Mapping strategies in message-based multiprocessor systems

Abstract Machines with distributed memory have the mapping problem—assigning processes to processors. In this paper we define the mapping problem as an optimization problem and discuss the question, how far is an optimum solution from an average or random solution. The term robustness is introduced and explained in detail with two examples, the SUPRENUM and the hypercube architecture. For the SUPRENUM architecture we show that a simple mapping strategy (optimal clustering of the processes) gives almost as good results as the optimal mapping. Optimal mapping is more important for the hypercube architecture. For nonhomogeneous networks adaptive routing seems promising.

[1]  Roger W. Hockney.  MIMD computing in the USA - 1984 , 1985, Parallel Comput..

[2]  Marco Ajmone Marsan,et al.  Comparative Performance Analysis of Single Bus Multiprocessor Architectures , 1982, IEEE Transactions on Computers.

[3]  S. P. Rana,et al.  Heuristic Algorithms for Process Assignment in Distributed Computing Systems , 1980, Inf. Process. Lett..

[4]  Jeffrey D Ullma.  Computational Aspects of VLSI , 1984 .

[5]  William J. Dally,et al.  The torus routing chip , 2005, Distributed Computing.

[6]  Heinz Mühlenbein,et al.  Parallel adaptive full-multigrid methods on message-based multiprocessors , 1986, Parallel Comput..

[7]  Joel H. Saltz,et al.  Dynamic Remapping of Parallel Computations with Varying Resource Demands , 1988, IEEE Trans. Computers.

[8]  Jeffrey D. Ullman,et al.  Some Thoughts About Supercomputer Organization , 1984, IEEE Computer Society International Conference.

[9]  Hideharu Amano,et al.  An Adaptable Cluster Structure of (SM)²-II , 1986, CONPAR.

[10]  Wesley W. Chu,et al.  Task Allocation in Distributed Data Processing , 1980, Computer.

[11]  Heinz Mühlenbein,et al.  New solutions to the mapping problem of parallel systems: The evolution approach , 1987, Parallel Comput..

[12]  Shahid H. Bokhari,et al.  On the Mapping Problem , 1981, IEEE Transactions on Computers.

[13]  John R. Rice,et al.  Partitioning PDE computations: Methods and performance evaluation , 1987, Parallel Comput..

[14]  R. Daniel Bergeron,et al.  Task Allocation Heuristics for Distributed Computing Systems , 1986, ICDCS.

[15]  Lawrence Snyder,et al.  Introduction to the configurable, highly parallel computer , 1982, Computer.

[16]  John P. Hayes,et al.  A Microprocessor-based Hypercube Supercomputer , 1986, IEEE Micro.

[17]  Heinz Mühlenbein,et al.  Design and Rationale for MUPPET: A Programming Environment for Message Based Multiprocessors , 1988, ICS.

[18]  Heinz Mühlenbein,et al.  Evolution algorithms in combinatorial optimization , 1988, Parallel Comput..