Automatic code generation of data decomposition

Authors:
Ya-Nan Shen;Rong-Cai Zhao;Jian-Min Pang
Affiliations:
ZhengZhou Information Science and Technology Institute ZhengZhou, China;ZhengZhou Information Science and Technology Institute ZhengZhou, China;ZhengZhou Information Science and Technology Institute ZhengZhou, China
Venue:
InfoScale '06 Proceedings of the 1st international conference on Scalable information systems
Year:
2006

Citing 3
Cited 0

Scanning polyhedra with DO loops

PPOPP '91 Proceedings of the third ACM SIGPLAN symposium on Principles and practice of parallel programming
Global optimizations for parallelism and locality on scalable parallel machines

PLDI '93 Proceedings of the ACM SIGPLAN 1993 conference on Programming language design and implementation
Parallelizing compiler techniques based on linear inequalities

Parallelizing compiler techniques based on linear inequalities

Quantified Score

Hi-index	0.00

Visualization

Abstract

How to decompose or map data of programs automatically onto scalable parallel processors is a key issue in developing parallelizing compilers in DSM architecture. Data locality is crucial for parallelized programs to achieve high performance. Based on a linear inequalities mathematical model a formal specification of an optimized data decomposing algorithm and its implementation in C++ are presented. The algorithm enhances data locality and minimizes communication. Experimental results indicate that the algorithm improves the performance of parallelized programs significantly.