Execution Models for Mapping Programs onto Distributed Memory Parallel Computers
Abstract
This paper addresses the problem of exploiting the parallelism available in a program to efficiently employ the resources of the target machine, in the context of building a mapping compiler for a distributed memory parallel machine. The paper describes using execution models to drive the process of mapping a program in the most efficient way onto a particular machine. Through analysis of the execution models for several mapping techniques for one class of programs, we show that the selection of the best technique for a particular program instance can make a significant difference in performance. On the other hand, the results of benchmarks from an implementation of a mapping compiler show that our execution models are accurate enough to select the best mapping technique for a given program. Performance modeling, Modeling, Compilers, Systolic arrays.
Document Details
- Document Type
- Technical Report
- Publication Date
- Mar 01, 1992
- Accession Number
- ADA248144
Entities
People
- Alan Sussman