Paper Info
Title
Evaluating I/O characteristics and methods for storing structured scientific data
Abstract
Many large-scale scientific simulations generate large, structured multi-dimensional datasets. Data is stored at various intervals on high performance I/O storage systems for checkpointing, post-processing, and visualization. Data storage is very I/O intensive and can dominate the overall running time of an application, depending on the characteristics of the I/O access pattern. Our NCIO benchmark determines how I/O characteristics greatly affect performance (up to 2 orders of magnitude) and provides scientific application developers with guidelines for improvement. In this paper, we examine the impact of various I/O parameters and methods when using the MPI-IO interface to store structured scientific data in an optimized parallel file system.
Year
DOI
Venue
2006
10.1109/IPDPS.2006.1639306
IPDPS
Keywords
Field
DocType
o access pattern,large-scale scientific simulation,o parameter,o characteristic,high performance,scientific data,scientific application developer,data storage,structured multi-dimensional datasets,o storage system,adaptive mesh refinement,concurrent computing,testing,storage system,parallel processing,data visualization,computational modeling
Data visualization,File system,Computer science,Visualization,Computer data storage,Parallel processing,Parallel computing,Adaptive mesh refinement,Input/output,Concurrent computing,Database,Distributed computing
Conference
ISBN
Citations 
PageRank 
1-4244-0054-6
29
1.21
References 
Authors
11
5
Name
Order
Citations
PageRank
Avery Ching122116.21
Alok Choudhary220511.94
Wei-keng Liao3109587.98
Lee Ward41859.81
Neil Pundit55114.13