{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T23:10:01Z","timestamp":1746400201627,"version":"3.40.4"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319099668"},{"type":"electronic","value":"9783319099675"}],"license":[{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2014,1,1]],"date-time":"2014-01-01T00:00:00Z","timestamp":1388534400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-09967-5_17","type":"book-chapter","created":{"date-parts":[[2014,9,30]],"date-time":"2014-09-30T15:10:04Z","timestamp":1412089804000},"page":"292-306","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Compile Time Modeling of Off-Chip Memory Bandwidth for Parallel Loops"],"prefix":"10.1007","author":[{"given":"Munara","family":"Tolubaeva","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghong","family":"Yan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barbara","family":"Chapman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2014,10,1]]},"reference":[{"unstructured":"The Open64 compiler. http:\/\/open64.sourceforge.net","key":"17_CR1"},{"unstructured":"Agarwal, D., Liu, W., Yeung, D.: Exploiting application-level information to reduce memory bandwidth consumption. In: Proceedings of 4th Workshop on Complexity-Effective Design (2003)","key":"17_CR2"},{"issue":"3","key":"17_CR3","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1177\/109434209100500306","volume":"5","author":"DH Bailey","year":"1991","unstructured":"Bailey, D.H., Barszcz, E., Barton, J.T., Browning, D.S., Carter, R.L., Dagum, D., Fatoohi, R.A., Frederickson, P.O., Lasinski, T.A., Schreiber, R.S., Simon, H.D., Venkatakrishnan, V., Weeratunga, S.K.: The NAS parallel benchmarks. Int. J. Supercomput. Appl. 5(3), 63\u201373 (1991)","journal-title":"Int. J. Supercomput. Appl."},{"unstructured":"Black, N., Moore, S., Weisstein, E.W.: Jacobi method. http:\/\/mathworld.wolfram.com\/JacobiMethod.html","key":"17_CR4"},{"issue":"2","key":"17_CR5","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/BF00939613","volume":"76","author":"ID Coope","year":"1993","unstructured":"Coope, I.D.: Circle fitting by linear and nonlinear least squares. J. Optim. Theor. Appl. 76(2), 381\u2013388 (1993)","journal-title":"J. Optim. Theor. Appl."},{"doi-asserted-by":"crossref","unstructured":"Ding, C., Kennedy, K.: Improving cache performance in dynamic applications through data and computation reorganization at run time. In: Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation, pp. 229\u2013241 (1999)","key":"17_CR6","DOI":"10.1145\/301631.301670"},{"unstructured":"Ding, C. Kennedy, K.: The memory bandwidth bottleneck and its amelioration by a compiler. In: Proceedings of the 14th International Symposium on Parallel and Distributed Processing (2000)","key":"17_CR7"},{"doi-asserted-by":"crossref","unstructured":"Jeremiassen, T., Eggers, S.J.: Reducing false sharing on shared memory multiprocessors through compile time data transformations. In: Proceedings of the Fifth ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp. 179\u2013188 (1994)","key":"17_CR8","DOI":"10.1145\/209937.209955"},{"issue":"18","key":"17_CR9","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1587\/elex.9.1461","volume":"9","author":"H-J Lee","year":"2012","unstructured":"Lee, H.-J., Cho, W.-C., Chung, E.-Y.: Analytical memory bandwidth model for many-core processor based systems. IEICE Electron. Express 9(18), 1461\u20131466 (2012)","journal-title":"IEICE Electron. Express"},{"doi-asserted-by":"crossref","unstructured":"Liu, F., Jiang, X., Solihin, Y.: Understanding how off-chip memory bandwidth partitioning in chip multiprocessors affects system performance. In: Proceedings of High Performance Computer Architecture (HPCA), pp. 1\u201312 (2010)","key":"17_CR10","DOI":"10.1109\/HPCA.2010.5416655"},{"doi-asserted-by":"crossref","unstructured":"Majo, Z., Gross, T.R.: Memory system performance in a numa multicore multiprocessor. In Proceedings of the 4th Annual International Conference on Systems and Storage (SYSTOR), pp. 12:1\u201312:10 (2011)","key":"17_CR11","DOI":"10.1145\/1987816.1987832"},{"doi-asserted-by":"crossref","unstructured":"Mandal, A., Fowler, R., Porterfield. Modeling memory concurrency for multi-socket multi-core systems. In: ISPASS, pp. 66\u201375 (2010)","key":"17_CR12","DOI":"10.1109\/ISPASS.2010.5452064"},{"doi-asserted-by":"crossref","unstructured":"Marchal, P., G\u00f3mez, J.I., Catthoor, F.: Optimizing the memory bandwidth with loop fusion. In: Proceedings of the 2nd IEEE\/ACM\/IFIP International Conference on Hardware\/Software Codesign and System Synthesis, pp. 188\u2013193 (2004)","key":"17_CR13","DOI":"10.1145\/1016720.1016767"},{"unstructured":"McCalpin, J.D.: Memory bandwidth and machine balance in current high performance computers. In: IEEE Computer Society Technical Committee on Computer Architecture (TCCA) Newsletter, pp. 19\u201325 (1995)","key":"17_CR14"},{"issue":"4","key":"17_CR15","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1145\/233561.233564","volume":"18","author":"KS McKinley","year":"1996","unstructured":"McKinley, K.S., Carr, S., Tseng, C.-W.: Improving data locality with loop transformations. ACM Trans. Program. Lang. Syst. 18(4), 424\u2013453 (1996)","journal-title":"ACM Trans. Program. Lang. Syst."},{"unstructured":"Mohideen, R.M., Sankaranarayanan, V.: An analytical model for optimum off-chip memory bandwidth partitioning in multicore architectures. In: Proceedings of the 2nd International Conference on Computer Science and Information Technology (ICCSIT) (2012)","key":"17_CR16"},{"doi-asserted-by":"crossref","unstructured":"Sandberg, A., Eklov, D., Hagersten, E.: Reducing cache pollution through detection and elimination of non-temporal memory accesses. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201311 (2010)","key":"17_CR17","DOI":"10.1109\/SC.2010.44"},{"doi-asserted-by":"crossref","unstructured":"Schuff, D., Parsons, B., Pai, V.: Multicore-aware reuse distance analysis. In: IPDPS Workshop on Performance Modeling, Evaluation, and Optimization of Ubiquitous Computing and Networked Systems (2010)","key":"17_CR18","DOI":"10.1109\/IPDPSW.2010.5470780"},{"doi-asserted-by":"crossref","unstructured":"Tolubaeva, M., Yan, Y., Chapman, B.: Compile-time detection of false sharing via loop cost modeling. In: Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 557\u2013566 (2012)","key":"17_CR19","DOI":"10.1109\/IPDPSW.2012.67"},{"doi-asserted-by":"crossref","unstructured":"Wang, R., Chen, L., Pinkston, T.M.: An analytical performance model for partitioning off-chip memory bandwidth. In: Proceedings of the IPDPS (2013)","key":"17_CR20","DOI":"10.1109\/IPDPS.2013.85"},{"doi-asserted-by":"crossref","unstructured":"Wu, X., Taylor, V.E.: Performance modeling of hybrid mpi\/openmp scientific applications on large-scale multicore cluster systems. In: CSE, pp. 181\u2013190 (2011)","key":"17_CR21","DOI":"10.1109\/CSE.2011.42"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-09967-5_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T22:57:02Z","timestamp":1746399422000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-09967-5_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319099668","9783319099675"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-09967-5_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2014]]},"assertion":[{"value":"1 October 2014","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}