@inproceedings{7503cc8490874123932681be3e048262,
title = "The MHETA execution model for heterogeneous clusters",
abstract = "The availability of inexpensive “off the shelf” machines increases the likelihood that parallel programs run on heterogeneous clusters of machines. These programs are increasingly likely to be out of core, meaning that portions of their datasets must be stored on disk during program execution. This results in significant, per-iteration, I/O cost. This paper describes an execution model, called MHETA, which is the key component to finding an effective data distribution on heterogeneous clusters. MHETA takes into account computation, communication, and I/O costs of iterative scientific applications. MHETA uses automatically extracted information from a single iteration to predict the execution time of the remaining iterations. Results show that MHETA predicts with on average 98% accuracy the execution time of several scientific benchmarks (with and without prefetching) and one full-scale scientific program that utilize pipelined and other communication. MHETA is thus an effective tool when searching for the most effective distribution on a heterogeneous cluster.",
keywords = "Data distribution, I/O, Modeling parallel execution",
author = "Mario Nakazawa and Lowenthal, {David K.} and Zhou Wendou",
note = "Funding Information: This research was funded in part by NSF grants CCF-0429643 and CCF-0234285. Publisher Copyright: {\textcopyright} 2005 IEEE.; 2005 ACM/IEEE Conference on Supercomputing, SC 2005 ; Conference date: 12-11-2005 Through 18-11-2005",
year = "2005",
doi = "10.1109/SC.2005.73",
language = "English (US)",
series = "Proceedings of the International Conference on Supercomputing",
publisher = "Association for Computing Machinery",
booktitle = "Proceedings of the ACM/IEEE SC 2005 Conference, SC 2005",
}