This paper presents an algorithm for computing a linear recurrence system R(n, m) of order m for n equations on MIMD parallel system. This algorithm is not only easy to be programmed on a parallel computer system, but...This paper presents an algorithm for computing a linear recurrence system R(n, m) of order m for n equations on MIMD parallel system. This algorithm is not only easy to be programmed on a parallel computer system, but also reduces the data-waiting time due to compute-ahead strategy. The paper analyses how to achieve maximal load balancing when the algorithm is implemented on MIMD parallel system. By the end of the paper, an analysis on the speedup and parallel efficiency are given. The results indicate that the new parallel elimination algorithm has great improvement compared with the old ones.展开更多
In this paper we discuss the convergence of the directed graph-algorithm for solving a kind of optimization problems where the objective and subjective functions are all separable, and the parallel implementation proc...In this paper we discuss the convergence of the directed graph-algorithm for solving a kind of optimization problems where the objective and subjective functions are all separable, and the parallel implementation process for the directed graph -algorithm is introduced.展开更多
本文讨论了摹矩阵连乘积M_1M_2…M_q的并行计算问题,其中M_是n_(-1)×n_矩阵,证明了如果n_=min{N_0,…,n_q},则从右至左计算M_1…M_,从左至右计算M_(+1)…M_q,再将二者摹乘的计算方案是最优的。最优方案的并行计算量为 n_(sum from ...本文讨论了摹矩阵连乘积M_1M_2…M_q的并行计算问题,其中M_是n_(-1)×n_矩阵,证明了如果n_=min{N_0,…,n_q},则从右至左计算M_1…M_,从左至右计算M_(+1)…M_q,再将二者摹乘的计算方案是最优的。最优方案的并行计算量为 n_(sum from =1 to q-1 n_-n_+min(n_0,n_1}展开更多
文摘This paper presents an algorithm for computing a linear recurrence system R(n, m) of order m for n equations on MIMD parallel system. This algorithm is not only easy to be programmed on a parallel computer system, but also reduces the data-waiting time due to compute-ahead strategy. The paper analyses how to achieve maximal load balancing when the algorithm is implemented on MIMD parallel system. By the end of the paper, an analysis on the speedup and parallel efficiency are given. The results indicate that the new parallel elimination algorithm has great improvement compared with the old ones.
文摘In this paper we discuss the convergence of the directed graph-algorithm for solving a kind of optimization problems where the objective and subjective functions are all separable, and the parallel implementation process for the directed graph -algorithm is introduced.
文摘本文讨论了摹矩阵连乘积M_1M_2…M_q的并行计算问题,其中M_是n_(-1)×n_矩阵,证明了如果n_=min{N_0,…,n_q},则从右至左计算M_1…M_,从左至右计算M_(+1)…M_q,再将二者摹乘的计算方案是最优的。最优方案的并行计算量为 n_(sum from =1 to q-1 n_-n_+min(n_0,n_1}
