A path-based method of parallelizing C++ programs

Authors:
Genjiang Zhu;Li Xie;Zhongxiu Sun
Affiliations:
Department of Computer Science, Nanjing University, Nanjing 210008, Jiangsu, P.R.. China;Department of Computer Science, Nanjing University, Nanjing 210008, Jiangsu, P.R.. China;Department of Computer Science, Nanjing University, Nanjing 210008, Jiangsu, P.R.. China
Venue:
ACM SIGPLAN Notices
Year:
1994

Citing 6
Cited 0

Virtual time

ACM Transactions on Programming Languages and Systems (TOPLAS)
An execution model for distributed object-oriented computation

OOPSLA '88 Conference proceedings on Object-oriented programming systems, languages and applications
A technique for summarizing data access and its use in parallelism enhancing transformations

PLDI '89 Proceedings of the ACM SIGPLAN 1989 Conference on Programming language design and implementation
Analysis of Interprocedural Side Effects in a Parallel Programming Environment

Proceedings of the 1st International Conference on Supercomputing
Speedup of ordinary programs

Speedup of ordinary programs
Optimizing supercompilers for supercomputers

Optimizing supercompilers for supercomputers

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents a path-based method for identifying parallelism in C++ programs and proposes an execution model which trades off the efficiency and parallelism. Based on the path information provided at compiler time or computed at run time, the model reduces the rollbacks while enhances the parallelism.