Filters








18 Hits in 5.8 sec

Remote I/O

Ian Foster, David Kohr, Rakesh Krishnaiyer, Jace Mogill
1997 Proceedings of the fifth workshop on I/O in parallel and distributed systems - IOPADS '97  
However, remote I/O also introduces new technical challenges in the areas of portability, performance, and integration with distributed computing systems.  ...  We argue instead for a remote I/O paradigm in which programs use familiar parallel I/O interfaces to access remote filesystems.  ...  Department of Energy, under Contract W-31-109-Eng-38, in support of the multiagency Scalable I/O project.  ... 
doi:10.1145/266220.266222 dblp:conf/iopads/FosterKKM97 fatcat:4z4kja2yvraqfc6h2wlluv7yby

GASS

Joseph Bester, Ian Foster, Carl Kesselman, Jean Tedesco, Steven Tuecke
1999 Proceedings of the sixth workshop on I/O in parallel and distributed systems - IOPADS '99  
High performance is achieved by incorporating default data movement strategies that are specialized for I/O patterns common in wide area applications and by providing support for programmer management  ...  This service defines a global name space via Uniform Resource Locators and allows applications to access remote files via standard I/O interfaces.  ...  This work was supported in part by the Mathematical, Information, and Computational Sciences Division subprogram of the Office of Computational and Technology Research, U.S.  ... 
doi:10.1145/301816.301839 dblp:conf/iopads/BesterFKTT99 fatcat:6nfbny3ggzeivhu25twmfthloa

Optimal read-once parallel disk scheduling

Mahesh Kallahalla, Peter J. Varman
1999 Proceedings of the sixth workshop on I/O in parallel and distributed systems - IOPADS '99  
An optimal prefetching and I/O scheduling algorithm L-OPT, for parallel I/O systems, using a read-once model of block references is presented.  ...  The algorithm uses knowledge of the next L references, L-block lookahead, to create a minimal-length I/O schedule.  ...  We thank the referees for their dedication and careful reading of the manuscript. Their valuable suggestions have been responsible for many improvements.  ... 
doi:10.1145/301816.301835 dblp:conf/iopads/KallahallaJ99 fatcat:uutex6np7vbazd4no24otg5m5m

Cluster I/O with River

Remzi H. Arpaci-Dusseau, Eric Anderson, Noah Treuhaft, David E. Culler, Joseph M. Hellerstein, David Patterson, Kathy Yelick
1999 Proceedings of the sixth workshop on I/O in parallel and distributed systems - IOPADS '99  
River is dcsioed to pmvide maximum performance in the c&on case -even in the-race a* nor,uniformities in hardware, software, and workload.  ...  River is based on two simple design features: a high-performanccdirniburedqueue, and a storage redundancy mechanism called gradunfed declusrering.  ...  We'd also like to thank Alan Mainwaring for his work on and support of Active Messages; it is the sine quo non of our work. Many thanks to the anonymous reviewen for all of their helpful commc~ts.  ... 
doi:10.1145/301816.301823 dblp:conf/iopads/Arpaci-DusseauATCHPY99 fatcat:agexl2kxdzgnxjbqchyep4rh6u

Efficient distributed backup with delta compression

Randal C. Burns, Darrell D. E. Long
1997 Proceedings of the fifth workshop on I/O in parallel and distributed systems - IOPADS '97  
Network resource limitations make it increasingly difficult to backup a distributed file system on a nightly or even weekly basis.  ...  This minimizes server workload and network transmission time on file restore.  ...  You who helped in the design and implementation of this system and to N. Pass, J. Menon, and R. Golding whose support and guidance are instrumental to the continuing success of our research.  ... 
doi:10.1145/266220.266223 dblp:conf/iopads/BurnsL97 fatcat:wj7ijf2g7nchrgmhjq2gmq4sm4

ENWRICH

Apratim Purakayastha, Carla Schlatter Ellis, David Kotz
1996 Proceedings of the fourth workshop on I/O in parallel and distributed systems part of the federated computing research conference - IOPADS '96  
Unfortunately, end-to-end parallel-I/O performance has not been able to keep up with substantial improvements in parallel-I/O hardware because of poor parallel file-system software.  ...  In this paper, we propose ENWRICH, a compute-processor write-caching scheme for write-only files in parallel file systems.  ...  Acknowledgments Many thanks to Sid Chatterjee at UNC for allowing the use of their DEC 5000 compute server; to Jeff Chase at Duke for allowing us to test the early versions of our simulator on his lab  ... 
doi:10.1145/236017.236034 dblp:conf/iopads/PurakayasthaEK96 fatcat:n7lewdkxgrdmlcxt7jaeo7lnsi

Competitive parallel disk prefetching and buffer management

Rakesh Barve, Mahesh Kallahalla, Peter J. Varman, Jeffrey Scott Vitter
1997 Proceedings of the fifth workshop on I/O in parallel and distributed systems - IOPADS '97  
Given a ¤ -disk parallel I/O system and a globally shared I/O buffer that can hold upto ¥ disk blocks, we derive a lower bound of ¦ § © ¤ on the competitive ratio of any deterministic online prefetching  ...  We provide a competitive analysis framework for online prefetching and buffer management algorithms in parallel I/O systems, using a read-once model of block references.  ...  Modeling a distributed parallel I/O system, with independent disks and a partitioned I/O buffer, they defined a parallel version of MIN, and showed that it is optimal.  ... 
doi:10.1145/266220.266225 dblp:conf/iopads/BarveKVV97 fatcat:ruiupg7l7zembnnrrcojvd3tmy

Browsing and placement of multiresolution images on parallel disks

Sunil Prabhakar, Divyakant Agrawal, Amr El Abbadi, Ambuj Singh, Terrence Smith
1997 Proceedings of the fifth workshop on I/O in parallel and distributed systems - IOPADS '97  
In order to reduce the demands on I/O and network resources, multiresolution representations are being proposed for the storage organization of images.  ...  Several strategies are evaluated to store the image coefficients on parallel disks.  ...  Another advantage of accessing the disk through the raw device interface is that operating system buffering is bypassed and I/O calls on the file result in actual physical operations on the disks.  ... 
doi:10.1145/266220.266230 dblp:conf/iopads/PrabhakarAASS97 fatcat:guinyy2vqrde7hoscdcazuztvu

Tuning the performance of I/O-intensive parallel applications

Anurag Acharya, Mustafa Uysal, Robert Bennett, Assaf Mendelson, Michael Beynon, Jeff Hollingsworth, Joel Saltz, Alan Sussman
1996 Proceedings of the fourth workshop on I/O in parallel and distributed systems part of the federated computing research conference - IOPADS '96  
We report the lessons learned in achieving high I O performance from these applications, including the need for code restructuring, local disks on every node and knowledge of future I O requests.  ...  Finally, w e comment on the necessity of complex I O interfaces like collective I O and strided requests to achieve high performance.  ...  We w ould like to thank Tonjua Hines and Steve Kempler from the Earth Science Data & Information Systems Project ESDIS at NASA Goddard Space  ... 
doi:10.1145/236017.236027 dblp:conf/iopads/AcharyaUBMBHSS96 fatcat:2ljwxgb2uvdhplib3wq5zqlmim

On implementing MPI-IO portably and with high performance

Rajeev Thakur, William Gropp, Ewing Lusk
1999 Proceedings of the sixth workshop on I/O in parallel and distributed systems - IOPADS '99  
In addition to basic I/O functionality, we consider the issues of supporting other MPI-IO features, such us 64-bit file sizes, noncontiguous accesses, collective I/O, asynchronous I/O, consistency and  ...  We discuss the issues involved in implementing MPI-IO portably on multiple machines and file systems and also achieving high performance.  ...  In the II0 phase, processes perform parallel UO in large chunks and therefore obtain high I/O performance.  ... 
doi:10.1145/301816.301826 dblp:conf/iopads/ThakurGL99 fatcat:nod6tqruk5gxdi6nyxylvcfdge

Efficient data-parallel files via automatic mode detection

Jason A. Moore, Philip J. Hatcher, Michael J. Quinn
1996 Proceedings of the fourth workshop on I/O in parallel and distributed systems part of the federated computing research conference - IOPADS '96  
Parallel languages rarely specify parallel I O constructs, and existing commercial systems provide the programmer with a low-level I O interface.  ...  We present design principles for integrating I O into languages and show h o w these principles are applied to a virtual-processor-oriented language.  ...  Acknowledgements This research w as supported by NSF grants ASC-9208971 and CDA-9216172.  ... 
doi:10.1145/236017.236025 dblp:conf/iopads/MooreHQ96 fatcat:w3s6q4mhdrhsbbbmyvamgk2hyq

A unified compiler algorithm for optimizing locality, parallelism and communication in out-of-core computations

M. Kandemir, A. Choudhary, J. Ramanujam, M. Kandaswamy
1997 Proceedings of the fifth workshop on I/O in parallel and distributed systems - IOPADS '97  
This approach considers array references one-by-one and attempts to optimize each reference for parallelism and locality.  ...  These algorithms consider loop and data layout transformations in a tied framework.  ...  The results however should not be interpreted as a general comparison of the two machines, es they are dependent on the parallel file systems, our parallel I/O library and the I/O access pattern of the  ... 
doi:10.1145/266220.266228 dblp:conf/iopads/KandemirCRK97 fatcat:udbihlxh5vcwdatqpecxlo53hm

Round-like behavior in multiple disks on a bus

Rakesh Barve, Phillip B. Gibbons, Bruce K. Hillyer, Yossi Matias, Elizabeth Shriver, Jeffrey Scott Vitter
1999 Proceedings of the sixth workshop on I/O in parallel and distributed systems - IOPADS '99  
In modern I/O architectures, multiple disk drives are attached to each I/O bus.  ...  Under I/O-intensive w orkloads, the disk latency for a request can be overlapped with the disk latency and data transfers of requests to other disks, potentially resulting in an aggregate I/O throughput  ...  In such applications, parallel I/O performance is often limited by the bus.  ... 
doi:10.1145/301816.301821 dblp:conf/iopads/BarveGHMSV99 fatcat:e4rmjslm5rhjnme3dnawcpobm4

Heuristics for scheduling I/O operations

R. Jain, K. Somalwar, J. Werth, J.C. Browne
1997 IEEE Transactions on Parallel and Distributed Systems  
The I/O bottleneck in parallel computer systems has recently begun receiving increasing interest.  ...  Most attention has focused on improving the performance of I/O devices using fairly low-level parallelism in techniques such as disk striping and interleaving.  ...  A preliminary version of part of this work appeared in the informal proceedings distributed to participants at the Workshop on I/O in Parallel Computer Systems, Newport Beach, California, April 13, 1993  ... 
doi:10.1109/71.584096 fatcat:vtty3dz7pbb5vj5547rgc2vrae

Page 1183 of IEEE Transactions on Computers Vol. 52, Issue 9 [page]

2003 IEEE Transactions on Computers  
Workshop on I/O in Parallel and Distributed Systems (IOPADS), pp. 122-127, May 1996. 6] E.L. Miller and R.H.  ...  Varman, “Optimal Read-Once Parallel Disk Scheduling,” Proc. Workshop on I/O in Parallel and Distributed Systems (IOPADS), pp. 68-77, 1999. D.A. Hutchinson, P. Sanders, and J.S.  ... 
« Previous Showing results 1 — 15 out of 18 results