Abstract
If a looping construct has the property that no iteration of the loop requires for its execution a result from a previous iteration, correct results can be obtained by executing all of the loop iterations simultaneously on different processors.
At Myrias Research Corporation, a virtual machine has been designed, and is being implemented, on which such parallel execution of loop constructs is achieved by replacing the looping instruction (“do” in ANSI Fortran 77) with a modified instruction (“par do” in Myrias Parallel Fortran — MPF). Each loop iteration executes in its own, separate memory space, and these memory spaces are automatically merged when all of the tasks have completed. The architecture of the Myrias parallel computer is described briefly.
We describe a new memory model which utilizes local, distributed memory, and allows for the dynamic reconfiguration of parallel tasks at the operating system level. Such a model gives rise to a powerful new parallel programming method. Further, we describe how recursive parallel methods (RPM) can be used effectively. The three main language extensions are orthogonal, and their combination provides easy access to flexible, high order, adaptive algorithms. Algorithmic examples of the application of this programming model are demonstrated.
This paper has been left virtually unchanged from its original version written in 1985. Since then, Myrias Research Corporation has developed a working prototype encompassing many of the features discussed herein, and is presently completing an advanced, commercially available, parallel system.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
D. Heller, A Survey of Parallel Algorithms in Numerical Linear Algebra, SIAM Review 20, (1978), 740–777.
Myrias 4000 System Description (unpublished), Myrias Research Corp., Edmonton, Alberta, Feb. 1986.
J. R. Savage, Parallel Processing as a Language Design Problem, Proc. 12th Annual Int. Symp. on Computer Architecture, Boston, MA, 1985, 221–224.
C. Y. Tang, Optimal Speeding-up of Parallel Algorithms Based Upon the Divide-and-Conquer Strategy, Information Sciences 82, (1984), 173–186.
J. Ortega and R. Voigt, Solution of Partial Differential Equations on Vector and Parallel Computers, SIAM Review 21, (1985), 149–240.
D. Gannon and J. Van Rosendale, Parallel Architectures for Iterative Methods on Adaptive, Block Structured Grids, in Elliptic Problem Solvers II, 1984, 93–104.
P. O. Frederickson, R. E. Jones and B. T. Smith, Synchronization and control of parallel algorithms, Parallel Computing 2, (1985), 255–264, North-Holland.
J. M. Varah, On the Solution of Block-Tridiagonal Systems Arising from Certain Finite-Difference Equations, Mathematics of Computation 26, 120 (1972), 859–868.
W. Gentzsch, Numerical algorithms in computational fluid dynamics on vector computers, Parallel Computing 1, (1984), 19–33, North-Holland.
D. Heller, Some Aspects of the Cyclic Reduction Algorithm for Block Tridiagonal Linear Systems, SIAM J. Numer. Anal 13, 4 (1976), 484–496.
R. N. Kapur and J. C. Browne, Techniques for Solving Block Tridiagonal Systems on Reconfigurable Array Computers, SIAM Journal of Scientific Statistical Computing 5, (1984), 701–719.
F. R. Bailey, Computational Limits on Scientific Applications, IEEE Proceedings of Compcon Spring, 1978.
V. L. Peterson, W. F. Ballhaus and F. R. Bailey, Numerical Aerodynamical Simulation (NAS), NASA Technical Memorandum 84386, Moffet Field, CA, July 1983.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1990 Plenum Press, New York
About this chapter
Cite this chapter
Kobos, A.M., VanKooten, R.E., Walker, M.A. (1990). A Powerful New Programming Model for Parallel Computation. In: Rosenblum, A. (eds) Relativity, Supersymmetry, and Strings. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-9504-5_10
Download citation
DOI: https://doi.org/10.1007/978-1-4615-9504-5_10
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4615-9506-9
Online ISBN: 978-1-4615-9504-5
eBook Packages: Springer Book Archive