DocumentCode
2806458
Title
Metacomputing with MILAN
Author
Baratloo, A. ; Dasgupta, P. ; Karamcheti, V. ; Kedem, Z.M.
Author_Institution
Courant Inst. of Math. Sci., New York Univ., NY, USA
fYear
1999
fDate
1999
Firstpage
169
Lastpage
183
Abstract
The MILAN project, a joint effort involving Arizona State University and New York University, has produced and validated fundamental techniques for the realization of efficient reliable, predictable virtual machines, that is, metacomputers, on top of environments that consist of an unreliable and dynamically changing set of machines. In addition to the techniques, the principal outcomes of the project include three parallel programming systems-Calypso, Chime, and Charlotte-which enable applications to be developed for ideal, shared memory, parallel machines to execute on distributed platforms that are subject to failures, slowdowns, and changing resource availability. The lessons learned from the MILAN project are being used to design Computing Communities, a metacomputing framework for general computations
Keywords
client-server systems; fault tolerant computing; parallel machines; parallel programming; shared memory systems; virtual machines; Arizona State University; Calypso; Charlotte; Chime; Computing Communities; MILAN project; New York University; distributed platforms; metacomputing; parallel programming systems; resource availability; shared memory parallel machines; slowdowns; system failure; virtual machines; Application software; Availability; Concurrent computing; Ear; Electrical capacitance tomography; Metacomputing; Middleware; Read only memory; Telecommunication network reliability; Virtual machining;
fLanguage
English
Publisher
ieee
Conference_Titel
Heterogeneous Computing Workshop, 1999. (HCW '99) Proceedings. Eighth
Conference_Location
San Juan
ISSN
1097-5209
Print_ISBN
0-7695-0107-9
Type
conf
DOI
10.1109/HCW.1999.765128
Filename
765128
Link To Document