{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T04:16:49Z","timestamp":1777954609413,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","funder":[{"name":"National Science Foundation","award":["2316176"],"award-info":[{"award-number":["2316176"]}]},{"name":"U.S. Department of Energy, Office of Science","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,16]]},"DOI":"10.1145\/3694906.3743357","type":"proceedings-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T16:19:56Z","timestamp":1752682796000},"page":"582-586","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Brief Announcement: Optimality Conditions for Parallel Communication-Avoiding Matrix Multiplication with Overlapped Communication"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2599-9741","authenticated-orcid":false,"given":"Mikhail","family":"Isaev","sequence":"first","affiliation":[{"name":"NVIDIA, Atlanta, Georgia, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3418-7796","authenticated-orcid":false,"given":"Srinivas","family":"Eswar","sequence":"additional","affiliation":[{"name":"Argonne National Laboratory, Lemont, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2178-138X","authenticated-orcid":false,"given":"Richard","family":"Vuduc","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, Georgia, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.395.0575"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1147\/rd.386.0673"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3490148.3538552"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2312005.2312021"},{"key":"e_1_3_2_1_5_1","unstructured":"Lynn Elliot Cannon. 1969. A cellular computer to implement the kalman filter algorithm. Ph.D. Dissertation. Montana State University USA. AAI7010025."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.4330060702"},{"key":"e_1_3_2_1_7_1","unstructured":"Hussam Al Daas Grey Ballard Laura Grigori Suraj Kumar and Kathryn Rouse. 2022. Tight Memory-Independent Parallel Matrix Multiplication Communication Lower Bounds. arXiv:2205.13407 [cs.DC]"},{"key":"e_1_3_2_1_8_1","unstructured":"James Demmel. 1996. CS267 Applications of Parallel Computers: Lecture 9 (part 2) Parallel Matrix Multiplication. https:\/\/people.eecs.berkeley.edu\/~demmel\/cs267\/lecture11\/lecture11.html"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2013.80"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2012.32"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2004.03.021"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356181"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2427023.2427030"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1137\/140993478"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23397-5_10"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1096-9128(199704)9:4<255::AID-CPE250>3.0.CO;2-2"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3567955.3567959"}],"event":{"name":"SPAA '25: 37th ACM Symposium on Parallelism in Algorithms and Architectures","location":"Portland OR USA","acronym":"SPAA '25","sponsor":["SIGACT ACM Special Interest Group on Algorithms and Computation Theory","SIGARCH ACM Special Interest Group on Computer Architecture","EATCS European Association for Theoretical Computer Science"]},"container-title":["Proceedings of the 37th ACM Symposium on Parallelism in Algorithms and Architectures"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3694906.3743357","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:19:47Z","timestamp":1777922387000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3694906.3743357"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":17,"alternative-id":["10.1145\/3694906.3743357","10.1145\/3694906"],"URL":"https:\/\/doi.org\/10.1145\/3694906.3743357","relation":{},"subject":[],"published":{"date-parts":[[2025,7,16]]},"assertion":[{"value":"2025-07-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}