{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:52:19Z","timestamp":1780674739844,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,8,29]]},"DOI":"10.1145\/3545008.3545032","type":"proceedings-article","created":{"date-parts":[[2023,1,15]],"date-time":"2023-01-15T01:04:08Z","timestamp":1673744648000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["IATF: An Input-Aware Tuning Framework for Compact BLAS Based on ARMv8 CPUs"],"prefix":"10.1145","author":[{"given":"Cunyang","family":"Wei","sequence":"first","affiliation":[{"name":"The Institute of Computing Technology of the Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haipeng","family":"Jia","sequence":"additional","affiliation":[{"name":"The Institute of Computing Technology of the Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Institute of Computing Technology of the Chinese Academy of Sciences, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liusha","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Qi","sequence":"additional","affiliation":[{"name":"Huawei Technologies Co., Ltd., China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,1,13]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"[n.d.]. ARM PERFORMANCE LIBRARIES. https:\/\/developer.arm.com\/tools-and-software\/server-and-hpc\/compile\/arm-compiler-for-linux\/arm-performance-libraries"},{"key":"e_1_3_2_2_2_1","unstructured":"[n.d.]. Intel oneAPI Math Kernel Library. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/onemkl.html"},{"key":"e_1_3_2_2_3_1","unstructured":"[n.d.]. OpenBLAS:An optimized BLAS library. http:\/\/www.openblas.net\/"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-41321-1_2"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3320060"},{"key":"e_1_3_2_2_6_1","unstructured":"Jean-Guillaume Dumas Cl\u00e9ment Pernet and Jean-Louis Roch. 2006. Adaptive triangular system solving. In Challenges in Symbolic Computation Software. 770."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210754"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3378671"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1377603.1377607"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"key":"e_1_3_2_2_12_1","volume-title":"International conference on learning representations.","author":"Hinton E","year":"2018","unstructured":"Geoffrey\u00a0E Hinton, Sara Sabour, and Nicholas Frosst. 2018. Matrix capsules with EM routing. In International conference on learning representations."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3178487.3178496"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126908.3126941"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356181"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2019.2939785"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2014.110"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503219"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2015.12.012"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3085578"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS.2012.97"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476217"}],"event":{"name":"ICPP '22: 51st International Conference on Parallel Processing","location":"Bordeaux France","acronym":"ICPP '22"},"container-title":["Proceedings of the 51st International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545032","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3545008.3545032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:02:43Z","timestamp":1750186963000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3545008.3545032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":23,"alternative-id":["10.1145\/3545008.3545032","10.1145\/3545008"],"URL":"https:\/\/doi.org\/10.1145\/3545008.3545032","relation":{},"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"2023-01-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}