{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T15:54:37Z","timestamp":1693842877797},"reference-count":38,"publisher":"Elsevier BV","issue":"1-2","license":[{"start":{"date-parts":[[2001,3,1]],"date-time":"2001-03-01T00:00:00Z","timestamp":983404800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2013,7,17]],"date-time":"2013-07-17T00:00:00Z","timestamp":1374019200000},"content-version":"vor","delay-in-days":4521,"URL":"https:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Theoretical Computer Science"],"published-print":{"date-parts":[[2001,3]]},"DOI":"10.1016\/s0304-3975(99)00313-8","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T21:51:54Z","timestamp":1027633914000},"page":"449-481","source":"Crossref","is-referenced-by-count":4,"title":["A theoretical foundation for program transformations to reduce cache thrashing due to true data sharing"],"prefix":"10.1016","volume":"255","author":[{"given":"Guohua","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiyuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fujie","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/S0304-3975(99)00313-8_BIB1","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1109\/71.86107","article-title":"Compile-time partitioning of iterative parallel loops to reduce cache coherence traffic","volume":"2","author":"Abraham","year":"1991","journal-title":"IEEE Trans. on Parallel Distributed Systems"},{"issue":"5","key":"10.1016\/S0304-3975(99)00313-8_BIB2","doi-asserted-by":"crossref","first-page":"341","DOI":"10.1109\/TC.1981.1675792","article-title":"On the performance enhancement of paging systems through program analysis and transformations","volume":"C-30","author":"Abu-Sufah","year":"1981","journal-title":"IEEE Trans. Comput."},{"issue":"9","key":"10.1016\/S0304-3975(99)00313-8_BIB3","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 Trans. Parallel Distributed Systems"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB4","doi-asserted-by":"crossref","unstructured":"J.R. Allen, K. Kennedy, Automatic loop interchange, Proc. SIGPLAN\u201984 Symp. on Compiler Construction, Montreal, Canada, June 1984.","DOI":"10.1145\/502874.502897"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB5","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/0743-7315(89)90001-4","article-title":"Multilevel cache hierarchies: organizations, protocols, and performance","volume":"6","author":"Baer","year":"1989","journal-title":"J. Parallel Distributed Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB6","series-title":"Dependence Analysis for Supercomputing","author":"Banerjee","year":"1988"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB7","doi-asserted-by":"crossref","unstructured":"D. Callahan, S. Carr, K. Kennedy, Improving register allocation for subscripted variables, in Proc. ACM SIGPLAN\u201990 Conf. on Programming Languages Design and Implementation, June 1990.","DOI":"10.1145\/93542.93553"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB8","doi-asserted-by":"crossref","unstructured":"S. Carr, K. Kennedy, Compiling scientific code for complex memory hierarchies, Proc. Hawaii Internat. Conf. on System Sciences, 1991, pp. 536\u2013544.","DOI":"10.1109\/HICSS.1991.183925"},{"issue":"4","key":"10.1016\/S0304-3975(99)00313-8_BIB9","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'Hollander","year":"1992","journal-title":"IEEE Trans. Parallel Distributed Systems"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB10","unstructured":"S.J. Eggers, T.E. Jeremiassen, Eliminating false sharing, Proc. 1991 Internat. Conf. on Parallel Processing, August 1991."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB11","unstructured":"J. Fang, M. Lu, A solution of cache ping-pong problem in RISC based parallel processing systems, Proc. 1991 Internat. Conf. on Parallel Processing, August 1991."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB12","unstructured":"Z. Fang, Cache or local memory thrashing and compiler strategy in parallel processing systems, Proc. 1990 Internat. Conf. on Parallel Processing, August 1990, pp. 271\u2013275."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB13","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1109\/12.223672","article-title":"An iteration partition approach for cache or local memory thrashing on parallel processing","volume":"C-42","author":"Fang","year":"1993","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB14","doi-asserted-by":"crossref","unstructured":"M. Galles, E. Williams, Performance optimizations, implementation, and verification of the SGI Challenge multiprocessor, Proc. 27th Ann. Hawaii Internat. Conf. on System Sciences, 1994.","DOI":"10.1109\/HICSS.1994.323177"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB15","doi-asserted-by":"crossref","unstructured":"K. Gallivan, W. Jalby, D. Gannon, On the problem of optimizing data transfers for complex memory systems, Proc. Supercomputing \u201988, 1988, pp. 238\u2013253.","DOI":"10.1145\/55364.55388"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB16","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1016\/0743-7315(88)90014-7","article-title":"Strategies for cache and local memory management by global program transformation","volume":"5","author":"Gannon","year":"1988","journal-title":"J. Parallel Distributed Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB17","unstructured":"M. Gupta, D. Padua, Effects of program parallelization and stripmining transformation on cache performance in a multiprocessor, Proc. 1991 Internat. Conf. on Parallel Processing, August 1991."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB18","doi-asserted-by":"crossref","unstructured":"D. Hudak, S. Abraham, Compiler techniques for data partitioning of sequentially iterated parallel loops, Proc. ACM Internat. Conf. on Supercomputing, 1990, pp. 187\u2013200.","DOI":"10.1145\/77726.255156"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB19","doi-asserted-by":"crossref","unstructured":"T.E. Jeremiassen, S.J. Eggers, Reducing false sharing on shared memory multiprocessors through compile-time data transformations, Proc. 5th ACM SIGPLAN Symp. on Principals and Practice of Parallel Programming, 1995, pp. 179\u2013188.","DOI":"10.1145\/209936.209955"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB20","unstructured":"G. Jin, F. Chen, The design and the implementation of a knowledge-based parallelizing tool, Proc. 2nd IES Inform. Technol. Conf., July 1991, Singapore."},{"issue":"5","key":"10.1016\/S0304-3975(99)00313-8_BIB21","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1109\/12.677228","article-title":"An efficient solution to the cache thrashing problem caused by true data sharing","volume":"47","author":"Jin","year":"1998","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB22","unstructured":"G. Jin, F. Chen. Loop restructuring techniques for the thrashing problem, Proc. 1992 Internat. Conf. on Parallel Architectures and Languages Europe, 1992."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB23","unstructured":"G. Jin, X. Yang, F. Chen, Loop staggering, loop staggering and loop compacting: restructuring techniques for the thrashing problem, Proc. 1991 Internat. Conf. on Parallel Processing, August 1991."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB24","unstructured":"W. Kelly, W. Pugh, Determining schedules based on performance estimation, Technical Report CS-TR-3108, University of Maryland, April 1993."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB25","unstructured":"W. Kelly, W. Pugh, A framework for unifying reordering transformations. Technical Report CS-TR-3193, University of Maryland, April 1993."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB26","doi-asserted-by":"crossref","unstructured":"W. Kelly, W. Pugh, Finding legal reordering transformations using mapping. Technical Report CS-TR-3297, University of Maryland, June 1994.","DOI":"10.1007\/BFb0025874"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB27","volume":"vol. 1","author":"Kuck","year":"1978"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB28","doi-asserted-by":"crossref","unstructured":"D. Kuck, R. Kuhn, D. Padua, B. Leasure, M. Wolfe, Dependence graphs and compiler optimizations, Proc. 8th ACM Symp. on Principle of Programming Languages (POPL), 1981.","DOI":"10.1145\/567532.567555"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB29","doi-asserted-by":"crossref","first-page":"158","DOI":"10.1016\/0743-7315(92)90030-Q","article-title":"A solution of the cache ping-pong problem in multiprocessor systems","volume":"16","author":"Lu","year":"1992","journal-title":"J. Parallel Distributed Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB30","series-title":"An Introduction to the Theory of Numbers","author":"Nivan","year":"1980"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB31","doi-asserted-by":"crossref","first-page":"1203","DOI":"10.1109\/12.30873","article-title":"Minimum distance: a method for partitioning recurrences for multiprocessors","volume":"C-38","author":"Peir","year":"1989","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB32","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":"C-36","author":"Polychronopoulos","year":"1987","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB33","doi-asserted-by":"crossref","first-page":"723","DOI":"10.1109\/12.90251","article-title":"Time optimal linear schedules for algorithms with uniform dependencies","volume":"C-40","author":"Shang","year":"1991","journal-title":"IEEE Trans. Comput."},{"issue":"3","key":"10.1016\/S0304-3975(99)00313-8_BIB34","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1109\/71.80162","article-title":"An empirical study of Fortran programs for parallelizing compilers","volume":"1","author":"Shen","year":"1990","journal-title":"IEEE Trans. Parallel Distributed Systems"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB35","doi-asserted-by":"crossref","unstructured":"K. Tomko, S. Abraham, Iteration partitioning for resolving stride conflicts on cache-coherent multiprocessors, Proc. 1993 Internat. Conf. on Parallel Processing, August 1993.","DOI":"10.1109\/ICPP.1993.107"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB36","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1109\/12.286299","article-title":"False sharing and spatial locality in multiprocessor caches","volume":"C-43","author":"Torrellas","year":"1994","journal-title":"IEEE Trans. Comput."},{"key":"10.1016\/S0304-3975(99)00313-8_BIB37","doi-asserted-by":"crossref","unstructured":"M. Wolf, M. Lam, A data locality optimizing algorithm, Proc. ACM SIGPLAN\u201991 Conf. on Program Language Design and Implementation, June 1991.","DOI":"10.1145\/113445.113449"},{"key":"10.1016\/S0304-3975(99)00313-8_BIB38","doi-asserted-by":"crossref","unstructured":"M. Wolfe, More iteration space tiling, Proc. Supercomputing\u201989, 1989.","DOI":"10.1145\/76263.76337"}],"container-title":["Theoretical Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0304397599003138?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0304397599003138?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2023,4,13]],"date-time":"2023-04-13T23:48:23Z","timestamp":1681429703000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0304397599003138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,3]]},"references-count":38,"journal-issue":{"issue":"1-2","published-print":{"date-parts":[[2001,3]]}},"alternative-id":["S0304397599003138"],"URL":"https:\/\/doi.org\/10.1016\/s0304-3975(99)00313-8","relation":{},"ISSN":["0304-3975"],"issn-type":[{"value":"0304-3975","type":"print"}],"subject":[],"published":{"date-parts":[[2001,3]]}}}