{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T08:12:12Z","timestamp":1770451932339,"version":"3.49.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T00:00:00Z","timestamp":1508457600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Computing"],"published-print":{"date-parts":[[2018,3]]},"DOI":"10.1007\/s00607-017-0576-3","type":"journal-article","created":{"date-parts":[[2017,10,20]],"date-time":"2017-10-20T02:11:00Z","timestamp":1508465460000},"page":"277-302","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Generation of parallel synchronization-free tiled code"],"prefix":"10.1007","volume":"100","author":[{"given":"Wlodzimierz","family":"Bielecki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marek","family":"Palkowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9105-911X","authenticated-orcid":false,"given":"Piotr","family":"Skotnicki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,10,20]]},"reference":[{"key":"576_CR1","doi-asserted-by":"crossref","unstructured":"Bastoul C (2004) Code generation in the polyhedral model is easier than you think. In: PACT\u201913 IEEE international conference on parallel architecture and compilation techniques, Juan-les-Pins, pp 7\u201316","DOI":"10.1109\/PACT.2004.1342537"},{"key":"576_CR2","doi-asserted-by":"crossref","unstructured":"Bandishti V, Pananilath I, Bondhugula U (2012) Tiling stencil computations to maximize parallelism. In: SC \u201912: Proceedings of the international conference on high performance computing, networking, storage and analysis, IEEE, Salt Lake City, Utah, pp 1\u201311","DOI":"10.1109\/SC.2012.107"},{"key":"576_CR3","doi-asserted-by":"crossref","first-page":"479","DOI":"10.1016\/j.parco.2010.12.005","volume":"37","author":"A Beletska","year":"2011","unstructured":"Beletska A, Bielecki W, Cohen A, Palkowski M, Siedlecki K (2011) Coarse-grained loop parallelization: Iteration space slicing vs affine transformations. Parallel Comput 37:479\u2013497","journal-title":"Parallel Comput"},{"key":"576_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/s10878-014-9740-2","author":"W Bielecki","year":"2014","unstructured":"Bielecki W et al (2014) Using basis dependence distance vectors to calculate the transitive closure of dependence relations by means of the Floyd-Warshall algorithm. J Comb Optim. doi: 10.1007\/s10878-014-9740-2","journal-title":"J Comb Optim"},{"key":"576_CR5","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1007\/978-3-319-15147-2_26","volume-title":"Soft computing in computer and information science, advances in intelligent systems and computing","author":"W Bielecki","year":"2015","unstructured":"Bielecki W, Palkowski M (2015) Perfectly nested loop tiling transformations based on the transitive closure of the program dependence graph. In: Wilinski A, Fray IE, Pejas J (eds) Soft computing in computer and information science, advances in intelligent systems and computing. Springer, Berlin, pp 309\u2013320"},{"issue":"4","key":"576_CR6","first-page":"919","volume":"26","author":"W Bielecki","year":"2016","unstructured":"Bielecki W, Palkowski M (2016) Tiling arbitrarily nested loops by means of the transitive closure of dependence graphs. Appl Math Comput Sci 26(4):919\u2013939","journal-title":"Appl Math Comput Sci"},{"issue":"9","key":"576_CR7","doi-asserted-by":"crossref","first-page":"518","DOI":"10.1016\/j.parco.2012.06.001","volume":"38","author":"W Bielecki","year":"2012","unstructured":"Bielecki W, Palkowski M, Klimek T (2012) Free scheduling for statement instances of parameterized arbitrarily nested affine loops. Parallel Comput 38(9):518\u2013532","journal-title":"Parallel Comput"},{"key":"576_CR8","unstructured":"Bielecki W, Palkowski M, Klimek T (2015) Free scheduling of tiles based on the transitive closure of dependence graphs. In: Wyrzykowski R (ed) 11th international conference on parallel processing and applied mathematics, Part II, Lecture notes in computer science, vol 9574. Springer, Berlin, Heidelberg, pp 133\u2013142"},{"key":"576_CR9","doi-asserted-by":"crossref","unstructured":"Bondhugula U, Baskaran M, Krishnamoorthy S, Ramanujam J, Rountev A, Sadayappan P (2008) Automatic transformations for communication-minimized parallelization and locality optimization in the polyhedral model. In: Compiler constructure. Lecture notes in computer science. Springer, pp 132\u2013146","DOI":"10.1007\/978-3-540-78791-4_9"},{"issue":"6","key":"576_CR10","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1145\/1379022.1375595","volume":"43","author":"U Bondhugula","year":"2008","unstructured":"Bondhugula U, Hartono A, Ramanujam J, Sadayappan P (2008) A practical automatic polyhedral parallelizer and locality optimizer. SIGPLAN Not 43(6):101\u2013113","journal-title":"SIGPLAN Not"},{"issue":"5","key":"576_CR11","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/BF01407835","volume":"21","author":"P Feautrier","year":"1992","unstructured":"Feautrier P (1992) Some efficient solutions to the affine scheduling problem: I. one-dimensional time. Int J Parallel Program 21(5):313\u2013348","journal-title":"Int J Parallel Program"},{"issue":"6","key":"576_CR12","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1007\/BF01379404","volume":"21","author":"P Feautrier","year":"1992","unstructured":"Feautrier P (1992) Some efficient solutions to the affine scheduling problem: II. multidimensional time. Int J Parallel Program 21(6):389\u2013420","journal-title":"Int J Parallel Program"},{"key":"576_CR13","unstructured":"Griebl M (2004) Automatic parallelization of loop programs for distributed memory architectures. University of Passau, Habilitation thesis"},{"issue":"4","key":"576_CR14","doi-asserted-by":"crossref","first-page":"12:1","DOI":"10.1145\/2743016","volume":"37","author":"T Grosser","year":"2015","unstructured":"Grosser T, Verdoolaege S, Cohen A (2015) Polyhedral ast generation is more than scanning polyhedra. ACM Trans Program Lang Syst 37(4):12:1\u201312:50","journal-title":"ACM Trans Program Lang Syst"},{"issue":"03","key":"576_CR15","doi-asserted-by":"crossref","first-page":"1441,002","DOI":"10.1142\/S0129626414410023","volume":"24","author":"T Grosser","year":"2014","unstructured":"Grosser T, Verdoolaege S, Cohen A, Sadayappan P (2014) The relation between diamond tiling and hexagonal tiling. Parallel Proces Lett 24(03):1441,002","journal-title":"Parallel Proces Lett"},{"key":"576_CR16","doi-asserted-by":"publisher","unstructured":"Hartono A, Baskaran MM, Bastoul C, Cohen A, Krishnamoorthy S, Norris B, Ramanujam J, Sadayappan P (2009) Parametric multi-level tiling of imperfectly nested loops. In: Proceedings of the 23rd international conference on Supercomputing, ICS \u201909. ACM, New York, NY, USA, pp 147\u2013157. doi: 10.1145\/1542275.1542301","DOI":"10.1145\/1542275.1542301"},{"key":"576_CR17","doi-asserted-by":"crossref","unstructured":"Irigoin F, Triolet R (1988) Supernode partitioning. In: Proceedings of the 15th ACM SIGPLAN-SIGACT symposium on principles of programming languages, POPL \u201988. ACM, New York, NY, USA, pp 319\u2013329","DOI":"10.1145\/73560.73588"},{"issue":"6","key":"576_CR18","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1007\/BF03356760","volume":"24","author":"W Kelly","year":"1996","unstructured":"Kelly W, Pugh W, Rosser E, Shpeisman T (1996) Transitive closure of infinite graphs and its applications. Int J Parallel Program 24(6):579\u2013598","journal-title":"Int J Parallel Program"},{"key":"576_CR19","unstructured":"Kim D, Rajopadhye S (2009) Efficient tiled loop generation: D-tiling. In: International workshop on languages and compilers for parallel computing. Springer, pp 293\u2013307"},{"key":"576_CR20","doi-asserted-by":"crossref","unstructured":"Krishnamoorthy S, Baskaran MM, Bondhugula U, Ramanujam J, Rountev A, Sadayappan P (2007) Effective automatic parallelization of stencil computations. In: PLDI, pp 235\u2013244","DOI":"10.1145\/1250734.1250761"},{"key":"576_CR21","doi-asserted-by":"crossref","unstructured":"Lim A, Cheong GI, Lam MS (1999) An affine partitioning algorithm to maximize parallelism and minimize communication. In: In Proceedings of the 13th ACM SIGARCH international conference on supercomputing. ACM Press, pp 228\u2013237","DOI":"10.1145\/305138.305197"},{"key":"576_CR22","unstructured":"Lim AW, Lam MS (1994) Communication-free parallelization via affine transformations. In: 24 th ACM symposium on principles of programming languages. Springer, pp 92\u2013106"},{"key":"576_CR23","unstructured":"NAS benchmarks suite. http:\/\/www.nas.nasa.gov (2015)"},{"key":"576_CR24","unstructured":"OpenMP Architecture Review Board (2012) OpenMP application program interface version 4.0"},{"key":"576_CR25","doi-asserted-by":"crossref","unstructured":"Palkowski M, Klimek T, Bielecki W (2015) Traco: An automatic loop nest parallelizer for numerical applications. In: 2015 Federated conference on computer science and information systems (FedCSIS). IEEE, pp 681\u2013686","DOI":"10.15439\/2015F34"},{"key":"576_CR26","unstructured":"Pouchet LN (2015) The polyhedral benchmark suite\/c4.1, http:\/\/web.cse.ohio-state.edu\/~pouchet\/software\/polybench"},{"key":"576_CR27","doi-asserted-by":"crossref","unstructured":"Pugh W, Rosser E (1997) Iteration space slicing and its application to communication optimization. In: International conference on supercomputing, pp 221\u2013228","DOI":"10.1145\/263580.263637"},{"key":"576_CR28","unstructured":"Pugh W, Rosser E (1999) Iteration space slicing for locality. In: LCPC, Lecture notes in computer science, vol 1863. Springer, pp 164\u2013184"},{"issue":"2","key":"576_CR29","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/0743-7315(92)90027-K","volume":"16","author":"J Ramanujam","year":"1992","unstructured":"Ramanujam J, Sadayappan P (1992) Tiling multidimensional iteration spaces for multicomputers. J Parallel Distrib Comput 16(2):108\u2013120","journal-title":"J Parallel Distrib Comput"},{"key":"576_CR30","doi-asserted-by":"crossref","unstructured":"Verdoolaege S (2010) ISL: an integer set library for the polyhedral model. In: Mathematical software\u2014ICMS 2010, Lecture notes in computer science. vol 6327. Springer, Berlin, pp 299\u2013302","DOI":"10.1007\/978-3-642-15582-6_49"},{"key":"576_CR31","unstructured":"Verdoolaege S (2011) Counting affine calculator and applications. In: First international workshop on polyhedral compilation techniques (IMPACT\u201911), Charmonix, France"},{"key":"576_CR32","unstructured":"Verdoolaege S (2016) Presburger formulas and polyhedral compilation, v0.02. Polly Labs and KU Leuven"},{"key":"576_CR33","doi-asserted-by":"crossref","unstructured":"Verdoolaege S, Cohen A, Beletska A (2011) Transitive closures of affine integer tuple relations and their overapproximations. In: Proceedings of the 18th international conference on Static analysis, SAS\u201911. Springer, pp 216\u2013232","DOI":"10.1007\/978-3-642-23702-7_18"},{"key":"576_CR34","unstructured":"Verdoolaege S, Grosser T (2012) Polyhedral extraction tool. In: In Proceedings of the 2nd international workshop on polyhedral compilation techniques. Paris, France"},{"key":"576_CR35","doi-asserted-by":"crossref","unstructured":"Wolf ME, Lam MS (1991) A data locality optimizing algorithm. In: Proceedings of the ACM SIGPLAN 1991 Conference on Programming Language Design and Implementation, pp. 30\u201344","DOI":"10.1145\/113445.113449"},{"key":"576_CR36","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4615-4337-4","volume-title":"Loop tiling for parallelism","author":"J Xue","year":"2000","unstructured":"Xue J (2000) Loop tiling for parallelism. Kluwer Academic Publishers, Norwell"}],"container-title":["Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00607-017-0576-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-017-0576-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00607-017-0576-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,4]],"date-time":"2019-10-04T18:51:07Z","timestamp":1570215067000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00607-017-0576-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,10,20]]},"references-count":36,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2018,3]]}},"alternative-id":["576"],"URL":"https:\/\/doi.org\/10.1007\/s00607-017-0576-3","relation":{},"ISSN":["0010-485X","1436-5057"],"issn-type":[{"value":"0010-485X","type":"print"},{"value":"1436-5057","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,10,20]]}}}