CSR: Medium: Effective Control to Maximize Resource Efficiency in Large Clusters; Hardware, Runtime, and Compiler Perspectives
CSR:中:有效控制以最大化大型集群中的资源效率;
基本信息
- 批准号:1763658
- 负责人:
- 金额:$ 120万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2018
- 资助国家:美国
- 起止时间:2018-08-15 至 2023-07-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Current computer systems use energy and other resources inefficiently. To improve efficiency, this proposal rethinks the way computer systems are controlled. This proposal uses formal methodologies based on control theory, and an analysis that cuts across software and hardware, to obtain orders of magnitude gains in resource efficiency. The proposal designs controllers in the hardware, in the runtime system, and in the compiler. The expected result is that large clusters can deliver higher performance for the same energy consumption, or consume lower energy for the same performance.This work involves building a prototype running an experimental runtime system and a compiler. It develops a set of technologies that will improve the resource efficiency of general-purpose computers by one or more orders of magnitude. The work will enable current technology computers to continue delivering increased capabilities, providing economic benefits to our society. The research has four thrusts: adapting control theory to computer architecture, developing hardware controllers, extending runtime systems to actuate on the hardware, and compiler-driven control. This research will be performed in collaboration with AMD Corporation Research. This effort enhances multidisciplinary research and education on cluster and datacenter technologies at the University of Illinois. The material in this work will enhance the courses on computer architecture, runtime systems, compilation, and parallel programming that the investigators are teaching. This work will place undergraduates and under-represented students in research groups. The research will also have a major impact on industry, since it addresses a real, very timely technical problem: that of making our cluster and datacenter infrastructure more energy efficient.This project will produce various deliverables that will be placed in a website for the community to access. The project repository will include data, code, results, a hardware emulator, a runtime system, and a compiler. These materials will be made available for at least two years beyond the project's lifetime. They will be accessible from http://iacoma.cs.uiuc.edu.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
目前的计算机系统使用能源和其他资源效率低下。为了提高效率,该提案重新考虑了计算机系统的控制方式。这一建议使用基于控制理论的正式方法,以及贯穿软件和硬件的分析,以获得资源效率的数量级收益。该方案在硬件、运行时系统和编译器中设计了控制器。预期的结果是,大型集群可以提供更高的性能相同的能源消耗,或消耗较低的能源相同的performance.This工作涉及到建立一个原型运行的实验运行时系统和编译器。它开发了一套技术,将通用计算机的资源效率提高一个或多个数量级。这项工作将使目前的技术计算机继续提供更高的能力,为我们的社会提供经济效益。该研究有四个重点:使控制理论适应计算机体系结构,开发硬件控制器,扩展运行时系统以在硬件上致动,以及编译器驱动的控制。这项研究将与AMD公司研究合作进行。这一努力加强了伊利诺伊大学关于集群和数据中心技术的多学科研究和教育。在这项工作中的材料将提高计算机体系结构,运行时系统,编译和并行编程的课程,调查人员正在教。这项工作将把本科生和代表性不足的学生放在研究小组中。这项研究还将对行业产生重大影响,因为它解决了一个真实的、非常及时的技术问题:使我们的集群和数据中心基础设施更加节能。该项目将产生各种可交付成果,这些成果将放在一个网站上供社区访问。项目存储库将包括数据、代码、结果、硬件仿真器、运行时系统和编译器。这些材料将在项目结束后至少两年提供。他们将可从http://iacoma.cs.uiuc.edu.This访问奖项反映了NSF的法定使命,并已被认为值得通过使用基金会的知识价值和更广泛的影响审查标准进行评估的支持。
项目成果
期刊论文数量(10)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Graphite: optimizing graph neural networks on CPUs through cooperative software-hardware techniques
- DOI:10.1145/3470496.3527403
- 发表时间:2022-06
- 期刊:
- 影响因子:0
- 作者:Zhangxiaowen Gong;Houxiang Ji;Yao Yao-Yao;Christopher W. Fletcher;C. Hughes;J. Torrellas
- 通讯作者:Zhangxiaowen Gong;Houxiang Ji;Yao Yao-Yao;Christopher W. Fletcher;C. Hughes;J. Torrellas
Maya: Using Formal Control to Obfuscate Power Side Channels
Maya:使用形式控制来混淆电源侧通道
- DOI:10.1109/mm.2022.3166886
- 发表时间:2022
- 期刊:
- 影响因子:3.6
- 作者:Pothukuchi, Raghavendra Pradyumna;Pothukuchi, Sweta Yamini;Voulgaris, Petros G.;Schwing, Alexander;Torrellas, Josep
- 通讯作者:Torrellas, Josep
Tangram: Integrated Control of Heterogeneous Computers
Tangram:异构计算机的集成控制
- DOI:10.1145/3352460.3358285
- 发表时间:2019
- 期刊:
- 影响因子:0
- 作者:Pothukuchi, Raghavendra Pradyumna;Greathouse, Joseph L.;Rao, Karthik;Erb, Christopher;Piga, Leonardo;Voulgaris, Petros G.;Torrellas, Josep
- 通讯作者:Torrellas, Josep
WISE: Predicting the Performance of Sparse Matrix Vector Multiplication with Machine Learning
- DOI:10.1145/3572848.3577506
- 发表时间:2023-02
- 期刊:
- 影响因子:0
- 作者:Serif Yesil;Azin Heidarshenas;Adam Morrison;J. Torrellas
- 通讯作者:Serif Yesil;Azin Heidarshenas;Adam Morrison;J. Torrellas
SPADE: A Flexible and Scalable Accelerator for SpMM and SDDMM
- DOI:10.1145/3579371.3589054
- 发表时间:2023-06
- 期刊:
- 影响因子:0
- 作者:Gerasimos Gerogiannis;Serif Yesil;Damitha Sandeepa Lenadora;Dingyuan Cao;Charith Mendis;J. Torrellas
- 通讯作者:Gerasimos Gerogiannis;Serif Yesil;Damitha Sandeepa Lenadora;Dingyuan Cao;Charith Mendis;J. Torrellas
{{
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 }}
Josep Torrellas其他文献
Software Trace Cache for Commercial Applications
- DOI:
10.1023/a:1019992713965 - 发表时间:
2002-10-01 - 期刊:
- 影响因子:0.900
- 作者:
Alex Ramirez;Josep Ll. Larriba-Pey;Carlos Navarro;Mateo Valero;Josep Torrellas - 通讯作者:
Josep Torrellas
An Empirical Study of the Effect of Source-level Transformations on Compiler Stability
源代码级转换对编译器稳定性影响的实证研究
- DOI:
- 发表时间:
2018 - 期刊:
- 影响因子:0
- 作者:
Zhangxiaowen Gong;Zhi Chen;J. Szaday;David C. Wong;Zehra Sura;Neftali Watkinson;Saeed Maleki;David Padua;Alexandru Nicolau;A. Veidenbaum;Josep Torrellas - 通讯作者:
Josep Torrellas
Uncorq: Unconstrained Snoop Request Delivery in Embedded-Ring Multiprocessors
Uncorq:嵌入式环多处理器中无约束的侦听请求传送
- DOI:
10.1109/micro.2007.43 - 发表时间:
2007 - 期刊:
- 影响因子:0
- 作者:
Karin Strauss;Xiaowei Shen;Josep Torrellas - 通讯作者:
Josep Torrellas
Josep Torrellas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('Josep Torrellas', 18)}}的其他基金
Collaborative Research: PPoSS: LARGE: General-Purpose Scalable Technologies for Fundamental Graph Problems
合作研究:PPoSS:大型:解决基本图问题的通用可扩展技术
- 批准号:
2316233 - 财政年份:2023
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
SHF: Medium: Cross-Cutting Effort to Make Non-Volatile Memories Truly Usable
SHF:中:使非易失性存储器真正可用的跨领域努力
- 批准号:
2107470 - 财政年份:2021
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
PPoSS: Planning: A Cross-Layer Approach to Accelerate Large-Scale Graph Computations on Distributed Platforms
PPoSS:规划:加速分布式平台上大规模图计算的跨层方法
- 批准号:
2028861 - 财政年份:2020
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
CNS Core: Medium: Rethinking Architecture and Operating Systems for Modern Virtualization Technologies
CNS 核心:中:重新思考现代虚拟化技术的架构和操作系统
- 批准号:
1956007 - 财政年份:2020
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
SPX: Secure, Highly-Parallel Training of Deep Neural Networks in the Cloud Using General-Purpose Shared-Memory Platforms
SPX:使用通用共享内存平台在云中对深度神经网络进行安全、高度并行的训练
- 批准号:
1725734 - 财政年份:2017
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Technologies for Ultra Energy-Efficient Multicores
超节能多核技术
- 批准号:
1649432 - 财政年份:2016
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
XPS: FULL: Breaking the Scalability Wall of Shared Memory through Fast On-Chip Wireless Communication
XPS:FULL:通过快速片上无线通信打破共享内存的可扩展性壁垒
- 批准号:
1629431 - 财政年份:2016
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
SHF: Small: Computer Architecture for Scripting Languages
SHF:小型:脚本语言的计算机体系结构
- 批准号:
1527223 - 财政年份:2015
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
SHF: Large: Collaborative Research: Designing the Programmable Many-Core for Extreme Scale Computing
SHF:大型:协作研究:为超大规模计算设计可编程众核
- 批准号:
1536795 - 财政年份:2014
- 资助金额:
$ 120万 - 项目类别:
Continuing Grant
CSR: Small: A Framework for Advanced Concurrency Debugging
CSR:小型:高级并发调试框架
- 批准号:
1116237 - 财政年份:2011
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
相似海外基金
Advances in Cost-Effective HV SiC Power Devices for Europe’s Medium Voltage Grids - AdvanSiC
适用于欧洲中压电网的经济高效高压 SiC 功率器件的进展 - AdvanSiC
- 批准号:
10048924 - 财政年份:2023
- 资助金额:
$ 120万 - 项目类别:
EU-Funded
Collaborative Research: III: Medium: Towards Effective Detection and Mitigation for Shortcut Learning: A Data Modeling Framework
协作研究:III:媒介:针对捷径学习的有效检测和缓解:数据建模框架
- 批准号:
2310262 - 财政年份:2023
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: III: Medium: Towards Effective Detection and Mitigation for Shortcut Learning: A Data Modeling Framework
协作研究:III:媒介:针对捷径学习的有效检测和缓解:数据建模框架
- 批准号:
2310261 - 财政年份:2023
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Language support in English-medium-instruction higher education: current challenges and effective collaboration between language and content teachers
英语教学高等教育中的语言支持:当前挑战以及语言和内容教师之间的有效合作
- 批准号:
2887906 - 财政年份:2023
- 资助金额:
$ 120万 - 项目类别:
Studentship
Collaborative Research: III: Medium: Towards Effective Detection and Mitigation for Shortcut Learning: A Data Modeling Framework
协作研究:III:媒介:针对捷径学习的有效检测和缓解:数据建模框架
- 批准号:
2310260 - 财政年份:2023
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
AdvanSiC - Advances in Cost-Effective HV SiC Power Devices for Europe’s Medium Voltage Grids
AdvanSiC - 欧洲中压电网经济高效的高压 SiC 功率器件的进步
- 批准号:
10063342 - 财政年份:2023
- 资助金额:
$ 120万 - 项目类别:
EU-Funded
Collaborative Research: SaTC: CORE: Medium: Methods and Tools for Effective, Auditable, and Interpretable Online Ad Transparency
协作研究:SaTC:核心:媒介:有效、可审核和可解释的在线广告透明度的方法和工具
- 批准号:
2149680 - 财政年份:2022
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: SaTC: CORE: Medium: Methods and Tools for Effective, Auditable, and Interpretable Online Ad Transparency
协作研究:SaTC:核心:媒介:有效、可审核和可解释的在线广告透明度的方法和工具
- 批准号:
2151340 - 财政年份:2022
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: SaTC: CORE: Medium: Methods and Tools for Effective, Auditable, and Interpretable Online Ad Transparency
协作研究:SaTC:核心:媒介:有效、可审核和可解释的在线广告透明度的方法和工具
- 批准号:
2151837 - 财政年份:2022
- 资助金额:
$ 120万 - 项目类别:
Standard Grant
Collaborative Research: SaTC: CORE: Medium: Methods and Tools for Effective, Auditable, and Interpretable Online Ad Transparency
协作研究:SaTC:核心:媒介:有效、可审核和可解释的在线广告透明度的方法和工具
- 批准号:
2151290 - 财政年份:2022
- 资助金额:
$ 120万 - 项目类别:
Standard Grant