Knowledge-Based Parallelization for Distributed Memory Systems

In current automatic parallelization systems for distributed-memory machines, the user must explicitly specify how the data domain of the sequential program is to be decomposed and distributed across the processors. In this paper, we outline the salient features of a new knowledge-based software tool that provides automatic support for data partitioning. The basic guidelines for the design of the tool are discussed, followed by a description of the adopted partitioning strategy.

[1]  J. Ramanujam,et al.  Compile-Time Techniques for Data Distribution in Distributed Memory Machines , 1991, IEEE Trans. Parallel Distributed Syst..

[2]  Pradip Bose,et al.  Heuristic Rule-Based Program Transformations for Enhanced Vectorization , 1988, International Conference on Parallel Processing.

[3]  Michael Gerndt,et al.  Optimizing Communication in Superb , 1990, CONPAR.

[4]  Michael Gerndt,et al.  Array distribution in SUPERB , 1989, ICS '89.

[5]  Pradip Bose,et al.  Interactive program improvement via EAVE: an expert adviser for vectorization , 1988, ICS '88.

[6]  Guy L. Steele,et al.  Data Optimization: Allocation of Arrays to Reduce Communication on SIMD Machines , 1990, J. Parallel Distributed Comput..

[7]  Jim Q. Ning,et al.  Knowledge-based program analysis , 1990, IEEE Software.

[8]  Fung F. Lee.  Partitioning of Regular Computation on Multiprocessor Systems , 1990, J. Parallel Distributed Comput..

[9]  Ken Kennedy,et al.  Interactive parallelization of numerical scientific programs , 1989 .

[10]  G. C. Fox,et al.  Solving Problems on Concurrent Processors , 1988 .

[11]  Santosh G. Abraham,et al.  Compiler techniques for data partitioning of sequentially iterated parallel loops , 1990, ICS '90.

[12]  Michael Gerndt,et al.  SUPERB: A tool for semi-automatic MIMD/SIMD parallelization , 1988, Parallel Comput..

[13]  Prithviraj Banerjee,et al.  Automatic Data Partitioning on Distributed Memory Multiprocessors , 1991, The Sixth Distributed Memory Computing Conference, 1991. Proceedings.

[14]  Ko-Yang Wang,et al.  A Framework for Intelligent Parallel Compilers , 1990 .

[15]  Anne Rogers,et al.  Process decomposition through locality of reference , 1989, PLDI '89.