17,395 Hits in 4.4 sec

Parallel Application Scheduling on Networks of Workstations

Stergios V. Anastasiadis, Kenneth C. Sevcik
1997 Journal of Parallel and Distributed Computing  
We conclude that AEP (2) is suitable for use in scheduling parallel applications on networks of workstations.  ...  Parallel applications can be executed using the idle computing capacity of workstation clusters.  ...  However, techniques and policies for efficiently supporting workloads of parallel applications on such platforms are still needed.  ... 
doi:10.1006/jpdc.1997.1335 fatcat:o3oi7qg57zd2fftwp3vz762t6i

The Effect of the 2 nd Generation Clusters: Changes in the Parallel Programming Paradigms [chapter]

Jari Porras, Pentti Huttunen, Jouni Ikonen
2004 Lecture Notes in Computer Science  
Programming paradigms for networks of symmetric multiprocessor (SMP) workstation (2 nd generation of clusters) are discussed and a new paradigm is introduced.  ...  The new programming paradigm provides a solution to write efficient parallel applications for the 2 nd generation of clusters.  ...  This new environment is a successor of a network of workstations where each workstation consists of one processor.  ... 
doi:10.1007/978-3-540-24688-6_3 fatcat:qlp24gzi4ng3phzxdiz7bomyge

Coordinating Parallel Processes on Networks of Workstations

Xing Du, Xiaodong Zhang
1997 Journal of Parallel and Distributed Computing  
The network of workstations (NOW) we consider for scheduling is heterogeneous and nondedicated, where computing power varies among the workstations and local and parallel jobs may interact with each other  ...  Based on a power usage agreement between local and parallel jobs, this scheme coordinates parallel processes independently in each workstation based on the coscheduling principle.  ...  We appreciate Andrea Dusseau at University of California, Berkeley, and Evangelos Makatos at FORTH in Greece for reading an early version of this paper and for their constructive suggestions.  ... 
doi:10.1006/jpdc.1997.1378 fatcat:ts6zfa2os5hsllbcjdqaopwo44

Instant-Access Cycle-Stealing for Parallel Applications Requiring Interactive Response [chapter]

P. H. J. Kelly, S. Pelagatti, M. Rossiter
2002 Lecture Notes in Computer Science  
In this paper we study the use of idle cycles in a network of desktop workstations under unfavourable conditions: we aim to use idle cycles to improve the responsiveness of interactive applications through  ...  Unlike much prior work in the area, our focus is on response time, not throughput, and short jobs -of the order of a few seconds.  ...  Fig. 6 . 6 Recruitment overhead on the sample application(left) and speedup on a dedicated workstation network(right).  ... 
doi:10.1007/3-540-45706-2_122 fatcat:qsjfdp37ojh4nd3bzbja2w52ve

A dynamic load balancing system for parallel cluster computing

B.J. Overeinder, P.M.A. Sloot, R.N. Heederik, L.O. Hertzberger
1996 Future generations computer systems  
In this paper we discuss a new approach to dynamic load balancing of parallel jobs in clusters of workstations and describe the implementation into a Unix run-time environment.  ...  The e ciency of the proposed methodology is shown by means of a number of case studies.  ...  The e ective global scheduling of application programs on a cluster of workstations is essential to e ciently use the potential of the system: it should achieve an e cient mapping between an application  ... 
doi:10.1016/0167-739x(95)00038-t fatcat:oipii436jnef3dkecmt2bu4gja

Cluster Computing [chapter]

Mark Baker, John Brooke, Ken Hawick, Rajkumar Buyya
2001 Lecture Notes in Computer Science  
Typically, there are three types of "owner": • Ones who use their workstations for sending and receiving mail or preparing papers, such as administrative staff, librarian, theoreticians, etc. • Ones involved  ...  This ownership often brings problems when attempting to form a cluster of workstations.  ...  PRM enables users to run sequential or parallel jobs on a network of workstations.  ... 
doi:10.1007/3-540-44681-8_100 fatcat:cr6rpynstjgufacwbmciciriha

Load balancing MPI algorithm for high throughput applications

Igor Grudenic, Stjepan Gros, Nikola Bogunovic
2008 ITI 2008 - 30th International Conference on Information Technology Interfaces  
In this paper we present a load balancing algorithm (LBA) that can be used instead of developing custom parallel application.  ...  In order to tackle complexity of parallel programming various methods are developed.  ...  This is equivalent to 9MB/s (1MB per job) outgoing network traffic on the workstation hosting the scheduling component.  ... 
doi:10.1109/iti.2008.4588520 dblp:conf/iti/GrudenicGB08 fatcat:tmmmy54rlnfl3i7sxuoouudjh4

Breaking the curse of dynamics by task migration: Pilot experiments in the polder metacomputer [chapter]

B. J. Overeinder, P. M. A. Sloot
1997 Lecture Notes in Computer Science  
In this paper, we focus on dynamic load balancing of resources and applications as one of the crucial techniques to optimize performance in distributed environments.  ...  With the advent of high speed networks, distributed cluster computing and metacomputing have assumed an enormous interest.  ...  Acknowledgments We express our thanks to Miron Livny (University of Wisconsin-Madison), Berry van Halderen (University of Amsterdam) and Judhi Santoso (University of Amsterdam/Institute of Technology Bandung  ... 
doi:10.1007/3-540-63697-8_86 fatcat:vawvyesz5nfg5o5hrxrtq5v35u

Managing checkpoints for parallel programs [chapter]

Jim Pruyne, Miron Livny
1996 Lecture Notes in Computer Science  
We therefore propose the use of checkpoint servers which are speci cally designed to move checkpoints from the checkpointing process, across the interconnection network, and on to stable storage.  ...  Checkpointing techniques are not new, but they have not been widely available on parallel platforms. We have implemented CoCheck, a system for checkpointing message passing parallel programs.  ...  The principle work on the implementation of the Checkpoint Server was done by Hsu-lin Tsao as part of a class project for Prof. Marvin Solomon.  ... 
doi:10.1007/bfb0022292 fatcat:7ytwd4cfvre35edpn4mol5gmv4

OCCAM- and C-Based Multiprocessor Environments for UNIX Clusters

D. G. Patrick
1997 Computer journal  
These are scalable modular software systems that enable parallel programs to run on clusters of UNIX workstations.  ...  Results con"rm that OCCNIX can execute OCCAM/Transputer binaries over groups of UNIX workstations and has the ability to run development tools such as the ISPY network debugger.  ...  Application programs are able to run on heterogeneous clusters of UNIX workstations.  ... 
doi:10.1093/comjnl/40.1.12 fatcat:swgkxmpg6neuvbt2t7sm7unb7u

Models and algorithms for coscheduling compute-intensive taks on a network of workstations

Mikhail J. Atallah, Christina Lock Black, Dan C. Marinescu, Howard Jay Siegel, Thomas L. Casavant
1992 Journal of Parallel and Distributed Computing  
the same pace on a group of workstations.  ...  The problem of using the idle cycles of a number of high performance workstations, interconnected by a high speed network, for solving computationally intensive tasks is discussed.  ...  More recently, since the proliferation of lowcost, powerful workstation networks, general purpose scheduling of this idle capacity has been addressed.  ... 
doi:10.1016/0743-7315(92)90015-f fatcat:3mdotvskzfgbdah4brx7j363iq

A case for NOW (Networks of Workstations)

T.E. Anderson, D.E. Culler, D. Patterson
1995 IEEE Micro  
computing to demanding sequential and parallel applications.  ...  In this paper, we argue that because of recent technology advances, networks of workstations (NOWs) are poised to become the primary computing infrastructure for science and engineering, from low end interactive  ...  For example, Figure 4 shows the slowdown with local scheduling, compared to co-scheduling all processes of a parallel application [Ous82] , as the number of competing parallel jobs increases.Two of  ... 
doi:10.1109/40.342018 fatcat:2otifldvrvdxxjg2xggme55duy

Parallel TLM simulation of MPSoC on SMP workstations: Influence of communication locality

Isaac Maia Pessoa, Aline Mello, Alain Greiner, Francois Pecheux
2010 2010 International Conference on Microelectronics  
The proposed approach is based on the Parallel Discrete Event Simulation principles, and our parallel version of the SystemC kernel (named SystemC-SMP) that can run advantageously on multiprocessor workstations  ...  As the speedup obtained by parallel simulation depends on the communication pattern between the parallel tasks, we study the influence of various locality characteristics for the software application running  ...  presented a parallel implementation of SystemC using the pthreads library. The parallel engine is executed on a SMP workstation, and not on a network of workstations.  ... 
doi:10.1109/icm.2010.5696160 fatcat:vkqg7z7jyfarjgqyh773exub4y

Special Issue on Software Support for Distributed Computing

Ishfaq Ahmad, Francis Lau
1999 Journal of Parallel and Distributed Computing  
Distributed computing, as it always has been, is about achieving high performance at low cost; it is a kind of"lowly parallel computing" that dwindling costs and increasing power of the hardware have brought  ...  Rapid advances in communications technology and the proliferation of inexpensive PCs and workstations have created a wide avenue for distributed computing to move into mainstream computing.  ...  ACKNOWLEDGMENTS We thankfully acknowledge all the authors of submitted papers.  ... 
doi:10.1006/jpdc.1999.1579 fatcat:dzeqwtta4zeeveqvwl3e6hq3um

Parallel I/O Scheduling in Multiprogrammed Cluster Computing Systems [chapter]

J. H. Abawajy
2003 Lecture Notes in Computer Science  
In this paper, we address the problem of effective management of parallel I/O in multiprogrammed cluster computing systems by using appropriate I/O scheduling strategies.  ...  The performance of I/O devices lags behind the performance of processors and network systems, resulting in I/O becoming the bottleneck in current systems.  ...  Each parallel job is composed of several tasks that can be scheduled to executed on a single workstation.  ... 
doi:10.1007/3-540-44864-0_23 fatcat:dqrgsh3s6bbbjasxtq333k6h7e
« Previous Showing results 1 — 15 out of 17,395 results