A wide range of matrix functions, including matrix exponentials, inversions and square roots can be transformed to matrix polynomials through Taylor series expansions. The efficient computation of such matrix polynomials is considered here, through the exploitation of their recursive nature. The Reconfigurable Systolic Torus is proposed for its ability to implement interative equations of various forms. Moreover, a detailed example of the matrix exponential realization is presented. together with the scaling and squaring method. The general design conepts of the Reconfigurable Systolic Torus are discussed and the algorithmic steps need for the implementation are presented. The Area and Time requirements, together with the accomplished utilization percentage conclude the presentation.
展开▼