{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T00:15:18Z","timestamp":1649031318473},"reference-count":25,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2003,2,1]],"date-time":"2003-02-01T00:00:00Z","timestamp":1044057600000},"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":["Parallel Computing"],"published-print":{"date-parts":[[2003,2]]},"DOI":"10.1016\/s0167-8191(02)00223-5","type":"journal-article","created":{"date-parts":[[2003,1,17]],"date-time":"2003-01-17T19:52:57Z","timestamp":1042833177000},"page":"209-239","source":"Crossref","is-referenced-by-count":2,"title":["Optimal task scheduling at run time to exploit intra-tile parallelism"],"prefix":"10.1016","volume":"29","author":[{"given":"Fabrice","family":"Rastello","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amit","family":"Rao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Santosh","family":"Pande","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"9","key":"10.1016\/S0167-8191(02)00223-5_BIB1","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1109\/71.466632","article-title":"Automatic partitioning of parallel loops and data arrays for distributed shared-memory multiprocessors","volume":"6","author":"Agarwal","year":"1995","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB2","doi-asserted-by":"crossref","unstructured":"J.M. Anderson, M.S. Lam, Global optmizations for parallelism and locality on scalable parallel machines, in: Proceedings of the ACM SIGPLAN \u201991 Conference on Programming Language Design and Implementation, June 1993, pp. 112\u2013125","DOI":"10.1145\/155090.155101"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB3","doi-asserted-by":"crossref","unstructured":"W.H. Chou, S.Y. Kung, Scheduling partitioned algorithms on processor arrays with limited communication supports, in: Proceedings of the International Conference on Application Specific Array Processors (ASAP), 1993, pp. 53\u201364","DOI":"10.1109\/ASAP.1993.397120"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB4","doi-asserted-by":"crossref","unstructured":"S. Coleman, K. Mckinley, Tile size selection using cache organization and data layout, in: Proceedings of the ACM SIGPLAN \u201995 Conference on Programming Language Design and Implementation, vol. 30(6), June 1995, pp. 279\u2013290","DOI":"10.1145\/207110.207162"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB5","series-title":"Parallel Computing \u201997 (ParCo97)","article-title":"Scheduling block-cyclic array redistribution","author":"Desprez","year":"1997"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB6","series-title":"Proceedings of the Conference on Parallel Architectures and Compilation Techniques (PACT \u201997)","first-page":"307","article-title":"Determining the idle time of a tiling: new results","author":"Desprez","year":"1997"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB7","series-title":"Europar\u201996 Parallel Processing","first-page":"165","article-title":"Optimal grain size computation for pipelined algorithms","volume":"vol. 1123","author":"Desprez","year":"1996"},{"issue":"4","key":"10.1016\/S0167-8191(02)00223-5_BIB8","doi-asserted-by":"crossref","first-page":"465","DOI":"10.1109\/71.149964","article-title":"Partitioning and labeling of loops by unimodular transformations","volume":"3","author":"D\u2019Hollander","year":"1992","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB9","unstructured":"M. Dion, Alignement et distribution en parall\u00e9lisation Automatique, PhD thesis, Ecole Normale Sup\u00e9rieure de Lyon, January 1996"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB10","series-title":"Proceedings of Euromicro Workshop on Parallel and Distributed Processing","first-page":"571","article-title":"Resource-constrained scheduling of partitioned algorithms on processor arrays","author":"Dion","year":"1995"},{"issue":"6","key":"10.1016\/S0167-8191(02)00223-5_BIB11","doi-asserted-by":"crossref","first-page":"316","DOI":"10.4153\/CJM-1954-030-1","article-title":"The hook graphs of the symmetric group","author":"Frame","year":"1954","journal-title":"Canadian Journal of Mathematics"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB12","doi-asserted-by":"crossref","unstructured":"F. Irigoin, R. Triolet, Supernode partitioning, in: 15th Symposium on Principles of Programming Languages (POPL XV), January 1988, pp. 319\u2013329","DOI":"10.1145\/73560.73588"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB13","unstructured":"W.K. Kaplow, B.K. Szymanski, Tiling for parallel execution\u2013\u2013optimizing node cache performance, in: Workshop on Challenges in Compiling for Scaleable Parallel Systems, Eighth IEEE Symposium on Parallel and Distributed Processing, 1996"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB14","doi-asserted-by":"crossref","unstructured":"W. Li, Compiler cache optimizations for banded matrix problems, in: Conference proceedings of the 1995 International Conference on Supercomputing, July 1995, pp. 21\u201330","DOI":"10.1145\/224538.224541"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB15","unstructured":"MPI Forum, MPI: a message passing interface standard, June 1995. Version 1.1, http:\/\/www.mcs.anl.gov\/mpi\/"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB16","doi-asserted-by":"crossref","unstructured":"H. Ohta, Y. Saito, M. Kainaga, H. Ona, Optimal tile size adjustment in compiling general DOACROSS loop nests, in: Conference Proceedings of the 1995 International Conference on Supercomputing, July 1995, pp. 270\u2013279","DOI":"10.1145\/224538.224571"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB17","first-page":"35","article-title":"A compile time partitioning method for DOALL loops on distributed memory systems","volume":"vol. III (Software)","author":"Pande","year":"1996"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB18","unstructured":"P.M. Petersen, D.A. Padua, Experimental evaluation of some data dependence tests (extended abstract). Technical report, Center for Supercomputing Research and Development, University of Illinois at Urbana-Champaign, February 1991, CSRD Report 1080"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB19","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\/S0167-8191(02)00223-5_BIB20","unstructured":"Stanford University. The SUIF Library, 1994. This manual is a part of the SUIF compiler documentation set, http:\/\/suif.stanford.edu\/"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB21","doi-asserted-by":"crossref","unstructured":"P. Tang, J.N. Zigman, Reducing data communication overhead for DOACROSS loop nests, in: Conference proceedings of the 1994 International Conference on Supercomputing, July 1994, pp. 44\u201353","DOI":"10.1145\/181181.181261"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB22","unstructured":"C.-W. Tseng, An optimizing Fortran D compiler for mimd distributed memory machines, Ph.D. thesis, Technical report, Center for Research in Parallel Computing, Rice University, January 1993, CRPC-TR93291-S"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB23","doi-asserted-by":"crossref","unstructured":"M.E. Wolf, M.S. Lam, A data locality optimizing algorithm, in: Proceedings of the ACM SIGPLAN \u201991 Conference on Programming Language Design and Implementation, June 1991, pp. 30\u201344","DOI":"10.1145\/113445.113449"},{"key":"10.1016\/S0167-8191(02)00223-5_BIB24","doi-asserted-by":"crossref","unstructured":"M.J. Wolfe, More iteration space tiling, in: Proceedings of Supercomputing \u201989, November 1989, pp. 655\u2013664","DOI":"10.1145\/76263.76337"},{"issue":"4","key":"10.1016\/S0167-8191(02)00223-5_BIB25","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"}],"container-title":["Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819102002235?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167819102002235?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2020,3,12]],"date-time":"2020-03-12T05:01:40Z","timestamp":1583989300000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167819102002235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2003,2]]},"references-count":25,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2003,2]]}},"alternative-id":["S0167819102002235"],"URL":"https:\/\/doi.org\/10.1016\/s0167-8191(02)00223-5","relation":{},"ISSN":["0167-8191"],"issn-type":[{"value":"0167-8191","type":"print"}],"subject":[],"published":{"date-parts":[[2003,2]]}}}