Parallel I/O

HPF is primarily designed to obtain high performance on massively parallel computers. Such massively parallel machines also need massively parallel input and output. Accordingly, there were three major proposals to include explicitly parallel I/O features in HPF, as well as several minor variations on the same theme. After much debate, HPFF voted not to include I/O extensions in the first version of HPF. (NOTE, however, that HPF1.1 defines changes to Fortran 90 data type of a few of the I/O keyword inquiry specifiers to allow for the possibility of very large files. See section on Fortran 90 Binding earlier in this chapter.)

The arguments for not making further extensions or changes for parallel I/O in HPF included:

• The diversity of current parallel I/O systems does not suggest any portable abstraction of I/O useful in a language model.

• Fortran I/O is already highly expressive.

• The HPF compiler can optimize the I/O when writing distributed arrays without any extensions to the source language.

• The management of distributed files (and their implementation) is a matter for the operating system, not the language.

Moreover the current lack of extensions does not limit features that may be added by system vendors. In particular:

• Vendors are allowed to implement any I/O extensions to the language they may wish. Indeed this would be impossible to prevent. There are simply no special I/O mechanisms mandated by HPF.

• The HPF run-time system may use whatever facilities the operating system provides for accessing ``high performance'' files, though the HPF language contains no I/O extensions that specifically describe such access.