TR-94-01-04.ps.Z

S. G. Dykes, X. Zhang, Y. Zhou, H. Yang, 
``Computation and communication patterns of large-scale 
image convolutions on parallel architectures". 

The was presented and published in Proceedings of the 8th 
International Parallel Processing 
Symposium (IPPS'94), IEEE CS Press, April, 1994, pp. 926-931. 

Abstract 
-------- 

Segmentation and other image processing operations rely on convolution 
calculations with heavy computational and memory access demands. 
This paper presents an analysis of a texture segmentation application 
containing 96x96 convolution. We implemented the application on 
CM-5, iPSC/860 and PVM workstations, tailoring the parallel algorithms 
to each machine's architecture. The results indicate for large kernel 
convolutions the size and bandwidth of the fast memory store is more 
important than processor power or communication overhead.