UniCoS: A Unified Neural and Accelerator Co-Search Framework for CNNs and ViTs
Current algorithm-hardware co-search works often suffer from lengthy training times and inadequate exploration of hardware design spaces, leading to suboptimal performance. This work introduces UniCoS, a unified framework for co-optimizing neural networks and accelerators for CNNs and Vision Transfo...
Saved in:
| Published in: | 2025 62nd ACM/IEEE Design Automation Conference (DAC) pp. 1 - 6 |
|---|---|
| Main Authors: | , , , , , , , |
| Format: | Conference Proceeding |
| Language: | English |
| Published: |
IEEE
22.06.2025
|
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Current algorithm-hardware co-search works often suffer from lengthy training times and inadequate exploration of hardware design spaces, leading to suboptimal performance. This work introduces UniCoS, a unified framework for co-optimizing neural networks and accelerators for CNNs and Vision Transformers (ViTs). By introducing a novel training-free proxy that evaluates accuracy within seconds and a clustering-based algorithm for exploring heterogeneous dataflows, UniCoS efficiently navigates the design spaces of both architectures. Experimental results demonstrate that the solutions generated by UniCoS consistently surpass state-of-the-art (SOTA) methods (e.g., 3.54 \times energy-delay product (EDP) improvement with a 1.76 \% higher accuracy on ImageNet) while requiring notably reduced search time (up to 48 \times, \sim 3 hours). The code is available at https://github.com/mine7777/Unicos.git. |
|---|---|
| AbstractList | Current algorithm-hardware co-search works often suffer from lengthy training times and inadequate exploration of hardware design spaces, leading to suboptimal performance. This work introduces UniCoS, a unified framework for co-optimizing neural networks and accelerators for CNNs and Vision Transformers (ViTs). By introducing a novel training-free proxy that evaluates accuracy within seconds and a clustering-based algorithm for exploring heterogeneous dataflows, UniCoS efficiently navigates the design spaces of both architectures. Experimental results demonstrate that the solutions generated by UniCoS consistently surpass state-of-the-art (SOTA) methods (e.g., 3.54 \times energy-delay product (EDP) improvement with a 1.76 \% higher accuracy on ImageNet) while requiring notably reduced search time (up to 48 \times, \sim 3 hours). The code is available at https://github.com/mine7777/Unicos.git. |
| Author | Zhou, Xuehai Tang, Cheng Wen, Hongbing Gong, Lei Wang, Chao Lou, Wenqi Qin, Yunji Fu, Wei |
| Author_xml | – sequence: 1 givenname: Wei surname: Fu fullname: Fu, Wei organization: University of Science and Technology of China,China – sequence: 2 givenname: Wenqi surname: Lou fullname: Lou, Wenqi organization: Suzhou Institute of Advanced Research, University of Science and Technology of China,China – sequence: 3 givenname: Cheng surname: Tang fullname: Tang, Cheng organization: University of Science and Technology of China,China – sequence: 4 givenname: Hongbing surname: Wen fullname: Wen, Hongbing organization: University of Science and Technology of China,China – sequence: 5 givenname: Yunji surname: Qin fullname: Qin, Yunji organization: University of Science and Technology of China,China – sequence: 6 givenname: Lei surname: Gong fullname: Gong, Lei email: louwenqi@ustc.edu.cn organization: University of Science and Technology of China,China – sequence: 7 givenname: Chao surname: Wang fullname: Wang, Chao email: cswang@ustc.edu.cn organization: University of Science and Technology of China,China – sequence: 8 givenname: Xuehai surname: Zhou fullname: Zhou, Xuehai organization: University of Science and Technology of China,China |
| BookMark | eNo1T8tOwzAQNBIcoPQPEPIPpNhZJ7G5RYECUhUObblWi70rItIYOUWIvye8NId5aDTSnInjIQ4kxKVWC62Vu7qpmxKscYtc5cUUaQCj7ZGYu8pZAF0oUMaeinY7dE1cX8taToo7CrKl94S9xCHI2nvqKeEhJtnEbE2Y_ItcJtzTR0yvkr_zth1_yk_dZjwXJ4z9SPM_nont8nbT3Gerx7uHpl5lqCt3yIiqgtWE0hv1HCaUpS8YHJmCLQeDlc0nq5DAGWKvcuDSWQJm1AFhJi5-dzsi2r2lbo_pc_d_E74AvUxMAw |
| ContentType | Conference Proceeding |
| DBID | 6IE 6IH CBEJK RIE RIO |
| DOI | 10.1109/DAC63849.2025.11133418 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Proceedings Order Plan (POP) 1998-present by volume IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) IEEE Proceedings Order Plans (POP) 1998-present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| EISBN | 9798331503048 |
| EndPage | 6 |
| ExternalDocumentID | 11133418 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China funderid: 10.13039/501100001809 – fundername: Youth Innovation Promotion Association funderid: 10.13039/501100012492 |
| GroupedDBID | 6IE 6IH CBEJK RIE RIO |
| ID | FETCH-LOGICAL-a179t-ee75f0f0f6c40bdbdb66c5f39e45f8fd4a782f390ae394efc023f698e3ffa1da3 |
| IEDL.DBID | RIE |
| IngestDate | Wed Oct 01 07:05:15 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-a179t-ee75f0f0f6c40bdbdb66c5f39e45f8fd4a782f390ae394efc023f698e3ffa1da3 |
| PageCount | 6 |
| ParticipantIDs | ieee_primary_11133418 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-June-22 |
| PublicationDateYYYYMMDD | 2025-06-22 |
| PublicationDate_xml | – month: 06 year: 2025 text: 2025-June-22 day: 22 |
| PublicationDecade | 2020 |
| PublicationTitle | 2025 62nd ACM/IEEE Design Automation Conference (DAC) |
| PublicationTitleAbbrev | DAC |
| PublicationYear | 2025 |
| Publisher | IEEE |
| Publisher_xml | – name: IEEE |
| Score | 2.29515 |
| Snippet | Current algorithm-hardware co-search works often suffer from lengthy training times and inadequate exploration of hardware design spaces, leading to suboptimal... |
| SourceID | ieee |
| SourceType | Publisher |
| StartPage | 1 |
| SubjectTerms | Accuracy Computer architecture Design automation Hardware acceleration hardware software co-exploration heterogeneous multi-core architecture Navigation Neural networks Software Space exploration Training Transformers zero-shot proxy |
| Title | UniCoS: A Unified Neural and Accelerator Co-Search Framework for CNNs and ViTs |
| URI | https://ieeexplore.ieee.org/document/11133418 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA62ePCkYsU3OXhNu22yycZbWS0eZClYS28ljwkUZFf68Pc7SVvFgwfJJRtCFmY3-SbJfPMRcq-t5xZxgsVEH1HCzDKLuwhmJOSFRgcakn7K9EVVVTGb6fGOrJ64MACQgs-gG6vpLt83bhOPynpRFh1X3aJFWkrJLVlrx_rtZ7r3OCzxbxKRfjLIu_vOv2RTEmqMjv_5vhPS-eHf0fE3spySA6jPSIXuYdm8PtAhxVpA15HGzBrmnZra06FzCCDpzpyWDdtGEdPRPvSKhtheVavUebqYrDrkbfQ0KZ_ZTg2BGZw0awag8pBhkU5k1mOR0uWBaxB5KIIXBsEeHzMDXAsIDtE4SF0AD8H0veHnpF03NVwQqhV4BRIiV1B4jqOh0-CsDkoEyx2_JJ1ojPnHNuHFfG-Hqz_ar8lRNHmMoBoMbkh7vdzALTl0n-vFanmXPtMXMRqUCA |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5aBT2pWPFtDl7TbjfZR7yV1VKxLgVr6a3kMQFBdqUPf7-TtFU8eJBcsiFkYXaTb5LMNx8ht1JbrhEnmE_04SXMNNO4i2AqhSSX6EBD0E8ZD7KyzCcTOVyT1QMXBgBC8Bm0fDXc5dvaLP1RWdvLouOqm2-TnUSIOFrRtda8304k2_fdAv8n4QkocdLadP8lnBJwo3fwzzcekuYPA48Ov7HliGxBdUxKdBCL-uWOdinWHDqP1OfWUO9UVZZ2jUEICbfmtKjZKo6Y9jbBV9T59rKch87jt9G8SV57D6Oiz9Z6CEzhtFkwgCxxEZbUiEhbLGlqEscliMTlzgqFcI-PkQIuBTiDeOxSmQN3TnWs4iekUdUVnBIqM7AZpODZgsJyHA3dBqOly4TT3PAz0vTGmH6sUl5MN3Y4_6P9huz1R8-D6eCxfLog-978Pp4qji9JYzFbwhXZNZ-Lt_nsOnyyLxR7l08 |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2025+62nd+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=UniCoS%3A+A+Unified+Neural+and+Accelerator+Co-Search+Framework+for+CNNs+and+ViTs&rft.au=Fu%2C+Wei&rft.au=Lou%2C+Wenqi&rft.au=Tang%2C+Cheng&rft.au=Wen%2C+Hongbing&rft.date=2025-06-22&rft.pub=IEEE&rft.spage=1&rft.epage=6&rft_id=info:doi/10.1109%2FDAC63849.2025.11133418&rft.externalDocID=11133418 |