Communication and computation patterns of large scale image convolutions on parallel architectures
S.G. Dykes, Xiaodong Zhang, Yan Zhou, Haixu Yang · 2002
Segmentation and other image processing operations rely on convolution calculations with heavy computational and memory access demands. The article presents an analysis of a texture segmentation application containing a 96/spl times/96 convolution. Sequential execution required several hours an single processor systems with over 99% of the time spent performing the large convolution. 70% to 75% of execution time is attributable to cache misses within the convolution. We implemented the same application on CM-5, iPSC/860 and PVM distributed memory multicomputers, tailoring the parallel algorithms to each machine's architecture. Parallelization significantly reduced execution time, taking 49 seconds on a 512 node CM-5 and 6.5 minutes on a 32 node iPSC/860. 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.>