{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T05:25:12Z","timestamp":1783574712917,"version":"3.55.0"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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":["62125403"],"award-info":[{"award-number":["62125403"]}],"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":["92164301"],"award-info":[{"award-number":["92164301"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0115201"],"award-info":[{"award-number":["2022ZD0115201"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0114400"],"award-info":[{"award-number":["2021ZD0114400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing S&T Project","award":["Z221100007722023"],"award-info":[{"award-number":["Z221100007722023"]}]},{"DOI":"10.13039\/501100017582","name":"Beijing National Research Center for Information Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017582","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Beijing Advanced Innovation Center for Integrated Circuits","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Solid-State Circuits"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/jssc.2024.3397189","type":"journal-article","created":{"date-parts":[[2024,5,14]],"date-time":"2024-05-14T17:31:58Z","timestamp":1715707918000},"page":"3342-3356","source":"Crossref","is-referenced-by-count":31,"title":["Ayaka: A Versatile Transformer Accelerator With Low-Rank Estimation and Heterogeneous Dataflow"],"prefix":"10.1109","volume":"59","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5530-5416","authenticated-orcid":false,"given":"Yubin","family":"Qin","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8293-8881","authenticated-orcid":false,"given":"Yang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dazheng","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolong","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiren","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanqi","family":"Fan","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5869-9094","authenticated-orcid":false,"given":"Jingchuan","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianbao","family":"Chen","sequence":"additional","affiliation":[{"name":"TsingMicro Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7548-4116","authenticated-orcid":false,"given":"Leibo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5117-7920","authenticated-orcid":false,"given":"Shaojun","family":"Wei","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6942-4395","authenticated-orcid":false,"given":"Yang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2309-572X","authenticated-orcid":false,"given":"Shouyi","family":"Yin","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Beijing Innovation Center for Future Chip, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref3","first-page":"1","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref4","volume-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref5","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref6","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref7","article-title":"Megatron-LM: Training multi-billion parameter language models using model parallelism","author":"Shoeybi","year":"1909","journal-title":"arXiv:1909.08053"},{"key":"ref8","article-title":"An image is worth 16\u271716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref9","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Dehghani"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref13","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref14","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","article-title":"Large scale learning of general visual representations for transfer","author":"Kolesnikov","year":"2019","journal-title":"arXiv:1912.11370"},{"key":"ref17","article-title":"Mogrifier LSTM","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Melis"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3213521"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref21","first-page":"328","article-title":"A3: Accelerating attention mechanisms in neural networks with approximation","volume-title":"Proc. IEEE Int. Symp. High Perform. Comput. Archit. (HPCA)","author":"Ham"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref23","article-title":"Long range arena: A benchmark for efficient transformers","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Tay"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref27","first-page":"15038","article-title":"Towards a unified view of sparse feed-forward network in pretraining large language model","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Liu"},{"key":"ref28","article-title":"GLM-130B: An open bilingual pre-trained model","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Zeng"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589057"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3140659.3080246"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ipdps.2017.7"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/375551.375608"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757323"},{"key":"ref35","article-title":"Pointer Sentinel mixture models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Merity"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/isscc42614.2022.9731645"}],"container-title":["IEEE Journal of Solid-State Circuits"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4\/10693678\/10530252.pdf?arnumber=10530252","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T19:48:46Z","timestamp":1736452126000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530252\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":36,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/jssc.2024.3397189","relation":{},"ISSN":["0018-9200","1558-173X"],"issn-type":[{"value":"0018-9200","type":"print"},{"value":"1558-173X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}