Lilith: Scalable Execution of User Code for Distributed Computing

Authors:
D. A. Evensky;A. C. Gentile;L. J. Camp;R. C. Armstrong
Affiliations:
-;-;-;-
Venue:
HPDC '97 Proceedings of the 6th IEEE International Symposium on High Performance Distributed Computing
Year:
1997

Citing 0
Cited 5

The DOGMA approach to parallel and distributed computing

Cluster computing
The Tool Dæmon Protocol (TDP)

Proceedings of the 2003 ACM/IEEE conference on Supercomputing
MRNet: A Software-Based Multicast/Reduction Network for Scalable Tools

Proceedings of the 2003 ACM/IEEE conference on Supercomputing
Tree-based overlay networks for scalable applications

IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
Order preserving event aggregation in TBONs

EuroMPI'11 Proceedings of the 18th European MPI Users' Group conference on Recent advances in the message passing interface

Quantified Score

Hi-index	0.00

Visualization

Abstract

Lilith is a general purpose tool to provide highly scalable, easy distribution of user code across a heterogeneous computing platform. Lilith's principle task is to span a heterogeneous tree of machines executing user-defined code in a scalable and secure fashion. Lilith will be used for controlling user processes as well as general system administrative tasks. Lilith is written in Java, taking advantage of Java's platform independence and intent to move code across networks. The design of Lilith provides hooks for experimenting with tree-spanning algorithms and security schemes. We present the Lilith Object model, security scheme, and implementation, and present timing results demonstrating Lilith' scalable behavior.