Filters








18 Hits in 3.5 sec

Parallel computing in networks of workstations with Paralex

R. Davoli, L.-A. Giachini, O. Babaoglu, A. Amoroso, L. Alvisi
1996 IEEE Transactions on Parallel and Distributed Systems  
All of the necessary code for distributing the computation across a network and replicating it to achieve fault tolerance and dynamic load balancing is automatically generated by the system In this paper  ...  distributed system include heterogeneity, high-latency communication, fault tolerance and dynamic load balancing.  ...  ACKNOWLEDGMENTS Giuseppe Serazzi and his group at the University of Milan contributed to early discussions on the mapping and dynamic load balancing strategies.  ... 
doi:10.1109/71.494632 fatcat:7eapddkksres3bu6u6eojb5iy4

Paralex

Özalp Babaoğlu, Lorenzo Alvisi, Alessandro Amoroso, Renzo Davoli, Luigi Alberto Giachini
1992 Proceedings of the 6th international conference on Supercomputing - ICS '92  
Acknowledgements Giuseppe Serazzi and his group at the University of Milan contributed to early discussions on the mapping and dynamic load balancing strategies.  ...  Alberto Baronio, Marco Grossi, Susanna Lambertini, Manuela Prati and Nicola Samoggia of the Paralex group at Bologna contributed to the various phases of the coding. We are grateful to all of them.  ...  , replica management and dynamic load balancing.  ... 
doi:10.1145/143369.143406 dblp:conf/ics/BabaogluAADG92 fatcat:ygdgldypgbfhlbmrcfpe7j5oq4

Tools and Techniques for Adding Fault Tolerance to Distributed and Parallel Programs [chapter]

Özalp Babaoğlu
1993 Parallel Computing on Distributed Memory Multiprocessors  
The Paralex rur-time system contains the primitives necessary to support fault tolerance and dynamic load balancing.  ...  Passive repiication not only satisfies this objective, it provides a uniform mechanism for dynamic load bv-A.cing through late binding of computations to hoots. Pa.  ... 
doi:10.1007/978-3-642-58066-6_13 fatcat:hvjqxtubgjeojpnksoezm7aku4

HeNCE: A Heterogeneous Network Computing Environment

Adam Beguelin, Jack J. Dongarra, George Al Geist, Robert Manchek, Keith Moore
1994 Scientific Programming  
The heterogeneous network computing environment (HeNCE) is an integrated graphical environment for creating and running parallel programs over a heterogeneous collection of computers.  ...  It is built on a lower level package called parallel virtual machine (PVM).  ...  When HeNCE executes an application graph HeNCE dynamically load balances the parallel tasks taking into account the heterogeneity in the algorithm and the machine performance.  ... 
doi:10.1155/1994/368727 fatcat:7ipcgyanerbmvjeg6m4aqmyeia

The Ubiquity Generator Framework: 7 Years of Progress in Parallelizing Branch-and-Bound [chapter]

Yuji Shinano
2018 Operations Research Proceedings  
It solved two instances from MIPLIB2003 and 12 from MIPLIB2010 for the first time to optimality by using up to 80,000 cores on supercomputers.  ...  Mixed integer linear programming (MILP) is a general form to model combinatorial optimization problems and has many industrial applications.  ...  Implementations of ramp-up, dynamic load balancing, and check-pointing and restarting mechanisms are available as a generic functionality (see details in [20] ).  ... 
doi:10.1007/978-3-319-89920-6_20 dblp:conf/or/Shinano17 fatcat:qs37orlcgrf4vbqkenblx33kse

Federated clusters using the transparent remote Execution (TREx) environment

Richert Wang, Enrique Cauich, Isaac D. Scherson
2007 2007 International Conference on Parallel and Distributed Systems  
TREx is a daemon that dynamically exploits idle operational in-use workstations.  ...  For example, multi-system wireless network simulations involve complex algorithms of traffic balancing and communication control on large geographical areas.  ...  Another key difference between Paralex and TREx is how slaves are selected during runtime. Paralex selects its slaves before execution starts for all services needed.  ... 
doi:10.1109/icpads.2007.4447831 dblp:conf/icpads/WangCS07 fatcat:cjiywzxhcbegrn2ggdi5dadtjy

Mapping parallel computations onto distributed systems in Paralex

O. Babaoglu, L. Alvisi, A. Amoroso, R. Davoli
[1991] Proceedings, Advanced Computer Technology, Reliable Systems and Applications  
The Paralex loader selects hosts of a distributed system to execute a parallel program so as to satisfy the heterogeneity and fault tolerance requirements while trying to maximize performance.  ...  Paralex is a programming environment that allows parallel programs to be developed and executed on distributed systems as if the latter were uniform parallel multiprocessor computers.  ...  While Paralex has demonstrated the feasibility of providing automatic support for parallel programs in a distributed system, the performance benefits of the approach remain to be demonstrated.  ... 
doi:10.1109/cmpeur.1991.257368 fatcat:ssxwj6x5cjbzzmp46iknpl7shu

A Reformed K-Nearest Neighbors Algorithm for Big Data Sets

Vo Ngoc Phu, Vo Thi Ngoc Tran
2018 Journal of Computer Science  
Future Work Based on the results of this proposed model, many future projects can be proposed, such as creating full emotional lexicons in a parallel network environment to shorten execution times, creating  ...  Fuzzy C-means for english sentiment classification in a distributed system Shirazi et al. (1995) No Yes Scheduling and Load Balancing in Parallel and Distributed Systems Chen et al. (2011) No Yes  ...  Therefore, we propose a new model to address these limitations.  ... 
doi:10.3844/jcssp.2018.1213.1225 fatcat:5mw325cfyzgd7frc5fot7ejvgq

TRAPPER: A graphical programming environment for parallel systems [chapter]

Lorenz Schäfers, Christian Scheidler, Ottmar Krämer-Fuhrmann
1994 Lecture Notes in Computer Science  
TRAPPER contains tools for the design, mapping and visualization of parallel systems.  ...  The Designtool supports a hybrid program development, where the parallel process structure is described using a graphical representation and the sequential behavior is described by sequential program code  ...  The Kiviat diagram displays the load of all processors including with a so-called high water mark. This Kiviat diagram is useful for the analysis of load balance.  ... 
doi:10.1007/3-540-57981-8_139 fatcat:rpcld6l6gzbqxkzeqwgcv62wzu

News Monitor: A Framework for Exploring News in Real-Time

Nikolaos Panagiotou, Antonia Saravanou, Dimitrios Gunopulos
2021 Data  
In addition, News Monitor crawls the Twitter stream using a dynamic set of "trending" keywords in order to retrieve all messages relevant to the news.  ...  This knowledge base is then used to create a summary for the user.  ...  (2021) News Monitor: A Framework for Querying News in Real Time.  ... 
doi:10.3390/data7010003 fatcat:t5vd6s5ckrcvfaftprpg6efr6y

The CODE 2.0 graphical parallel programming language

Peter Newton, James C. Browne
1992 Proceedings of the 6th international conference on Supercomputing - ICS '92  
Ease of use is provided by an integrated graphical/textual interface, a powerful dynamic model of parallel computation, and an integrated concept of program component reuse.  ...  CODE 2.0 represents a major conceptual advance over its predecessor systems (CODE 1.0 and CODE 1.2) in terms of the expressive power of the model of computation which is implemented and in potential for  ...  The Paralex system [BAB92] is less expressive than CODE 2.0 or HeNCE but stresses fault tolerance and dynamic load balancing.  ... 
doi:10.1145/143369.143405 dblp:conf/ics/NewtonB92 fatcat:oggvkiuggjcjdawfprbdvwk7w4

FiberSCIP—A Shared Memory Parallelization of SCIP

Yuji Shinano, Stefan Heinz, Stefan Vigerske, Michael Winkler
2018 INFORMS journal on computing  
Third, a way to evaluate the performance of new algorithms and parameter settings of the parallel extensions is presented.  ...  In order to obtain the benefit of using parallel computing environments, we have to deploy our programs for these effectively.  ...  Acknowledgments This research is partially supported by the DFG Research Center Matheon Mathematics for key technologies in Berlin. The work of Yuji Shinano was supported by a Google Research Grant.  ... 
doi:10.1287/ijoc.2017.0762 fatcat:kmwwzfzxrvbwzpt4t5kgawvwza

Problem Solving Environment Infrastructure for High Performance Computer Systems [chapter]

Daniel C. Stanzione, Walter B. Ligon
2000 Lecture Notes in Computer Science  
In this work, a methodology for constructing PSEs is proposed. A model for PSE construction is introduced, and a toolkit is constructed based on this model.  ...  Recently, problem solving environments (PSEs) have emerged as a potential solution to this problem.  ...  In order to allow for a variety of cluster architectures, and to allow for static load-balancing and optimum code generation, a number of different characteristics about the cluster are represented.  ... 
doi:10.1007/3-540-45591-4_41 fatcat:uciwum46g5ecljkgg4f6zu5wvi

The Measurement of Residual Stresses by X-Ray Diffraction Techniques [chapter]

M.R. James, J.B. Cohen
1980 Treatise on Materials Science and Technology  
As seen in Fig. 6 this pro- Fig. 6 duces a new focal point.  ...  We first review the literature on stresses produced during manufacturing 3nd then the changes in stress distribution during dynamic loading.  ...  In this report the main aim is to present, in a single chapter, many of the recent instrumental advances and to explain the fundamental limitations associated with the measurement, in the hope of providing  ... 
doi:10.1016/b978-0-12-341819-7.50007-9 fatcat:g2vjbhl6wvf2vo4x5l34mqfj6q

A hierarchical software development environment for performance oriented parallel programming [article]

David A. Feldcamp
1992
Of these tools, the most important from the developer's point of view is the user interface which provides both support for constructing programs and interacting with the rest of the environment.  ...  It is well known that better performance will be achieved when there is a close match between the structure of a virtual machine and the algorithms of a program built using the machine.  ...  Paralex is distinct from the other systems described in this section in its support for fault tolerance through replication, dynamic load balancing, and the sophistication of its mapping system.  ... 
doi:10.14288/1.0051189 fatcat:53yqoi3cmreutc7fc5fvobxxda
« Previous Showing results 1 — 15 out of 18 results