{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T19:28:42Z","timestamp":1725391722645},"reference-count":28,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1109\/snpd.2015.7176172","type":"proceedings-article","created":{"date-parts":[[2015,8,12]],"date-time":"2015-08-12T22:38:15Z","timestamp":1439419095000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Optimizing strassen matrix multiply on GPUs"],"prefix":"10.1109","author":[{"given":"Ayaz","family":"ul Hasan Khan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mayez","family":"Al-Mouhamed","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Allam","family":"Fatayer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1080\/10637199408915454"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.113"},{"journal-title":"Intel Corporation Intel Knights Corner Software Developer Guide","year":"2012","key":"ref12"},{"journal-title":"Intel Corporation Intel Xeon Phi Coprocessor Instruction Set Architecture Reference Manual","year":"2012","key":"ref13"},{"journal-title":"Programming Massively Parallel Processors A Hands-on Approach","year":"2010","author":"kirk","key":"ref14"},{"journal-title":"Autotuning gemms for fermi Tech Rep 245 LAPACK Working Note","year":"2011","author":"kurzak","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-013-0252-y"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2011.130"},{"key":"ref18","first-page":"884","article-title":"A note on Autotuning GEMM for GPUs. In: Proceedings of the 9th Inter","author":"li","year":"2009","journal-title":"Conf on Computational Science Part I ICCS '09"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.33"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-012-0228-3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312044"},{"journal-title":"Some Remarks on FAST Multiplication of Polynomials","year":"1973","author":"winograd","key":"ref27"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1137\/0909040"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-013-0279-2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2556647.2556660"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10586-013-0329-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/28395.28396"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2464996.2465010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2010.64"},{"key":"ref1","article-title":"Exploration of automatic optimization for cuda programming","author":"al-mouhamed","year":"2014","journal-title":"International Journal of Parallel Emergent and Distributed Systems (IJPEDS)"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010385729"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-13866-8"},{"journal-title":"Nvidia CUBLAS","year":"2013","key":"ref21"},{"journal-title":"Toward and optimal algorithm for matrix multiplication SIAM News","year":"2005","author":"robinson","key":"ref24"},{"journal-title":"An Overview of Programming for Intel Xeon Processors and Intel Xeon Phi Coprocessors","year":"2012","author":"reinders","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2008.5214359"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/BF02165411"}],"event":{"name":"2015 IEEE\/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing (SNPD)","start":{"date-parts":[[2015,6,1]]},"location":"Takamatsu","end":{"date-parts":[[2015,6,3]]}},"container-title":["2015 IEEE\/ACIS 16th International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel\/Distributed Computing (SNPD)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7159154\/7176160\/07176172.pdf?arnumber=7176172","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,25]],"date-time":"2017-03-25T05:16:35Z","timestamp":1490418995000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7176172\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,6]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/snpd.2015.7176172","relation":{},"subject":[],"published":{"date-parts":[[2015,6]]}}}