AF: Small: Green Computing Algorithmics

AF：小型：绿色计算算法

• 批准号: 1115575
• 负责人: Kirk Pruhs
• 金额: $ 34.99万
• 依托单位: University of Pittsburgh
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2011
• 资助国家: 美国
• 起止时间: 2011-09-01 至 2015-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1115575&HistoricalAwards=false
• 关键词: AF; Small; Green; Computing; Algorithmics

The ascension of power, to join time and space, in the top ranks of scarce computational resources is relatively recent. Over the last several decades, when time and space were the key computational resources, computer science researchers developed many algorithmic techniques for designing time and space efficient algorithms, and for analyzing the time and space required by particular algorithms on simple models. The immediate goal of this research is to build a toolkit of widely applicable algorithmic design and analysis techniques for algorithmic problems where energy, power and temperature are the key resources. This will require the discovery of new algorithmic techniques, as these energy related resources have different physical characteristics than the resources of time and space.Energy-efficient computing and power management are two important focus areas within green computing, which is the study and practice of designing, manufacturing, using, and disposing of computers, servers, and associated subsystems, efficiently and effectively with minimal impact on the environment. Currently the energy usage of information technology is roughly comparable to that used by the airline industry. On one hand, given that the growth of information technology is still exponential, this fraction could grow significantly if there are no changes in information technology. On the other hand, given that until recently energy efficiency wasn't a first order design constraint, an order of magnitude improvements in the energy efficiency of information technology is possible.A long term goal of this research is to build a science of algorithmic power management to support the computing community's ability to abstractly reason about power, energy and temperature. This science will serve these software engineers, when faced with information technology design problems in which power/energy/temperature is the key scarce resource, just as the science of algorithms serves them when they are concerned with the resources of time and space.

权力的提升，加入时间和空间，进入稀缺计算资源的顶级行列是相对较新的事情。在过去的几十年里，当时间和空间成为关键的计算资源时，计算机科学研究人员开发了许多算法技术来设计时间和空间高效的算法，以及在简单模型上分析特定算法所需的时间和空间。这项研究的直接目标是建立一个广泛适用的算法设计和分析技术工具包，用于解决以能量、功率和温度为关键资源的算法问题。这将需要发现新的算法技术，因为这些与能源相关的资源与时间和空间资源具有不同的物理特性。节能计算和电源管理是绿色计算的两个重要重点领域，这是绿色计算的研究和实践高效且有效地设计、制造、使用和处置计算机、服务器和相关子系统，并对环境影响最小。目前，信息技术的能源使用量与航空业的能源使用量大致相当。一方面，鉴于信息技术的增长仍然呈指数级增长，如果信息技术没有变化，这一比例可能会大幅增长。另一方面，鉴于直到最近能源效率还不是一阶设计约束，信息技术能源效率的数量级改进是可能的。这项研究的长期目标是建立一门算法能力科学管理以支持计算社区对功率、能量和温度进行抽象推理的能力。 当这些软件工程师面临以功率/能量/温度为关键稀缺资源的信息技术设计问题时，这门科学将为他们服务，就像当他们关心时间和空间资源时算法科学为他们服务一样。