AIMES Final Technical Report
Abstract
This is the final technical report for the AIMES project. Many important advances in science and engineering are due to large scale distributed computing. Notwithstanding this reliance, we are still learning how to design and deploy large-scale production Distributed Computing Infrastructures (DCI). This is evidenced by missing design principles for DCI, and an absence of generally acceptable and usable distributed computing abstractions. The AIMES project was conceived against this backdrop, following on the heels of a comprehensive survey of scientific distributed applications. AIMES laid the foundations to address the tripartite challenge of dynamic resource management, integrating information, and portable and interoperable distributed applications. Four abstractions were defined and implemented: skeleton, resource bundle, pilot, and execution strategy. The four abstractions were implemented into software modules and then aggregated into the AIMES middleware. This middleware successfully integrates information across the application layer (skeletons) and resource layer (Bundles), derives a suitable execution strategy for the given skeleton and enacts its execution by means of pilots on one or more resources, depending on the application requirements, and resource availabilities and capabilities.
- Authors:
-
- Univ. of Minnesota, Minneapolis, MN (United States)
- Univ. of Illinois, Urbana-Champaign, IL (United States). National Center for Supercomputing Applications (NCSA)
- Rutgers Univ., New Brunswick, NJ (United States)
- Publication Date:
- Research Org.:
- Univ. of Minnesota, Minneapolis, MN (United States)
- Sponsoring Org.:
- USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
- OSTI Identifier:
- 1341754
- DOE Contract Number:
- SC0008651
- Resource Type:
- Technical Report
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; distributed computing; scientific applications
Citation Formats
Weissman, Jon, Katz, Dan, Jha, Shantenu, and Turilli, Matteo. AIMES Final Technical Report. United States: N. p., 2017.
Web.
Weissman, Jon, Katz, Dan, Jha, Shantenu, & Turilli, Matteo. AIMES Final Technical Report. United States.
Weissman, Jon, Katz, Dan, Jha, Shantenu, and Turilli, Matteo. 2017.
"AIMES Final Technical Report". United States.
@article{osti_1341754,
title = {AIMES Final Technical Report},
author = {Weissman, Jon and Katz, Dan and Jha, Shantenu and Turilli, Matteo},
abstractNote = {This is the final technical report for the AIMES project. Many important advances in science and engineering are due to large scale distributed computing. Notwithstanding this reliance, we are still learning how to design and deploy large-scale production Distributed Computing Infrastructures (DCI). This is evidenced by missing design principles for DCI, and an absence of generally acceptable and usable distributed computing abstractions. The AIMES project was conceived against this backdrop, following on the heels of a comprehensive survey of scientific distributed applications. AIMES laid the foundations to address the tripartite challenge of dynamic resource management, integrating information, and portable and interoperable distributed applications. Four abstractions were defined and implemented: skeleton, resource bundle, pilot, and execution strategy. The four abstractions were implemented into software modules and then aggregated into the AIMES middleware. This middleware successfully integrates information across the application layer (skeletons) and resource layer (Bundles), derives a suitable execution strategy for the given skeleton and enacts its execution by means of pilots on one or more resources, depending on the application requirements, and resource availabilities and capabilities.},
doi = {},
url = {https://www.osti.gov/biblio/1341754},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Jan 31 00:00:00 EST 2017},
month = {Tue Jan 31 00:00:00 EST 2017}
}