{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,8]],"date-time":"2023-10-08T20:57:05Z","timestamp":1696798625714},"reference-count":40,"publisher":"Elsevier BV","issue":"11","license":[{"start":{"date-parts":[[1999,7,1]],"date-time":"1999-07-01T00:00:00Z","timestamp":930787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computer Communications"],"published-print":{"date-parts":[[1999,7]]},"DOI":"10.1016\/s0140-3664(99)00073-0","type":"journal-article","created":{"date-parts":[[2002,7,26]],"date-time":"2002-07-26T02:56:11Z","timestamp":1027652171000},"page":"1017-1033","source":"Crossref","is-referenced-by-count":10,"title":["Partitioning and scheduling loops on NOWs"],"prefix":"10.1016","volume":"22","author":[{"given":"S.","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J.","family":"Xue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/S0140-3664(99)00073-0_BIB1","first-page":"27","article-title":"Ultracompter a Teraflop before its time","volume":"17","author":"Bell","year":"1992","journal-title":"Communication of the ACM"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB2","doi-asserted-by":"crossref","unstructured":"Al Geist, et al., PVM\u2014Parallel Virtual Machine: A User's Guide and Tutorial for Networked Parallel Computing, 0-262-57108-0, The MIT Press, 1994.","DOI":"10.7551\/mitpress\/5712.001.0001"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB3","unstructured":"E. Lusk, W. Gropp, A. Skjellum, Using MPI: Portable Parallel Programming with the Message-Passing Interface, 0-262-57104-8, The MIT Press, 1994."},{"key":"10.1016\/S0140-3664(99)00073-0_BIB4","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1109\/40.342015","article-title":"Myrinet, a gigabit per second local area network","volume":"15","author":"Boden","year":"1995","journal-title":"IEEE Micro Magazine"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB5","series-title":"Performance Analysis of Local Computer Network","author":"Hammond","year":"1986"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB6","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1145\/143103.143134","article-title":"A dynamic scheduling method for irregular parallel programs","author":"Lucco","year":"1992","journal-title":"ACM SIGPLAN\u201992"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB7","doi-asserted-by":"crossref","unstructured":"R. Sakellariou, J.R. Gurd, Compile-time minimisation of load imbalance in loop nests, in: Proc. of the International Conference on Supercomputing (ICS), Vienna, July 1997.","DOI":"10.1145\/263580.263811"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB8","doi-asserted-by":"crossref","unstructured":"M. Zaki, W. Li, S. Parthasarathy, Customized dynamic load balancing for a network of workstations, Technical Report TR-602, Department of Computer Science, University of Rochester, December. 1995.","DOI":"10.1109\/HPDC.1996.546198"},{"issue":"1","key":"10.1016\/S0140-3664(99)00073-0_BIB9","doi-asserted-by":"crossref","first-page":"19","DOI":"10.1109\/40.566189","article-title":"Using the memory channel network","volume":"17","author":"Gillett","year":"1997","journal-title":"IEEE Micro"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB10","doi-asserted-by":"crossref","unstructured":"M. Cierniak, W. Li, M. Zaki, Loop scheduling for heterogeneity, in: Proc. of the Fourth IEEE International Symposium on High-Performance Distributed Computing, Pentagon City, Virginia, August 1995.","DOI":"10.1109\/HPDC.1995.518697"},{"issue":"34","key":"10.1016\/S0140-3664(99)00073-0_BIB11","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1006\/jpdc.1996.0058","article-title":"Parallel execution of iterative computation on workstation clusters","volume":"1","author":"Wang","year":"1996","journal-title":"Journal of Parallel and Distributed Computing"},{"issue":"4","key":"10.1016\/S0140-3664(99)00073-0_BIB12","doi-asserted-by":"crossref","first-page":"444","DOI":"10.1145\/63334.63337","article-title":"Linda in context","volume":"32","author":"Carriero","year":"1989","journal-title":"Communication of the ACM"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB13","unstructured":"R. Butler, E. Lusk, User's guide to the p4 parallel programming system, Technical Report ANL-92\/17, Argonne National Laboratory, October. 1992."},{"key":"10.1016\/S0140-3664(99)00073-0_BIB14","doi-asserted-by":"crossref","unstructured":"D.C. Schmidt, T. Suda, A high-performance endsystem architecture for real-time corba, IEEE Communications Magazine, 14 (2) February 1997.","DOI":"10.1109\/35.565659"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB15","series-title":"High Performance Compilers for Parallel Processing","author":"Wolfe","year":"1996"},{"issue":"4","key":"10.1016\/S0140-3664(99)00073-0_BIB16","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1109\/71.97902","article-title":"loop transformation theory and an algorithm to maximize parallelism","volume":"2","author":"Wolf","year":"1991","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"issue":"4","key":"10.1016\/S0140-3664(99)00073-0_BIB17","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1142\/S0129626497000401","article-title":"On tiling as a loop transformation","volume":"7","author":"Xue","year":"1997","journal-title":"Parallel Processing Letters"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB18","doi-asserted-by":"crossref","unstructured":"F. Desprez, J. Dongarra, F. Rastello, Y. Robert, Determining the idle time of a tiling: new results, Technical Report UT-CS-97-360, Department of Computer Science, University of Tennessee, May 1997.","DOI":"10.1109\/PACT.1997.644026"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB19","doi-asserted-by":"crossref","unstructured":"K. Hogstedt, L. Carter, J. Ferrante, Determining the idle time of a tiling, in: ACM Symposium on Principles of Programming Languages, January 1997.","DOI":"10.1145\/263699.263716"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB20","doi-asserted-by":"crossref","unstructured":"W.K. Kaplow, W.A. Maniatty, B.K. Szymanski, Impact of memory hierarchy on program partitioning and scheduling, in: Proc. of HICSS-28, Hawaii, Maui, Hawaii, January. 1995.","DOI":"10.1109\/HICSS.1995.375473"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB21","doi-asserted-by":"crossref","unstructured":"W.K. Kaplow, B.K. Szymanski, Program optimization based on compile-time cache performance prediction, Parallel Processing Letter, 6 (1) 1996.","DOI":"10.1142\/S0129626496000170"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB22","doi-asserted-by":"crossref","unstructured":"M.E. Wolf, M.S. Lam, A data locality optimizing algorithm, in: Proc. of the ACM SIGPLAN\u201991 Conf. on Programming Language Design and Implementation, June 1991, pp. 173\u2013184.","DOI":"10.1145\/113445.113449"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB23","doi-asserted-by":"crossref","unstructured":"R. Andonov, S. Rajopadhye, Optimal tiling of two-dimensional uniform recurrences, Technical Report 97-01, LIMAV, Universit\u00e9 de Valenciennes, January 1997.","DOI":"10.1006\/jpdc.1997.1371"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB24","doi-asserted-by":"crossref","unstructured":"H. Ohta, Y. Saito, M. Kainaga, H. Ono, Optimal tile size adjustment in compiling for general DOACROSS loop nests, in: Supercomputing\u201995, pp. 270\u2013279. ACM Press, 1995.","DOI":"10.1145\/224538.224571"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB25","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/0167-9260(94)90019-1","article-title":"(Pen)-ultimate tiling","volume":"17","author":"Boulet","year":"1994","journal-title":"Integration, the VLSI Journal"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB26","unstructured":"P. Calland, T. Risset, Precise tiling for uniform loop nests, Technical Report 94-29, Ecole Normale Superieure de Lyon, September. 1994."},{"issue":"2","key":"10.1016\/S0140-3664(99)00073-0_BIB27","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/0743-7315(92)90027-K","article-title":"Tiling multidimensional iteration spaces for multicomputers","volume":"16","author":"Ramanujam","year":"1992","journal-title":"Journal of Parallel and Distributed Computing"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB28","unstructured":"R. Schreiber, J.J. Dongarra, Automatic blocking of nested loops. Technical Report 90.38, RIACS, May 1990."},{"issue":"1","key":"10.1016\/S0140-3664(99)00073-0_BIB29","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1006\/jpdc.1997.1310","article-title":"Communication\u2014minimal tiling of uniform dependence loops","volume":"42","author":"Xue","year":"1997","journal-title":"Journal of Parallel Distributed Computing"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB30","unstructured":"W.K. Kaplow, B.K. Szymanski, Tiling for parallel execution\u2014optimizing node cache performance, in: Workshop on Challenges in Compiling for Scaleable Parallel Systems, Eighth IEEE Symposium on Parallel and Distributed Processing, January 1996."},{"issue":"6","key":"10.1016\/S0140-3664(99)00073-0_BIB31","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1023\/A:1018734612524","article-title":"Reuse-driven tiling for improving data locality","volume":"26","author":"Xue","year":"1998","journal-title":"International Journal of Parallel Programming"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB32","unstructured":"M. Zaki, W. Li, M. Cierniak, Performance impact of processor and memory heterogeneity in a network of machines, in: Proc. of the 4th Heterogeneous Computing Workshop, Santa Barbara, California, April 1995."},{"key":"10.1016\/S0140-3664(99)00073-0_BIB33","unstructured":"J.M. Chambers, T.M. Hastie, Statistical Models in S. 0-534-16764-0, Wadsworth Inc., 1992."},{"key":"10.1016\/S0140-3664(99)00073-0_BIB34","unstructured":"S. Bokhari, Communication overhead on the inter paragon, IBM-SP2 and meiko CS-2, Technical Report TR-28, NASA Langley Research Center, August 1995."},{"key":"10.1016\/S0140-3664(99)00073-0_BIB35","article-title":"Theory of Linear and Integer Programming","author":"Schrijver","year":"1986"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB36","unstructured":"F. Irigoin, R. Triolet, Computing dependence direction vectors and dependence cones with linear systems, Technical Report No. E94, Centre d'autmatique et informatique, September 1987."},{"key":"10.1016\/S0140-3664(99)00073-0_BIB37","doi-asserted-by":"crossref","unstructured":"R. Sakellariou, J.R. Gurd, Compile-time minimisation of load imbalance in loop nests. In Proceedings of the 11th International Conference on Supercomputing (ICS\u201997), Vienna, July 1997, pp. 277\u2013284.","DOI":"10.1145\/263580.263811"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB38","unstructured":"P. Tang, P.C. Yew, The processor self-scheduling for multiple nested parallel loops, in: Proc. of \u201986 International Conference on Parallel Processing, 1986."},{"issue":"1","key":"10.1016\/S0140-3664(99)00073-0_BIB39","doi-asserted-by":"crossref","first-page":"1425","DOI":"10.1109\/TC.1987.5009495","article-title":"Guided self-scheduling: a practical scheduling scheme for parallel supercomputers","volume":"36","author":"Polychronopoulos","year":"1987","journal-title":"IEEE Transaction on Computers"},{"key":"10.1016\/S0140-3664(99)00073-0_BIB40","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1109\/SUPERC.1992.236705","article-title":"Using processor affinity in loop scheduling on shared-memory multiprocessors","author":"Markatos","year":"1992","journal-title":"Proc. of Supercomputing \u201992"}],"container-title":["Computer Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0140366499000730?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0140366499000730?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,2,5]],"date-time":"2020-02-05T06:05:55Z","timestamp":1580882755000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0140366499000730"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1999,7]]},"references-count":40,"journal-issue":{"issue":"11","published-print":{"date-parts":[[1999,7]]}},"alternative-id":["S0140366499000730"],"URL":"https:\/\/doi.org\/10.1016\/s0140-3664(99)00073-0","relation":{},"ISSN":["0140-3664"],"issn-type":[{"value":"0140-3664","type":"print"}],"subject":[],"published":{"date-parts":[[1999,7]]}}}