A parallel software infrastructure for structured adaptive mesh methods
Supercomputing '95 Proceedings of the 1995 ACM/IEEE conference on Supercomputing
Extending high performance Fortran for the support of unstructured computations
ICS '95 Proceedings of the 9th international conference on Supercomputing
Software infrastructure for non-uniform scientific computations on parallel processors
ACM SIGAPP Applied Computing Review
Analysis of the Numerical Effects of Parallelism on a Parallel Genetic Algorithm
IPPS '96 Proceedings of the 10th International Parallel Processing Symposium
LCR '98 Selected Papers from the 4th International Workshop on Languages, Compilers, and Run-Time Systems for Scalable Computers
Irregular Coarse-Grain Data Parallelism under LPARX
Scientific Programming
Hi-index | 0.00 |
The stated goal of High Performance Fortran (HPF) was to ``address the problems of writing data parallel programs where the distribution of data affects performance''''. After examining the current version of the language we are led to the conclusion that HPF has not fully achieved this goal. While the basic distribution functions offered by the language - regular block, cyclic, and block cyclic distributions - can support regular numerical algorithms, advanced applications such as particle-in-cell codes or unstructured mesh solvers cannot be expressed adequately. We believe that this is a major weakness of HPF, significantly reducing its chances of becoming accepted in the numerical community. The paper discusses the data distribution and alignment issues in detail, points out some flaws in the basic language, and outlines possible future paths of development. Furthermore, we briefly deal with the issue of task parallelism and its integration with the data parallel paradigm of HPF.