Paper Info
Title
Low entropy data mapping for sparse iterative linear solvers
Abstract
An efficient parallel data structure implementation is presented to modify the permutation on the residual vector to achieve optimized memory layout of partitioned meshes for solving sparse linear systems. This novel algorithm is proposed to sort the data on each processor with respect to a set of rules. This simplifies implementation of parallel iterative solver algorithms and allows an overlap between non-blocking MPI communication and computations in matrix-vector product operations.
Year
DOI
Venue
2013
10.1145/2484762.2484797
XSEDE
Keywords
Field
DocType
sparse linear system,low entropy data,optimized memory layout,residual vector,non-blocking mpi communication,sparse iterative linear solvers,parallel iterative solver algorithm,simplifies implementation,efficient parallel data structure,partitioned mesh,novel algorithm,matrix-vector product operation,message passing interface,finite element methods
Residual,Data structure,Linear system,Computer science,Data mapping,Parallel computing,Permutation,sort,Message Passing Interface,Solver
Conference
Citations 
PageRank 
References 
0
0.34
0
Authors
3
Name
Order
Citations
PageRank
Mahdi Esmaily-Moghadam100.34
Yuri Bazilevs2476.09
Alison Marsden3528.83