Solving Partial Differential Equations in a data-driven multiprocessor environment
Partial differential equations can be found in a host of engineering and scientific problems. The emergence of new parallel architectures has spurred research in the definition of parallel PDE solvers. Concurrently, highly programmable systems such as data-how architectures have been proposed for the exploitation of large scale parallelism. The implementation of some Partial Differential Equation solvers (such as the Jacobi method) on a tagged token data-flow graph is demonstrated here. Asynchronous methods (chaotic relaxation) are studied and new scheduling approaches (the Token No-Labeling scheme) are introduced in order to support the implementation of the asychronous methods in a data-driven environment. New high-level data-flow language program constructs are introduced in order to handle chaotic operations. Finally, the performance of the program graphs is demonstrated by a deterministic simulation of a message passing data-flow multiprocessor. An analysis of the overhead in the data-flow graphs is undertaken to demonstrate the limits of parallel operations in dataflow PDE program graphs.
- Research Organization:
- University of Southern California, Los Angeles, CA (United States). Computer Research Inst.
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- FG03-87ER25043
- OSTI ID:
- 10190202
- Report Number(s):
- CONF-880540-4; ON: DE94000317
- Resource Relation:
- Conference: 15. annual international symposium on computer architecture,No City Given, HI (United States),30 May - 2 Jun 1988; Other Information: PBD: [1988]
- Country of Publication:
- United States
- Language:
- English
Similar Records
A parallel multigrid method for data-driven multiprocessor systems
Chaotic linear system solvers in a variable-grain data-driven multiprocessor system