The practice of i/o optimizations for out-of-core computation

Authors:
Jianqi Tang;Binxing Fang;Mingzeng Hu;Hongli Zhang
Affiliations:
Department of Computer Science and Engineering, Harbin Institute of Technology, Harbin, China;Department of Computer Science and Engineering, Harbin Institute of Technology, Harbin, China;Department of Computer Science and Engineering, Harbin Institute of Technology, Harbin, China;Department of Computer Science and Engineering, Harbin Institute of Technology, Harbin, China
Venue:
PDCAT'04 Proceedings of the 5th international conference on Parallel and Distributed Computing: applications and Technologies
Year:
2004

Citing 5
Cited 0

Software prefetching

ASPLOS IV Proceedings of the fourth international conference on Architectural support for programming languages and operating systems
High-performance I/O for massively parallel computers: problems and prospects

Computer
Compilation techniques for out-of-core parallel computations

Parallel Computing - Special issues on languages and compilers for parallel computers
Compiler-based I/O prefetching for out-of-core applications

ACM Transactions on Computer Systems (TOCS)
Parallel I/O

Sourcebook of parallel computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Out-of-core computation needs high I/O performance as the out-of-core data stored in files has to be moved between memory and disks during the execution of an application program. In order to obtain better performance of out-of-core programs, two I/O optimizations are practiced, which are data prefetching and data reuse. This paper focuses on discussing the mechanism and implementation of each method and under which condition a method should be used. Several sets of experiments are taken to test the strategies and the results show that the I/O performance is efficiently improved by using these optimization methods.