Compiler Support for Analysis and Tuning Data Parallel Programs
نویسندگان
چکیده
Data parallel languages such as High-Performance Fortran (HPF) and Fortran D simplify the task of parallel programming by enabling users to express parallel algorithms at a high level. Compilers for these languages are responsible for realizing parallelism and inserting all interprocessor communication. For this reason, these compilers have detailed knowledge of the the relationship between its parallelism and communication in the program. Here, we explore how this knowledge can be exploited to support the process of tuning programs for high performance.
منابع مشابه
Compiler Support for Analysis and Tuning Data Parallel Programs Compiler Support for Analysis and Tuning Data Parallel Programs
Data parallel languages such as High-Performance Fortran (HPF) and Fortran D simplify the task of parallel programming by enabling users to express parallel algorithms at a high level. Compilers for these languages are responsible for realizing parallelism and inserting all interprocessor communication. For this reason, these compilers have detailed knowledge of the the relationship between its...
متن کاملPerformance Analysis of Data-Parallel Programs
EEective strategies for performance analysis and tuning will be essential for the success of data parallel languages such as High-Performance Fortran (HPF) and Fortran D. Since compilers for these languages insert all communication, they have considerable knowledge about a program's dynamic structure and the relationship between its parallelism and communication. This paper explores how this co...
متن کاملCompile-Time Estimation of Communication Costs for Data Parallel Programs
Most of the current compiler projects for distributed memory architectures leave the critical and time-consuming problem of nding performance-eecient data distributions and prootable program transformations for a given parallel program almost entirely to the programmer. Performance estimators provide critical performance information to both programmers and parallelizing compilers, the most cruc...
متن کاملData Flow Pattern Analysis of Scientific Applications
Many parallel and distributed applications have well defined structure which can be described by few simple relations. Some structures are so common that they are abstracted to parallel and grid benchmarks, other structures, are data and application dependent, become evident only at run-time. Many of these patterns reflect flow of data in the applications. Data Flow Graphs (DFG) provide an abst...
متن کاملVisualizing Distributed Data Structures
A new programming style for large-scale parallel programs centered around distributed data structures has emerged. The current parallel program visualization tools were intended for the old style and do not deal with distributed data structures. We show, with several examples of visualizations and animations developed for large scale pC++ programs, that visualizing and animating distributed dat...
متن کامل