SHF: Small: Techniques and Frameworks for Exploiting Recent SIMD Architectural Advances

SHF：小型：利用最新 SIMD 架构进步的技术和框架

• 批准号: 1526386
• 负责人: Rajiv Ramnath
• 金额: $ 45万
• 依托单位: Ohio State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-07-01 至 2020-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1526386&HistoricalAwards=false
• 关键词: SHF; Small; Techniques; Frameworks; Exploiting

Single Instruction Multiple Data (SIMD) parallelism has been available in common processors for several decades now, and has been widely exploited for dense matrix and other regular problems. Recent architectural trends, such as increasing width of SIMD lanes coupled with instruction sets, provide significantly enhanced functionality. There is a need to effectively use the new architectural features for dynamic or irregular applications, which have not been easy to perform on parallel on SIMD processors in the past. The PI proposes comprehensive research program on mapping various classes of unstructured and/or irregular applications to modern SIMD novel architectural features and developing optimized compiler transformations from programs written in CUDA and OpenCL. This research proposal proposes to address the challenge of developing and executing unstructured and/or irregular applications using novel SIMD processors' instructions such as scatter and gather. The PI plans to design compiler transformation methods from CUDA and OpenCL programs to increase the number of contiguous accesses and decrease the number of cache lines from which data needs to be accessed. These novel transformation methods are targeting applications such as unstructured grid kernels, sparse matrix computations, and graph and tree traversals. The PI plans to continue development of an Operator Overloading based library.

单指令多数据（SIMD）并行已经在普通处理器中应用了几十年，并被广泛应用于稠密矩阵和其他规则问题。最近的架构趋势，例如增加与指令集耦合的SIMD通道的宽度，提供了显著增强的功能。 有必要有效地使用新的架构功能的动态或不规则的应用程序，这并不容易在SIMD处理器上并行执行在过去。 PI提出了全面的研究计划，将各种非结构化和/或不规则应用程序映射到现代SIMD新的架构功能，并从CUDA和OpenCL编写的程序中开发优化的编译器转换。本研究建议，以解决开发和执行非结构化和/或不规则的应用程序，使用新的SIMD处理器的指令，如分散和聚集的挑战。PI计划从CUDA和OpenCL程序中设计编译器转换方法，以增加连续访问的数量，并减少需要访问数据的缓存行的数量。这些新的转换方法的目标应用程序，如非结构化网格内核，稀疏矩阵计算，图形和树遍历。 PI计划继续开发基于运算符重载的库。