97 Hits in 5.8 sec

Scalable, parallel computers: Alternatives, issues, and challenges

Gordon Bell
1994 International journal of parallel programming  
Cray supers evolved from a 120 Mflops processor and 1 Megaword memory (1976) to sixteen 1000 Mflops processors and 4 Gigaword memory (1992). A cluster of 4-C90s increases the range to 400.  ...  This amounts to a factor of 17% and 36% per year performance increase for processor and system (including multiprocessor), respectively.  ...  ATOMIC, for ATM over Mosaic, is a switch built by Danny Cohen at the University of Southern California Information Sciences Institute (USC/ISI) from Seitz's Mosaic fine-grain, multicomputer modules. gcs  ... 
doi:10.1007/bf02577791 fatcat:jnvgpsftabcnnabkmpcm5kifqq

Multigrain shared memory

Donald Yeung, John Kubiatowicz, Anant Agarwal
2000 ACM Transactions on Computer Systems  
Multigrain shared memory enables the collaboration of hardware and software shared memory, thus synthesizing a single transparent shared memory address space across a cluster of multiprocessors.  ...  This paper introduces the design of a shared memory system that uses multiple granularities of sharing, called MGS, and presents a prototype implementation of MGS on the MIT Alewife multiprocessor.  ...  We call a large-scale system built from a collection of SMPs a Distributed Shared memory MultiProcessor (DSMP).  ... 
doi:10.1145/350853.350871 fatcat:s32qyjg7wra7jc6iho426iczra

Performances of multiprocessor multidisk architectures for continuous media storage

Benoit A. Gennart, Vincent Messerli, Roger D. Hersch, Ishwar K. Sethi, Ramesh C. Jain
1996 Storage and Retrieval for Still Image and Video Databases IV  
This contribution analyzes through bottleneck performance evaluation and simulation the behavior of two m ulti-processor multi-disk architectures : a point-to-point architecture and a shared-bus architecture  ...  In order to fulll these requirements, we consider a parallel image server architecture which relies on arrays of intelligent disk nodes, each disk node being composed of one processor and one or more disks  ...  A number of architectures based on transputer links have been proposed and built, and achieve excellent performance and load balancing. 12 The transputer links support the concept of virtual channels  ... 
doi:10.1117/12.234806 dblp:conf/spieSR/GennartMH96 fatcat:4k2pjsxt45dmdclhumhheco6sa

Effectiveness of Dynamic Prefetching in Multiple-Writer Distributed Virtual Shared-Memory Systems

Magnus Karlsson, Per Stenström
1997 Journal of Parallel and Distributed Computing  
Based on detailed architectural simulations and seven scientific applications we find that our prefetch algorithm can remove a vast majority of the remote operations which improves the performance of all  ...  We consider a network of workstations (NOW) organization consisting of busbased multiprocessors interconnected by an ATM interconnect on which a sharedmemory programming model is imposed by using a multiple-writer  ...  Acknowledgments The authors are indebted to Mats Brorsson of Lund University and Jan Jonsson of Chalmers University of Technology for their suggestions and comments and to Robert Fowler of Rice University  ... 
doi:10.1006/jpdc.1997.1333 fatcat:e736a5vfczdilhzjbbnjlrva3a

Paradigm: a highly scalable shared-memory multicomputer architecture

D.R. Cheriton, H.A. Goosen, P.D. Boyle
1991 Computer  
Acknowledgments This paper has benefited from comments and criticisms of members of the Distributed Systems Group at Stanford.  ...  It was also significantly revised in response to helpful and insightful comments from the referees. Gert Slavenburg contributed significantly to the original VMP design.  ...  ParaDiGM Configurations The ParaDiGM building blocks described above allow configuration of a range of machines from a personal multiprocessor workstation to a large compute server.  ... 
doi:10.1109/2.67209 fatcat:5kz5tvcknvbrtjln6acvlm44uu

Design and evaluation of a generic software architecture for on-demand video servers

J. Chien-Liang Liu, D.H.C. Du, S.S.Y. Shim, Jenwei Hsieh, MengJou Lin
1999 IEEE Transactions on Knowledge and Data Engineering  
Our research and experimental results are based on video servers currently under construction across a variety of hardware platforms, including SMP, DMP, and clusters of PC or workstations.  ...  The most-advanced prototype server is based on an SGI shared-memory multiprocessor with a mass storage system consisting of RAID-3 disk arrays.  ...  ACKNOWLEDGMENTS The authors thank the editors of IEEE Transactions on Knowledge and Data Engineering and the anonymous reviewers, whose comments significantly improved the quality of this paper.  ... 
doi:10.1109/69.774101 fatcat:e6hc7d3pnjdpjc4h3uhqrhnoji

ParaStation: Efficient parallel computing by clustering workstations: Design and evaluation

Thomas M. Warschko, Joachim M. Blum, Walter F. Tichy
1998 Journal of systems architecture  
Performance gures ATM cell round-trip time of 3.9 s at 10Mbytes s are based on VHDL simulations; hardware development is in progress.  ...  This situation is not unique to MPP systems; it applies to multiprocessor servers as well ACP95 .  ...  Performance of the Protocol Hierarchy Switching from single to multi programming environments often su ers from a drastic performance decrease.  ... 
doi:10.1016/s1383-7621(97)00039-8 fatcat:qtrrift3gnde3porf6565p56ty

Distributed shared memory: concepts and systems

J. Protic, M. Tomasevic, V. Milutinovic
1996 IEEE Parallel & Distributed Technology Systems & Applications  
His research interests are computer architectures, multiprocessor systems, and distributed shared-memory systems. He can be reached a t  ...  He was a coarchitect of one of the first 200-MHz microprocessors, and is active in parallel and distributed processing. He has published over 40 IEEE journal papers.  ...  ACKNOWLEDGMENTS This work was partly supported by National Science Foundation of Serbia and National Technology Foundation of Serbia.  ... 
doi:10.1109/88.494605 fatcat:56jusk7vobepvhcvroadujiiae

A comprehensive bibliography of distributed shared memory

M. Rasit Eskicioglu
1996 ACM SIGOPS Operating Systems Review  
This bibliography identifies the results of research on DSM and related topics.  ...  In the past decade, a popular research topic has been the design of systems to provide the shared memory abstraction on physically distributed memory machines.  ...  [Karlsson and Stenstrom 1996] Karlsson, M. and Stenstrom, P. Performance Evaluation of Cluster-Based Multicomputer Built from ATM Switches and Bus-Based Multiprocessor Servers.  ... 
doi:10.1145/218646.218651 fatcat:ildcgoxumvheharepblsrqm5ui

A case for NOW (Networks of Workstations)

T.E. Anderson, D.E. Culler, D. Patterson
1995 IEEE Micro  
We identify three opportunities for NOWs that will benefit endusers: dramatically improving virtual memory and file system performance by using the aggregate DRAM of a NOW as a giant cache for disk; achieving  ...  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  ...  On emerging switch-based local area networks, ample bandwidth is available and the remote memory access time is an order of magnitude faster than disk.  ... 
doi:10.1109/40.342018 fatcat:2otifldvrvdxxjg2xggme55duy

Cluster computing: the commodity supercomputer

Mark Baker, Rajkumar Buyya
1999 Software, Practice & Experience  
Finally, we summarise our findings and draw a number of conclusions relating to the usefulness and likely future of cluster computing.  ...  We describe the current enabling technologies and present four state-of-theart cluster-based projects.  ...  ACKNOWLEDGEMENTS We would like to thank Rose Rayner, John Rosbottom, Toni Cortes and Lars Rzymianowicz for their efforts proof reading this paper.  ... 
doi:10.1002/(sici)1097-024x(199905)29:6<551::aid-spe248>;2-c fatcat:sxxtvtczcrb75fxl4olnbljiqi

Mediaworm: a qos capable router architecture for clusters

Ki Hwan Yum, Eun Jung Kim, C.R. Das, A.S. Vaidya
2002 IEEE Transactions on Parallel and Distributed Systems  
Simulation of a 2 2 fat-mesh using this router shows performance comparable to that of a single switch, and suggests that clusters designed with appropriate bandwidth balance between links can provide  ...  Although the MediaWorm router shows a slightly lower performance than a pipelined circuit switched PCS router, commercial success of wormhole switching, coupled with simpler and cheaper design, makes it  ...  One is based on the cutthrough switching mechanisms wormhole 12 and virtual cut-through VCT 13 , originally proposed for multiprocessor switches, and the other is based on packet switching Store and Forward  ... 
doi:10.1109/tpds.2002.1158264 fatcat:g6pp45mqnzhzvptooaploqu6iu

Commercial fault tolerance: a tale of two systems

W. Bartlett, L. Spainhower
2004 IEEE Transactions on Dependable and Secure Computing  
coupled multiprocessor design that supports a "fail-fast" philosophy implemented through a combination of hardware and software, with workload being actively taken over by another resource when one fails  ...  Server.  ...  s prediction is based on an optimistic evaluation of software detection.  ... 
doi:10.1109/tdsc.2004.4 fatcat:g5ht4nlexrdjtmpka2tjcai6fa

Key Messaging on SOME-Bus clusters

Ming Zhu, Constantine Katsinis, Wentong Cai, Bu-Sung Lee
2004 Parallel Computing  
One implementation of broadcast-based networks is the Simultaneous Optical Multiprocessor Exchange Bus (SOME-Bus).  ...  After presenting KM algorithm with SOME-Bus structure which is modeled by a M/D/1 queue, an analytical method is adopted to evaluate its performance.  ...  Ming Zhu has been supported by a National Science Foundation Postdoctoral Research Grant #0103675.  ... 
doi:10.1016/j.parco.2004.07.004 fatcat:abpr5mp6ojfj3bmj2cyovzryia

High-performance ethernet-based communications for future multi-core processors

Michael Schlansker, Norman P. Jouppi, Nagabhushan Chitlur, Erwin Oertli, Paul M. Stillwell, Linda Rankin, Dennis Bradford, Richard J. Carter, Jayaram Mudigonda, Nathan Binkert
2007 Proceedings of the 2007 ACM/IEEE conference on Supercomputing - SC '07  
The primary contribution of this work is the design, implementation, and evaluation of a network architecture for Ethernet-based communications in future data centers.  ...  However, Ethernet's low cost and high performance are causing a shift from specialized fabrics toward standard Ethernet.  ...  An early use for credit-based flow control was to manage available buffer space across transmission links within switched ATM networks [8] .  ... 
doi:10.1145/1362622.1362672 dblp:conf/sc/SchlanskerCOSRBCMBJ07 fatcat:b6nqg7loczb6bifp5cptihxjgy
« Previous Showing results 1 — 15 out of 97 results