Paper Info
Title
A distributed data implementation of parallel full CI program
Abstract
A distributed data parallel full CI program is described The implementation of the FCI algorithm is organized in a combined Cl driven approach With extra computation we were able to avoid redundant communication, and convert the collective communication into more efficient point-to-point communication. The network performance is further optimized by improved DDI library. Examples show very good speedup performance on 16 node PC clusters. The application of the code is also demonstrated.
Year
DOI
Venue
2002
10.1109/CLUSTR.2002.1137786
CLUSTER
Keywords
Field
DocType
collective communication,ddi library,full ci program,configuration interactions,efficientpoint-to-point communication,parallel programming,network performance,hamiltonian matrix,schrodinger equation,redundant communication,fci algorithm,improved ddi library,parallel full ci program,good speedup performance,eigenvalue problem,eigenvalues and eigenfunctions,extra computation,data implementation,combined ci,full configuration interaction,distributed data parallel program,point to point,computer science,clustering algorithms,chemistry,distributed computing,concurrent computing,sparse matrices
Computer science,Parallel computing,Collective communication,Concurrent computing,Cluster analysis,Sparse matrix,Distributed computing,Speedup,Network performance,Computation
Conference
ISBN
Citations 
PageRank 
0-7695-2066-9
0
0.34
References 
Authors
2
4
Name
Order
Citations
PageRank
zhengting gana120.88
Yuri Alexeev2152.30
Ricky A. Kendall36712.26
Mark S. Gordon428325.73