CISE Experimental Partnerships: MIT Raw Machine

CISE 实验合作伙伴：MIT Raw Machine

• 批准号: 0071841
• 负责人: Saman Amarasinghe
• 金额: $ 209.9万
• 依托单位: Massachusetts Institute of Technology
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2000
• 资助国家: 美国
• 起止时间: 2000-09-15 至 2005-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0071841&HistoricalAwards=false
• 关键词: CISE; Experimental; Partnerships; MIT; Raw

EIA-0071841Amarasighe, Saman P.MITCISE Experimental Partnerships: Partnerships: MIT Raw MachineRapidly evolving technology places a billion transistors on a chip within reach of the computer architect. Several approaches to utilizing the large amount of silicon resources have been put forth, with the single important goal of obtaining the most performance out of approximately one square inch of silicon. These approaches exploit more parallelism in one or more instruction streams. Examples include more aggressive superscalars, multiscalars, processor-coupled designs, simultaneous multi-threading processors, multiprocessors on a chip and VLIWs. The goal of this project is to discover, implement and evaluate simple architectural mechanisms that scale with increasing VLSI clock speed, and software techniques that orchestrate high-level computations on the low-level architectural resources for maximum efficiency.

【参考译文】amarasighe， Saman P.MITCISE实验合作伙伴关系：合作伙伴关系：麻省理工学院原始机器快速发展的技术使计算机架构师可以在芯片上安装10亿个晶体管。已经提出了几种利用大量硅资源的方法，其重要目标是在大约一平方英寸的硅中获得最大的性能。这些方法在一个或多个指令流中利用更多的并行性。例子包括更激进的超标量、多标量、处理器耦合设计、并发多线程处理器、芯片上的多处理器和vliw。该项目的目标是发现、实现和评估随着VLSI时钟速度的增加而扩展的简单架构机制，以及在底层架构资源上协调高级计算以实现最高效率的软件技术。