Matrix Operations on a Multicomputer System with Switchable Main Memory Modules and Dynamic Control

This paper presents an analysis and evaluation of the performance of a multicomputer system (SM3) in supporting two basic matrix operations, namely multiplication and inversion. The system supports the efficient execution of the above mentioned operations by 1) achieving a high-bandwidth data transfer among computers by switching main memory modules, 2) supporting network partitioning, 3) employing a hardware communication and synchronization scheme, 4) using a distributed control technique, and 5) providing means to dynamically transfer control. Timing equations are derived and evaluated in an attempt to analyze the performance. Different cases which arise due to the relative sizes of memory modules and matrices during matrix multiplication are analyzed. The cases of partial and maximal pivoting during inversion are also analyzed. The SM3 system is compared quantitatively and qualitatively to a hypercube architecture.

[1]  Chaitanya K. Baru,et al.  Dynamically partitionable multicomputers with switchable memory , 1984, J. Parallel Distributed Comput..

[2]  Chaitanya K. Baru,et al.  The Architecture of SM3: A Dynamically Partitionable Multicomputer System , 1986, IEEE Transactions on Computers.

[3]  Ahmed Sameh,et al.  The Illiac IV system , 1972 .

[4]  C. Norrie.  Supercomputers for Superproblems: An Architectural Introduction , 1984, Computer.

[5]  John L. Larson.  Multitasking on the Cray X-MP-2 Multiprocessor , 1984, Computer.

[6]  C. K. Baru,et al.  Matrix multiplication on a multicomputer system with switchable main memory modules , 1985 .

[7]  Zhiwei Xu,et al.  Remps: A Reconfigurable Multiprocessor for Scientific Supercomputing , 1985, ICPP.

[8]  Dharma P. Agrawal,et al.  B - HIVE: a heterogeneous, interconnected, versatile and expandable multicomputer system , 1984, CARN.

[9]  Tilak Agerwala,et al.  Communication Issues in the Design and Analysis of Parallel Algorithms , 1981, IEEE Transactions on Software Engineering.

[10]  Richard M. Russell,et al.  The CRAY-1 computer system , 1978, CACM.

[11]  Kai Hwang,et al.  Multiprocessor Supercomputers for Scientific/Engineering Applications , 1985, Computer.

[12]  Chaitanya K. Baru,et al.  SM3: A dynamically partitionable multicomputer system with switchable main memory modules , 1984, 1984 IEEE First International Conference on Data Engineering.

[13]  James C. Browne.  TRAC: An Environment for Parallel Computing , 1984, COMPCON.

[14]  Edward F. Gehringer,et al.  The Cm* Multiprocessor Project: A Research Review , 1980 .

[15]  Chaitanya K. Baru,et al.  Performance evaluation of the statistical aggregation by categorization in the SM3 system , 1984, SIGMOD '84.

[16]  James W. Moore,et al.  A Benchmark Comparison of Three Supercomputers: Fujitsu VP-200, Hitachi S810/120, and Cray X-MP/2 , 1985, Computer.

[17]  Charles L. Seitz,et al.  The cosmic cube , 1985, CACM.