Results 1 
8 of
8
Techniques for Mapping Tasks to Machines in Heterogeneous Computing Systems
 2004 INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING (ICPP 2004
, 2004
"... Heterogeneous computing (HC) is the coordinated use of different types of machines, networks, and interfaces to maximize their combined performance and/or costeffectiveness. HC systems are becoming a plausible technique for eciently solving computationally intensive problems. The applicability and ..."
Abstract

Cited by 33 (2 self)
 Add to MetaCart
Heterogeneous computing (HC) is the coordinated use of different types of machines, networks, and interfaces to maximize their combined performance and/or costeffectiveness. HC systems are becoming a plausible technique for eciently solving computationally intensive problems. The applicability and strength of HC systems are derived from their ability to match computing needs to appropriate resources. In an HC system, tasks need to be matched to machines, and the execution of the tasks must be scheduled. The goal of this invited keynote paper is to: (1) introduce the reader to some of the different distributed and parallel types of HC environments
Wrekavoc: a Tool for Emulating Heterogeneity
"... Computer science and especially heterogeneous distributed computing is an experimental science. Simulation, emulation, or insitu implementation are complementary methodologies to conduct experiments in this context. In this paper we address the problem of defining and controlling the heterogeneity ..."
Abstract

Cited by 12 (4 self)
 Add to MetaCart
(Show Context)
Computer science and especially heterogeneous distributed computing is an experimental science. Simulation, emulation, or insitu implementation are complementary methodologies to conduct experiments in this context. In this paper we address the problem of defining and controlling the heterogeneity of a platform. We evaluate the proposed solution, called Wrekavoc, with microbenchmark and by implementing algorithms of the literature. 1.
Algorithmes et protocoles pour la gestion des données et des calculs dans les environnements distribués et hétérogènes
, 2007
"... ..."
1 Data Partitioning with a Realistic Performance Model of Networks of Heterogeneous Computers
"... AbstractIn this paper, we address the problem of optimal distribution of computational tasks on a network of heterogeneous computers when one or more tasks do not fit into the main memory of the processors and when relative speeds cannot be accurately approximated by constant functions of problem ..."
Abstract
 Add to MetaCart
(Show Context)
AbstractIn this paper, we address the problem of optimal distribution of computational tasks on a network of heterogeneous computers when one or more tasks do not fit into the main memory of the processors and when relative speeds cannot be accurately approximated by constant functions of problem size. We design efficient algorithms to solve the scheduling problem using a realistic performance model of network of heterogeneous computers. This model integrates many essential features of a network of heterogeneous computers having a major impact on its performance such as the processor heterogeneity, the heterogeneity of memory structure, and the effects of paging. Under this model, the speed of each processor is represented by a continuous and relatively smooth function of the size of the problem whereas standard models use single numbers to represent the speeds of the processors. We formulate a problem of partitioning of an nelement set over p heterogeneous processors using this model and design efficient algorithms for its solution whose worstcase complexity is O(p 2 ×log 2 n) but the bestcase complexity is O(p×log 2 n). Index TermsHeterogeneous systems, Scheduling and task partitioning, Load balancing and task assignment
Appears in the Proceedings of the 11 ¢ ¡ InternationalConference on Parallel and DistributedComputingSystems (PDCS 1998)1 BlockCyclic Redistribution over Heterogeneous Networks
"... Clusters of workstations and networked parallel computing systems are emerging as promising computational platforms for HPC applications. The processors in such systems are typically interconnected by a collection of heterogeneous networks such as Ethernet, ATM, and FDDI, among others. In this paper ..."
Abstract
 Add to MetaCart
(Show Context)
Clusters of workstations and networked parallel computing systems are emerging as promising computational platforms for HPC applications. The processors in such systems are typically interconnected by a collection of heterogeneous networks such as Ethernet, ATM, and FDDI, among others. In this paper, we develop techniques to perform blockcyclic redistributionover ¨ processors interconnected by such a collection of heterogeneous networks. We represent the communication scheduling problem using a timing diagram formalism. Here, each interprocessor communication event is represented by a rectangle whose height denotes the time to perform this event over the heterogeneous network. The communication scheduling problem is then one of appropriately positioning the rectangles so as to minimize the completion time of all the communication events. For the important case where the block size changes by a factor of © , we develop a heuristic algorithm whose completion time is atmost twice the optimal. The running time of the heuristic is ���¢¨�©��� �. Our heuristic algorithm is adaptive to variations in network performance, and derives schedules at runtime, based on current information about available network bandwidth. Our experimental results show that our schedules always have communication times that are very close to optimal.