Power and Performance in I/O for Scientific Applications

Authors:
K. Coloma;A. Choudhary;A. Ching;W. K. Liao;S. W. Son;M. Kandemir;L. Ward
Affiliations:
Northwestern University;Northwestern University;Northwestern University;Northwestern University;Pennsylvania State University;Pennsylvania State University;Sandia National Laboratories
Venue:
IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 10 - Volume 11
Year:
2005

Citing 4
Cited 0

Maximizing Multiprocessor Performance with the SUIF Compiler

Computer
Adaptive Disk Spin-down Policies for Mobile Computers

MLICS '95 Proceedings of the 2nd Symposium on Mobile and Location-Independent Computing
DRPM: dynamic speed control for power management in server class disks

Proceedings of the 30th annual international symposium on Computer architecture
Thwarting the power-hungry disk

WTEC'94 Proceedings of the USENIX Winter 1994 Technical Conference on USENIX Winter 1994 Technical Conference

Quantified Score

Hi-index	0.00

Visualization

Abstract

The I/O patterns of large scale scientific applications can often be characterized as small, non-contiguous, and regular. From a performance and power perspective, this is perhaps the worse kind of I/O for a disk. Two approaches to mitigating the mechanical limitations of disks are write-back caches and software-directed power management. Previous distributed caches are plagued by synchronization and scalability issues. The Direct Access Cache: DAChe system is a user-level distributed cached that addresses both these problems. Past work on managing disk power during run time were effective, one should be able to improve on those results by adopting a proactive scheme.