The effect of average parallelism and CPU-I/O overlap on application speedup

Author

Diaconescu, Luca ; Majumdar, Shikharesh

Author_Institution

Dept. of Syst. & Comput. Eng., Carleton Univ., Ottawa, Ont., Canada

fYear

2000

fDate

36800

Firstpage

370

Lastpage

377

Abstract

Parallelization of I/O using multiple disk drives is warranted for achieving high performance on systems running CPU and I/O intensive applications. This paper is concerned with the characterization of applications with parallel I/O and the derivation of analytic bounds on speedup. New characteristics for capturing parallelism in I/O are introduced. These characteristics are used in conjunction with other characteristics available in the literature for the derivation of the bounds. Both parallelism in CPU and I/O operations in applications as well as the degree of overlap between CPU and I/O are observed to have a strong impact on speedup

Keywords

disc drives; input-output programs; parallel processing; performance evaluation; CPU-input output overlap; application speedup; high performance; multiple disk drives; parallel input-output; Application software; Computer applications; Computer networks; Concurrent computing; Disk drives; Distributed computing; High performance computing; Parallel processing; System performance; Systems engineering and theory;

fLanguage

English

Publisher

ieee

Conference_Titel

Parallel and Distributed Systems: Workshops, Seventh International Conference on, 2000

Conference_Location

Iwate

Print_ISBN

0-7695-0571-6

Type

conf

DOI

10.1109/PADSW.2000.884646

Filename

884646