{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:09:12Z","timestamp":1758089352359,"version":"3.44.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132765","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Principle-based Dataflow Optimization for Communication Lower Bound in Operator-Fused Tensor Accelerator"],"prefix":"10.1109","author":[{"given":"Lei","family":"Xu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Yin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zelong","family":"Yuan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiguang","family":"Sheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfei","family":"Jiang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naifeng","family":"Jing","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2985963"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref7","first-page":"1","article-title":"GAMMA: Automating the HW Mapping of DNN Models on Accelerators via Genetic Algorithm","volume-title":"2020 IEEE\/ACM International Conference On Computer Aided Design (ICCAD)","author":"Kao"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304014"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589048"},{"key":"ref14","first-page":"1271","article-title":"TileFlow: A Framework for Modeling Fusion Dataflow via Tree-based Analysis","volume-title":"Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture, ser. MICRO \u201823.","author":"Zheng"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3649329.3657317"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586216"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00062"},{"key":"ref18","first-page":"16344","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-Awareness","volume":"35","author":"Dao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00062"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3485137"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2025,6,22]]},"location":"San Francisco, CA, USA","end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11132765.pdf?arnumber=11132765","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:31:27Z","timestamp":1758000687000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132765\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132765","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}