IEEE Transactions on Parallel and Distributed Systems
A linear-time algorithm for computing the memory access sequence in data-parallel programs
PPOPP '95 Proceedings of the fifth ACM SIGPLAN symposium on Principles and practice of parallel programming
Visualization and sonification of methods
PAS '95 Proceedings of the First Aizu International Symposium on Parallel Algorithms/Architecture Synthesis
Hi-index | 0.00 |
The recently released high performance Fortran forum (HPFF)proposal has stirred much interest in the high performancecomputing industry. HPFF's most important design goal is to createa language that has source code portability and that achieves highperformance on single instruction multiple data (SIMD),distributed-memory multiple instruction multiple data (MIMD), andshared-memory MIMD architectures. The HPFF proposal brings to theforefront many questions about design of portable and efficientlanguages for parallel machines. In this article, we discuss issuesthat need to be addressed before an efficient production qualitycompiler will be available for any such language. We examine somespecific issues that are related to HPF's model of computation andanalyze several implementation issues. We also provide some resultsfrom another data parallel compiler to help gain insight on some ofthe implementation issues that are relevant to HPF. Finally, weprovide a summary of options currently available for applicationdevelopers in industry.