Results 1  10
of
10
Messages Scheduling for Parallel Data Redistribution between Clusters
 IEEE Transactions on Parallel and Distributed Systems
, 2006
"... ..."
(Show Context)
Data Redistribution Algorithms For Heterogeneous Processor Rings
, 2004
"... We consider the problem of redistributing data on homogeneous and heterogeneous ring of processors. The problem arises in several applications, each time after that a loadbalancing mechanism is invoked (but we do not discuss the loadbalancing mechanism itself). We provide algorithms that aim at op ..."
Abstract

Cited by 7 (5 self)
 Add to MetaCart
(Show Context)
We consider the problem of redistributing data on homogeneous and heterogeneous ring of processors. The problem arises in several applications, each time after that a loadbalancing mechanism is invoked (but we do not discuss the loadbalancing mechanism itself). We provide algorithms that aim at optimizing the data redistribution, both for unidirectional and bidirectional rings, and we give complete proofs of correctness. 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 bidirectional heterogeneous ring, for which the problem remains open.
On the Complexity of the MaxEdgeColoring Problem with Its Variant
"... The maxedgecoloring problem (MECP) is finding an edge colorings {E1, E2, E3, …, Ez} of a weighted graph G=(V, E) to minimize z ∑ i = 1 max { w( e) e ∈ E} ..."
Abstract

Cited by 1 (0 self)
 Add to MetaCart
The maxedgecoloring problem (MECP) is finding an edge colorings {E1, E2, E3, …, Ez} of a weighted graph G=(V, E) to minimize z ∑ i = 1 max { w( e) e ∈ E}
Efficient Multidimensional Data Redistribution for Resizable Parallel Computations
, 2007
"... Traditional parallel schedulers running on cluster supercomputers support only static scheduling, where the number of processors allocated to an application remains fixed throughout the execution of the job. This results in underutilization of idle system resources thereby decreasing overall system ..."
Abstract

Cited by 1 (1 self)
 Add to MetaCart
(Show Context)
Traditional parallel schedulers running on cluster supercomputers support only static scheduling, where the number of processors allocated to an application remains fixed throughout the execution of the job. This results in underutilization of idle system resources thereby decreasing overall system throughput. In our research, we have developed a prototype framework called ReSHAPE, which supports dynamic resizing of parallel MPI applications executing on distributed memory platforms. The resizing library in ReSHAPE includes support for releasing and acquiring processors and efficiently redistributing application state to a new set of processors. In this paper, we derive an algorithm for redistributing twodimensional blockcyclic arrays from P to Q processors, organized as 2D processor grids. The algorithm ensures a contentionfree communication schedule for data redistribution if Pr ≤ Qr and Pc ≤ Qc. In other cases, the algorithm implements circular row and column shifts on the communication schedule to minimize node contention.
ARRAY REDISTRIBUTION ALGORITHMS FOR BIDIRECTIONAL PROCESSOR RINGS
"... The Block Cyclic Array Redistribution problem occurs in many important applications in parallel computing. In this paper, we consider this problem on bidirectional processor rings. We present a message combining (MC) approach that splits any array redistribution problem in a series of broadcasts whe ..."
Abstract
 Add to MetaCart
The Block Cyclic Array Redistribution problem occurs in many important applications in parallel computing. In this paper, we consider this problem on bidirectional processor rings. We present a message combining (MC) approach that splits any array redistribution problem in a series of broadcasts where all sources send messages of the same size, thus a balanced traffic load is achieved. Unlike existing array redistribution algorithms, the message combining scheme introduced in this work eliminates the need for data reorganization in the memory of the source and target processors. Moreover, the processing of the scheduled broadcasts is pipelined, thus the total cost of redistribution is reduced.
www.elsevier.com/locate/jpdc Improving communication scheduling for array redistribution
, 2004
"... Many scientific applications require array redistribution when the programs run on distributed memory parallel computers. It is essential to use efficient algorithms for redistribution, otherwise the performance of the programs will degrade considerably. The redistribution overheads consist of two p ..."
Abstract
 Add to MetaCart
(Show Context)
Many scientific applications require array redistribution when the programs run on distributed memory parallel computers. It is essential to use efficient algorithms for redistribution, otherwise the performance of the programs will degrade considerably. The redistribution overheads consist of two parts: index computation and interprocessor communication. If there is no communication scheduling in a redistribution routine, the interprocessor communication will incur a larger communication idle time when there exists node contention and/or difference among message lengths during one particular communication step. In order to solve this problem, in this paper, we propose an efficient scheduling scheme that not only minimizes the number of communication steps and eliminates node contention, but also minimizes the difference of message lengths in each communication step. Thus, the communication idle time is reduced in redistribution routines.
Data redistribution algorithms for heterogeneous processor rings
, 2004
"... We consider the problem of redistributing data on homogeneous and heterogeneous ring of processors. The problem arises in several applications, each time after that a loadbalancing mechanism is invoked (but we do not discuss the loadbalancing mechanism itself). We provide algorithms that aim at op ..."
Abstract
 Add to MetaCart
(Show Context)
We consider the problem of redistributing data on homogeneous and heterogeneous ring of processors. The problem arises in several applications, each time after that a loadbalancing mechanism is invoked (but we do not discuss the loadbalancing mechanism itself). We provide algorithms that aim at optimizing the data redistribution, both for unidirectional and bidirectional rings, and we give complete proofs of correctness. 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 bidirectional heterogeneous ring, for which the problem remains open.
31DATA REDISTRIBUTION ON RINGS DATA REDISTRIBUTION ALGORITHMS FOR HETEROGENEOUS PROCESSOR RINGS
"... We consider the problem of redistributing data on homogeneous and heterogeneous rings of processors. The problem arises in several applications, after each invocation of a loadbalancing mechanism (but we do not discuss the loadbalancing mechanism itself). We provide algorithms that aim at optim ..."
Abstract
 Add to MetaCart
We consider the problem of redistributing data on homogeneous and heterogeneous rings of processors. The problem arises in several applications, after each invocation of a loadbalancing mechanism (but we do not discuss the loadbalancing mechanism itself). We provide algorithms that aim at optimizing the data redistribution, both for unidirectional and bidirectional 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 bidirectional heterogeneous ring, for which the problem remains open. Key words: heterogeneous rings, data redistribution algorithms, load balancing 1