Computation of large scale constrained matrix problems: the splitting equilibration algorithm

The authors introduce a general parallelizable computational method called the splitting equilibration algorithm for solving the entire class of constrained matrix problems. The empirical performance of the algorithm is investigated on the largest quadratic constrained matrix problems reported to date using the IBM 3090-600E at the Cornell National Supercomputer Facility in a serial and in a parallel environment. The goals are to compare the relative efficiency of the splitting equilibration algorithm to both the earlier equilibration algorithm and the much-cited Bachem and Korte algorithm, (1978) and to investigate the speedups obtained with parallelization of the splitting equilibration algorithm