{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T07:17:27Z","timestamp":1772695047178,"version":"3.50.1"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62332021"],"award-info":[{"award-number":["62332021"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408456","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-14","source":"Crossref","is-referenced-by-count":0,"title":["SFD: Towards Segment Fusion Dataflow for Spatial Accelerators"],"prefix":"10.1109","author":[{"given":"Fuyu","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghua","family":"Shen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufei","family":"Ding","sequence":"additional","affiliation":[{"name":"University of California,San Diego"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nong","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University,Guangzhou"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref4","article-title":"Attention is all you need","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Vaswani","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref6","article-title":"Language models are few-shot learners","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Brown","year":"2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3282307"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3361682"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3360307"},{"key":"ref10","year":"2017","journal-title":"Nvdla deep learning accelerator"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358302"},{"key":"ref13","author":"Genc","year":"2019","journal-title":"Gemmini: An agile systolic array generator enabling systematic evaluations of deep-learning architectures"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527440"},{"key":"ref16","doi-asserted-by":"crossref","DOI":"10.1145\/3613424.3623792","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 (MICRO)","author":"Zheng","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3575747"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507767"},{"key":"ref21","first-page":"701","article-title":"Welder: Scheduling deep learning memory access via tilegraph","volume-title":"17th USENIX Symposium on Operating Systems Design and Implementation (OSDI 23)","author":"Shi","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589048"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624865"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3061394"},{"key":"ref26","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proceedings of the International conference on machine learning (ICML)","author":"Tan","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378508"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00058"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00065"},{"key":"ref31","article-title":"Ansor: Generating \\{High-Performance\\}\\} tensor programs for deep learning","volume-title":"Proceedings of the 14th USENIX symposium on operating systems design and implementation (OSDI)","author":"Zheng","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00062"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1145\/3613424.3623797","article-title":"Dosa: Differentiable model-based one-loop search for dnn accelerators","volume-title":"Proceedings of the 56th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO)","author":"Hong","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00021"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00094"},{"key":"ref37","year":"2021","journal-title":"Tensorflow xla"},{"key":"ref38","author":"Dao","year":"2023","journal-title":"Flashattention-2: Faster attention with better parallelism and work partitioning"},{"key":"ref39","article-title":"\\{TVM\\}: An automated \\{End-toEnd\\} optimizing compiler for deep learning","volume-title":"Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Chen","year":"2018"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080221"},{"key":"ref41","author":"Team","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref42","author":"Kipf","year":"2016","journal-title":"Semi-supervised classification with graph convolutional networks"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750389"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.40"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454106"},{"key":"ref51","article-title":"Learning to optimize tensor programs","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems (NeurIPS)","author":"Chen","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00086"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3576933"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00076"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3453483.3454083"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408456.pdf?arnumber=11408456","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:42:41Z","timestamp":1772692961000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408456\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408456","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}