Contiguous and Non - Contiguous Processorallocation Algorithms for K - Ary N - Cubes

EEcient utilization of processing resources in a large, multiuser parallel computer depends on processor allocation algorithms that minimize system fragmentation. We propose three processor allocation algorithms for the k-ary n-cube class of parallel architectures, which includes the hypercube and multidi-mensional torus. The k-ary Partner strategy is a conventional contiguous processor allocation strategy that improves subcube recognition. The non-contiguous Multiple Buddy and Multiple Partner strategies lift the restriction of contiguity in order to address the problem of fragmentation associated with contiguous strategies. Simulations compare the performance of these three strategies with the performance of other k-ary n-cube allocation strategies, showing that non-contiguous allocation provides signiicantly increased system utilization by eliminating fragmentation.