{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:19:42Z","timestamp":1774365582279,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":4,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T00:00:00Z","timestamp":1676937600000},"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":[[2023,2,25]]},"DOI":"10.1145\/3572848.3577479","type":"proceedings-article","created":{"date-parts":[[2023,2,21]],"date-time":"2023-02-21T16:02:30Z","timestamp":1676995350000},"page":"429-431","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Stream-K"],"prefix":"10.1145","author":[{"given":"Muhammad","family":"Osama","sequence":"first","affiliation":[{"name":"University of California, Davis"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Duane","family":"Merrill","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cris","family":"Cecka","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Garland","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John D.","family":"Owens","sequence":"additional","affiliation":[{"name":"University of California, Davis"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,2,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2818311"},{"key":"e_1_3_2_1_2_1","volume-title":"CUTLASS: Fast Linear Algebra in CUDA C++.","author":"Kerr Andrew","year":"2017","unstructured":"Andrew Kerr, Duane Merrill, Julien Demouth, and John Tran. 2017. CUTLASS: Fast Linear Algebra in CUDA C++. (2017). https:\/\/devblogs.nvidia.com\/cutlass-linear-algebra-cuda\/"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/1094342010385729"},{"key":"e_1_3_2_1_4_1","unstructured":"NVIDIA Corporation. 2007--2022. CUDA C++ Programming Guide. (Dec. 2007--2022). https:\/\/docs.nvidia.com\/cuda\/ PG-02829-001_v12.0."}],"event":{"name":"PPoPP '23: The 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","location":"Montreal QC Canada","acronym":"PPoPP '23","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing"]},"container-title":["Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577479","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3572848.3577479","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:08:09Z","timestamp":1750183689000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3572848.3577479"}},"subtitle":["Work-Centric Parallel Decomposition for Dense Matrix-Matrix Multiplication on the GPU"],"short-title":[],"issued":{"date-parts":[[2023,2,21]]},"references-count":4,"alternative-id":["10.1145\/3572848.3577479","10.1145\/3572848"],"URL":"https:\/\/doi.org\/10.1145\/3572848.3577479","relation":{},"subject":[],"published":{"date-parts":[[2023,2,21]]},"assertion":[{"value":"2023-02-21","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}