{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:12:48Z","timestamp":1782544368020,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,11,13]],"date-time":"2021-11-13T00:00:00Z","timestamp":1636761600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,14]]},"DOI":"10.1145\/3458817.3476154","type":"proceedings-article","created":{"date-parts":[[2021,11,24]],"date-time":"2021-11-24T14:42:14Z","timestamp":1637764934000},"page":"1-15","source":"Crossref","is-referenced-by-count":10,"title":["Reducing redundancy in data organization and arithmetic calculation for stencil computations"],"prefix":"10.1145","author":[{"given":"Kun","family":"Li","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Yue","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2021,11,13]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/800168.811537"},{"key":"e_1_3_2_1_2_1","volume-title":"Optimizing compilers for modern architectures: a dependence-based approach","author":"Allen Randy"},{"key":"e_1_3_2_1_3_1","volume-title":"Joseph James Gebis, Parry Husbands, Kurt Keutzer, David A Patterson, William Lester Plishker, John Shalf, Samuel Webb Williams, et al.","author":"Asanovic Krste","year":"2006"},{"key":"e_1_3_2_1_4_1","unstructured":"Krste Asanovic Ras Bodik James Demmel Tony Keaveny Kurt Keutzer John D Kubiatowicz Edward A Lee Nelson Morgan George Necula David A Patterson etal 2008. The parallel computing laboratory at UC Berkeley: A research agenda based on the Berkeley view. EECS Department University of California Berkeley Tech. Rep (2008).  Krste Asanovic Ras Bodik James Demmel Tony Keaveny Kurt Keutzer John D Kubiatowicz Edward A Lee Nelson Morgan George Necula David A Patterson et al. 2008. The parallel computing laboratory at UC Berkeley: A research agenda based on the Berkeley view. EECS Department University of California Berkeley Tech. Rep (2008)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/2388996.2389051"},{"key":"e_1_3_2_1_6_1","volume-title":"Compiler-Directed Transformation for Higher-Order Stencils. In 2015 IEEE International Parallel and Distributed Processing Symposium. 313--323","author":"Basu P."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375581.1375595"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.70"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5222004"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2591006"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/377792.377807"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Chris Ding and Yun He. 2001. A Ghost Cell Expansion Method for Reducing Communications in Solving PDE Problems (SC '01). 50--50.  Chris Ding and Yun He. 2001. A Ghost Cell Expansion Method for Reducing Communications in Solving PDE Problems (SC '01) . 50--50.","DOI":"10.1145\/582034.582084"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Matteo Frigo and Volker Strumpen. 2005. Cache oblivious stencil computations (ICS '05). 361--366.  Matteo Frigo and Volker Strumpen. 2005. Cache oblivious stencil computations (ICS '05) . 361--366.","DOI":"10.1145\/1088149.1088197"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2751205.2751223"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1987237.1987255"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2467268"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"F. Irigoin and R. Triolet. 1988. Supernode Partitioning (POPL '88). 319--329.  F. Irigoin and R. Triolet. 1988. Supernode Partitioning (POPL '88) . 319--329.","DOI":"10.1145\/73560.73588"},{"key":"e_1_3_2_1_18_1","volume-title":"Increasing Temporal Locality with Skewing and Recursive Blocking (SC '01)","author":"Jin Guohua","year":"2001"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2010.5470421"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1178597.1178605"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/1273442.1250761"},{"key":"e_1_3_2_1_22_1","volume-title":"Wolf","author":"Lam Monica D.","year":"1991"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356165"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3155290"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/362875.362879"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542313"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"A. Nguyen N. Satish J. Chhugani C. Kim and P. Dubey. 2010. 3.5-D Blocking Optimization for Stencil Computations on Modern CPUs and GPUs (SC '10). 1--13.  A. Nguyen N. Satish J. Chhugani C. Kim and P. Dubey. 2010. 3.5-D Blocking Optimization for Stencil Computations on Modern CPUs and GPUs (SC '10) . 1--13.","DOI":"10.1109\/SC.2010.2"},{"key":"e_1_3_2_1_28_1","volume-title":"Stencil Pattern. https:\/\/ipcc.cs.uoregon.edu\/lectures\/lecture-8-stencil.pdf [Online","author":"C.S. Department of University of Oregon. 2014.","year":"2020"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Fabrice Rastello and Thierry Dauxois. 2002. Efficient Tiling for an ODE Discrete Integration Program: Redundant Tasks Instead of Trapezoidal Shaped-Tiles (IPDPS '02). 138--.  Fabrice Rastello and Thierry Dauxois. 2002. Efficient Tiling for an ODE Discrete Integration Program: Redundant Tasks Instead of Trapezoidal Shaped-Tiles (IPDPS '02) . 138--.","DOI":"10.1109\/IPDPS.2002.1016667"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178500"},{"key":"e_1_3_2_1_31_1","volume-title":"SC18: International Conference for High Performance Computing, Networking, Storage and Analysis. 590--602","author":"Rawat P. S."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"crossref","unstructured":"Gabriel Rivera and Chau-Wen Tseng. 2000. Tiling Optimizations for 3D Scientific Computations (SC '00). Article 32.  Gabriel Rivera and Chau-Wen Tseng. 2000. Tiling Optimizations for 3D Scientific Computations (SC '00) . Article 32.","DOI":"10.1109\/SC.2000.10015"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of 6th ECMWF Workshop on the Use of Parallel Processors in Meteorology: Coming of Age. 523--550","author":"Sawdey Aaron","year":"1995"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Yonghong Song and Zhiyuan Li. 1999. New Tiling Techniques to Improve Cache Temporal Locality (PLDI '99). 215--228.  Yonghong Song and Zhiyuan Li. 1999. New Tiling Techniques to Improve Cache Temporal Locality (PLDI '99) . 215--228.","DOI":"10.1145\/301618.301668"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/2594291.2594342"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1810085.1810096"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/1989493.1989508"},{"key":"e_1_3_2_1_38_1","article-title":"Intel\u00ae OpenMP C++\/Fortran Compiler for Hyper-Threading Technology: Implementation and Performance","volume":"6","author":"Tian Xinmin","year":"2002","journal-title":"Intel Technology Journal"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 23rd international conference on Supercomputing. 244--255","author":"Venkatasubramanian Sundaresan"},{"key":"e_1_3_2_1_40_1","volume-title":"Wikichip of Intel Xeon Gold 6140. https:\/\/en.wikichip.org\/wiki\/intel\/xeon_gold\/6140 [Online","year":"2020"},{"key":"e_1_3_2_1_41_1","volume-title":"Lam","author":"Wolf Michael E.","year":"1991"},{"key":"e_1_3_2_1_42_1","volume-title":"More Iteration Space Tiling (Supercomputing '89)","author":"Wolfe M.","year":"1989"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1015460304860"},{"key":"e_1_3_2_1_44_1","volume-title":"IMPACT 2013","author":"Wonnacott David G","year":"2013"},{"key":"e_1_3_2_1_45_1","volume-title":"Vector Folding: improving stencil performance via multidimensional SIMD-vector representation. In 2015 IEEE 17th International Conference on High Performance Computing and Communications","author":"Yount Charles","year":"2015"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/WOLFHPC.2016.08"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3337821.3337835"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126920"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/2259016.2259037"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356210"}],"event":{"name":"SC '21: The International Conference for High Performance Computing, Networking, Storage and Analysis","location":"St. Louis Missouri","acronym":"SC '21","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","IEEE CS"]},"container-title":["Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458817.3476154","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3458817.3476154","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:06Z","timestamp":1750268946000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3458817.3476154"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,13]]},"references-count":50,"alternative-id":["10.1145\/3458817.3476154","10.1145\/3458817"],"URL":"https:\/\/doi.org\/10.1145\/3458817.3476154","relation":{},"subject":[],"published":{"date-parts":[[2021,11,13]]}}}