{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:40:02Z","timestamp":1763458802111,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":25,"publisher":"ACM","license":[{"start":{"date-parts":[[2016,11,15]],"date-time":"2016-11-15T00:00:00Z","timestamp":1479168000000},"content-version":"vor","delay-in-days":366,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC-0010042"],"award-info":[{"award-number":["DE-SC-0010042"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2015,11,15]]},"DOI":"10.1145\/2834899.2834907","type":"proceedings-article","created":{"date-parts":[[2015,11,9]],"date-time":"2015-11-09T11:29:04Z","timestamp":1447068544000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["GPU-accelerated co-design of induced dimension reduction"],"prefix":"10.1145","author":[{"given":"Hartwig","family":"Anzt","sequence":"first","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eduardo","family":"Ponce","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory D.","family":"Peterson","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jack","family":"Dongarra","sequence":"additional","affiliation":[{"name":"University of Tennessee, Knoxville, Tennessee"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2015,11,15]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"The induced dimension reduction method; http:\/\/ta.twi.tudelft.nl\/nw\/users\/gijzen\/IDR.html."},{"key":"e_1_3_2_1_2_1","unstructured":"The top 500 list http:\/\/www.top.org\/."},{"key":"e_1_3_2_1_3_1","volume-title":"http:\/\/viennacl.sourceforge.net\/","author":"CL.","year":"2015","unstructured":"ViennaCL. http:\/\/viennacl.sourceforge.net\/, 2015."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPP.2013.41"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-48096-0_52"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342015580139"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049663"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-14325-5_2"},{"key":"e_1_3_2_1_9_1","volume-title":"Optimizing CUDA code by kernel fusion---application on BLAS. CoRR, abs\/1305.1183","author":"Filipovic J.","year":"2013","unstructured":"J. Filipovic, M. Madzin, J. Fousek, and L. Matyska. Optimizing CUDA code by kernel fusion---application on BLAS. CoRR, abs\/1305.1183, 2013."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2011.07.021"},{"key":"e_1_3_2_1_11_1","volume-title":"ExaScale computing study: Technology challenges in achieving ExaScale systems","author":"Kogge P.","year":"2008","unstructured":"P. Kogge et al. ExaScale computing study: Technology challenges in achieving ExaScale systems, 2008."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-012-0825-3"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.5555\/2338816.2338829"},{"key":"e_1_3_2_1_14_1","volume-title":"http:\/\/icl.cs.utk.edu\/magma\/","author":"AGMA","year":"2015","unstructured":"MAGMA 1.6.2. http:\/\/icl.cs.utk.edu\/magma\/, 2015."},{"key":"e_1_3_2_1_15_1","volume-title":"http:\/\/www.paralution.com\/","author":"PARALUTION.","year":"2015","unstructured":"PARALUTION. http:\/\/www.paralution.com\/, 2015."},{"key":"e_1_3_2_1_16_1","volume-title":"March","author":"NVIDIA Corporation","year":"2015","unstructured":"NVIDIA Corporation. CUDA Toolkit v7.0, March 2015."},{"key":"e_1_3_2_1_17_1","volume-title":"March","author":"NVIDIA Corporation","year":"2015","unstructured":"NVIDIA Corporation. cuSPARSE Toolkit v7.0, v7.0 edition, March 2015."},{"key":"e_1_3_2_1_18_1","volume-title":"March","author":"NVIDIA Corporation v7.0.","year":"2015","unstructured":"NVIDIA Corporation v7.0. CUDA cuBLAS Toolkit, March 2015."},{"key":"e_1_3_2_1_19_1","volume-title":"17th Conference of the International Linear Algebra Society","author":"Rendel O.","year":"2011","unstructured":"O. Rendel, A. Rizvanolli, and J.-P. M. Zemke. IDR: A new generation of Krylov subspace methods? Linear Algebra and its Applications, 439(4):1040--1061, 2013. 17th Conference of the International Linear Algebra Society, Braunschweig, Germany, August 2011."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.5555\/829576"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1137\/090774756"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1137\/070685804"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-014-1102-4"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2049662.2049667"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/GreenCom-CPSCom.2010.102"}],"event":{"name":"SC15: The International Conference for High Performance Computing, Networking, Storage and Analysis","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture","IEEE-CS\\DATC IEEE Computer Society"],"location":"Austin Texas","acronym":"SC15"},"container-title":["Proceedings of the 2nd International Workshop on Hardware-Software Co-Design for High Performance Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2834899.2834907","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2834899.2834907","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2834899.2834907","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T09:35:26Z","timestamp":1763458526000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2834899.2834907"}},"subtitle":["algorithmic fusion and kernel overlap"],"short-title":[],"issued":{"date-parts":[[2015,11,15]]},"references-count":25,"alternative-id":["10.1145\/2834899.2834907","10.1145\/2834899"],"URL":"https:\/\/doi.org\/10.1145\/2834899.2834907","relation":{},"subject":[],"published":{"date-parts":[[2015,11,15]]},"assertion":[{"value":"2015-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}