Varying Diameter and Problem Size in Mesh-Connected Computers

On a mesh-connected computer, moving data across the mesh is the most time-consuming operation in many algorithms. This time can be reduced by using a mesh with smaller diameter, i.e., with fewer processing elements. To accomodate inputs of the same size, this requires that the processors have more memory. For image processing and graph theoretic algorithms we analyze the time as a function of the mesh diameter and problem size. We show that for many problems, smaller diameters can yield faster algorithms, and that there is a choice of diameter that is simultaneously best for several of these problems. Further, for these problems and this number of processing elements (or any smaller number), the mesh is an optimal interconnection scheme.

[1]  Kai Hwang,et al.  Integrated Computer Architectures for Image Processing and Database Management , 1983, Computer.

[2]  Francis Y. L. Chin,et al.  Efficient parallel algorithms for some graph problems , 1982, CACM.

[3]  Azriel Rosenfeld,et al.  Parallel Image Processing by Memory-Augmented Cellular Automata , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Herbert Freeman,et al.  Determining the minimum-area encasing rectangle for an arbitrary closed curve , 1975, CACM.

[5]  Quentin F. Stout,et al.  Meshes with multiple buses , 1986, 27th Annual Symposium on Foundations of Computer Science (sfcs 1986).

[6]  Stefano Levialdi,et al.  Computer Architectures for Pictorial Information Systems , 1981, Computer.

[7]  H. T. Kung,et al.  Sorting on a mesh-connected parallel computer , 1976, STOC '76.

[8]  Lynn Conway,et al.  Introduction to VLSI systems , 1978 .

[9]  Sartaj Sahni,et al.  Bitonic Sort on a Mesh-Connected Parallel Computer , 1979, IEEE Transactions on Computers.

[10]  Sartaj Sahni,et al.  Finding Connected Components and Connected Ones on a Mesh-Connected Parallel Computer , 1980, SIAM J. Comput..

[11]  Quentin F. Stout,et al.  Mesh-Connected Computers with Broadcasting , 1983, IEEE Transactions on Computers.

[12]  Russ Miller,et al.  Geometric Algorithms for Digitized Pictures on a Mesh-Connected Computer , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Kai Hwang,et al.  Computer architecture and parallel processing , 1984, McGraw-Hill Series in computer organization and architecture.

[14]  Mikhail J. Atallah,et al.  Graph Problems on a Mesh-Connected Processor Array , 1984, JACM.

[15]  Viktor K. Prasanna,et al.  Array Processor with Multiple Broadcasting , 1985, ISCA.

[16]  S StoneHarold,et al.  A Parallel Algorithm for the Efficient Solution of a General Class of Recurrence Equations , 1973 .

[17]  Alok Aggarwal.  Optimal Bounds for Finding Maximum on Array of Processors with k Global Buses , 1986, IEEE Transactions on Computers.

[18]  Richard M. Brown,et al.  The ILLIAC IV Computer , 1968, IEEE Transactions on Computers.

[19]  W. R. Moore,et al.  Parallel processor array architecture and its implementation in silicon , 1982 .

[20]  Azriel Rosenfeld,et al.  Digital Straight Lines and Convexity of Digital Regions , 1982, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Anthony P. Reeves,et al.  Parallel computer architectures for image processing , 1984, Comput. Vis. Graph. Image Process..

[22]  Azriel Rosenfeld,et al.  Parallel Image Processing Using Cellular Arrays , 1983, Computer.

[23]  Quentin F. Stout.  Tree-Based Graph Algorithms for Some Parallel Computers , 1985, ICPP.

[24]  Joseph JáJá,et al.  Fast, Efficient Parallel Algorithms for Some Graph Problems , 1981, SIAM J. Comput..