{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,25]],"date-time":"2025-09-25T15:01:31Z","timestamp":1758812491309,"version":"3.40.3"},"publisher-location":"Berlin, Heidelberg","reference-count":27,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642303968"},{"type":"electronic","value":"9783642303975"}],"license":[{"start":{"date-parts":[[2012,1,1]],"date-time":"2012-01-01T00:00:00Z","timestamp":1325376000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-30397-5_7","type":"book-chapter","created":{"date-parts":[[2012,5,12]],"date-time":"2012-05-12T11:41:27Z","timestamp":1336822887000},"page":"72-83","source":"Crossref","is-referenced-by-count":3,"title":["Using Free Scheduling for Programming Graphic Cards"],"prefix":"10.1007","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"}]}],"member":"297","reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Bastoul, C.: Code generation in the polyhedral model is easier than you think. In: PACT 13 IEEE International Conference on Parallel Architecture and Compilation Techniques, Juan-les-Pins, pp. 7\u201316 (September 2004)","DOI":"10.1109\/PACT.2004.1342537"},{"key":"7_CR2","doi-asserted-by":"publisher","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.: Coarse-grained loop parallelization: Iteration space slicing vs affine transformations. Parallel Computing\u00a037, 479\u2013497 (2011)","journal-title":"Parallel Computing"},{"key":"7_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/978-3-540-45209-6_44","volume-title":"Euro-Par 2003 Parallel Processing","author":"V. Beletskyy","year":"2003","unstructured":"Beletskyy, V., Siedlecki, K.: Finding Free Schedules for Non-uniform Loops. In: Kosch, H., B\u00f6sz\u00f6rm\u00e9nyi, L., Hellwagner, H. (eds.) Euro-Par 2003. LNCS, vol.\u00a02790, pp. 297\u2013302. Springer, Heidelberg (2003)"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.endm.2009.03.002","volume":"33","author":"W. Bielecki","year":"2009","unstructured":"Bielecki, W., Klimek, T., Trifunovic, K.: Calculating exact transitive closure for a normalized affine integer tuple relation. Electronic Notes in Discrete Mathematics\u00a033, 7\u201314 (2009)","journal-title":"Electronic Notes in Discrete Mathematics"},{"key":"7_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1007\/978-3-642-17458-2_10","volume-title":"Combinatorial Optimization and Applications","author":"B. Wlodzimierz","year":"2010","unstructured":"Wlodzimierz, B., Tomasz, K., Marek, P., Beletska, A.: An Iterative Algorithm of Computing the Transitive Closure of a Union of Parameterized Affine Integer Tuple Relations. In: Wu, W., Daescu, O. (eds.) COCOA 2010, Part I. LNCS, vol.\u00a06508, pp. 104\u2013113. Springer, Heidelberg (2010)"},{"key":"7_CR6","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1007\/978-3-642-14390-8_21","volume-title":"Parallel Processing and Applied Mathematics","author":"W. Bielecki","year":"2010","unstructured":"Bielecki, W., Palkowski, M.: Extracting Both Affine and Non-linear Synchronization-Free Slices in Program Loops. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Wasniewski, J. (eds.) PPAM 2009. LNCS, vol.\u00a06067, pp. 196\u2013205. Springer, Heidelberg (2010)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Bondhugula, U., Hartono, A., Ramanujam, J., Sadayappan, P.: A practical automatic polyhedral parallelizer and locality optimizer. In: Conference on Programming Language Design and Implementation, pp. 101\u2013113. ACM (2008)","DOI":"10.1145\/1379022.1375595"},{"key":"7_CR8","unstructured":"Chen, D.K.: Compiler optimizations for parallel loops with fine-grained synchronization. Ph.D. thesis, Champaign, IL, USA (1994), uMI Order No. GAX95-12325"},{"key":"7_CR9","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1109\/71.298207","volume":"5","author":"A. Darte","year":"1994","unstructured":"Darte, A., Robert, Y.: Constructive methods for scheduling uniform loop nests. IEEE Trans. Parallel Distrib. Syst.\u00a05, 814\u2013822 (1994)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"7_CR10","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/PACT.1996.552676","volume-title":"Proceedings of the 1996 Conference on Parallel Architectures and Compilation Techniques, PACT 1996","author":"A. Darte","year":"1996","unstructured":"Darte, A., Vivien, F.: Optimal fine and medium grain parallelism detection in polyhedral reduced dependence graphs. In: Proceedings of the 1996 Conference on Parallel Architectures and Compilation Techniques, PACT 1996, pp. 281\u2013291. IEEE Computer Society, Washington, DC, USA (1996)"},{"issue":"2","key":"7_CR11","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1142\/S0129626491000021","volume":"1","author":"A. Darte","year":"1991","unstructured":"Darte, A., Khachiyan, L., Robert, Y.: Linear scheduling is nearly optimal. Parallel Processing Letters\u00a01(2), 73\u201381 (1991)","journal-title":"Parallel Processing Letters"},{"issue":"5","key":"7_CR12","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/BF01407835","volume":"21","author":"P. Feautrier","year":"1992","unstructured":"Feautrier, P.: Some efficient solutions to the affine scheduling problem: I. one-dimensional time. Int. J. Parallel Program.\u00a021(5), 313\u2013348 (1992)","journal-title":"Int. J. Parallel Program."},{"issue":"5","key":"7_CR13","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1007\/BF01379404","volume":"21","author":"P. Feautrier","year":"1992","unstructured":"Feautrier, P.: Some efficient solutions to the affine scheduling problem: II. multi-dimensional time. Int. J. Parallel Program.\u00a021(5), 389\u2013420 (1992)","journal-title":"Int. J. Parallel Program."},{"key":"7_CR14","unstructured":"Kelly, W., Maslov, V., Pugh, W., Rosser, E., Shpeisman, T., Wonnacott, D.: The omega library interface guide. Tech. rep., College Park, MD, USA (1995)"},{"key":"7_CR15","unstructured":"Kelly, W., Pugh, W.: A framework for unifying reordering transformations. Tech. rep., Univ. of Maryland Institute for Advanced Computer Studies Report No. UMIACS-TR-92-126.1, College Park, MD, USA (1993)"},{"issue":"6","key":"7_CR16","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1007\/BF03356760","volume":"24","author":"W. Kelly","year":"1996","unstructured":"Kelly, W., Pugh, W., Rosser, E., Shpeisman, T.: Transitive closure of infinite graphs and its applications. Int. J. Parallel Programming\u00a024(6), 579\u2013598 (1996)","journal-title":"Int. J. Parallel Programming"},{"key":"7_CR17","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1109\/71.86104","volume":"2","author":"V. Krothapalli","year":"1991","unstructured":"Krothapalli, V., Sadayappan, P.: Removal of redundant dependences in doacross loops with constant dependences. IEEE Transactions on Parallel and Distributed Systems\u00a02, 281\u2013289 (1991)","journal-title":"IEEE Transactions on Parallel and Distributed Systems"},{"key":"7_CR18","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/S0304-3975(97)00209-0","volume":"196","author":"P. Gou\u00ebslier d\u2019Argence Le","year":"1998","unstructured":"Le Gou\u00ebslier d\u2019Argence, P.: Affine scheduling on bounded convex polyhedric domains is asymptotically optimal. Theor. Comput. Sci.\u00a0196, 395\u2013415 (1998)","journal-title":"Theor. Comput. Sci."},{"key":"7_CR19","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 ACM SIGARCH International Conference on Supercomputing, pp. 228\u2013237. ACM Press (1999)","DOI":"10.1145\/305138.305197"},{"key":"7_CR20","unstructured":"Surhone, L.M., Tennoe, M.T., Henssonow, S.F.: Presburger Arithmetic. VDM Verlag Dr. Mueller AG & Co. Kg (2010); ISBN: 6133083557"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1109\/TC.1987.5009499","volume":"36","author":"S.P. Midkiff","year":"1987","unstructured":"Midkiff, S.P., Padua, D.A.: Compiler algorithms for synchronization. IEEE Transactions on Computers\u00a036, 1485\u20131495 (1987)","journal-title":"IEEE Transactions on Computers"},{"key":"7_CR22","unstructured":"Midkiff, S.P., Padua, D.A.: A comparison of four synchronization optimization techniques. In: ICPP (2), pp. 9\u201316 (1991)"},{"key":"7_CR23","unstructured":"NAS: Parallel Benchmarks Suite, Version 3.3 (February 2008), http:\/\/www.nas.nasa.gov"},{"key":"7_CR24","unstructured":"NVIDIA: NVIDIA CUDA C Programming Guide 4.0 (2011), http:\/\/developer.download.nvidia.com\/compute\/DevZone\/docs\/html\/C\/doc\/CUDA_C_Programming_Guide.pdf"},{"key":"7_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"546","DOI":"10.1007\/3-540-57659-2_31","volume-title":"Languages and Compilers for Parallel Computing","author":"W. Pugh","year":"1994","unstructured":"Pugh, W., Wonnacott, D.: An Exact Method for Analysis of Value-Based Array Data Dependences. In: Banerjee, U., Gelernter, D., Nicolau, A., Padua, D.A. (eds.) LCPC 1993. LNCS, vol.\u00a0768, pp. 546\u2013566. Springer, Heidelberg (1994)"},{"key":"7_CR26","unstructured":"Verdoolaege, S.: Integer set library - manual. Tech. rep. (2011), http:\/\/www.kotnet.org\/~skimo\/\/isl\/manual.pdf"},{"key":"7_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/3-540-45706-2_39","volume-title":"Euro-Par 2002. Parallel Processing","author":"F. Vivien","year":"2002","unstructured":"Vivien, F.: On the Optimality of Feautrier\u2019s Scheduling Algorithm. In: Monien, B., Feldmann, R.L. (eds.) Euro-Par 2002. LNCS, vol.\u00a02400, pp. 299\u2013308. Springer, Heidelberg (2002)"}],"container-title":["Lecture Notes in Computer Science","Facing the Multicore - Challenge II"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-30397-5_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T22:04:32Z","timestamp":1743113072000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-30397-5_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642303968","9783642303975"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-30397-5_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}