EMPLOYING K-ARY n-CUBES FOR PARALLEL LAGRANGE INTERPOLATION

摘要: This paper proposes a parallel algorithm for computing anN( = Kn) point Lagrange interpolation on fc-ary n-cube networks. The consists of three phases: initialisation, main and final. There is no computation in the initialisation phase. phase composed N/2 steps, each consisting four multiplications subtractions, an additional step including one division multiplication. Communication based all-to-all broadcast Hamiltonian ring embedded k-ary n-cube. final carried out n x ⌊k/l⌋ requiring addition. A performance evaluation proposed reveals near to optimum speedup typical range sy:;tem parameters used current state-of-the-art implementations. Our study also that when implementation cost taken into account low-dimensional K-ary n-cubes achieve better than their higher-dimensional counterparts.