计算机工程与设计
計算機工程與設計
계산궤공정여설계
COMPUTER ENGINEERING AND DESIGN
2009年
14期
3448-3450,3454
,共4页
核姆霍兹方程%GCR(k)算法%并行计算%同步开销%非对称稀疏线性方程组
覈姆霍玆方程%GCR(k)算法%併行計算%同步開銷%非對稱稀疏線性方程組
핵모곽자방정%GCR(k)산법%병행계산%동보개소%비대칭희소선성방정조
Helmholtz equation%GCR (k) algorithm%parallel computation%synchronization overhead%non-symmetric sparse linearsystems
针对多尺度预报模式离散得到的非对称稀疏线性方程组的求解,通过利用GCR(k)算法的固有性质,消除GCR(k)算法的内积计算数据相关性,给出了一种改进的GCR(R)(IGCR(k))算法.同GCR(k)算法对比,IGCR(k)算法与GCR(k)算法有相同的收敛性,在基于MPI的分布式存储并行机群上进行并行计算时,同步开销次数减少为GCR(k)算法的一半.数值计算结果与理论分析表明改进的GCR(k)算法的性能要优于GCR(k)算法.
針對多呎度預報模式離散得到的非對稱稀疏線性方程組的求解,通過利用GCR(k)算法的固有性質,消除GCR(k)算法的內積計算數據相關性,給齣瞭一種改進的GCR(R)(IGCR(k))算法.同GCR(k)算法對比,IGCR(k)算法與GCR(k)算法有相同的收斂性,在基于MPI的分佈式存儲併行機群上進行併行計算時,同步開銷次數減少為GCR(k)算法的一半.數值計算結果與理論分析錶明改進的GCR(k)算法的性能要優于GCR(k)算法.
침대다척도예보모식리산득도적비대칭희소선성방정조적구해,통과이용GCR(k)산법적고유성질,소제GCR(k)산법적내적계산수거상관성,급출료일충개진적GCR(R)(IGCR(k))산법.동GCR(k)산법대비,IGCR(k)산법여GCR(k)산법유상동적수렴성,재기우MPI적분포식존저병행궤군상진행병행계산시,동보개소차수감소위GCR(k)산법적일반.수치계산결과여이론분석표명개진적GCR(k)산법적성능요우우GCR(k)산법.
Employing an intrinsic propcrty of the GCR (k) algodthm and eliminating data interdependence for inner product computation in the GCR (k) algorithm, an improved parallel GCR (k) algorithm called IGCR (k) algorithm is established for solving large non-symmetric sparse linear systems derived from multi-scale prediction model. The convergence of IGCR (k) algorithm is as same as GCR (k) algorithm, but the times of the synchronization overhead arc reduced by a factor of two when we compute using the IGCR (k) algorithm on distributed memory cluster systems based on MPI environment. The numerical result and theoretical analysis prove that the performance of the IGCR (k) algorithm is better than that of the GCR (k) algorithm.
