{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T17:37:06Z","timestamp":1768412226281,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":26,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,21]],"date-time":"2023-06-21T00:00:00Z","timestamp":1687305600000},"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":[[2023,6,21]]},"DOI":"10.1145\/3577193.3593707","type":"proceedings-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T18:47:05Z","timestamp":1687286825000},"page":"111-121","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards a Unified Implementation of GEMM in BLIS"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5782-716X","authenticated-orcid":false,"given":"RuQing G.","family":"Xu","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2498-9430","authenticated-orcid":false,"given":"Field G.","family":"Van Zee","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6434-8492","authenticated-orcid":false,"given":"Robert A.","family":"van de Geijn","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.385.0563"},{"key":"e_1_3_2_1_2_1","unstructured":"Peter Cawley. 2022. Apple AMX. https:\/\/github.com\/corsix\/amx.  Peter Cawley. 2022. Apple AMX. https:\/\/github.com\/corsix\/amx."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/77626.79170"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/42288.42291"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3210754"},{"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","doi-asserted-by":"publisher","DOI":"10.1145\/1377603.1377607"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2016.83"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the International Conference for High Performance Computing, Networking, Storage Analysis (SC'16)","author":"Huang Jianyu","unstructured":"Jianyu Huang , Tyler M. Smith , Greg M. Henry , and Robert A . van de Geijn. 2016. Strassen's Algorithm Reloaded . In Proceedings of the International Conference for High Performance Computing, Networking, Storage Analysis (SC'16) (Salt Lake City, Utah). Article 59. http:\/\/dl.acm.org\/citation.cfm?id=3014904.3014983 Jianyu Huang, Tyler M. Smith, Greg M. Henry, and Robert A. van de Geijn. 2016. Strassen's Algorithm Reloaded. In Proceedings of the International Conference for High Performance Computing, Networking, Storage Analysis (SC'16) (Salt Lake City, Utah). Article 59. http:\/\/dl.acm.org\/citation.cfm?id=3014904.3014983"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3519939.3523446"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3534933"},{"key":"e_1_3_2_1_13_1","first-page":"3","article-title":"Basic Linear Algebra Subprograms for Fortran Usage","volume":"5","author":"Lawson C. L.","year":"1979","unstructured":"C. L. Lawson , R. J. Hanson , D. R. Kincaid , and F. T. Krogh . 1979 . Basic Linear Algebra Subprograms for Fortran Usage . ACM Trans. Math. Soft. 5 , 3 (Sept. 1979). C. L. Lawson, R. J. Hanson, D. R. Kincaid, and F. T. Krogh. 1979. Basic Linear Algebra Subprograms for Fortran Usage. ACM Trans. Math. Soft. 5, 3 (Sept. 1979).","journal-title":"ACM Trans. Math. Soft."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2925987"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1137\/16M108968X"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the 28th International Parallel and Distributed Processing Symposium (IPDPS). 1049--1059","author":"Smith Tyler M","unstructured":"Tyler M Smith , Robert van de Geijn, Mikhail Smelyanskiy, Jeff R Hammond, and Field G Van Zee. 2014. Anatomy of high-performance many-threaded matrix multiplication . In Proceedings of the 28th International Parallel and Distributed Processing Symposium (IPDPS). 1049--1059 . Tyler M Smith, Robert van de Geijn, Mikhail Smelyanskiy, Jeff R Hammond, and Field G Van Zee. 2014. Anatomy of high-performance many-threaded matrix multiplication. In Proceedings of the 28th International Parallel and Distributed Processing Symposium (IPDPS). 1049--1059."},{"key":"e_1_3_2_1_17_1","volume-title":"van de Geijn","author":"Smith Tyler M.","year":"2019","unstructured":"Tyler M. Smith and Robert A . van de Geijn . 2019 . The MOMMS Family of Matrix Multiplication Algorithms. CoRR abs\/1904.05717 (2019). arXiv:1904.05717 http:\/\/arxiv.org\/abs\/1904.05717 Tyler M. Smith and Robert A. van de Geijn. 2019. The MOMMS Family of Matrix Multiplication Algorithms. CoRR abs\/1904.05717 (2019). arXiv:1904.05717 http:\/\/arxiv.org\/abs\/1904.05717"},{"key":"e_1_3_2_1_18_1","unstructured":"Vijay Thakkar Pradeep Ramani Cris Cecka Aniket Shivam Honghao Lu Ethan Yan Jack Kosaian Mark Hoemmen Haicheng Wu Andrew Kerr Matt Nicely Duane Merrill Dustyn Blasig Fengqi Qiao Piotr Majcher Paul Springer Markus Hohnerbach Jin Wang and Manish Gupta. 2023. CUTLASS. https:\/\/github.com\/NVIDIA\/cutlass  Vijay Thakkar Pradeep Ramani Cris Cecka Aniket Shivam Honghao Lu Ethan Yan Jack Kosaian Mark Hoemmen Haicheng Wu Andrew Kerr Matt Nicely Duane Merrill Dustyn Blasig Fengqi Qiao Piotr Majcher Paul Springer Markus Hohnerbach Jin Wang and Manish Gupta. 2023. CUTLASS. https:\/\/github.com\/NVIDIA\/cutlass"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_2_1_20_1","unstructured":"Field G. Van Zee. 2019. BLIS Performance. https:\/\/github.com\/flame\/blis\/blob\/master\/docs\/Performance.md.  Field G. Van Zee. 2019. BLIS Performance. https:\/\/github.com\/flame\/blis\/blob\/master\/docs\/Performance.md."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1137\/19M1282040"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3086466"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/2755561"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/2764454"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8191(00)00086-7"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807601"},{"key":"e_1_3_2_1_27_1","unstructured":"Xianyi Zhang. 2011. OpenBLAS. http:\/\/www.openblas.net.  Xianyi Zhang. 2011. OpenBLAS. http:\/\/www.openblas.net."}],"event":{"name":"ICS '23: 37th International Conference on Supercomputing","location":"Orlando FL USA","acronym":"ICS '23","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 37th International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577193.3593707","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:47:31Z","timestamp":1750178851000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3577193.3593707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,21]]},"references-count":26,"alternative-id":["10.1145\/3577193.3593707","10.1145\/3577193"],"URL":"https:\/\/doi.org\/10.1145\/3577193.3593707","relation":{},"subject":[],"published":{"date-parts":[[2023,6,21]]},"assertion":[{"value":"2023-06-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}