HPF+(ID:7065/)


High Performance Fortran extended


Related languages
HPF => HPF+   Evolution of

References:
  • Mehrotra, Piyush; Van Rosendale, John; Zima, Hans "High Performance Fortran: History, Status and Future" Technical Report TR 97-8, Institute for Software Technology and Parallel Systems, University of Vienna, September 1997. view details Extract: HPF+
    The Vienna Fortran Compilation System (VFCS) extends the Superb compiler to HPF and HPF+, targeting a wide range of distributed-memory machines. Several other projects have also contributed to the understanding necessary for the development of HPF and the compiling technology required for such a language including commercial efforts such as [?, ?, ?]. Extract: Conclusion
    Conclusion
    HPF is a well-designed language which can handle most data parallel scientific applications with reasonable facility. However, as architectures evolve and scientific programming becomes more sophisticated, the limi-  tations of the language are becoming increasingly apparent. There are at least three points of view one could  take:
    1. HPF is too high-level a language --- MPI-style languages are more appropriate.
    2. HPF is too low-level a language --- aggressive compiler technologies and improving architectures obviate the need for HPF-style compiler directives.
    3. The level of HPF is about right, but extensions are required to handle some applications for some upcoming architectures.

    All three of these alternatives are being actively pursued by language researchers. For example, HPC++ [?] is an effort to design an HPF-style language using C++ as a base. On the other hand, F - - [?] is an attempt  to provide a lower-level data-parallel language than HPF. Like HPF, F - - provides a single thread of flow  control. But unlike HPF, F - - requires all communication to be explicit using "get'' and "put'' primitives.

    While it is difficult to predict where languages will head, the coming generation of SMP-cluster ar- chitectures may induce new families of languages which will take advantage of the hardware support for  shared-memory semantics with an SMP, while covering the limited global communication capability of the  architectures. In this effort the experience gained in the development and implementation of HPF will surely  serve us well.