Double standards: bringing task parallelism to HPF via the message passing interface
- Argonne National Lab., IL (United States)
- Syracuse Univ., NY (United States). School of Computer and Information Science
- Syracuse Univ., NY (United States)
High Performance Fortran (HPF) does not allow efficient expression of mixed task/data-parallel computations or the coupling of separately compiled data-parallel modules. In this paper, we show how a coordination library implementing the Message Passing Interface (MPI) can be used to represent these common parallel program structures. This library allows data-parallel tasks to exchange distributed data structures using calls to simple communication functions. We present microbenchmark results that characterize the performance of this library and that quantify the impact of optimizations that allow reuse of communication schedules in common situations. In addition, results from two-dimensional FFT, convolution, and multiblock programs demonstrate that the HPF/MPI library can provide performance superior to that of pure HPF. WE conclude that this synergistic combination of two parallel programming standards represents a useful approach to task parallelism in a data-parallel framework, increasing the range of problems addressable in HPF without requiring complex compiler technology.
- Research Organization:
- Argonne National Lab. (ANL), Argonne, IL (United States)
- Sponsoring Organization:
- USDOE Office of Energy Research, Washington, DC (United States)
- DOE Contract Number:
- W-31109-ENG-38
- OSTI ID:
- 469060
- Report Number(s):
- ANL/MCS-P-593-0596; CONF-961104-7; ON: DE97003896
- Resource Relation:
- Conference: Supercomputing `96, Pittsburgh, PA (United States), 18-22 Nov 1996; Other Information: PBD: [1996]
- Country of Publication:
- United States
- Language:
- English
Similar Records
Global Arrays Parallel Programming Toolkit
Optimizing Bandwidth Limited Problems Using One-SidedCommunication and Overlap