Software Issues for the PASM Parallel Processing System

Partitionable mixed-mode systems can be dynamically reconfigured to form independent or communicating submachines of various sizes, where each submachine can switch between the SIMD and MIMD modes of parallelism at instruction level granularity. These systems allow software developers to tailor the system size and mode of parallelism to best match the problem. This chapter explores software issues related to one such system, the PASM parallel processing system. Specific topics addressed include a programming language, overlapped CU/PE operation, trade-offs between the SIMD and MIMD modes of parallelism, and aspects of operating systems for automatic system reconfiguration. A reading-list of PASM-related publications is appended.

[1]  Alexandru Nicolau,et al.  Advances in languages and compilers for parallel processing , 1991 .

[2]  Leah H. Jamieson,et al.  Simulation of a Word Recognition System on Two Parallel Architectures , 1985, IEEE Trans. Computers.

[3]  FAYÉ A. BRIGGS,et al.  PM4—A reconfigurable multiprocessor system for pattern recognition and image processing , 1979, 1979 International Workshop on Managing Requirements Knowledge (MARK).

[4]  Harry F. Jordan,et al.  Report of the Purdue Workshop on Grand Challenges in Computer Architecture for the Support of High Performance Computing , 1992, J. Parallel Distributed Comput..

[5]  Howard Jay Siegel,et al.  A parallel approach to hybrid range image segmentation , 1992, Proceedings Sixth International Parallel Processing Symposium.

[6]  Henry G. Dietz,et al.  Loop Coalescing and Scheduling for Barrier MIMD Architectures , 1993, IEEE Trans. Parallel Distributed Syst..

[7]  Kendall Preston,et al.  Evaluation of Multicomputers for Image Processing , 1987 .

[8]  Howard Jay Siegel,et al.  Data Management and Control-Flow Aspects of an SIMD/SPMD Parallel Language/Compiler , 1993, IEEE Trans. Parallel Distributed Syst..

[9]  Andrew B. Whinston,et al.  A Model for an Intelligent Operating System for Executing Image Understanding Tasks on a Reconfigurable Parallel Architecture , 1985, J. Parallel Distributed Comput..

[10]  Howard Jay Siegel,et al.  Determining an Optimal Secondary Storage Service Rate for the PASM Control System , 1986, IEEE Transactions on Computers.

[11]  Howard Jay Siegel,et al.  Adaptable Software for Supercomputers , 1986, Computer.

[12]  Richard F. Freund,et al.  Superconcurrency: A Form of Distributed Heterogeneous Supercomputing , 1991 .

[13]  Howard Jay Siegel,et al.  A survey and comparison of fault-tolerant multistage interconnection networks , 1994 .

[14]  Howard Jay Siegel,et al.  Limitations Imposed on Mixed-Mode Performance of Optimized Phases Due to Temporal Juxtaposition , 1991, J. Parallel Distributed Comput..

[15]  Howard Jay Siegel,et al.  Design and Analysis of Dynamic Redundancy Networks , 1988, IEEE Trans. Computers.

[16]  Howard Jay Siegel,et al.  Using the multistage cube network topology in parallel supercomputers , 1989 .

[17]  Thomas L. Casavant,et al.  Efficient masking techniques for large-scale SIMD architectures , 1990, [1990 Proceedings] The Third Symposium on the Frontiers of Massively Parallel Computation.

[18]  Howard Jay Siegel,et al.  A Distributed Management Scheme for Partitionable Parallel Computers , 1990, IEEE Trans. Parallel Distributed Syst..

[19]  V. K. Prasanna Kumar,et al.  Parallel architectures and algorithms for image understanding , 1991 .

[20]  Edward J. Delp,et al.  An Analysis of Fixed-Assignment Hypercube Partitioning , 1990, ICPP.

[21]  Howard Jay Siegel,et al.  Mapping computer-vision-related tasks onto reconfigurable parallel-processing systems , 1992, Computer.

[22]  Leah H. Jamieson,et al.  Experiments with Parallel Fast Fourier Transforms , 1991 .

[23]  Howard Jay Siegel,et al.  Execution mode management and CU/PE overlap in an SIMD/SPMD parallel language/compiler , 1991, [1991] Proceedings The Fifteenth Annual International Computer Software & Applications Conference.

[24]  Howard Jay Siegel,et al.  Instruction execution trade-offs for SIMD vs. MIMD vs. mixed mode parallelism , 1991, [1991] Proceedings. The Fifth International Parallel Processing Symposium.

[25]  Thomas L. Casavant,et al.  Optimizing Task Migration Transfers Using Multistage Cube Networks , 1994, ICPP.

[26]  Dan C. Marinescu,et al.  Specification and identification of events for debugging and performance monitoring of distributed multiprocessor systems , 1990, Proceedings.,10th International Conference on Distributed Computing Systems.

[27]  Anthony A. Maciejewski,et al.  Exploiting concurrency among tasks in partitionable parallel processing systems , 1992, Proceedings Sixth International Parallel Processing Symposium.

[28]  Howard Jay Siegel,et al.  A model of task migration in partitionable parallel processing systems , 1988, Proceedings., 2nd Symposium on the Frontiers of Massively Parallel Computation.

[29]  Howard Jay Siegel,et al.  Examining the effects of CU/PE overlap and synchronization overhead when using the complete sums approach to image correlation , 1991, Proceedings of the Third IEEE Symposium on Parallel and Distributed Processing.

[30]  Thomas L. Casavant,et al.  Task Migration Transfers in Multistage Cube Based Parallel Systems , 1989, ICPP.

[31]  Howard Jay Siegel,et al.  PASM: A Partitionable SIMD/MIMD System for Image Processing and Pattern Recognition , 1981, IEEE Transactions on Computers.

[32]  Howard Jay Siegel,et al.  Modeling Overlapped Operation between the Control Unit and Processing Elements in an SIMD Machine , 1991, J. Parallel Distributed Comput..

[33]  Thomas L. Casavant,et al.  Experimental Application-Driven Architecture Analysis of an SIMD/MIMD Parallel Processing System , 1990, IEEE Trans. Parallel Distributed Syst..

[34]  Howard Jay Siegel,et al.  FFT Algorithms for SIMD Parallel Processing Systems , 1986, J. Parallel Distributed Comput..

[35]  Henry G. Dietz,et al.  Static synchronization beyond VLIW , 1989, Proceedings of the 1989 ACM/IEEE Conference on Supercomputing (Supercomputing '89).

[36]  Juan Li,et al.  A software environment for parallel computer vision , 1992, Computer.

[37]  Thomas L. Casavant,et al.  Non-Deterministic Instruction Time Experiments on the PASM System Prototype , 1988, ICPP.

[38]  Edward J. Delp,et al.  Dynamic Intelligent Scheduling and Control of Reconfigurable Parallel Architectures for Computer Vision/Image Processing , 1991, J. Parallel Distributed Comput..

[39]  Michael Philippsen,et al.  Project Triton: towards improved programmability of parallel machines , 1993, [1993] Proceedings of the Twenty-sixth Hawaii International Conference on System Sciences.

[40]  G. Jack Lipovski,et al.  Parallel computing - theory and comparisons , 1987 .

[41]  Dharma P. Agrawal,et al.  A Survey and Comparision of Fault-Tolerant Multistage Interconnection Networks , 1987, Computer.

[42]  Thomas L. Casavant,et al.  Experimental Analysis of a Mixed-Mode Parallel Architecture Using Bitonic Sequence Sorting , 1991, J. Parallel Distributed Comput..

[43]  Gérard Giraudon,et al.  Image processing on a SIMD/SPMD architecture: OPSILA , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[44]  Howard Jay Siegel,et al.  Fault Side-Effects in Fault Tolerant Multistage Interconnection Networks , 1991, ICPP.

[45]  Theoharis Theoharis,et al.  Polygon rendering on a dual-paradigm parallel processor , 1989, Comput. Graph..

[46]  Howard Jay Siegel,et al.  On the Viability of a Quantitative Model of System Reconfiguration Due to a Fault , 1992, ICPP.

[47]  Howard Jay Siegel,et al.  Eliminating Memory for Fragmentation Within Partitionable SIMD/SPMD Machines , 1991, IEEE Trans. Parallel Distributed Syst..

[48]  Janak H. Patel,et al.  Architecture and Performance Evaluation of NETRA , 1991 .

[49]  Leah H. Jamieson,et al.  Experimental Verification of the Critical Path Simulation of an SIMD/MIMD Parallel Processing System , 1991, ICPP.