Filters








1,723 Hits in 5.9 sec

FASTEST: a practical low-complexity algorithm for compile-time assignment of parallel programs to multiprocessors

Yu-Kwong Kwok, I. Ahmad
1999 IEEE Transactions on Parallel and Distributed Systems  
The FASTEST algorithm generates optimal solutions for a majority of the test cases and close-to-optimal solutions for the rest.  ...  A variety of heuristics have been proposed to generate efficient solutions but they take prohibitively long execution times for moderate size or large problems.  ...  prototype software tool for program parallelization and scheduling.  ... 
doi:10.1109/71.752781 fatcat:wgpihdacvrc7hfe4lrsiyko7ci

An implementation of storage management in capability environments

Paolo Corsini, Lanfranco Lopriore
1995 Software, Practice & Experience  
In this paper, we present an approach to the management of a large virtual memory space aimed at solving these problems.  ...  The exploitation of the salient features of capability-based addressing environments leads to a high number of small objects existing in memory at the same time.  ...  The operations of a primitive type are implemented by software routines, in the same way as those of an extended type.  ... 
doi:10.1002/spe.4380250503 fatcat:i2jwep4imrbmbnmpkrib6fugr4

POLYSHIFT Communications Software for the Connection Machine System CM-200

William George, Ralph G. Brickner, S. Lennart Johnsson
1994 Scientific Programming  
Our implementation of the PSHIFT function on the Connection Machine systems CM-2 and CM-200 offers a speedup of up to a factor of 3–4 compared with CSHIFT when the local data motion within a node is small  ...  We describe the use and implementation of a polyshift function PSHIFT for circular shifts and end-offs shifts.  ...  We thank the Advanced Computing Laboratory of Los Alamos National Laboratory for access to the CM{200 located there. Valuable assistance and advice was given by a  ... 
doi:10.1155/1994/987498 fatcat:zedkqcuyqvbz7lxmgvr7p2e7ou

Achieving High Performance With TCP Over 40 GbE on NUMA Architectures for CMS Data Acquisition

Tomasz Bawej, Ulf Behrens, James Branson, Olivier Chaze, Sergio Cittolin, Georgiana-Lavinia Darlea, Christian Deldicque, Marc Dobson, Aymeric Dupont, Samim Erhan, Andrew Forrest, Dominique Gigi (+24 others)
2015 IEEE Transactions on Nuclear Science  
This paper describes the architecture, the technologies involved and the performance measurements of the software in the context of the CMS distributed event building.  ...  During the first long shutdown of LHC, the CMS DAQ system is going to be upgraded for operation from 2015 onwards and a new software component has been designed and developed in the CMS online framework  ...  XDAQ is a software platform created specifically for the development of distributed data acquisition systems. The development is carried out at CERN for the CMS experiment.  ... 
doi:10.1109/tns.2015.2409898 fatcat:cbygwnwm5bgclgheogx3f7kmmy

Benchmarking the computation and communication performance of the CM-5

Kivanc Dincer, Zeki Bozkus, Sanjay Ranka, Geoffrey Fox
1996 Concurrency Practice and Experience  
Thinking Machines' CM-5 machine is a distributed-memory, message-passing computer.  ...  The CM-5 is a parallel distributed-memory machine that can scale up to 16,384 processing nodes.  ...  Acknowledgments We w ould like to thank Steve S w artz of the Thinking Machines Corporation for his many clari cations regarding the architecture of the CM-5.  ... 
doi:10.1002/(sici)1096-9128(199601)8:1<47::aid-cpe194>3.0.co;2-9 fatcat:n6luvtb2jbggdazfooou22wk2a

The design of a distributed kernel for a multiprocessor system

Patrick David Boyle
1982
This thesis describes an experiment in the design of a multiprocessor operating system based on the distribution of kernel functionality among the processors.  ...  The possibilities of increased responsiveness, throughput, availability, reliability and cost-effectiveness invite investigation of the hardware and software design of multiprocessor computing systems.  ...  With the extension of Verex to a multiprocessor system, this constraint has also been -extended: the Distributed Verex master kernel must not allow the incorrect execution of any software, including the  ... 
doi:10.14288/1.0051817 fatcat:3dbzwzh5izb4dk5oh7bb6vwxli

Shaman: a distributed simulator for shared memory multiprocessors

H. Matsuo, S. Imafuku, K. Ohno, H. Nakashima
Proceedings. 10th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunications Systems  
This paper describes our distributed architectural simulator of shared memory multiprocessors named Shaman.  ...  The simulator runs on a PC cluster that consists of multiple front-end nodes to simulate the instruction level behavior of a target multiprocessor in parallel and a back-end node to simulate the target  ...  Thus we adopted a software distributed shared memory (DSM) technique that has been proved to work efficiently on a distributed memory environment such as a PC cluster.  ... 
doi:10.1109/mascot.2002.1167095 dblp:conf/mascots/MatsuoION02 fatcat:qithcgawybb5zprz6dvlgrbfue

Performance analysis of median filtering on Meiko-a distributed multiprocessor system

K.M. Poon, N.H.C. Yung
Proceedings 1st International Conference on Algorithms and Architectures for Parallel Processing  
This paper presents the performance analysis of realizing median filtering on a distributed multiprocessor system.  ...  The results of the performance analysis give a good indication of the performance gain in using multi-processor for median filtering over uni-proces-SOT.  ...  " Computing Surface is a RISC-based distributed-memory multiprocessor system.  ... 
doi:10.1109/icapp.1995.472250 fatcat:rph5uukvqfe5zcqgnc5g7tvaxe

Characterizing parallel file-access patterns on a large-scale multiprocessor

A. Purakayastha, C. Ellis, D. Kotz, N. Nieuwejaar, M.L. Best
Proceedings of 9th International Parallel Processing Symposium  
Design of such high-performance parallel file systems depends on a thorough grasp of the expected workload. So far there have been no comprehensive usage studies of multiprocessor file systems.  ...  This paper presents results from a different platform, the CM-5 at the National Center for Supercomputing Applications.  ...  Acknowledgments We thank Michael Welge who provided CM-5 access without which this tracing study would not have been possible.  ... 
doi:10.1109/ipps.1995.395928 dblp:conf/ipps/PurakayasthaEKNB95 fatcat:ru5b75kygra5dfwscrtsw3eokq

Multiprocessing: An Annotated Bibliography

Satyanarayanan
1980 Computer  
The concept of functional partitioning exists here, but theassignment of functions to processors is on *These digests and proceedings are available from the IEEE Computer Socia temporary rather than permanent  ...  The years since the advent of multiprocessing have and dynanmically assigned specific hardware functions as Univac 1110 permits every I/O device to communicate with the need arises.  ...  ., "Software Management of Cm*-A Distributed Multiprocessor," AFIPS Conf Proc., Vol. 46, 1977 NCC, pp. 657-663.  ... 
doi:10.1109/mc.1980.1653627 fatcat:fw6llehhwnepvp3ve6shtw4zgu

Introduction to Multiprocessor I/O Architecture [chapter]

David Kotz
1996 The Kluwer International Series in Engineering and Computer Science  
In this paper we p r o vide an introduction to I/O architectural issues in multiprocessors, with a focus on disk subsystems.  ...  The computational performance of multiprocessors continues to improve b y leaps and bounds, fueled in part by rapid improvements in processor and interconnection technology.  ...  understanding CM-5 details.  ... 
doi:10.1007/978-1-4613-1401-1_4 fatcat:zdvyvbg7xrdr3jzuhis5a6vrjy

The LOFAR EoR Data Model: (I) Effects of Noise and Instrumental Corruptions on the 21-cm Reionization Signal-Extraction Strategy [article]

Panagiotis Labropoulos , Sarod Yatawatta, Michiel Brentjens, Geraint Harker, Saleem Zaroubi Kapteyn Astronomical Institute, University of Groningen, Groningen, the Netherlands, Max-Planck Institute for Astrophysics, Garching, Germany, Leiden Observatory, Leiden University, Leiden (+1 others)
2009 arXiv   pre-print
A number of experiments are set to measure the 21-cm signal of neutral hydrogen from the Epoch of Reionization (EoR).  ...  A detailed study of the statistical properties of our data model and more complex instrumental models will be considered in the future.  ...  ACKNOWLEDGMENTS The authors would like to thank Johan Hamaker, Jan Noordam, Oleg Smirnov and Stephan Wijnholds for useful discussions during the various stages of this work.  ... 
arXiv:0901.3359v1 fatcat:ouqpmdphizf2nlcysawwa4hbq4

Page 143 of Journal of Research and Practice in Information Technology Vol. 12, Issue 4 [page]

1980 Journal of Research and Practice in Information Technology  
This would benefit uniprocessors, multiprocessors and distributed systems alike. 3.2 Task Decomposition If the performance of a multiprocessor or distributed system on a single task is inadequate then  ...  The software problems of distributed systems are surmountable if a disciplined approach is taken to pro- gramming.  ... 

Medusa

John K. Ousterhout, Donald A. Scelza, Pradeep S. Sindhu
1979 Proceedings of the seventh symposium on Operating systems principles - SOSP '79  
The paper is a discussion of the issues that arose in the design of an operating system for a distributed multiprocessor, Cm*.  ...  Cm. consists of fifty processor-memory pairs arranged in five clusters, with one communication controller (Kmap) managing interprocessor communication for each chtster.  ...  Each utility executes in a consequence of the distribution of low-level system functions such as memory management and process management.  ... 
doi:10.1145/800215.806578 dblp:conf/sosp/OusterhoutSS79 fatcat:7emjsxzqfrh6lckmtrsefshg3u

DSM perspective: another point of view

G. Bell, C. van Ingen
1999 Proceedings of the IEEE  
Gray for his interaction and tireless editing of two of the drafts.  ...  ACKNOWLEDGMENT The authors would like to thank the editors and reviewers who stimulated them to solidify and clarify their position so as to present DSM in a less biased light.  ...  The CMU Cm* project [6] was the first distributed shared memory (DSM)-a scalable, shared memory multiprocessor. LSI-11 microprocessors were the basic modular building block.  ... 
doi:10.1109/5.747862 fatcat:47y3mush5jestl2gklmgdtghwi
« Previous Showing results 1 — 15 out of 1,723 results