Loop fusion in high performance Fortran
- 13 July 1998
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 125-132
- https://doi.org/10.1145/277830.277857
Abstract
In this paper we investigate a unique problem associatedwith fusing loops within a High Performance Fortran (HPF)program. In particular, we discuss the issue of performingloop fusion in an HPF compiler when compiling Fortran90array assignment statements for execution on a distributedmemorymachine. During compilation of an HPF program,Fortran90 array assignment statements must be scalarizedinto loop nests. We show how a certain class of these loopnests, when fused, can cause problems for ...Keywords
This publication has 16 references indexed in Scilit:
- Using integer sets for data-parallel program analysis and optimizationPublished by Association for Computing Machinery (ACM) ,1998
- The implementation and evaluation of fusion and contraction in array languagesPublished by Association for Computing Machinery (ACM) ,1998
- A Case Study of Some Issues in the Optimization of Fortran 90 Array NotationScientific Programming, 1995
- Compiler transformations for high-performance computingACM Computing Surveys, 1994
- Optimization techniques for SIMD Fortran compilersConcurrency: Practice and Experience, 1993
- Compiling data parallel programs to message passing programs for massively parallel MIMD systemsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1993
- Section 1: OverviewScientific Programming, 1993
- Vector register allocationIEEE Transactions on Computers, 1992
- Compiling communication-efficient programs for massively parallel machinesIEEE Transactions on Parallel and Distributed Systems, 1991
- A hierarchical basis for reordering transformationsPublished by Association for Computing Machinery (ACM) ,1984