基于OpenMP的对称矩阵LDL^T分解并行算法实现  

Parallel Algorithm Based on OpenMP of LDL^T Decomposition for Symmetric Matrix

作　　者：张锦雄[1] 韦化[1] 

机构地区：[1]广西大学电气工程学院,广西南宁530004

出　　处：《广西科学院学报》2008年第3期248-250,共3页Journal of Guangxi Academy of Sciences

摘　　要：分析对称矩阵LDLT分解过程的并行结构,给出对称矩阵LDLT分解的并行算法,然后考虑粗粒度组合后的负载平衡,提出基于OpenMP的对称矩阵LDLT分解并行算法的实现方案,并对该方案的并行计算性能进行数值实验.实验表明,基于OpenMP的对称矩阵LDLT分解并行算法在多核处理器系统中能够显著地提高算法性能.By analyzing the parallelism of LDL^T Decomposition for Symmetric Matrix,a parallel algorithm of LDL^T Decomposition for Symmetric Matrix is proposed and an OpenMP-based implementation with load-balancing for rough granularity is obtain. Then the parallel algorithm performance is tested. The numerical experiments show that the performance of algorithm is obviously improved in multi-core processor system.

关 键 词：并行计算 对称矩阵 LDL^T分解 OPENMP 

分 类 号：TP312[自动化与计算机技术—计算机软件与理论]