{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T13:04:39Z","timestamp":1751634279611},"reference-count":22,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013,12]]},"DOI":"10.1109\/hipc.2013.6799109","type":"proceedings-article","created":{"date-parts":[[2014,5,2]],"date-time":"2014-05-02T18:26:14Z","timestamp":1399055174000},"source":"Crossref","is-referenced-by-count":17,"title":["Accelerating Strassen-Winograd's matrix multiplication algorithm on GPUs"],"prefix":"10.1109","author":[{"given":"Pai-Wei","family":"Lai","sequence":"first","affiliation":[]},{"given":"Humayun","family":"Arafat","sequence":"additional","affiliation":[]},{"given":"Venmugil","family":"Elango","sequence":"additional","affiliation":[]},{"given":"P.","family":"Sadayappan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/SC.1998.10045"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1007\/BF02165411"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1986.52"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1137\/0210032"},{"key":"16","author":"stothers","year":"2010","journal-title":"On the Complexity of Matrix Multiplication"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/SFCS.1979.17"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1137\/0209027"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2011.130"},{"key":"12","first-page":"10101","article-title":"Communicationavoiding parallel strassen: Implementation and performance","author":"lipshitz","year":"2012","journal-title":"Proceedings of the International Conference on High Performance Computing Networking Storage and Analysis SC '12"},{"key":"21","year":"0"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/S0747-7171(08)80013-2"},{"key":"20","year":"0"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1145\/1576702.1576713"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1137\/0909040"},{"key":"10","year":"0"},{"key":"7","year":"0"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1080\/10637199408915454"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1006\/jcph.1994.1001"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"9","article-title":"On the comparative performance of parallel algorithms on small GPU\/CUDA clusters","author":"karunadasa","year":"2009","journal-title":"Pages Student Research Symposium Cochin India On-line Proceedings"},{"key":"8","doi-asserted-by":"crossref","DOI":"10.1145\/369028.369096","article-title":"Implementation of strassen's algorithm for matrix multiplication","author":"huss-lederman","year":"1996","journal-title":"Proceedings of the 1996 ACM\/IEEE Conference on Supercomputing (CDROM) Supercomputing '96"}],"event":{"name":"2013 20th International Conference on High Performance Computing (HiPC)","location":"Bengaluru (Bangalore), Karnataka, India","start":{"date-parts":[[2013,12,18]]},"end":{"date-parts":[[2013,12,21]]}},"container-title":["20th Annual International Conference on High Performance Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6784161\/6799095\/06799109.pdf?arnumber=6799109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T12:33:43Z","timestamp":1498134823000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6799109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/hipc.2013.6799109","relation":{},"subject":[],"published":{"date-parts":[[2013,12]]}}}