{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T12:10:07Z","timestamp":1763467807256},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540693291"},{"type":"electronic","value":"9783540693307"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/978-3-540-69330-7_8","type":"book-chapter","created":{"date-parts":[[2007,5,14]],"date-time":"2007-05-14T21:16:20Z","timestamp":1179177380000},"page":"106-120","source":"Crossref","is-referenced-by-count":6,"title":["A Cache-Conscious Profitability Model for Empirical Tuning of Loop Fusion"],"prefix":"10.1007","author":[{"given":"Apan","family":"Qasem","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ken","family":"Kennedy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"8_CR1","unstructured":"Carr, S.: Memory-Hierarchy Management. PhD thesis, Dept. of Computer Science, Rice University (September 1992)"},{"key":"8_CR2","series-title":"Lecture Notes in Computer Science","volume-title":"Parallel Computing Technologies","author":"A. Darte","year":"1999","unstructured":"Darte, A.: On the complexity of loop fusion. In: Malyshkin, V.E. (ed.) PaCT 1999. LNCS, vol.\u00a01662. Springer, Heidelberg (1999)"},{"key":"8_CR3","unstructured":"Ding, C., Kennedy, K.: Resource-constrained loop fusion. Technical report, Dept. of Computer Science, Rice University (October 2000)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Ding, C., Kennedy, K.: Improving effective bandwidth through compiler enhancement of global cache reuse. In: International Parallel and Distributed Processing Symposium, San Francisco, CA (Best Paper Award) (April 2001)","DOI":"10.1109\/IPDPS.2001.924975"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Gao, G., Olsen, R., Sarkar, V., Thekkath, R.: Collective loop fusion for array contraction. In: Proceedings of the Fifth Workshop on Languages and Compilers for Parallel Computing, New Haven, CT (August 1992)","DOI":"10.1007\/3-540-57502-2_53"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Hill, M.D., Smith, A.J.: Evaluating associativity in cpu caches. IEEE Trans. Comput.\u00a038(12) (1989)","DOI":"10.1109\/12.40842"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Kennedy, K.: Fast greedy weighted fusion. In: ICS 2000: Proceedings of the 14th international conference on Supercomputing (2000)","DOI":"10.1145\/335231.335244"},{"key":"8_CR8","series-title":"Lecture Notes in Computer Science","volume-title":"Languages and Compilers for Parallel Computing","author":"K. Kennedy","year":"1994","unstructured":"Kennedy, K., McKinley, K.S.: Maximizing loop parallelism and improving data locality via loop fusion and distribution. In: Banerjee, U., Gelernter, D., Nicolau, A., Padua, D.A. (eds.) LCPC 1993. LNCS, vol.\u00a0768. Springer, Heidelberg (1994)"},{"key":"8_CR9","unstructured":"Lim, A., Lam, M.: Cache optimizations with affine partitioning. In: Proceedings of the Tenth SIAM Conference on Parallel Processing for Scientific Computing, Portsmouth, Virginia (March 2001)"},{"issue":"4","key":"8_CR10","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1145\/233561.233564","volume":"18","author":"K.S. McKinley","year":"1996","unstructured":"McKinley, K.S., Carr, S., Tseng, C.-W.: Improving data locality with loop transformations. ACMTransactions on Programming Languages and Systems\u00a018(4), 424\u2013453 (1996)","journal-title":"ACMTransactions on Programming Languages and Systems"},{"key":"8_CR11","unstructured":"Qasem, A., Kennedy, K.: Evaluating a model for cache conflict miss prediction. Technical report, Dept. of Computer Science, Rice University (October 2005)"},{"key":"8_CR12","unstructured":"Qasem, A., Kennedy, K., Mellor-Crummey, J.: Automatic tuning of whole applications using direct search and a performance-based transformation system. In: Proceedings of the Los Alamos Computer Science Institute Second Annual Symposium, Santa Fe, NM (October 2004)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Song, Y., Xu, R., Wang, C., Li, Z.: Data locality enhancement by memory reduction. In: Proceedings of the 15th ACM International Conference on Supercomputing, Sorrento, Italy (June 2001)","DOI":"10.1145\/377792.377806"},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Verdoolaege, S., Bruynooghe, M., Jenssens, G., Catthoor, F.: Multi-dimensional incremental loop fusion for data locality. In: Proceedings of the IEEE International Conference on Application Specific Systems, Architectures, and Processors (June 2003)","DOI":"10.1109\/ASAP.2003.1212826"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Wolf, M.E., Lam, M.: A data locality optimizing algorithm. In: Proceedings of the SIGPLAN 1991 Conference on Programming Language Design and Implementation, Toronto, Canada (June 1991)","DOI":"10.1145\/113445.113449"}],"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\/978-3-540-69330-7_8.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,19]],"date-time":"2020-11-19T04:57:39Z","timestamp":1605761859000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-69330-7_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540693291","9783540693307"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-69330-7_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2006]]}}}