{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:31:18Z","timestamp":1771468278802,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2012,6,25]],"date-time":"2012-06-25T00:00:00Z","timestamp":1340582400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2012,6,25]]},"DOI":"10.1145\/2304576.2304626","type":"proceedings-article","created":{"date-parts":[[2012,6,27]],"date-time":"2012-06-27T13:31:21Z","timestamp":1340803881000},"page":"377-386","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["An optimized large-scale hybrid DGEMM design for CPUs and ATI GPUs"],"prefix":"10.1145","author":[{"given":"Jiajia","family":"Li","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingjian","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangming","family":"Tan","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ninghui","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2012,6,25]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD Accelerated Parallel Processing Math Libraries.  AMD Accelerated Parallel Processing Math Libraries."},{"key":"e_1_3_2_1_2_1","unstructured":"AMD Core Math Library for Graphic Processors.  AMD Core Math Library for Graphic Processors."},{"key":"e_1_3_2_1_3_1","unstructured":"HPL - a portable implementation of the high-performance linpack benchmark for distributed-memory computers.  HPL - a portable implementation of the high-performance linpack benchmark for distributed-memory computers."},{"key":"e_1_3_2_1_4_1","unstructured":"ATI Stream SDK CAL Programming Guide v2.0 2010.  ATI Stream SDK CAL Programming Guide v2.0 2010."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/110382.110385"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2004.840848"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010391989"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1993498.1993516"},{"key":"e_1_3_2_1_11_1","unstructured":"C. Jang. GATLAS: GPU automatically tuned linear algebra software.  C. Jang. GATLAS: GPU automatically tuned linear algebra software."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-01970-8_89"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1964218.1964227"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010385729"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2008.4536163"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1345206.1345220"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356058.1356084"},{"key":"e_1_3_2_1_18_1","first-page":"501","volume-title":"GPU Computing Gems","volume":"2","author":"Silberstein M.","year":"2011"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542329"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/1542275.1542312"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/1413370.1413402"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2010.5452013"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTER.2010.12"}],"event":{"name":"ICS'12: International Conference on Supercomputing","location":"San Servolo Island, Venice Italy","acronym":"ICS'12","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 26th ACM international conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2304576.2304626","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2304576.2304626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T08:48:47Z","timestamp":1750236527000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2304576.2304626"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,6,25]]},"references-count":23,"alternative-id":["10.1145\/2304576.2304626","10.1145\/2304576"],"URL":"https:\/\/doi.org\/10.1145\/2304576.2304626","relation":{},"subject":[],"published":{"date-parts":[[2012,6,25]]},"assertion":[{"value":"2012-06-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}