{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:26:17Z","timestamp":1750220777536,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,4,14]],"date-time":"2020-04-14T00:00:00Z","timestamp":1586822400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Hunan Science and Technology Plan Project Funding","award":["2018XK2102"],"award-info":[{"award-number":["2018XK2102"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,4,14]]},"DOI":"10.1145\/3397125.3397140","type":"proceedings-article","created":{"date-parts":[[2020,5,30]],"date-time":"2020-05-30T04:36:16Z","timestamp":1590813376000},"page":"122-128","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Design of GEMM Parallel Computing Accelerator Based on Vector SIMD Technology"],"prefix":"10.1145","author":[{"given":"YunPing","family":"Zhao","sequence":"first","affiliation":[{"name":"Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China"}]},{"given":"JianZhuang","family":"Lu","sequence":"additional","affiliation":[{"name":"Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China"}]},{"given":"XiaoWen","family":"Chen","sequence":"additional","affiliation":[{"name":"Natl Univ Def Technol, Coll Comp, Changsha, Hunan, Peoples R China"}]}],"member":"320","published-online":{"date-parts":[[2020,5,29]]},"reference":[{"key":"e_1_3_2_1_1_1","first-page":"214","article-title":"testing and analysis of BLAS libraries on multi-core CPUs.","volume":"21","author":"Chen Shao Hu","year":"2010","journal-title":"Journal of Software"},{"key":"e_1_3_2_1_2_1","unstructured":"Wang Yang Tao Huamin. Research on hardware acceleration technology of matrix multiplier based on pulse array[J] 2015 31(11):120--124  Wang Yang Tao Huamin. Research on hardware acceleration technology of matrix multiplier based on pulse array[J] 2015 31(11):120--124"},{"key":"e_1_3_2_1_3_1","unstructured":"Jia Xun Wu Guiming Xie Xianghui Wu Dong. Research on double precision floating point matrix multiplication coprocessor [J]. Computer research and development 19 59 410--420  Jia Xun Wu Guiming Xie Xianghui Wu Dong. Research on double precision floating point matrix multiplication coprocessor [J]. Computer research and development 19 59 410--420"},{"volume-title":"CHINA","year":"2019","author":"Raehyun Kim","key":"e_1_3_2_1_4_1"},{"key":"e_1_3_2_1_5_1","article-title":"Dual-Addressing Non-Volatile Memory Architecture Supporting Both Row and Column Memory Accesses[J]","volume":"239","author":"Li S","year":"2019","journal-title":"IEEE Transactions on Computers"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-58485-9_8"},{"key":"e_1_3_2_1_7_1","article-title":"GEMM kernels on the Intel KNL and Intel Skylake-SP processors[J]","volume":"7895","author":"Lim Roktaek","year":"2019","journal-title":"Journal of Supercomputing"},{"key":"e_1_3_2_1_8_1","unstructured":"Shen Junzhong Xiao Tao. A matrix multiplier accelerator design to support the optimization of partitioning strategy [J] computer engineering and science 2016 38(9): 1748--1754.  Shen Junzhong Xiao Tao. A matrix multiplier accelerator design to support the optimization of partitioning strategy [J] computer engineering and science 2016 38(9): 1748--1754."},{"key":"e_1_3_2_1_9_1","first-page":"408","article-title":"Large matrix multiplication on a novel heterogeneous parallel DSP architecture\/\/Preceedings of the 8th International Symposium on Advanced","volume":"20009","author":"Sohl J","journal-title":"Springer"},{"key":"e_1_3_2_1_10_1","unstructured":"H T Kung C E Leiserson. Systolic Arrays [R]. 1978  H T Kung C E Leiserson. Systolic Arrays [R]. 1978"},{"issue":"10","key":"e_1_3_2_1_11_1","first-page":"2251","article-title":"Matrix multiplication and vectorization for multi-core vector processors [J]","volume":"41","author":"Liu Zhong","year":"2018","journal-title":"Journal of Computer Science"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2012.132"}],"event":{"name":"ICCTA '20: 2020 6th International Conference on Computer and Technology Applications","acronym":"ICCTA '20","location":"Antalya Turkey"},"container-title":["Proceedings of the 2020 6th International Conference on Computer and Technology Applications"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397125.3397140","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3397125.3397140","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:41:25Z","timestamp":1750200085000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3397125.3397140"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,14]]},"references-count":12,"alternative-id":["10.1145\/3397125.3397140","10.1145\/3397125"],"URL":"https:\/\/doi.org\/10.1145\/3397125.3397140","relation":{},"subject":[],"published":{"date-parts":[[2020,4,14]]},"assertion":[{"value":"2020-05-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}