Title
Dynamic structured partitioning for parallel scientific applications with pointwise varying workloads
Abstract
Parallel implementations of scientific applications involving the simulation of reactive flow on structured grids are challenging, since the underlying phenomena include transport processes with uniform computational loads as well as reactive processes having pointwise varying workloads. As a result, traditional parallelization approaches that assume homogeneous loads are not suitable for these simulations. This paper presents "Dispatch", a dynamic structured partitioning strategy that has been applied to parallel uniform and adaptive formulations of simulations with computational heterogeneity. Dispatch maintains the computational weights associated with pointwise processes in a distributed manner, computes the local workloads and partitioning thresholds, and performs in-situ localitypreserving load balancing. The experimental evaluation of Dispatch using an illustrative 2-D reactive-diffusion kernel demonstrates improvement in load distribution and overall application performance.
Year
DOI
Venue
2006
10.1109/IPDPS.2006.1639294
IPDPS
Keywords
Field
DocType
computational heterogeneity,parallel implementation,uniform computational,partitioning threshold,load distribution,computational weight,dynamic structured partitioning strategy,local workloads,in-situ localitypreserving load balancing,homogeneous load,pointwise varying workloads,parallel scientific application,parallel processing,computational modeling,resource allocation,distributed computing,grid computing,application software,load balance,concurrent computing
Kernel (linear algebra),Load management,Grid computing,Computer science,Load balancing (computing),Parallel computing,Resource allocation,Concurrent computing,Application software,Distributed computing,Pointwise
Conference
ISBN
Citations 
PageRank 
1-4244-0054-6
3
0.59
References 
Authors
1
3
Name
Order
Citations
PageRank
Sumir Chandra1374.98
Manish Parashar23876343.30
Jaideep Ray319824.42