{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:03:43Z","timestamp":1750309423134,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,3]],"date-time":"2024-06-03T00:00:00Z","timestamp":1717372800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,3]]},"DOI":"10.1145\/3659997.3660032","type":"proceedings-article","created":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T16:51:06Z","timestamp":1726073466000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Mapping Parallel Matrix Multiplication in GotoBLAS2 to the AMD Versal ACAP for Deep Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9998-9503","authenticated-orcid":false,"given":"Jie","family":"Lei","sequence":"first","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5454-165X","authenticated-orcid":false,"given":"Enrique S.","family":"Quintana-Ort\u00ed","sequence":"additional","affiliation":[{"name":"Universitat Polit\u00e8cnica de Val\u00e8ncia, Valencia, Spain"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,9,11]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875639"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/N-SSC.2007.4785534"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2023.102990"},{"key":"e_1_3_2_1_5_1","volume-title":"Is Moore's Law Slowing Down? What's Next? IEEE Micro 37, 04","author":"Eeckhout Lieven","year":"2017","unstructured":"Lieven Eeckhout. 2017. Is Moore's Law Slowing Down? What's Next? IEEE Micro 37, 04 (2017), 4--5."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/1356052.1356053"},{"key":"e_1_3_2_1_7_1","unstructured":"Sehoon Kim et al. 2023. Full Stack Optimization of Transformer Inference: a Survey. arXiv:2302.14017 [cs.CL] arXiv cs.CL 2302.14017."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/PDP59025.2023.00043"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925987"},{"key":"e_1_3_2_1_10_1","unstructured":"Cristina Silvano et al. 2023. A Survey on Deep Learning Hardware Accelerators for Heterogeneous HPC Platforms. arXiv:2306.15552 [cs.AR]"},{"key":"e_1_3_2_1_11_1","first-page":"2","article-title":"2016","volume":"42","author":"Van Zee Field G.","year":"2016","unstructured":"Field G. Van Zee et al. 2016. The BLIS Framework: Experiments in Portability. ACM Trans. Math. Softw. 42, 2, Article 12 (2016), 12:1--12:19 pages.","journal-title":"The BLIS Framework: Experiments in Portability. ACM Trans. Math. Softw."},{"key":"e_1_3_2_1_12_1","first-page":"3","article-title":"Van Zee and Robert A. van de Geijn. 2015","volume":"41","author":"Field","year":"2015","unstructured":"Field G. Van Zee and Robert A. van de Geijn. 2015. BLIS: A Framework for Rapidly Instantiating BLAS Functionality. ACM Trans. Math. Softw. 41, 3 (2015), 14:1--14:33.","journal-title":"BLIS: A Framework for Rapidly Instantiating BLAS Functionality. ACM Trans. Math. Softw."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/HCS49909.2020.9220682"}],"event":{"name":"PECS '24: 4th Workshop on Performance and Energy Efficiency in Concurrent and Distributed Systems","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"],"location":"Pisa Italy","acronym":"PECS '24"},"container-title":["Proceedings of the 4th Workshop on Performance and Energy Efficiency in Concurrent and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659997.3660032","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3659997.3660032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:58:30Z","timestamp":1750294710000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3659997.3660032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,3]]},"references-count":12,"alternative-id":["10.1145\/3659997.3660032","10.1145\/3659997"],"URL":"https:\/\/doi.org\/10.1145\/3659997.3660032","relation":{},"subject":[],"published":{"date-parts":[[2024,6,3]]},"assertion":[{"value":"2024-09-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}