{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:50:49Z","timestamp":1743043849954,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319527086"},{"type":"electronic","value":"9783319527093"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"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":[[2017]]},"DOI":"10.1007\/978-3-319-52709-3_16","type":"book-chapter","created":{"date-parts":[[2017,1,23]],"date-time":"2017-01-23T07:13:25Z","timestamp":1485155605000},"page":"203-217","source":"Crossref","is-referenced-by-count":4,"title":["The Importance of Efficient Fine-Grain Synchronization for Many-Core Systems"],"prefix":"10.1007","author":[{"given":"Tongsheng","family":"Geng","sequence":"first","affiliation":[]},{"given":"St\u00e9phane","family":"Zuckerman","sequence":"additional","affiliation":[]},{"given":"Jos\u00e9","family":"Monsalve","sequence":"additional","affiliation":[]},{"given":"Alfredo","family":"Goldman","sequence":"additional","affiliation":[]},{"given":"Sami","family":"Habib","sequence":"additional","affiliation":[]},{"given":"Jean-Luc","family":"Gaudiot","sequence":"additional","affiliation":[]},{"given":"Guang R.","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,1,24]]},"reference":[{"issue":"7","key":"16_CR1","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1145\/109626.109631","volume":"26","author":"C Ancourt","year":"1991","unstructured":"Ancourt, C., Irigoin, F.: Scanning polyhedra with DO loops. SIGPLAN Not. 26(7), 39\u201350 (1991)","journal-title":"SIGPLAN Not."},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Bandishti, V., Pananilath, I., Bondhugula, U.: Tiling stencil computations to maximize parallelism. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2012. IEEE Computer Society Press, Salt Lake City (2012)","DOI":"10.1109\/SC.2012.107"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Barik, R., et al.: The Habanero multicore software research project. In: Proceedings of the 24th ACM SIGPLAN Conference Companion on Object Oriented Programming Systems Languages and Applications, OOPSLA 2009. ACM, Orlando (2009)","DOI":"10.1145\/1639950.1639989"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Bertolacci, I.J., et al.: Parameterized diamond tiling for stencil computations with chapel parallel iterators. In: Proceedings of the 29th ACM on International Conference on Supercomputing, ICS 2015. ACM, Newport Beach (2015)","DOI":"10.1145\/2751205.2751226"},{"issue":"1","key":"16_CR5","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1006\/jpdc.1996.0107","volume":"37","author":"RD Blumofe","year":"1996","unstructured":"Blumofe, R.D., et al.: Cilk: an efficient multithreaded runtime system. J. Parallel Distrib. Comput. 37(1), 55\u201369 (1996)","journal-title":"J. Parallel Distrib. Comput."},{"key":"16_CR6","unstructured":"OpenMP Architecture Review Board. OpenMP Application Program Interface version 4.0 (2013)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Christen, M., Schenk, O., Burkhart, H.: PATUS: a code generation and autotuning framework for parallel iterative stencil computations on modern microarchitectures. In: 2011 IEEE International Parallel Distributed Processing Symposium (IPDPS) (2011)","DOI":"10.1109\/IPDPS.2011.70"},{"key":"16_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"362","DOI":"10.1007\/3-540-06859-7_145","volume-title":"Programming Symposium","author":"JB Dennis","year":"1974","unstructured":"Dennis, J.B.: First version of a data flow procedure language. In: Robinet, B. (ed.) Programming Symposium. LNCS, vol. 19, pp. 362\u2013376. Springer, Heidelberg (1974). doi: 10.1007\/3-540-06859-7_145"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Gautier, T., et al.: XKaapi: a runtime system for data-flow task programming on heterogeneous architectures. In: 2013 IEEE 27th International Symposium on Parallel Distributed Processing (IPDPS) (2013)","DOI":"10.1109\/IPDPS.2013.66"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Kamil, S., et al.: An auto-tuning framework for parallel multicore stencil computations. In: 2010 IEEE International Symposium on Parallel Distributed Processing (IPDPS) (2010)","DOI":"10.1109\/IPDPS.2010.5470421"},{"key":"16_CR11","unstructured":"Knobe, K.: Ease of use with concurrent collections (CnC). In: Hot Topics in Parallelism (2009)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Lauderdale, C., Khan, R.: Towards a codelet-based runtime for exascale computing: position paper. In: Proceedings of the 2nd International Workshop on Adaptive Self-Tuning Computing Systems for the Exafop Era, EXADAPT 2012. ACM, London (2012)","DOI":"10.1145\/2185475.2185478"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Lesniak, M.: PASTHA: parallelizing stencil calculations in Haskell. In: Proceedings of the 5th ACM SIGPLAN Workshop on Declarative Aspects of Multicore Programming, DAMP 2010. ACM, Madrid (2010)","DOI":"10.1145\/1708046.1708052"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Liu, C., Kulkarni, M.: Optimizing the LULESH stencil code using concurrent collections. In: Proceedings of the 5th International Workshop on Domain-Specific Languages and High-Level Frame-Works for High Performance Computing, WOLFHPC 2015. ACM, Austin (2015)","DOI":"10.1145\/2830018.2830024"},{"key":"16_CR15","unstructured":"Mattson, T., et al.: OCR: the open community runtime interface. Technical report, June 2015. https:\/\/xstack.exascaletech.com\/git\/public"},{"key":"16_CR16","doi-asserted-by":"crossref","first-page":"1303","DOI":"10.1016\/j.procs.2015.05.315","volume":"51","author":"T Muranushi","year":"2015","unstructured":"Muranushi, T., Makino, J.: Optimal temporal blocking for stencil computation. Procedia Comput. Sci. 51, 1303\u20131312 (2015). International Conference on Computational Science, ICCS 2015 Computational Science at the Gates of Nature","journal-title":"Procedia Comput. Sci."},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Schweizer, H., Besta, M., Hoefler, T.: Evaluating the cost of atomic operations on modern architectures. Technical report ETH Zurich, Department of Computer Science (2015)","DOI":"10.1109\/PACT.2015.24"},{"key":"16_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/978-3-319-17473-0_11","volume-title":"Languages and Compilers for Parallel Computing","author":"S Shrestha","year":"2015","unstructured":"Shrestha, S., Manzano, J., Marquez, A., Feo, J., Gao, G.R.: Jagged tiling for intra-tile parallelism and fine-grain multithreading. In: Brodman, J., Tu, P. (eds.) LCPC 2014. LNCS, vol. 8967, pp. 161\u2013175. Springer, Heidelberg (2015). doi: 10.1007\/978-3-319-17473-0_11"},{"key":"16_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1007\/978-3-642-40047-6_63","volume-title":"Euro-Par 2013 Parallel Processing","author":"J Suettlerlein","year":"2013","unstructured":"Suettlerlein, J., Zuckerman, S., Gao, G.R.: An implementation of the codelet model. In: Wolf, F., Mohr, B., Mey, D. (eds.) Euro-Par 2013. LNCS, vol. 8097, pp. 633\u2013644. Springer, Heidelberg (2013). doi: 10.1007\/978-3-642-40047-6_63"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: The pochoir stencil compiler. In: Proceedings of the Twenty-Third Annual ACM Symposium on Parallelism in Algorithms and Architectures, SPAA 2011. ACM, San Jose (2011)","DOI":"10.1145\/1989493.1989508"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Zuckerman, S., et al.: Using a \u201ccodelet\u201d program execution model for exascale machines: position paper. In: Proceedings of the 1st International Workshop on Adaptive Self-Tuning Computing Systems for the Exaflop Era, EXADAPT 2011. ACM, San Jose (2011)","DOI":"10.1145\/2000417.2000424"}],"container-title":["Lecture Notes in Computer Science","Languages and Compilers for Parallel Computing"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-52709-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,17]],"date-time":"2019-09-17T17:59:14Z","timestamp":1568743154000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-52709-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319527086","9783319527093"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-52709-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]}}}