Features of Method of Special-Purpose Calculating Unit Functioning for Linear System Solution Based on the Second Order Delta-Transformation

Theoretical representations of special-purpose calculating unit functioning for the iteration solution of linear systems using deltatransformations and variable quantum is considered, that allows to achieve high performance and hardware resources. The algorithm for parallel solution of linear systems based on the second order delta-transformations and variable quantum is developed and adapted for implementation in a special-purpose calculating unit. It is presented the architecture and peculiarities of this unit functioning, which makes the possibility of linear systems solution with variable free terms at each time step of the steady-state process within one iteration. With the orientation to FPGA, comparative estimates are obtained for the hardware resources and the speed of the developed algorithm for special-purpose calculating unit functioning. In this paper for the developed algorithm of the unit functioning, it is shown that it is possible to reduce the execution of one iteration and the iterative process as a whole and the amount of hardware resources in comparison with the special-purpose calculating unit functioning based on the simple iteration method.