A processor allocation strategy using cube coalescing in hypercube multicomputers

We propose a new processor allocation strategy for hypercube multicomputers. The allocation strategy is called cube coalescing (CC) strategy since it uses a cube coalescing method to find an available subcube which is formed by the non-neighbored nodes. The main advantage of this strategy is that the nodes which do not contribute to form a requested subcube can be filtered out by coalescing, and thus the exhaustive search for possible subcubes can be avoided even in the worst case. It is theoretically shown that that proposed CC strategy is not only statistically optimal but also it has a complete subcube recognition capability. Extensive simulation is carried out to compare this strategy with the other strategies in terms of performance measures of interest such as processor utilization, completion time, and allocation/deallocation time. It is shown that the CC strategy gives better performance and the least allocation/deallocation time compared to the other schemes in a dynamic environment