{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:48:07Z","timestamp":1772164087236,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2017,1,26]],"date-time":"2017-01-26T00:00:00Z","timestamp":1485388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2017,1,26]]},"DOI":"10.1145\/3018743.3018744","type":"proceedings-article","created":{"date-parts":[[2017,1,27]],"date-time":"2017-01-27T13:41:04Z","timestamp":1485524464000},"page":"163-177","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Simple, Accurate, Analytical Time Modeling and Optimal Tile Size Selection for GPGPU Stencils"],"prefix":"10.1145","author":[{"given":"Nirmal","family":"Prajapati","sequence":"first","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}]},{"given":"Waruna","family":"Ranasinghe","sequence":"additional","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}]},{"given":"Sanjay","family":"Rajopadhye","sequence":"additional","affiliation":[{"name":"Colorado State University, Fort Collins, CO, USA"}]},{"given":"Rumen","family":"Andonov","sequence":"additional","affiliation":[{"name":"IRISA, Rennes, France"}]},{"given":"Hristo","family":"Djidjev","sequence":"additional","affiliation":[{"name":"LANL, Los Alamos, USA"}]},{"given":"Tobias","family":"Grosser","sequence":"additional","affiliation":[{"name":"ETH, Zurich, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2017,1,26]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1012293814832"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.107"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1175\/1520-0485(1992)022%3C1486:SDTTIA%3E2.0.CO;2"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2628071.2628106"},{"key":"e_1_3_2_1_7_1","volume-title":"Bonmin Project Page. https:\/\/projects. coin-or.org\/Bonmin","author":"Bonmin","year":"2015","unstructured":"Bonmin 2016. Bonmin Project Page. https:\/\/projects. coin-or.org\/Bonmin , 2015 (accessed March 11, 2016). Bonmin 2016. Bonmin Project Page. https:\/\/projects. coin-or.org\/Bonmin, 2015 (accessed March 11, 2016)."},{"issue":"3","key":"e_1_3_2_1_8_1","first-page":"495","article-title":"Cacheoblivious dynamic programming for bioinformatics","volume":"7","author":"Chowdhury R. A.","year":"2010","unstructured":"R. A. Chowdhury , H.-S. Le , and V. Ramachandran . Cacheoblivious dynamic programming for bioinformatics . TCBB , 7 ( 3 ): 495 -- 510 , July-September 2010 . R. A. Chowdhury, H.-S. Le, and V. Ramachandran. Cacheoblivious dynamic programming for bioinformatics. TCBB, 7 (3):495--510, July-September 2010.","journal-title":"TCBB"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.70"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1362-8"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413375"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-03869-3_61"},{"key":"e_1_3_2_1_13_1","first-page":"533","volume-title":"PDPTA","author":"Dursun H.","year":"2009","unstructured":"H. Dursun , K. Nomura , W. Wang , M. Kunaseth , L. Peng , R. Seymour , R. K. Kalia , A. Nakano , and P. Vashishta . Incore optimization of high-order stencil computations . In PDPTA , pages 533 -- 538 , Las Vegas, NV , July 2009 . H. Dursun, K. Nomura, W. Wang, M. Kunaseth, L. Peng, R. Seymour, R. K. Kalia, A. Nakano, and P. Vashishta. Incore optimization of high-order stencil computations. In PDPTA, pages 533--538, Las Vegas, NV, July 2009."},{"key":"e_1_3_2_1_14_1","volume-title":"An Introduction to Numerical Methods and Analysis","author":"Epperson J. F.","year":"2007","unstructured":"J. F. Epperson . An Introduction to Numerical Methods and Analysis . Wiley-Interscience , 2007 . J. F. Epperson. An Introduction to Numerical Methods and Analysis. Wiley-Interscience, 2007."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407931"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01407835"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF01379404"},{"key":"e_1_3_2_1_18_1","volume-title":"AMPL: A Modelling Language for Mathematical Programming","author":"Fourer R.","year":"2002","unstructured":"R. Fourer , D. M. Gay , and B. W. Kernighan . AMPL: A Modelling Language for Mathematical Programming . Duxbury Press, Brooks\/ Cole Publishing Company , 2 nd edition, 2002 . R. Fourer, D. M. Gay, and B. W. Kernighan. AMPL: A Modelling Language for Mathematical Programming. Duxbury Press, Brooks\/Cole Publishing Company, 2nd edition, 2002.","edition":"2"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1088149.1088197"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/SFFCS.1999.814600"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/S1463-5003(00)00014-7"},{"key":"e_1_3_2_1_22_1","volume-title":"CGO, page 66","author":"Grosser T.","year":"2014","unstructured":"T. Grosser , A. Cohen , J. Holewinski , P. Sadayappan , and S. Verdoolaege . Hybrid hexagonal\/classical tiling for GPUs . In CGO, page 66 , Orlando , FL , Feb 2014 . T. Grosser, A. Cohen, J. Holewinski, P. Sadayappan, and S. Verdoolaege. Hybrid hexagonal\/classical tiling for GPUs. In CGO, page 66, Orlando, FL, Feb 2014."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751223"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807627"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2467268"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304619"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/1555754.1555775"},{"key":"e_1_3_2_1_28_1","unstructured":"C. John. Options Futures and Other Derivatives. Prentice Hall 2006.  C. John. Options Futures and Other Derivatives. Prentice Hall 2006."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1111583.1111589"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/1178597.1178605"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470421"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1250734.1250761"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/1034774.1034777"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161248"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.1990.145447"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.2000.6522"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542313"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1513895.1513905"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2694344.2694364"},{"key":"e_1_3_2_1_40_1","volume-title":"Multiresolution Molecular Dynamics Algorithm for Realistic Materials Modeling on Parallel Computers. Computer Physics Communications, 83(2--3):197--214","author":"Nakano A.","year":"1994","unstructured":"A. Nakano , R. K. Kalia , and P. Vashishta . Multiresolution Molecular Dynamics Algorithm for Realistic Materials Modeling on Parallel Computers. Computer Physics Communications, 83(2--3):197--214 , 1994 . A. Nakano, R. K. Kalia, and P. Vashishta. Multiresolution Molecular Dynamics Algorithm for Realistic Materials Modeling on Parallel Computers. Computer Physics Communications, 83(2--3):197--214, 1994."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2010.2"},{"key":"e_1_3_2_1_42_1","volume-title":"Friedrich-Alexander-Universitt ErlangenNrnberg","author":"Nitsure A.","year":"2006","unstructured":"A. Nitsure . Implementation and optimization of a cache oblivious lattice boltzmann algorithm. Master's thesis, Institut fr Informatic , Friedrich-Alexander-Universitt ErlangenNrnberg , July 2006 . A. Nitsure. Implementation and optimization of a cache oblivious lattice boltzmann algorithm. Master's thesis, Institut fr Informatic, Friedrich-Alexander-Universitt ErlangenNrnberg, July 2006."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161011"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02477176"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2491956.2462176"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-17179-7_30"},{"key":"e_1_3_2_1_47_1","volume-title":"Morgan Kauffman","author":"Rizk G.","year":"2010","unstructured":"G. Rizk , D. Lavenier , and S. Rajopadhye . GPU accelerated RNA folding algorithm, chapter 14 . Morgan Kauffman , 2010 . in GPU Computing Gems 4, editor: W-M. Hwu. G. Rizk, D. Lavenier, and S. Rajopadhye. GPU accelerated RNA folding algorithm, chapter 14. Morgan Kauffman, 2010. in GPU Computing Gems 4, editor: W-M. Hwu."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2012.50"},{"key":"e_1_3_2_1_49_1","first-page":"101","volume-title":"Analytical Bounds for Optimal Tile Size Selection","author":"Shirako J.","year":"2012","unstructured":"J. Shirako , K. Sharma , N. Fauzia , L.-N. Pouchet , J. Ramanujam , P. Sadayappan , and V. Sarkar . Analytical Bounds for Optimal Tile Size Selection , pages 101 -- 121 . Springer Berlin Heidelberg, Berlin , Heidelberg , 2012 . J. Shirako, K. Sharma, N. Fauzia, L.-N. Pouchet, J. Ramanujam, P. Sadayappan, and V. Sarkar. Analytical Bounds for Optimal Tile Size Selection, pages 101--121. Springer Berlin Heidelberg, Berlin, Heidelberg, 2012."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810096"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1941553.1941596"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2011.47"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989493.1989508"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/113445.113449"},{"key":"e_1_3_2_1_57_1","first-page":"357","volume-title":"Parallel Processing for Scientific Computing (SIAM)","author":"Wolfe M. J.","year":"1987","unstructured":"M. J. Wolfe . Iteration space tiling for memory hierarchies . Parallel Processing for Scientific Computing (SIAM) , pages 357 -- 361 , 1987 . M. J. Wolfe. Iteration space tiling for memory hierarchies. Parallel Processing for Scientific Computing (SIAM), pages 357--361, 1987."},{"key":"e_1_3_2_1_58_1","first-page":"477","volume-title":"12th International Workshop, LCPC'99, La Jolla\/San Diego, CA, USA, August 4--6, 1999","author":"Wonnacott D.","year":"1999","unstructured":"D. Wonnacott . Time skewing for parallel computers. In Languages and Compilers for Parallel Computing , 12th International Workshop, LCPC'99, La Jolla\/San Diego, CA, USA, August 4--6, 1999 , Proceedings , pages 477 -- 480 , 1999 . D. Wonnacott. Time skewing for parallel computers. In Languages and Compilers for Parallel Computing, 12th International Workshop, LCPC'99, La Jolla\/San Diego, CA, USA, August 4--6, 1999, Proceedings, pages 477--480, 1999."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015460304860"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"crossref","unstructured":"J.\n      Xue\n    . \n      Loop Tiling\n       for \n      Parallelism volume \n  575\n   of \n  Kluwer International Series in Engineering and Computer Science\n  . \n  Kluwer 2000\n  .  J. Xue. Loop Tiling for Parallelism volume 575 of Kluwer International Series in Engineering and Computer Science. Kluwer 2000.","DOI":"10.1007\/978-1-4615-4337-4"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781140"}],"event":{"name":"PPoPP '17: 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","location":"Austin Texas USA","acronym":"PPoPP '17","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages"]},"container-title":["Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3018743.3018744","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3018743.3018744","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:24:10Z","timestamp":1750206250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3018743.3018744"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,1,26]]},"references-count":60,"alternative-id":["10.1145\/3018743.3018744","10.1145\/3018743"],"URL":"https:\/\/doi.org\/10.1145\/3018743.3018744","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3155284.3018744","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2017,1,26]]},"assertion":[{"value":"2017-01-26","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}