网络。世界各地的计算机消耗惊人的能量。据《纽约时报》2012年9月报道,像电子仓库这样的数字仓库使用了300亿瓦的电力,相当于30座核电站的发电量。网络化计算元素在所有计算机器中无处不在,如数据中心、服务器和高性能计算(HPC)。成千上万的多核芯片相互连接,形成一个完整的数据中心,使网络在整个系统的性能和能源效率方面发挥着至关重要的作用。在大型计算机器中的不同芯片中的核或存储器组件之间的数据传输需要在网络的不同级别上遍历各种互连技术,经常需要改变交换协议,从而导致开销。更重要的是,根据国际半导体技术路线图(ITRS),芯片间互连的间距没有像芯片上互连的间距那样快速扩展,导致未来的性能差距。此外,芯片上和芯片外互连的布线复杂性通过提出设计挑战、串扰和信号完整性问题而加剧了该问题。最近的研究设想使用毫米波(mm波)技术设计片上网络的片上无线互连,与传统架构相比,这种技术的能效要高得多。另一方面,近年来已经进行了大量的研究来开发使用相同的60GHz未许可无线频谱的无线收发器。在这项工作中提出的集成架构将能够在数据中心的通信处理核心之间建立无线路由。这个高度跨学科的项目将吸引来自学术界和工业界的计算机工程,计算机科学和电气工程学科的专家。该项目将利用计算机架构、通信、集成电路封装和数据中心等不同领域的概念和技术,建立大型计算仓库的无线互连方法,以减少其能源消耗和碳足迹,最终形成绿色和可持续的计算模式。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Amlan Ganguly其他文献
Design of Low Power & Reliable Networks on Chip Through Joint Crosstalk Avoidance and Multiple Error Correction Coding
- DOI:
10.1007/s10836-007-5035-1 - 发表时间:
2008-01-05 - 期刊:
- 影响因子:1.300
- 作者:
Amlan Ganguly;Partha Pratim Pande;Benjamin Belzer;Cristian Grecu - 通讯作者:
Cristian Grecu
Amlan Ganguly的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Amlan Ganguly', 18)}}的其他基金
IUCRC: Planning Grant: RIT: Center for Smart Spaces Research (CSSR)
IUCCRC:规划补助金:RIT:智能空间研究中心 (CSSR)
- 批准号:
2113905 - 财政年份:2021
- 资助金额:
$ 59.65万 - 项目类别:
Standard Grant
Collaborative Research: Workshop Series on Sustainable Computing
协作研究:可持续计算研讨会系列
- 批准号:
2126011 - 财政年份:2021
- 资助金额:
$ 59.65万 - 项目类别:
Standard Grant
SHF: CSR: Medium: Collaborative Research: Hierarchical On-Chip Millimeter-Wave Wireless Micro-Networks for Multi-Core Systems
SHF:CSR:媒介:协作研究:用于多核系统的分层片上毫米波无线微网络
- 批准号:
1162123 - 财政年份:2012
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
相似国自然基金
度量测度空间上基于狄氏型和p-energy型的热核理论研究
- 批准号:QN25A010015
- 批准年份:2025
- 资助金额:0.0 万元
- 项目类别:省市级项目
相似海外基金
CAREER: Resilient and Efficient Automatic Control in Energy Infrastructure: An Expert-Guided Policy Optimization Framework
职业:能源基础设施中的弹性和高效自动控制:专家指导的政策优化框架
- 批准号:
2338559 - 财政年份:2024
- 资助金额:
$ 59.65万 - 项目类别:
Standard Grant
CAREER: SHF: Bio-Inspired Microsystems for Energy-Efficient Real-Time Sensing, Decision, and Adaptation
职业:SHF:用于节能实时传感、决策和适应的仿生微系统
- 批准号:
2340799 - 财政年份:2024
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: Unary Computing in Memory for Fast, Robust and Energy-Efficient Processing
职业:内存中的一元计算,实现快速、稳健和节能的处理
- 批准号:
2339701 - 财政年份:2024
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: Computation-efficient Resolution for Low-Carbon Grids with Renewables and Energy Storage
职业:可再生能源和能源存储低碳电网的计算高效解决方案
- 批准号:
2340095 - 财政年份:2024
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: Exploring Mixed-Signal Computation for Energy-Efficient and Robust Brain-Machine Interfaces
职业:探索节能且鲁棒的脑机接口的混合信号计算
- 批准号:
2338159 - 财政年份:2024
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: Toward energy-efficient bio-inspired magnonic processing with nanomagnetic arrays
职业:利用纳米磁性阵列实现节能的仿生磁力处理
- 批准号:
2339475 - 财政年份:2024
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: Designing Ultra-Energy-Efficient Intelligent Hardware with On-Chip Learning, Attention, and Inference
职业:设计具有片上学习、注意力和推理功能的超节能智能硬件
- 批准号:
2336012 - 财政年份:2023
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: Computation-efficient Algorithms for Grid-scale Energy Storage Control, Bidding, and Integration Analysis
职业:用于电网规模储能控制、竞价和集成分析的计算高效算法
- 批准号:
2239046 - 财政年份:2023
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: Leveraging physical properties of modern flash memory chips for resilient, secure, and energy-efficient edge storage systems
职业:利用现代闪存芯片的物理特性打造弹性、安全且节能的边缘存储系统
- 批准号:
2346853 - 财政年份:2023
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant
CAREER: SHF: Chimp: Algorithm-Hardware-Automation Co-Design Exploration of Real-Time Energy-Efficient Motion Planning
职业:SHF:黑猩猩:实时节能运动规划的算法-硬件-自动化协同设计探索
- 批准号:
2239945 - 财政年份:2023
- 资助金额:
$ 59.65万 - 项目类别:
Continuing Grant