{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T20:45:47Z","timestamp":1777581947965,"version":"3.51.4"},"reference-count":7,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62404033"],"award-info":[{"award-number":["62404033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62404034"],"award-info":[{"award-number":["62404034"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Scientific Research Fundation of the Education Department of Sichuan Province, China","award":["2024NSFSC1435"],"award-info":[{"award-number":["2024NSFSC1435"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Arch. Lett."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/lca.2026.3678312","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:05:32Z","timestamp":1774901132000},"page":"138-141","source":"Crossref","is-referenced-by-count":0,"title":["FlowFlash: An Efficient Dataflow Strategy for FlashAttention Execution on Systolic Arrays"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-4424-4019","authenticated-orcid":false,"given":"Baosen","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7183-422X","authenticated-orcid":false,"given":"Junjie","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3095-3242","authenticated-orcid":false,"given":"Siyu","family":"Xiao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0615-7036","authenticated-orcid":false,"given":"Y.","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Thin Solid Films and Integrated Devices, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2193"},{"key":"ref3","article-title":"TPU V5E Documentation","year":"2025"},{"key":"ref4","article-title":"NeuronCore","year":"2024"},{"key":"ref5","article-title":"SystolicAttention: Fusing flashattention within a single systolic array","author":"Lin","year":"2025"},{"key":"ref6","article-title":"The LLAMA 3 herd of models","author":"Dubey","year":"2024"},{"key":"ref7","article-title":"Qwen technical report","author":"Bai","year":"2023"}],"container-title":["IEEE Computer Architecture Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10208\/11321093\/11457241.pdf?arnumber=11457241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T19:47:01Z","timestamp":1777405621000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11457241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":7,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/lca.2026.3678312","relation":{},"ISSN":["1556-6056","1556-6064","2473-2575"],"issn-type":[{"value":"1556-6056","type":"print"},{"value":"1556-6064","type":"electronic"},{"value":"2473-2575","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}