{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T14:24:26Z","timestamp":1761920666294},"publisher-location":"Cham","reference-count":26,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030346263"},{"type":"electronic","value":"9783030346270"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-34627-0_6","type":"book-chapter","created":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T14:02:55Z","timestamp":1573567375000},"page":"70-77","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Towards an Achievable Performance for the Loop Nests"],"prefix":"10.1007","author":[{"given":"Aniket","family":"Shivam","sequence":"first","affiliation":[]},{"given":"Neftali","family":"Watkinson","sequence":"additional","affiliation":[]},{"given":"Alexandru","family":"Nicolau","sequence":"additional","affiliation":[]},{"given":"David","family":"Padua","sequence":"additional","affiliation":[]},{"given":"Alexander V.","family":"Veidenbaum","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,11,13]]},"reference":[{"issue":"4","key":"6_CR1","doi-asserted-by":"publisher","first-page":"491","DOI":"10.1145\/29873.29875","volume":"9","author":"R Allen","year":"1987","unstructured":"Allen, R., Kennedy, K.: Automatic translation of fortran programs to vector form. ACM Trans. Program. Lang. Syst. 9(4), 491\u2013542 (1987)","journal-title":"ACM Trans. Program. Lang. Syst."},{"issue":"3","key":"6_CR2","first-page":"29","volume":"14","author":"AH Ashouri","year":"2017","unstructured":"Ashouri, A.H., et al.: MiCOMP: mitigating the compiler phase-ordering problem using optimization sub-sequences and machine learning. ACM Trans. Arch. Code Optim. (TACO) 14(3), 29 (2017)","journal-title":"ACM Trans. Arch. Code Optim. (TACO)"},{"key":"6_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1007\/978-3-540-78791-4_9","volume-title":"Compiler Construction","author":"U Bondhugula","year":"2008","unstructured":"Bondhugula, U., Baskaran, M., Krishnamoorthy, S., Ramanujam, J., Rountev, A., Sadayappan, P.: Automatic transformations for communication-minimized parallelization and locality optimization in the polyhedral model. In: Hendren, L. (ed.) CC 2008. LNCS, vol. 4959, pp. 132\u2013146. Springer, Heidelberg (2008). \nhttps:\/\/doi.org\/10.1007\/978-3-540-78791-4_9"},{"key":"6_CR4","unstructured":"Callahan, D., Dongarra, J., Levine, D.: Vectorizing compilers: a test suite and results. In: Proceedings of the 1988 ACM\/IEEE Conference on Supercomputing, Supercomputing 1988, pp. 98\u2013105. IEEE Computer Society Press, Los Alamitos (1988)"},{"key":"6_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/978-3-642-45293-2_15","volume-title":"Advanced Parallel Processing Technologies","author":"R Cammarota","year":"2013","unstructured":"Cammarota, R., Beni, L.A., Nicolau, A., Veidenbaum, A.V.: Optimizing program performance via similarity, using a feature-agnostic approach. In: Wu, C., Cohen, A. (eds.) APPT 2013. LNCS, vol. 8299, pp. 199\u2013213. Springer, Heidelberg (2013). \nhttps:\/\/doi.org\/10.1007\/978-3-642-45293-2_15"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Cavazos, J., et al.: Rapidly selecting good compiler optimizations using performance counters. In: International Symposium on Code Generation and Optimization, CGO 2007, pp. 185\u2013197. IEEE (2007)","DOI":"10.1109\/CGO.2007.32"},{"key":"6_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1362-8","volume-title":"Scheduling and Automatic Parallelization","author":"A Darte","year":"2012","unstructured":"Darte, A., Robert, Y., Vivien, F.: Scheduling and Automatic Parallelization. Springer, New York (2012). \nhttps:\/\/doi.org\/10.1007\/978-1-4612-1362-8"},{"issue":"1","key":"6_CR8","first-page":"2349","volume":"14","author":"J Dem\u0161ar","year":"2013","unstructured":"Dem\u0161ar, J., et al.: Orange: data mining toolbox in python. J. Mach. Learn. Res. 14(1), 2349\u20132353 (2013)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"6_CR9","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/s10766-010-0161-2","volume":"39","author":"G Fursin","year":"2011","unstructured":"Fursin, G., et al.: Milepost GCC: machine learning enabled self-tuning compiler. Int. J. Parallel Program. 39(3), 296\u2013327 (2011)","journal-title":"Int. J. Parallel Program."},{"issue":"OOPSLA","key":"6_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3276496","volume":"2","author":"Zhangxiaowen Gong","year":"2018","unstructured":"Gong, Z., et al.: An empirical study of the effect of source-level loop transformations on compiler stability. Proc. ACM Program. Lang. 2(OOPSLA), 126:1\u2013126:29 (2018)","journal-title":"Proceedings of the ACM on Programming Languages"},{"issue":"04","key":"6_CR11","doi-asserted-by":"publisher","first-page":"1250010","DOI":"10.1142\/S0129626412500107","volume":"22","author":"T Grosser","year":"2012","unstructured":"Grosser, T., Groesslinger, A., Lengauer, C.: Polly - performing polyhedral optimizations on a low-level intermediate representation. Parallel Process. Lett. 22(04), 1250010 (2012)","journal-title":"Parallel Process. Lett."},{"key":"6_CR12","volume-title":"Optimizing Compilers for Modern Architectures: A Dependence-Based Approach","author":"K Kennedy","year":"2002","unstructured":"Kennedy, K., Allen, J.R.: Optimizing Compilers for Modern Architectures: A Dependence-Based Approach. Morgan Kaufmann Publishers Inc., San Francisco (2002)"},{"key":"6_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/3-540-57502-2_60","volume-title":"Languages and Compilers for Parallel Computing","author":"W Li","year":"1993","unstructured":"Li, W., Pingali, K.: A singular loop transformation framework based on non-singular matrices. In: Banerjee, U., Gelernter, D., Nicolau, A., Padua, D. (eds.) LCPC 1992. LNCS, vol. 757, pp. 391\u2013405. Springer, Heidelberg (1993). \nhttps:\/\/doi.org\/10.1007\/3-540-57502-2_60"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Lim, A.W., Cheong, G.I., Lam, M.S.: An affine partitioning algorithm to maximize parallelism and minimize communication. In: Proceedings of the 13th International Conference on Supercomputing, ICS 1999, pp. 228\u2013237. ACM, New York (1999)","DOI":"10.1145\/305138.305197"},{"issue":"3\u20134","key":"6_CR15","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1016\/S0167-8191(98)00021-0","volume":"24","author":"AW Lim","year":"1998","unstructured":"Lim, A.W., Lam, M.S.: Maximizing parallelism and minimizing synchronization with affine partitions. Parallel Comput. 24(3\u20134), 445\u2013475 (1998)","journal-title":"Parallel Comput."},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Lim, A.W., Liao, S.-W., Lam, M.S.: Blocking and array contraction across arbitrarily nested loops using affine partitioning. In: Proceedings of the Eighth ACM SIGPLAN Symposium on Principles and Practices of Parallel Programming, PPoPP 2001, pp. 103\u2013112. ACM, New York (2001)","DOI":"10.1145\/568014.379586"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Maleki, S., et al.: An evaluation of vectorizing compilers. In: 2011 International Conference on Parallel Architectures and Compilation Techniques, pp. 372\u2013382, October 2011","DOI":"10.1109\/PACT.2011.68"},{"issue":"9","key":"6_CR18","doi-asserted-by":"publisher","first-page":"763","DOI":"10.1109\/TC.1980.1675676","volume":"C-29","author":"Padua","year":"1980","unstructured":"Padua, D.A., Kuck, D.J., Lawrie, D.H.: High-speed multiprocessors and compilation techniques. IEEE Trans. Comput. C-29(9), 763\u2013776 (1980)","journal-title":"IEEE Transactions on Computers"},{"issue":"12","key":"6_CR19","doi-asserted-by":"publisher","first-page":"1184","DOI":"10.1145\/7902.7904","volume":"29","author":"DA Padua","year":"1986","unstructured":"Padua, D.A., Wolfe, M.: Advanced compiler optimizations for supercomputers. Commun. ACM 29(12), 1184\u20131201 (1986)","journal-title":"Commun. ACM"},{"key":"6_CR20","unstructured":"Polly: LLVM Framework for High-Level Loop and Data-Locality Optimizations. \nhttp:\/\/polly.llvm.org"},{"key":"6_CR21","unstructured":"PolyBench\/C 4.1. \nhttp:\/\/web.cse.ohio-state.edu\/~pouchet\/software\/polybench\/"},{"issue":"4","key":"6_CR22","first-page":"50","volume":"8","author":"K Stock","year":"2012","unstructured":"Stock, K., Pouchet, L.-N., Sadayappan, P.: Using machine learning to improve automatic vectorization. ACM Trans. Arch. Code Optim. (TACO) 8(4), 50 (2012)","journal-title":"ACM Trans. Arch. Code Optim. (TACO)"},{"issue":"6","key":"6_CR23","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1145\/1543135.1542496","volume":"44","author":"Georgios Tournavitis","year":"2009","unstructured":"Tournavitis, G., et al.: Towards a holistic approach to auto-parallelization: integrating profile-driven parallelism detection and machine-learning based mapping. In: Proceedings of the 30th ACM SIGPLAN Conference on Programming Language Design and Implementation, PLDI 2009, pp. 177\u2013187. ACM, New York (2009)","journal-title":"ACM SIGPLAN Notices"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Z., O\u2019Boyle, M.F.: Mapping parallelism to multi-cores: a machine learning based approach. In: Proceedings of the 14th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP 2009, pp. 75\u201384. ACM, New York (2009)","DOI":"10.1145\/1504176.1504189"},{"key":"6_CR25","unstructured":"Watkinson, N., et al.: Using hardware counters to predict vectorization. In: Languages and Compilers for Parallel Computing, LCPC 2017. Springer, in Press"},{"key":"6_CR26","volume-title":"High Performance Compilers for Parallel Computing","author":"MJ Wolfe","year":"1995","unstructured":"Wolfe, M.J.: High Performance Compilers for Parallel Computing. Addison-Wesley Longman Publishing Co. Inc., Boston (1995)"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-34627-0_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,11,12]],"date-time":"2019-11-12T14:04:03Z","timestamp":1573567443000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-34627-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030346263","9783030346270"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-34627-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"13 November 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LCPC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Workshop on Languages and Compilers for Parallel Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Salt Lake City, UT","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 October 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"lcpc2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.lcpcworkshop.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Confy","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"26","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"54% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}