Paper Info
Title
Performance and Implementation of Distributed Data CPHF and SCF Algorithms
Abstract
This paper describes a novel distributed data parallel Self Consistent Field (SCF) algorithm and the distributed data Coupled Perturbed Hartree-Fock (CPHF) step of an analytic Hessian algorithm. The distinguishing features of these algorithms are: (a) columns of density and Fock matrices are distributed among processors, (b) pair-wise dynamic load balancing and an efficient static load balancer were developed to achieve a good workload, (c) network communication time is minimized via careful analysis of data flow in the SCF and CPHF algorithms. By using a shared memory model, novel work load balancers, and improved analytic Hessian steps, we have developed codes that achieve superb performance. The performance of the CPHF code is demonstrated on a large biological system.
Year
DOI
Venue
2002
10.1109/CLUSTR.2002.1137738
CLUSTER
Keywords
Field
DocType
cphf code,cphf algorithm,efficient static load balancer,scf algorithms,superb performance,pair-wise dynamic load balancing,analytic hessian algorithm,improved analytic hessian step,fock matrix,novel work load balancer,data flow,data cphf,chemicals,chemistry,biological systems,games,clustering algorithms,data models,quantum chemistry,concurrent computing,performance,distributed algorithms,resource allocation,hartree fock,wave functions,load balance,distributed computing,algorithm design and analysis,shared memory
Data modeling,Algorithm design,Data analysis,Computer science,Load balancing (computing),Parallel computing,Algorithm,Hessian matrix,Distributed algorithm,Concurrent computing,Cluster analysis,Distributed computing
Conference
ISBN
Citations 
PageRank 
0-7695-1745-5
0
0.34
References 
Authors
5
5
Name
Order
Citations
PageRank
Yuri Alexeev1152.30
Michael W. Schmidt28111.56
Theresa L. Windus322930.66
Mark S. Gordon428325.73
Ricky A. Kendall56712.26