{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T18:10:26Z","timestamp":1791223826110,"version":"4.1.0"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2013,11,17]],"date-time":"2013-11-17T00:00:00Z","timestamp":1384646400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["0833203, 0747357"],"award-info":[{"award-number":["0833203, 0747357"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC001770"],"award-info":[{"award-number":["DE-SC001770"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61272136, 61133005"],"award-info":[{"award-number":["61272136, 61133005"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002855","name":"Ministry of Science and Technology of the People's Republic of China","doi-asserted-by":"publisher","award":["2012AA010903"],"award-info":[{"award-number":["2012AA010903"]}],"id":[{"id":"10.13039\/501100002855","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2013,11,17]]},"DOI":"10.1145\/2503210.2503219","type":"proceedings-article","created":{"date-parts":[[2013,10,30]],"date-time":"2013-10-30T08:55:22Z","timestamp":1383123322000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":151,"title":["AUGEM"],"prefix":"10.1145","author":[{"given":"Qian","family":"Wang","sequence":"first","affiliation":[{"name":"University of Chinese, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Yi","sequence":"additional","affiliation":[{"name":"University of Colorado at Colorado Springs, Colorado"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2013,11,17]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"10","year":"2012","unstructured":"Advanced Micro Devices, Inc . AMD New Bulldozer and Piledriver Instructions , 2012 . 10 . Advanced Micro Devices, Inc. AMD New Bulldozer and Piledriver Instructions, 2012.10.","journal-title":"AMD New Bulldozer and Piledriver Instructions"},{"key":"e_1_3_2_1_2_1","volume-title":"Communication-optimal parallel algorithm for strassen's matrix multiplication. CoRR, abs\/1202.3173","author":"Ballard G.","year":"2012","unstructured":"G. Ballard , J. Demmel , O. Holtz , B. Lipshitz , and O. Schwartz . Communication-optimal parallel algorithm for strassen's matrix multiplication. CoRR, abs\/1202.3173 , 2012 . G. Ballard, J. Demmel, O. Holtz, B. Lipshitz, and O. Schwartz. Communication-optimal parallel algorithm for strassen's matrix multiplication. CoRR, abs\/1202.3173, 2012."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2395116.2395121"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/1654059.1654119"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/263580.263662"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2005.10"},{"key":"e_1_3_2_1_7_1","volume-title":"Morgan Kaufmann","author":"Cooper K.","year":"2004","unstructured":"K. Cooper and L. Torczon . Engineering a Compiler . Morgan Kaufmann , 2004 . K. Cooper and L. Torczon. Engineering a Compiler. Morgan Kaufmann, 2004."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2011.33"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2190025.2190058"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2400682.2400694"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/1274971.1275010"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1377603.1377607"},{"key":"e_1_3_2_1_14_1","volume-title":"ACM","author":"Siek J. G.","year":"2008","unstructured":"J. G. Siek and M. Vachharajani . Build to order linear algebra kernels. In DLS, page 7 . ACM , 2008 . J. G. Siek and M. Vachharajani. Build to order linear algebra kernels. In DLS, page 7. ACM, 2008."},{"key":"e_1_3_2_1_15_1","volume-title":"SuperComputing 1998: High Performance Networking and Computing","author":"Whaley R. C.","year":"1998","unstructured":"R. C. Whaley and J. Dongarra . Automatically tuned linear algebra software . In SuperComputing 1998: High Performance Networking and Computing , 1998 . R. C. Whaley and J. Dongarra. Automatically tuned linear algebra software. In SuperComputing 1998: High Performance Networking and Computing, 1998."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00087-9"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2190025.2190057"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1002\/spe.1089"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-89740-8_24"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2007.370637"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2012.97"}],"event":{"name":"SC13: International Conference for High Performance Computing, Networking, Storage and Analysis","location":"Denver Colorado","acronym":"SC13","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 Computer Society"]},"container-title":["Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2503210.2503219","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/2503210.2503219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:18:55Z","timestamp":1750220335000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/2503210.2503219"}},"subtitle":["automatically generate high performance dense linear algebra kernels on x86 CPUs"],"short-title":[],"issued":{"date-parts":[[2013,11,17]]},"references-count":21,"alternative-id":["10.1145\/2503210.2503219","10.1145\/2503210"],"URL":"https:\/\/doi.org\/10.1145\/2503210.2503219","relation":{},"subject":[],"published":{"date-parts":[[2013,11,17]]},"assertion":[{"value":"2013-11-17","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}