Computer Science – Distributed – Parallel – and Cluster Computing
Scientific paper
2002-07-29
Computer Science
Distributed, Parallel, and Cluster Computing
10 pages, 17 figures
Scientific paper
With the tremendous advances in processor and memory technology, I/O has risen to become the bottleneck in high-performance computing for many applications. The development of parallel file systems has helped to ease the performance gap, but I/O still remains an area needing significant performance improvement. Research has found that noncontiguous I/O access patterns in scientific applications combined with current file system methods to perform these accesses lead to unacceptable performance for large data sets. To enhance performance of noncontiguous I/O we have created list I/O, a native version of noncontiguous I/O. We have used the Parallel Virtual File System (PVFS) to implement our ideas. Our research and experimentation shows that list I/O outperforms current noncontiguous I/O access methods in most I/O situations and can substantially enhance the performance of real-world scientific applications.
Ching Avery
Choudhary Alok
Gropp William
Liao Wei-keng
Ross Rob
No associations
LandOfFree
Noncontiguous I/O through PVFS does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Noncontiguous I/O through PVFS, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Noncontiguous I/O through PVFS will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-251174