A selection theory and methodology for heterogeneous supercomputing
Document Type
Conference Proceeding
Publication Date
1-1-1993
Abstract
In this paper, a methodology for mapping algorithms onto heterogeneous suite of supercomputers is presented. An approach for selecting an optimal suite of computers for solving problems with diverse computational requirements, called Heterogeneous Optimal Selection Theory (HOST), is presented. HOST is an extension to Augmented Optimal Selection Theory in two ways: It incorporates heterogeneous parallelism embedded in the tasks, and it reflects the costs associated in using various fine grain mapping strategies at individual machine level. The proposed mapping methodology is based on the Cluster-M programming paradigm. For the mapping purpose, the input format, assumed in HOST, is modeled in terms vf Hierarchical Cluster-M specification and representation. For a given problem, a Hierarchical Cluster-M specification is generated to indicate the execution of concurrent tasks at different stages of the computation. This specification is then mapped onto the Hierarchical Cluster-M representation of the underlying heterogeneous suite of supercomputers.
Identifier
84990683901 (Scopus)
ISBN
[0818635312, 9780818635311]
Publication Title
Proceedings Workshop on Heterogeneous Processing Vvhp 1993 Held in Conjunction with the 7th International Parallel Processing Symposium
External Full Text Location
https://doi.org/10.1109/WHP.1993.664360
First Page
15
Last Page
22
Recommended Citation
Chen, Song; Eshaghian, Mary M.; Khokhar, Ashfaq; and Shaaban, Muhammad E., "A selection theory and methodology for heterogeneous supercomputing" (1993). Faculty Publications. 17200.
https://digitalcommons.njit.edu/fac_pubs/17200
