Automatic data distribution
This paper outlines the design of a fully-automatic source-to-source translator which can accept a program written in a subset of Fortran90 and determine a data distribution scheme (including, where beneficial, dynamic redistributions) for the arrays of the program. The translator generates a semantically equivalent Fortran90 program incorporating the distribution scheme in the form of language extensions, such as the Vienna Fortran  or HPF  extensions.
Keywordsautomatic data distribution dynamic redistribution parallelizing compilers
Unable to display preview. Download preview PDF.
- B. Chapman, P. Mehrotra, H. Zima: “Programming in Vienna Fortran” Scientific Programming. Vol. 1, No. 1, Autumn 1992, pp 31–50.Google Scholar
- High Performance Fortran. Scientific Programming. Vol. 2, No. 2, Spring 1993, pp 1 168.Google Scholar
- F. Bodin, P. Beckmann, D. Gannon, et al: “Sage++: A Class Library for Building Fortran90 and C++ Restructuring Tools: DRAFT 0.1”Google Scholar
- P. Crooks, R.H. Perrott: “Language Constructs for Data Partitioning and Distribution”, Internal Report, Dept. of Computer Science, Queen's University, Belfast, June 1993Google Scholar