XPS: FULL: CCA: Collaborative Research: CASH: Cost-aware Adaptation of Software and Hardware

XPS：完整：CCA：协作研究：CASH：软件和硬件的成本意识适应

• 批准号: 1439156
• 负责人: Henry Hoffmann
• 金额: $ 30万
• 依托单位: University of Chicago
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2014
• 资助国家: 美国
• 起止时间: 2014-09-01 至 2019-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1439156&HistoricalAwards=false
• 关键词: XPS; FULL; CCA; Collaborative; Research

Programming for and leveraging the benefits of scalable and highlyparallel computer architectures is becoming increasinglychallenging. In order to ease programmer and user effort in achievingefficient use of parallel architectures and to enable optimal usage ofparallel hardware both within a single chip and across a data center,this project explores the co-design of a fine-grain configurable (downto the ALU, FPU, Cache bank, fetch unit, etc) architecture along witha software optimizing runtime system which controls the architecture?sconfiguration. This runtime management system understands high-levelgoals and constraints such as optimizing for power, latency, cost, orcomplex mixed-goals and dynamically allocates fine-grain resources tomeet the constraints. This project will evaluate and design a configurablemanycore-inspired architecture and a self-adapting runtime system.This project will investigate the creation of a complete, scalable,self-adaptive computing system; and will push the boundaries ofadapting systems by utilizing hardware that is configurable andmonitorable below the processor core level. By providing such aflexible and highly monitored architecture to the adaptation runtime,this project will explore the scalability of adaptive runtimealgorithms to handle a game-changing increase in the number ofcontrollable parameters. This project will explore the extent towhich it is fruitful to configure a parallel architecture.

编程和利用可扩展和高度并行的计算机体系结构的好处正变得越来越具有挑战性。为了减轻程序员和用户的努力，在开发有效的使用并行架构，并使最佳的使用并行硬件都在一个单一的芯片和跨数据中心，这个项目探讨了协同设计的细粒度可配置（下至ALU，FPU，缓存银行，取单元等）的架构沿着的软件优化运行时系统，控制的架构？sconfiguration.该运行时管理系统理解高级目标和约束，例如优化功耗、延迟、成本或复杂的混合目标，并动态分配细粒度资源以满足约束。这个项目将评估和设计一个可配置的任何核心启发的架构和自适应运行时系统。这个项目将研究创建一个完整的，可扩展的，自适应的计算系统;并将推动边界的适应系统，利用硬件是可配置的和可监控的处理器核心以下的水平。通过为自适应运行时提供这种灵活和高度监控的架构，该项目将探索自适应运行时算法的可扩展性，以处理可控参数数量的变化。这个项目将探讨在何种程度上是富有成效的配置并行架构。

项目成果

Generative and Multi-phase Learning for Computer Systems Optimization

• DOI: 10.1145/3307650.3326633
• 发表时间: 2019-06
• 期刊: 2019 ACM/IEEE 46th Annual International Symposium on Computer Architecture (ISCA)
• 作者: Yi Ding;Nikita Mishra;H. Hoffmann

CoPPer: Soft Real-time Application Performance Using Hardware Power Capping

CoPPer：使用硬件功率上限的软实时应用程序性能

• 发表时间: 2019
• 期刊: International Confernce on Autonomic Computing
• 作者: Imes, Connor;Zhang, Huazhe;Zhao, Kevin;Hoffmann, Henry
• 通讯作者: Hoffmann, Henry