{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T23:14:35Z","timestamp":1776122075921,"version":"3.50.1"},"publisher-location":"Berlin, Heidelberg","reference-count":38,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783642286513","type":"print"},{"value":"9783642286520","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-28652-0_6","type":"book-chapter","created":{"date-parts":[[2012,3,22]],"date-time":"2012-03-22T21:02:02Z","timestamp":1332450122000},"page":"101-121","source":"Crossref","is-referenced-by-count":37,"title":["Analytical Bounds for Optimal Tile Size Selection"],"prefix":"10.1007","author":[{"given":"Jun","family":"Shirako","sequence":"first","affiliation":[]},{"given":"Kamal","family":"Sharma","sequence":"additional","affiliation":[]},{"given":"Naznin","family":"Fauzia","sequence":"additional","affiliation":[]},{"given":"Louis-No\u00ebl","family":"Pouchet","sequence":"additional","affiliation":[]},{"given":"J.","family":"Ramanujam","sequence":"additional","affiliation":[]},{"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[]},{"given":"Vivek","family":"Sarkar","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"6_CR1","first-page":"48","volume-title":"ISCA 2010","author":"T.W. Barr","year":"2010","unstructured":"Barr, T.W., Cox, A.L., Rixner, S.: Translation caching: skip, don\u2019t walk (the page table). In: ISCA 2010, pp. 48\u201359. ACM, New York (2010)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Baskaran, M., Hartono, A., Tavarageri, S., Henretty, T., Ramanujam, J., Sadayappan, P.: Parameterized tiling revisited. In: CGO, pp. 200\u2013209 (2010)","DOI":"10.1145\/1772954.1772983"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Bhargava, R., Serebrin, B., Spadini, F., Manne, S.: Accelerating two-dimensional page walks for virtualized systems. In: ASPLOS XIII, pp. 26\u201335 (2008)","DOI":"10.1145\/1353536.1346286"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Bilmes, J., Asanovic, K., Chin, C., Demmel, J.: Optimizing matrix multiply using PHiPAC. In: Proc. ICS, pp. 340\u2013347 (1997)","DOI":"10.1145\/263580.263662"},{"key":"6_CR5","doi-asserted-by":"crossref","unstructured":"Bodin, F., Jalby, W., Windheiser, D., Eisenbeis, C.: A quantitative algorithm for data locality optimization. In: Code Generation, pp. 119\u2013145 (1991)","DOI":"10.1007\/978-1-4471-3501-2_8"},{"key":"6_CR6","unstructured":"Bondhugula, U., Hartono, A., Ramanujam, J., Sadayappan, P.: A practical automatic polyhedral program optimization system. In: PLDI (2008)"},{"issue":"1","key":"6_CR7","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/0167-9260(94)90019-1","volume":"17","author":"P. Boulet","year":"1994","unstructured":"Boulet, P., Darte, A., Risset, T., Robert, Y. (Pen)-ultimate tiling? Integration, the VLSI Journal\u00a017(1), 33\u201351 (1994)","journal-title":"Integration, the VLSI Journal"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Chame, J., Moon, S.: A tile selection algorithm for data locality and cache interference. In: ICS, pp. 492\u2013499 (1999)","DOI":"10.1145\/305138.305245"},{"key":"6_CR9","unstructured":"Chen, C., Chame, J., Hall, M.: Combining models and guided empirical search to optimize for multiple levels of the memory hierarchy. In: CGO 2005 (2005)"},{"key":"6_CR10","doi-asserted-by":"crossref","unstructured":"Coleman, S., McKinley, K.: Tile Size Selection Using Cache Organization and Data Layout. In: PLDI, pp. 279\u2013290 (1995)","DOI":"10.1145\/223428.207162"},{"key":"6_CR11","unstructured":"Datta, K.: Auto-tuning stencil codes for cache-based multicore platforms. Technical report, University of California, Berkeley (December 2009)"},{"key":"6_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1007\/BFb0038674","volume-title":"Languages and Compilers for Parallel Computing","author":"J. Ferrante","year":"1992","unstructured":"Ferrante, J., Sarkar, V., Thrash, W.: On Estimating and Enhancing Cache Effectiveness. In: Banerjee, U., Nicolau, A., Gelernter, D., Padua, D.A. (eds.) LCPC 1991. LNCS, vol.\u00a0589, pp. 328\u2013343. Springer, Heidelberg (1992)"},{"issue":"4","key":"6_CR13","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1145\/325478.325479","volume":"21","author":"S. Ghosh","year":"1999","unstructured":"Ghosh, S., Martonosi, M., Malik, S.: Cache miss equations: a compiler framework for analyzing and tuning memory behavior. ACM TOPLAS\u00a021(4), 703\u2013746 (1999)","journal-title":"ACM TOPLAS"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Goto, K., van de Geijn, R.A.: High-performance implementation of the level-3 BLAS. ACM Trans. Math. Softw.\u00a035(1) (July 2008)","DOI":"10.1145\/1377603.1377607"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Hartono, A., Baskaran, M.M., Bastoul, C., Cohen, A., Krishnamoorthy, S., Norris, B., Ramanujam, J., Sadayappan, P.: Parametric multi-level tiling of imperfectly nested loops. In: Proc. ICS (2009)","DOI":"10.1145\/1542275.1542301"},{"issue":"3","key":"6_CR16","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1023\/B:SUPE.0000011388.54204.8e","volume":"27","author":"C. Hsu","year":"2004","unstructured":"Hsu, C., Kremer, U.: A quantitative analysis of tile size selection algorithms. J. Supercomput.\u00a027(3), 279\u2013294 (2004)","journal-title":"J. Supercomput."},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Irigoin, F., Triolet, R.: Supernode partitioning. In: ACM POPL, pp. 319\u2013329 (1988)","DOI":"10.1145\/73560.73588"},{"key":"6_CR18","doi-asserted-by":"crossref","unstructured":"Kim, D., Renganarayanan, L., Strout, M., Rajopadhye, S.: Multi-level tiling: \u2019m\u2019 for the price of one. In: SC (2007)","DOI":"10.1145\/1362622.1362691"},{"issue":"1","key":"6_CR19","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1023\/A:1020989410030","volume":"24","author":"P.M.W. Knijnenburg","year":"2003","unstructured":"Knijnenburg, P.M.W., Kisuki, T., O\u2019Boyle, M.F.P.: Combined selection of tile sizes and unroll factors using iterative compilation. The Journal of Supercomputing\u00a024(1), 43\u201367 (2003)","journal-title":"The Journal of Supercomputing"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Lam, M., Rothberg, E., Wolf, M.: The cache performance and optimizations of blocked algorithms. In: Proc. 4th ACM ASPLOS, pp. 63\u201374 (1991)","DOI":"10.1145\/106973.106981"},{"issue":"1-2","key":"6_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/s00158-003-0320-9","volume":"27","author":"M. Luersen","year":"2004","unstructured":"Luersen, M., Riche, R.L., Guyon, F.: A constrained, globalized, and bounded nelder-mead method for engineering optimization. Structural and Multidisciplinary Optimization\u00a027(1-2), 43\u201354 (2004)","journal-title":"Structural and Multidisciplinary Optimization"},{"issue":"4","key":"6_CR22","doi-asserted-by":"crossref","first-page":"308","DOI":"10.1093\/comjnl\/7.4.308","volume":"7","author":"J.A. Nelder","year":"1965","unstructured":"Nelder, J.A., Mead, R.: A simplex method for function minimization. Computer Journal\u00a07(4), 308\u2013313 (1965)","journal-title":"Computer Journal"},{"issue":"2","key":"6_CR23","first-page":"108","volume":"16","author":"J. Ramanujam","year":"1992","unstructured":"Ramanujam, J., Sadayappan, P.: Tiling multidimensional iteration spaces for multicomputers. JPDC\u00a016(2), 108\u2013230 (1992)","journal-title":"JPDC"},{"key":"6_CR24","doi-asserted-by":"crossref","unstructured":"Renganarayana, L., Kim, D., Rajopadhye, S., Strout, M.: Parameterized tiled loops for free. In: PLDI, pp. 405\u2013414 (2007)","DOI":"10.1145\/1273442.1250780"},{"key":"6_CR25","unstructured":"Resource Characterization in the PACE Project, \n                    \n                      http:\/\/www.pace.rice.edu\/Content.aspx?id=41"},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Rivera, G., Tseng, C.: Locality optimizations for multi-level caches. In: SC (1999)","DOI":"10.1145\/331532.331534"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Sarkar, V.: Automatic Selection of High Order Transformations in the IBM XL Fortran Compilers. IBM J. Res. & Dev.\u00a041(3) (May 1997)","DOI":"10.1147\/rd.413.0233"},{"key":"6_CR28","unstructured":"Sarkar, V., Megiddo, N.: An analytical model for loop tiling and its solution. In: IEEE ISPASS (2000)"},{"key":"6_CR29","unstructured":"Schreiber, R., Dongarra, J.: Automatic blocking of nested loops. Tech. Report 90.38, RIACS, NASA Ames Research Center (1990)"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Tabatabaee, V., Tiwari, A., Hollingsworth, J.K.: Parallel parameter tuning for applications with performance variability. In: Proc. Supercomputing 2005 (2005)","DOI":"10.1109\/SC.2005.52"},{"key":"6_CR31","doi-asserted-by":"crossref","unstructured":"Tapus, C., Chung, I.-H., Hollingsworth, J.K.: Active harmony: towards automated performance tuning. In: SC, pp. 1\u201311 (2002)","DOI":"10.1109\/SC.2002.10062"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Tiwari, A., Chen, C., Chame, J., Hall, M., Hollingsworth, J.: Scalable autotuning framework for compiler optimization. In: IPDPS 2009 (2009)","DOI":"10.1109\/IPDPS.2009.5161054"},{"issue":"1\u20132","key":"6_CR33","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0167-8191(00)00087-9","volume":"27","author":"R.C. Whaley","year":"2001","unstructured":"Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimization of software and the ATLAS project. Parallel Computing\u00a027(1\u20132), 3\u201335 (2001)","journal-title":"Parallel Computing"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Wolf, M., Lam, M.S.: A data locality optimizing algorithm. In: PLDI 1991, pp. 30\u201344 (1991)","DOI":"10.1145\/113446.113449"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Wolfe, M.: More iteration space tiling. In: Proc. Supercomputing, pp. 655\u2013664 (1989)","DOI":"10.1145\/76263.76337"},{"key":"6_CR36","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-4337-4","volume-title":"Loop tiling for parallelism","author":"J. Xue","year":"2000","unstructured":"Xue, J.: Loop tiling for parallelism. Kluwer Academic Publishers, Norwell (2000)"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Yotov, K., Pingali, K., Stodghill, P.: Think globally, search locally. In: International Conference on Supercomputing (2005)","DOI":"10.1145\/1088149.1088168"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Yuki, T., Renganarayanan, L., Rajopadhye, S., Anderson, C., Eichenberger, A., O\u2019Brien, K.: Automatic creation of tile size selection models. In: CGO, pp. 190\u2013199 (2010)","DOI":"10.1145\/1772954.1772982"}],"container-title":["Lecture Notes in Computer Science","Compiler Construction"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-28652-0_6.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T11:04:10Z","timestamp":1620126250000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-28652-0_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642286513","9783642286520"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-28652-0_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2012]]}}}