Communication and memory requirements as the basis for mapping task and data parallel programs
- 17 December 2002
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
For a wide variety of applications, both task and data parallelism must be exploited to achieve the best possible performance on a multicomputer. Recent research has underlined the importance of exploiting task and data parallelism in a single compiler framework, and such a compiler can map a single source program in many different ways onto a parallel machine. The tradeoffs between task and data parallelism are complex and depend on the characteristics of the program to be executed, most significantly the memory and communication requirements, and the performance parameters of the target parallel machine. We present a framework to isolate and examine the specific characteristics of programs that determine the performance for different mappings. Our focus is on applications that process a stream of input, and whose computation structure is fairly static and predictable. We describe three such applications that were developed with our compiler: fast Fourier transforms, narrowband tracking radar; and multibaseline stereo. We examine the tradeoffs between various mappings for them and show how the framework is used to obtain efficient mappings.<>Keywords
This publication has 16 references indexed in Scilit:
- Implementation and performance of fast parallel multi-baseline stereo visionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Supporting systolic and memory communication in iWarpPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Integrated Support for Task and Data ParallelismThe International Journal of Supercomputer Applications and High Performance Computing, 1994
- Task Parallelism in a High Performance Fortran FrameworkIEEE Parallel & Distributed Technology: Systems & Applications, 1994
- Function-Parallel Computation in a Data-Parallel EnvironmentPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- A multiple-baseline stereoPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Latency and bandwidth considerations in parallel robotics image processingPublished by Association for Computing Machinery (ACM) ,1993
- Computational Frameworks for the Fast Fourier TransformPublished by Society for Industrial & Applied Mathematics (SIAM) ,1992
- Improved algorithms for mapping pipelined and parallel computationsIEEE Transactions on Computers, 1991
- Assignment Problems in Parallel and Distributed ComputingPublished by Springer Nature ,1987