Packing/Unpacking Information Generation for Efficient Generalized kr→r and r→kr Array Redistribution

Array redistribution is usually required to enhance algorithm performance in many parallel programs on distributed memory multicomputers. Since it is performed at run-time, there is a performance tradeoff between the efficiency of new data decomposition for a subsequent phase of an algorithm and the cost of redistributing data among processors. In this paper, we present efficient methods to generate the packing/unpacking information for BOLCK-CYCLIC(kr) to BLOCK-CYCLIC(r) and BOLCK-CYCLIC(r) to BLOCK-CYCLIC(kr) redistribution with arbitrary source/destination processor sets. The most significant improvement of this paper is that a processor does not need to construct the send/receive data sets for a redistribution. Based on the packing/unpacking information derived from kr→r and r→kr redistributions, a processor can pack/unpack array elements into (from) messages directly. To evaluate the performance of our methods, we have implemented our methods along with the PITFALLS method and the Prylli’s method on an IBM SP2 parallel machine. The experimental results show that our algorithms outperform the PITFALLS method and the Prylli’s method for all test samples.