12th Euromicro Conference on Parallel, Distributed and Network-Based Processing, 2004. Proceedings. 2004
DOI: 10.1109/empdp.2004.1271465
|View full text |Cite
|
Sign up to set email alerts
|

Jace: a Java environment for distributed asynchronous iterative computations

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
18
0

Year Published

2006
2006
2019
2019

Publication Types

Select...
3
3
2

Relationship

0
8

Authors

Journals

citations
Cited by 22 publications
(18 citation statements)
references
References 8 publications
0
18
0
Order By: Relevance
“…Bertsekas and Tsitsiklis [7] have raised an issue of the accurate evaluation of a residual based stopping criterion. JACE [2] is a multi-threaded library aiming at the execution of asynchronous iterative algorithms based on Java Remote Method Invocation (RMI) middleware. It has been improved with a centralized volatility tolerant extension named JaceV [6].…”
Section: Asynchronous Interactionsmentioning
confidence: 99%
“…Bertsekas and Tsitsiklis [7] have raised an issue of the accurate evaluation of a residual based stopping criterion. JACE [2] is a multi-threaded library aiming at the execution of asynchronous iterative algorithms based on Java Remote Method Invocation (RMI) middleware. It has been improved with a centralized volatility tolerant extension named JaceV [6].…”
Section: Asynchronous Interactionsmentioning
confidence: 99%
“…• JACE: [5] "Java Asynchronous Computation Environment" is a multi-threaded Java based library designed to build synchronous and asynchronous iterative algorithms and execute them in a Grid environment. In JACE, two nodes exchange data (synchronously or asynchronously) using either Sockets or RMI (Remote Method Invocation) or NIO (New Input/Output) as a communication API (Application Programming Interface).…”
Section: Related Workmentioning
confidence: 99%
“…. , m, with X 0 given (2) and the iterative algorithm can be parallelized by letting each of the m processors update a different block-component of x according to (2) (see [18]). At each stage, the ith processor knows the value of all components of X k on which G i depends.…”
Section: Synchronous Parallel Iterative Algorithmsmentioning
confidence: 99%
“…Nevertheless, they are generally not designed to take into account the performance aspects. A good example is the JACE library [2] which has been especially written to implement AIAC algorithms. The goal of the authors was to provide an easy and efficient way to implement those algorithms with the portability feature.…”
Section: Tested Environmentsmentioning
confidence: 99%