{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T23:20:58Z","timestamp":1725664858125},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540610533"},{"type":"electronic","value":"9783540499398"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[1996]]},"DOI":"10.1007\/3-540-61053-7_49","type":"book-chapter","created":{"date-parts":[[2012,2,26]],"date-time":"2012-02-26T21:13:02Z","timestamp":1330290782000},"page":"1-16","source":"Crossref","is-referenced-by-count":4,"title":["Pipelining-dovetailing: A transformation to enhance software pipelining for nested loops"],"prefix":"10.1007","author":[{"given":"Jian","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2005,6,7]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"B. R. Rau and J.A. Fisher. Instruction-level parallel processing: History, overview and perspective. The Journal of Supercomputing, 7(1), January 1993.","DOI":"10.1007\/BF01205181"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"B.R. Rau and C.D. Glaeser. Some scheduling techniques and an easily schedulable horizontal architecture for high performance scientific computing. In proceedings of the 14th International Symposium on Microprogramming and Microarchitectures (MICRO-14), pages 183\u2013198, October 1981.","DOI":"10.1145\/1014192.802449"},{"key":"1_CR3","first-page":"213","volume-title":"Languages and Compilers for Parallel Computing","author":"K. Ebcioglu","year":"1989","unstructured":"K. Ebcioglu and T. Nakatani. A new compilation technique for paralelizing loops with unpredictable branches on a vliw architecture. In A. Nicolau D. Gelernter and D. Padua, editors, Languages and Compilers for Parallel Computing, pages 213\u2013229. Pitman\/The MIT Press, London, 1989."},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"M.S. Lam. A Systolic Array Optimizing Compiler. PhD thesis, CMU, 1987. CMU-CS-87-187.","DOI":"10.1007\/978-1-4613-1705-0"},{"key":"1_CR5","unstructured":"C. Eisenbeis, W. Jalby, and A. Lichnewsky. Compile-time optimization of memory and register usage on the cray-2. In proceedings of the second Workshop on Languages and Compilers, 1989."},{"key":"1_CR6","first-page":"274","volume-title":"Languages and Compilers for Parallel Computing","author":"A. Aiken","year":"1991","unstructured":"A. Aiken and A. Nicolau. A realistic resource-constrainted software pipelining algorithm. In T. Gross A. Nicolau, D. Gelernter and D. Padua, editors, Languages and Compilers for Parallel Computing, pages 274\u2013290. Pitman\/The MIT Press, London, 1991."},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"R. Huff. Lifetime-sensitive modulo scheduling. In proceedings of ACM SIGPLAN PLDI, pages 258\u2013267, June 1993.","DOI":"10.1145\/173262.155115"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Q. Ning and G.R. Gao. A novel framework of register allocation for software pipelining. In proceedings of POPL, January 1993.","DOI":"10.1145\/158511.158519"},{"issue":"3","key":"1_CR9","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1007\/BF02577737","volume":"22","author":"J. Wang","year":"1994","unstructured":"Jian Wang, Christine Eisenbeis, Martin Jourdan, and Bogong Su. Decomposed Software Pipelining: A new perspective and a new approach. International Journal of Parallel Programming, 22(3):357\u2013379, 1994.","journal-title":"International Journal of Parallel Programming"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Michael E. Wolf and M. S. Lam. A loop transformation theory and an algorithm to maximize parallelism. IEEE Transactions on Parallel and Distributed Systems, 2(4), 1991.","DOI":"10.1109\/71.97902"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"U. Banerjee. Loop Transformations for Restructuring Compilers. Kluwer Academic, 1993.","DOI":"10.1007\/b102311"},{"key":"1_CR12","unstructured":"A. Darte, L. Risset, and Y. Robert. Loop nest scheduling and transformations. In proceedings of Environments and Tools for Parallel Scientific Computing, 1992."},{"key":"1_CR13","unstructured":"Amy W. Lim and M. S. Lam. Communication-free parallelization via affine transformations. In proceedings of LCPC'94, 1994."},{"key":"1_CR14","unstructured":"F. Gasperoni. Compilation techniques for vliw architectures. Technical Report TR435, New York University, March 1989."},{"key":"1_CR15","volume-title":"Supercompilers for Parallel and Vector Computers","author":"H. Zima","year":"1990","unstructured":"Hans Zima and Barbara Chapman. Supercompilers for Parallel and Vector Computers. ACM Press, New York, 1990."},{"key":"1_CR16","unstructured":"U. Banerjee. Unimodular transformations of double loops. In proceedings of the 3rd Workshop on Languages and Compilers for Parallel Computing, 1990."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Bogong Su, Shiyuan Ding, Jian Wang, and Jinshi Xia. GURPR-a method for global software pipelining. In proceedings of the 20th Annual International Workshop on Microprogramming (MICRO-20), pages 88\u201396. ACM and IEEE, November 1987.","DOI":"10.1145\/255305.255322"},{"key":"1_CR18","unstructured":"Guang R. Gao, Qi Ning, and Vincent Van Dongen. Extending software pipelining techniques for scheduling nested loops. In proceedings of the 6th Workshop on Languages and Compilers for Parallel Computing, 1993."},{"key":"1_CR19","unstructured":"Ki chang Kim and Alexandru Nicolau. Parallelizing tightly nested loops. In proceedings of International Conference on Parallel Processing, 1991."},{"key":"1_CR20","unstructured":"P. Feautrier. A collection of papers on the systematic construction of parallel and distributed programs. Technical Report Hors-serie, Lab. MASI, Universite P. et M. Curie, 1992."},{"key":"1_CR21","volume-title":"Optimizing Supercompilers for Supercomputers","author":"M. J. Wolfe","year":"1989","unstructured":"M. J. Wolfe. Optimizing Supercompilers for Supercomputers. MIT Press, Cambridge, MA, 1989."}],"container-title":["Lecture Notes in Computer Science","Compiler Construction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/3-540-61053-7_49.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,17]],"date-time":"2020-11-17T21:03:48Z","timestamp":1605647028000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/3-540-61053-7_49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1996]]},"ISBN":["9783540610533","9783540499398"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/3-540-61053-7_49","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[1996]]}}}