Search For:

Displaying 1-5 out of 5 total
Delegation-Based I/O Mechanism for High Performance Computing Systems
Found in: IEEE Transactions on Parallel and Distributed Systems
By Arifa Nisar,Wei-Keng Liao,Alok Choudhary
Issue Date:February 2012
pp. 271-279
Massively parallel applications often require periodic data checkpointing for program restart and post-run data analysis. Although high performance computing systems provide massive parallelism and computing power to fulfill the crucial requirements of the...
 
Scaling parallel I/O performance through I/O delegate and caching system
Found in: SC Conference
By Arifa Nisar, Wei-keng Liao, Alok Choudhary
Issue Date:November 2008
pp. 1-12
Increasingly complex scientific applications require massive parallelism to achieve the goals of fidelity and high computational performance. Such applications periodically offload checkpointing data to file system for post-processing and program resumptio...
 
Using MPI file caching to improve parallel write performance for large-scale scientific applications
Found in: 2007 SC - International conference for High Performance Computing, Networking, Storage and Analysis
By Wei-keng Liao,Avery Ching,Kenin Coloma,Arifa Nisar,Alok Choudhary,Jacqueline Chen,Ramanan Sankaran,Scott Klasky
Issue Date:November 2007
pp. 1-11
Typical large-scale scientific applications periodically write checkpoint files to save the computational state throughout execution. Existing parallel file systems improve such write-only I/O patterns through the use of client-side file caching and write-...
 
pNFS, POSIX, and MPI-IO: a tale of three semantics
Found in: Proceedings of the 4th Annual Workshop on Petascale Data Storage (PDSW '09)
By Arifa Nisar, Dean Hildebrand, Roger Haskin
Issue Date:November 2009
pp. 32-36
MPI-IO is emerging as the standard mechanism for file I/O within HPC applications. While pNFS demonstrates high-performance I/O for bulk data transfers, its performance and scalability with MPI-IO is unproven. To attain success, the consistency semantics a...
     
Using MPI file caching to improve parallel write performance for large-scale scientific applications
Found in: Proceedings of the 2007 ACM/IEEE conference on Supercomputing (SC '07)
By Alok Choudhary, Arifa Nisar, Avery Ching, Jacqueline Chen, Kenin Coloma, Ramanan Sankaran, Scott Klasky, Wei-keng Liao
Issue Date:November 2007
pp. 24-31
Typical large-scale scientific applications periodically write checkpoint files to save the computational state throughout execution. Existing parallel file systems improve such write-only I/O patterns through the use of client-side file caching and write-...
     
 1