{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:34:59Z","timestamp":1773192899061,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","license":[{"start":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T00:00:00Z","timestamp":1554336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["CONIX CMU 1042741-394324 AM01"],"award-info":[{"award-number":["CONIX CMU 1042741-394324 AM01"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004356","name":"Nokia","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004356","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ACI OAC--1535191"],"award-info":[{"award-number":["ACI OAC--1535191"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Mozilla"},{"DOI":"10.13039\/100005144","name":"Qualcomm","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005144","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2019,4,4]]},"DOI":"10.1145\/3297858.3304059","type":"proceedings-article","created":{"date-parts":[[2019,4,4]],"date-time":"2019-04-04T18:38:43Z","timestamp":1554403123000},"page":"65-78","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["Swizzle Inventor"],"prefix":"10.1145","author":[{"given":"Phitchaya Mangpo","family":"Phothilimthana","sequence":"first","affiliation":[{"name":"University of California, Berkeley & Google Brain, Berkeley, CA, USA"}]},{"given":"Archibald Samuel","family":"Elliott","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}]},{"given":"An","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}]},{"given":"Abhinav","family":"Jangda","sequence":"additional","affiliation":[{"name":"University of Massachusetts Amherst, Amherst, MA, USA"}]},{"given":"Bastian","family":"Hagedorn","sequence":"additional","affiliation":[{"name":"University of M\u00fcnster, M\u00fcnster, Germany"}]},{"given":"Henrik","family":"Barthels","sequence":"additional","affiliation":[{"name":"RWTH Aachen University, Aachen, Germany"}]},{"given":"Samuel J.","family":"Kaufman","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}]},{"given":"Vinod","family":"Grover","sequence":"additional","affiliation":[{"name":"NVIDIA, Redmond, WA, USA"}]},{"given":"Emina","family":"Torlak","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}]},{"given":"Rastislav","family":"Bodik","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}]}],"member":"320","published-online":{"date-parts":[[2019,4,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2442516.2442529"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/1375527.1375562"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925426.2926259"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"James Bornholt Emina Torlak Dan Grossman and Luis Ceze. 2016. Optimizing Synthesis with Metasketches. In Principles of Programming Languages (POPL). 10.1145\/2837614.2837666","DOI":"10.1145\/2837614.2837666"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Eric Butler Emina Torlak and Zoran Popovi\u0107. 2018. A Framework for Computer-Aided Design of Educational Domain Models. In Verification Model Checking and Abstract Interpretation (VMCAI) Isil Dillig and Jens Palsberg (Eds.).","DOI":"10.1007\/978-3-319-73721-8_7"},{"key":"e_1_3_2_1_6_1","unstructured":"Bryan Catanzaro. 2018. Trove. https:\/\/github.com\/bryancatanzaro\/trove ."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Bryan Catanzaro Alexander Keller and Michael Garland. 2014. A Decomposition for In-place Matrix Transposition. In Principles and Practice of Parallel Programming (PPoPP). 10.1145\/2555243.2555253","DOI":"10.1145\/2555243.2555253"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342007078442"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/1898699.1898801"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3168824"},{"key":"e_1_3_2_1_11_1","unstructured":"Matan Hamilis. 2018. https:\/\/github.com\/HamilM\/GpuBinFieldMult ."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2304576.2304619"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3079079.3079105"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3075564.3075583"},{"key":"e_1_3_2_1_15_1","unstructured":"Forrest Iandola. 2018. https:\/\/github.com\/forresti\/convolution."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2013.6738436"},{"issue":"1","key":"e_1_3_2_1_17_1","first-page":"0","article-title":"The Omega Calculator and Library","volume":"1","author":"Kelly Wayne","year":"1996","unstructured":"Wayne Kelly, Vadim Maslov, William Pugh, Evan Rosser, Tatiana Shpeisman, and Dave Wonnacott. 1996. The Omega Calculator and Library, Version 1.1.0. (1996). http:\/\/www.cs.utah.edu\/ mhall\/cs6963s09\/lectures\/omega.ps","journal-title":"Version"},{"key":"e_1_3_2_1_18_1","volume-title":"International Carnahan Conference on Security Technology (ICCST).","author":"Lee Wai-Kong","unstructured":"Wai-Kong Lee, Xian-Fu Wong, Bok-Min Goi, and Raphael C.-W. Phan. 2017. CUDA-SSL: SSL\/TLS accelerated by GPU. In International Carnahan Conference on Security Technology (ICCST)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/305138.305197"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/2908080.2908122"},{"key":"e_1_3_2_1_21_1","volume-title":"NVIDIA Performance Primitives. https:\/\/developer.nvidia.com\/npp. Accessed","author":"NVIDIA.","year":"2019","unstructured":"NVIDIA. 2019. NVIDIA Performance Primitives. https:\/\/developer.nvidia.com\/npp. Accessed 15 January 2019."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/109025.109108"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1629911.1630074"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","unstructured":"Armando Solar-Lezama Gilad Arnold Liviu Tancau Rastislav Bodik Vijay Saraswat and Sanjit Seshia. 2007. Sketching Stencils. In Programming Language Design and Implementation (PLDI). 10.1145\/1250734.1250754","DOI":"10.1145\/1250734.1250754"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","unstructured":"Armando Solar-Lezama Rodric Rabbah Rastislav Bod'ik and Kemal Ebciouglu. 2005. Programming by Sketching for Bit-streaming Programs. In Programming Language Design and Implementation (PLDI). 10.1145\/1065010.1065045","DOI":"10.1145\/1065010.1065045"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2509578.2509586"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","unstructured":"Emina Torlak and Rastislav Bodik. 2014. A Lightweight Symbolic Virtual Machine for Solver-aided Host Languages. In Programming Language Design and Implementation (PLDI). 10.1145\/2594291.2594340","DOI":"10.1145\/2594291.2594340"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400713"},{"key":"e_1_3_2_1_29_1","volume-title":"Communication Optimization on GPU: A Case Study of Sequence Alignment Algorithms. In International Parallel and Distributed Processing Symposium (IPDPS).","author":"Wang Jie","year":"2017","unstructured":"Jie Wang, Xinfeng Xie, and Jason Cong. 2017. Communication Optimization on GPU: A Case Study of Sequence Alignment Algorithms. In International Parallel and Distributed Processing Symposium (IPDPS)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.31"},{"key":"e_1_3_2_1_32_1","unstructured":"Pavan Yalamanchili Umar Arshad Zakiuddin Mohammed Pradeep Garigipati Peter Entschev Brian Kloppenborg James Malcolm and John Melonakos. 2015. ArrayFire: A High Performance Software Library for Parallel Computing with an Easy-To-Use API. https:\/\/github.com\/arrayfire\/arrayfire."}],"event":{"name":"ASPLOS '19: Architectural Support for Programming Languages and Operating Systems","location":"Providence RI USA","acronym":"ASPLOS '19","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304059","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304059","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3297858.3304059","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T23:53:15Z","timestamp":1750204395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3297858.3304059"}},"subtitle":["Data Movement Synthesis for GPU Kernels"],"short-title":[],"issued":{"date-parts":[[2019,4,4]]},"references-count":31,"alternative-id":["10.1145\/3297858.3304059","10.1145\/3297858"],"URL":"https:\/\/doi.org\/10.1145\/3297858.3304059","relation":{},"subject":[],"published":{"date-parts":[[2019,4,4]]},"assertion":[{"value":"2019-04-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}