{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:09:57Z","timestamp":1725548997260},"publisher-location":"Berlin, Heidelberg","reference-count":16,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540307815"},{"type":"electronic","value":"9783540316121"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2005]]},"DOI":"10.1007\/11596110_21","type":"book-chapter","created":{"date-parts":[[2005,12,15]],"date-time":"2005-12-15T00:39:40Z","timestamp":1134607180000},"page":"309-328","source":"Crossref","is-referenced-by-count":1,"title":["Removing Impediments to Loop Fusion Through Code Transformations"],"prefix":"10.1007","author":[{"given":"Bob","family":"Blainey","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Barton","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jos\u00e9 Nelson","family":"Amaral","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Lim, W., Liao, S.-W., Lam, M.S.: Blocking and array contraction across arbitrarily nested loops using affine partitioning. In: Proceedings of the ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, June 2001, pp. 103\u2013112 (2001)","DOI":"10.1145\/379539.379586"},{"issue":"4","key":"21_CR2","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1145\/197405.197406","volume":"26","author":"D.F. Bacon","year":"1994","unstructured":"Bacon, D.F., Graham, S.L., Sharp, O.J.: Compiler transformations for high performance computing. ACM Computing Surveys\u00a026(4), 345\u2013420 (1994)","journal-title":"ACM Computing Surveys"},{"key":"21_CR3","unstructured":"Behling, S., Bell, R., Farrell, P., Holthoff, H., O\u2019Connell, F., Weir, W.: The power4 processor introduction and tuning guide. Technical Report SG24-7041-00, IBM (November 2001)"},{"key":"21_CR4","doi-asserted-by":"crossref","unstructured":"Ding, C., Kennedy, K.: The memory bandwidth bottleneck and its amelioration by a compiler. In: 2000 International Parallel and Distributed Processing Symposium, Cancun, Mexico, May 2000, pp. 181\u2013189 (2000)","DOI":"10.1109\/IPDPS.2000.845980"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Ding, C., Kennedy, K.: Improving effective bandwidth through compiler enhancement of global cache reuse. In: International Parallel and Distribute Processing Symposium, San Francisco, CA (April 2001)","DOI":"10.1109\/IPDPS.2001.924975"},{"key":"21_CR6","first-page":"281","volume-title":"1992 Workshop on Languages and Compilers for Parallel Computing","author":"G.R. Gao","year":"1992","unstructured":"Gao, G.R., Olsen, R., Sarkar, V., Thekkath, R.: Collective loop fusion for array contraction. In: 1992 Workshop on Languages and Compilers for Parallel Computing, New Haven, Conn., pp. 281\u2013295. Springer, Berlin (1992)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Gupta, R., Bodik, R.: Adaptive loop transformations for scientific programs. In: IEEE Symposium on Parallel and Distributed Processing, San Antonio, Texas, October 1995, pp. 368\u2013375 (1995)","DOI":"10.1109\/SPDP.1995.530707"},{"key":"21_CR8","doi-asserted-by":"crossref","unstructured":"Hsieh, B.-M., Hind, M., Cytron, R.: Loop distribution with multiple exits. In: Proceedings of Supercomputing, November 1992, pp. 204\u2013213 (1992)","DOI":"10.1109\/SUPERC.1992.236693"},{"key":"21_CR9","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/SUPERC.1990.130048","volume-title":"Proceedings of Supercomputing","author":"K. Kennedy","year":"1990","unstructured":"Kennedy, K., McKinley, K.S.: Loop distribution with arbitrary control flow. In: Proceedings of Supercomputing, pp. 407\u2013417. IEEE Computer Society Press, Los Alamitos (1990)"},{"key":"21_CR10","unstructured":"Kennedy, K., McKinley, K.S.: Typed fusion with applications to parallel and sequential code generation. Technical Report CRPC-TR94646, Rice University, Center for Research on Parallel Computation (1994)"},{"key":"21_CR11","first-page":"301","volume-title":"1993 Workshop on Languages and Compilers for Parallel Computing","author":"K. Kennedy","year":"1993","unstructured":"Kennedy, K., McKinley, K.S.: Maximizing loop parallelism and improving data locality via loop fusion and distribution. In: 1993 Workshop on Languages and Compilers for Parallel Computing, Portland, Ore., pp. 301\u2013320. Springer, Berlin (1993)"},{"key":"21_CR12","unstructured":"Krewell, K.: Ibm\u2019s power4 unveiling continues: New details revealed at microprocessor forum 2000. In: Microprocessor Report: The Insider\u2019s Guide to Microprocessor Hardware (November 2000)"},{"issue":"1","key":"21_CR13","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1145\/356683.356686","volume":"9","author":"D.J. Kuck","year":"1977","unstructured":"Kuck, D.J.: A survey of parallel machine organization and programming. ACM Computing Surveys\u00a09(1), 29\u201359 (1977)","journal-title":"ACM Computing Surveys"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Megiddo, N., Sarkar, V.: Optimal weighted loop fusion for parallel programs. In: ACM Symposium on Parallel Algorithms and Architectures, pp. 282\u2013291 (1997)","DOI":"10.1145\/258492.258520"},{"key":"21_CR15","unstructured":"Muraoka, Y.: Parallelism Exposure and Exploitation in Programs. PhD thesis, University of Illinois at Urbana Champaign, Dept. of Computer Science, Report No. 71-424 (February 1971)"},{"issue":"6","key":"21_CR16","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1093\/comjnl\/40.6.340","volume":"40","author":"S. Singhai","year":"1997","unstructured":"Singhai, S., McKinley, K.: A parameterized loop fusion algorithm for improving parallelism and cache locality. The Computer Journal\u00a040(6), 340\u2013355 (1997)","journal-title":"The Computer Journal"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11596110_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,3,12]],"date-time":"2019-03-12T09:21:22Z","timestamp":1552382482000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11596110_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005]]},"ISBN":["9783540307815","9783540316121"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/11596110_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2005]]}}}