• Documents
  • Authors
  • Tables
  • Log in
  • Sign up
  • MetaCart
  • DMCA
  • Donate

CiteSeerX logo

Advanced Search Include Citations
Advanced Search Include Citations | Disambiguate

Data redistribution algorithms for heterogeneous processor rings (0)

by H Renard, Y Robert, F Vivien
Add To MetaCart

Tools

Sorted by:
Results 1 - 7 of 7

Scheduling and Data Redistribution Strategies on Star Platforms

by Loris Marchal, Veronika Rehn, Yves Robert, Frédéric Vivien
"... In this work we are interested in the problem of scheduling and redistributing data on master-slave platforms. We consider the case were the workers possess initial loads, some of which having to be redistributed in order to balance their completion times. We assume that the data consists of indepen ..."
Abstract - Cited by 4 (3 self) - Add to MetaCart
In this work we are interested in the problem of scheduling and redistributing data on master-slave platforms. We consider the case were the workers possess initial loads, some of which having to be redistributed in order to balance their completion times. We assume that the data consists of independent and identical tasks. As the general case is NP-complete in the strong sense, we propose three heuristics. Simulations consolidate the theoretical results. 1.
(Show Context)

Citation Context

...ll studied in the literature. Unfortunately already simple redistribution problems are NP complete [8]. For this reason, optimal algorithms can be designed only for particular cases, as it is done in =-=[13]-=-. In their research, the authors restrict the platform architecture to ring topologies, both uni-directional and bidirectional. In the homogeneous case, they were able to prove optimality, but the het...

Data Redistribution Algorithms for Homogeneous and Heterogeneous Processor Rings

by Helene Renard, Yves Robert, Frederic Vivien - in "International Conference on High Performance Computing HiPC’2004", LNCS , 2004
"... We consider the problem of redistributing data on homogeneous and heterogeneous processor rings. The problem arises in several applications, each time after a load-balancing mechanism is invoked (but we do not discuss the load-balancing mechanism itself). We provide algorithms that aim at optimi ..."
Abstract - Cited by 3 (2 self) - Add to MetaCart
We consider the problem of redistributing data on homogeneous and heterogeneous processor rings. The problem arises in several applications, each time after a load-balancing mechanism is invoked (but we do not discuss the load-balancing mechanism itself). We provide algorithms that aim at optimizing the data redistribution, both for unidirectional and bi-directional rings. One major contribution of the paper is that we are able to prove the optimality of the proposed algorithms in all cases except that of a bi-directional heterogeneous ring, for which the problem remains open.
(Show Context)

Citation Context

... the first time that optimal algorithms are introduced. Due to the lack of space, the detailed proofs of correctness and optimality of the algorithms are not provided: please see the extended version =-=[6]-=-. Similarly, please refer to [6] for a survey of related work. 2 Framework We consider a set of n processors P1,P2,...,Pn arranged along a ring. The successor of Pi in the ring is Pi+1, and its predec...

encadré par Yves Robert,

by École Normale, Supérieure Lyon, Veronika Rehn, Frédéric Vivien, Loris Marchal, École Normale, Supérieure Lyon, Veronika Rehn, Encadré Par Yves Robert, Frédéric Vivien, Loris Marchal , 2006
"... Rapport de M2 N o DEA2006-05 Scheduling and data redistribution strategies on star platforms ..."
Abstract - Add to MetaCart
Rapport de M2 N o DEA2006-05 Scheduling and data redistribution strategies on star platforms
(Show Context)

Citation Context

...d Vivien present some 1 Last In First Out 2 First In First OutsScheduling and data redistribution strategies on star platforms 3 optimal redistribution algorithms for heterogeneous processor rings in =-=[20]-=-. We could use this approach and redistribute the data first and then enter in a computation phase. But our problem is more complicated as we suppose that communication and computation can overlap, i....

4.4.

by unknown authors , 2005
"... c t i v it y ..."
Abstract - Add to MetaCart
c t i v it y

Scheduling and data redistribution strategies on star platforms

by École Normale, Supérieure Lyon, Loris Marchal, Veronika Rehn, Yves Robert, Frédéric Vivien, École Normale, Supérieure Lyon, Loris Marchal, Veronika Rehn, Yves Robert, Frédéric Vivien , 2006
"... Scheduling and data redistribution strategies on star platforms ..."
Abstract - Add to MetaCart
Scheduling and data redistribution strategies on star platforms
(Show Context)

Citation Context

...d Vivien present some 1 Last In First Out 2 First In First OutsScheduling and data redistribution strategies on star platforms 3 optimal redistribution algorithms for heterogeneous processor rings in =-=[20]-=-. We could use this approach and redistribute the data first and then enter in a computation phase. But our problem is more complicated as we suppose that communication and computation can overlap, i....

The`me NUM

by Loris Marchal, Veronika Rehn, Yves Robert, Loris Marchal, Veronika Rehn, Yves Robert, Projet Graal
"... Scheduling and data redistribution strategies on star platforms ..."
Abstract - Add to MetaCart
Scheduling and data redistribution strategies on star platforms
(Show Context)

Citation Context

...en present some 1 Last In First Out 2 First In First Out INRIAsScheduling and data redistribution strategies on star platforms 5 optimal redistribution algorithms for heterogeneous processor rings in =-=[20]-=-. We could use this approach and redistribute the data first and then enter in a computation phase. But our problem is more complicated as we suppose that communication and computation can overlap, i....

3.1. Scheduling Strategies and Algorithm Design for Heterogeneous Platforms 3

by unknown authors
"... d' ctivity eport 2006 Table of contents ..."
Abstract - Add to MetaCart
d' ctivity eport 2006 Table of contents
Powered by: Apache Solr
  • About CiteSeerX
  • Submit and Index Documents
  • Privacy Policy
  • Help
  • Data
  • Source
  • Contact Us

Developed at and hosted by The College of Information Sciences and Technology

© 2007-2019 The Pennsylvania State University