{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T07:56:59Z","timestamp":1786435019377,"version":"build-2736575974"},"reference-count":45,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2024,4,22]],"date-time":"2024-04-22T00:00:00Z","timestamp":1713744000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"CHIMES"},{"name":"SRC\/DARPA JUMP 2.0 centers"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Des. Autom. Electron. Syst."],"published-print":{"date-parts":[[2024,5,31]]},"abstract":"<jats:p>Prior hardware accelerator designs primarily focused on single-chip solutions for 10 MB-class computer vision models. The GB-class transformer models for natural language processing (NLP) impose challenges on existing accelerator design due to the massive number of parameters and the diverse matrix multiplication (MatMul) workloads involved. This work proposes a heterogeneous 3D-based accelerator design for transformer models, which adopts an interposer substrate with multiple 3D memory\/logic hybrid cubes optimized for accelerating different MatMul workloads. An approximate computing scheme is proposed to take advantage of heterogeneous computing paradigms of mixed-signal compute-in-memory (CIM) and digital tensor processing units (TPU). From the system-level evaluation results, 10 TOPS\/W energy efficiency is achieved for the BERT and GPT2 model, which is about 2.6\u00d7 \u223c 3.1\u00d7 higher than the baseline with 7 nm TPU and stacked FeFET memory.<\/jats:p>","DOI":"10.1145\/3649219","type":"journal-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T12:53:50Z","timestamp":1709124830000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":28,"title":["H3D-Transformer: A Heterogeneous 3D (H3D) Computing Platform for Transformer Model Acceleration on Edge Devices"],"prefix":"10.1145","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8239-0492","authenticated-orcid":false,"given":"Yandong","family":"Luo","sequence":"first","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0068-3652","authenticated-orcid":false,"given":"Shimeng","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,4,22]]},"reference":[{"key":"e_1_3_1_2_2","doi-asserted-by":"crossref","unstructured":"O. Rybakov N. Kononenko N. Subrahmanya M. Visontai and S. Laurenzo. 2020. Streaming keyword spotting on mobile devices. arXiv: 2005.06720 (2020).","DOI":"10.21437\/Interspeech.2020-1003"},{"key":"e_1_3_1_3_2","unstructured":"Y. Wu M. Schuster Z. Chen Q. V. Le M. Norouzi W. Macherey M. Krikun Y. Cao Q. Gao K. Macherey J. Klingner A. Shah M. Johnson X. Liu \u0141. Kaiser S. Gouws Y. Kato T. Kudo H. Kazawa K. Stevens G. Kurian N. Patil W. Wang C. Young J. Smith J. Riesa A. Rudnick O. Vinyals G. Corrado M. Hughes and J. Dean. 2016. Google's neural machine translation system: Bridging the gap between human and machine translation. arXiv:1609.08144 (2016)."},{"key":"e_1_3_1_4_2","unstructured":"OpenAI. 2022. \u201cIntroducing ChatGPT.\u201d Retrieved from https:\/\/openai.com\/blog\/chatgpt"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067555"},{"key":"e_1_3_1_6_2","first-page":"18.1.1","volume-title":"IEEE International Electron Devices Meeting (IEDM\u201918)","year":"2018","unstructured":"O. Golonzka, J.-G. Alzate, U. Arslan, M. Bohr, P. Bai, J. Brockman, B. Buford, C. Connor, N. Das, B. Doyle, T. Ghani, F. Hamzaoglu, P. Heil, P. Hentges, R. Jahan, D. Kencke, B. Lin, M. Lu, M. Mainuddin, M. Meterelliyoz, P. Nguyen, D. Nikonov, K. O'brien, J. ODonnell, K. Oguz, D. Ouellette, J. Park, J. Pellegren, C. Puls, P. Quintero, T. Rahman, A. Romang, M. Sekhar, A. Selarka, M. Seth, A. J. Smith, A. K. Smith, L. Wei, C. Wiegand, Z. Zhang, and K. Fischer. 2018. MRAM as embedded non-volatile memory solution for 22FFL FinFET technology. In IEEE International Electron Devices Meeting (IEDM\u201918). 18.1.1\u201318.1.4."},{"key":"e_1_3_1_7_2","first-page":"19.7.1","article-title":"A FeFET based super-low-power ultra-fast embedded NVM technology for 22nm FDSOI and beyond","year":"2017","unstructured":"S. D\u00fcnkel, M. Trentzsch, R. Richter, P. Moll, C. Fuchs, O. Gehring, M. Majer, S. Wittek, B. M\u00fcller, T. Melde, H. Mulaosmanovic, S. Slesazeck, S. M\u00fcller, J. Ocker, M. Noack, D.-A. L\u00f6hr, P. Polakowski, J. M\u00fcller, T. Mikolajick, J. H\u00f6ntschel, B. Rice, J. Pellerin, and S. Beyer. 2017. A FeFET based super-low-power ultra-fast embedded NVM technology for 22nm FDSOI and beyond. In IEEE International Electron Devices Meeting (IEDM\u201917). 19.7.1\u201319.7.4.","journal-title":"IEEE International Electron Devices Meeting (IEDM\u201917)"},{"key":"e_1_3_1_8_2","first-page":"11.5.1","article-title":"A 28nm HKMG super low power embedded NVM technology based on ferroelectric FETs","year":"2016","unstructured":"M. Trentzsch, S. Flachowsky, R. Richter, J. Paul, B. Reimer, D. Utess, S. Jansen, H. Mulaosmanovic, S. M\u00fcller, S. Slesazeck, J. Ocker, M. Noack, J. M\u00fcller, P. Polakowski, J. Schreiter, S. Beyer, T. Mikolajick, and B. Rice. 2016. A 28nm HKMG super low power embedded NVM technology based on ferroelectric FETs. In IEEE International Electron Devices Meeting (IEDM). 11.5.1\u201311.5.4.","journal-title":"IEEE International Electron Devices Meeting (IEDM)"},{"key":"e_1_3_1_9_2","first-page":"1283","volume-title":"IEEE 68th Electronic Components and Technology Conference (ECTC\u201918)","author":"Jangam S.","year":"2018","unstructured":"S. Jangam, A. A. Bajwa, K. K. Thankkappan, P. Kittur, and S. S. Iyer. 2018. Electrical characterization of high performance fine pitch interconnects in silicon-interconnect fabric. In IEEE 68th Electronic Components and Technology Conference (ECTC\u201918). 1283\u20131288."},{"key":"e_1_3_1_10_2","first-page":"1","article-title":"3D stacked ICs using Cu TSVs and die to wafer hybrid collective bonding","year":"2009","unstructured":"G. Katti, A. Mercha, J. Van Olmen, C. Huyghebaert, A. Jourdain, M. Stucchi, M. Rakowski, I. Debusschere, P. Soussan, W. Dehaene, K. De Meyer, Y. Travaly, E. Beyne, S. Biesemans, and B. Swinnen. 2009. 3D stacked ICs using Cu TSVs and die to wafer hybrid collective bonding. In IEEE International Electron Devices Meeting (IEDM\u201909). 1\u20134.","journal-title":"IEEE International Electron Devices Meeting (IEDM\u201909)"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2017.2737644"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2019.00095"},{"key":"e_1_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM19573.2019.8993637"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2022.3177577"},{"key":"e_1_3_1_15_2","first-page":"1","volume-title":"ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA\u201917)","author":"Jouppi N. P.","year":"2017","unstructured":"N. P. Jouppi et al. 2017. In-datacenter performance analysis of a tensor processing unit. In ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA\u201917). 1\u201312. https:\/\/arxiv.org\/abs\/1704.04760"},{"key":"e_1_3_1_16_2","volume-title":"Conference on Advances in Neural Information Processing Systems","author":"Vaswani A.","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, \u0141. Kaiser, and I. Polosukhin. 2017. Attention is all you need. In Conference on Advances in Neural Information Processing Systems."},{"key":"e_1_3_1_17_2","volume-title":"Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL\u201919)","author":"Devlin J.","year":"2019","unstructured":"J. Devlin, M. W. Chang, K. Lee, and K. Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL\u201919)."},{"key":"e_1_3_1_18_2","volume-title":"Improving Language Understanding by Generative Pre-training","author":"Radford A.","year":"2018","unstructured":"A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever. 2018. Improving Language Understanding by Generative Pre-training. Technical Report. Retrieved from https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2910232"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2022.3200515"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2022.3142239"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067527"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062985"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830153"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2963616"},{"key":"e_1_3_1_26_2","first-page":"32.5.1","volume-title":"IEEE International Electron Devices Meeting (IEDM\u201919)","author":"Peng X.","year":"2019","unstructured":"X. Peng, S. Huang, Y. Luo, X. Sun, and S. Yu. 2019. DNN+NeuroSim: An end-to-end benchmarking framework for compute-in-memory accelerators with versatile device technologies. In IEEE International Electron Devices Meeting (IEDM\u201919). 32.5.1\u201332.5.4."},{"key":"e_1_3_1_27_2","volume-title":"IEEE 71st Electronic Components and Technology Conference (ECTC\u201921)","year":"2021","unstructured":"J. Derakhshandeh, C. Gerets, F. Inoue, G. Capuz, V. Cherman, M. Lofrano, L. Hou, T. Cochet, I. D. Preter, T. Webers, P. Bex, G. Jamieson, M. Maehara, E. Shafahian, J. Bertheau, E. Beyne, D. C. Tulipe, G. Beyer, and G. V. Miller. 2021. A study on IMC morphology and integration flow for low temperature and high throughput TCB down to 10\u03bcm pitch microbumps. In IEEE 71st Electronic Components and Technology Conference (ECTC\u201921)."},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2017.8268486"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnology18217.2020.9265044"},{"key":"e_1_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2018.00096"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"e_1_3_1_32_2","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1145\/3466752.3480125","volume-title":"Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Lu L.","year":"2021","unstructured":"L. Lu, Y. Jin, H. Bi, Z. Luo, P. Li, T. Wang, and Y. Liang. 2021. Sanger: A co-design framework for enabling sparse attention using reconfigurable architecture. In Annual IEEE\/ACM International Symposium on Microarchitecture. 977\u2013991."},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731686"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE51398.2021.9474146"},{"key":"e_1_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731645"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"e_1_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/EMC2-NIPS53020.2019.00016"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9181022"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2009.2034508"},{"key":"e_1_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/66.827350"},{"key":"e_1_3_1_41_2","first-page":"1283","volume-title":"IEEE 68th Electronic Components and Technology Conference (ECTC\u201918)","author":"Jangam S.","year":"2018","unstructured":"S. Jangam, A. A. Bajwa, K. K. Thankkappan, P. Kittur, and S. S. Iyer. 2018. Electrical characterization of high performance fine pitch interconnects in silicon-interconnect fabric. In IEEE 68th Electronic Components and Technology Conference (ECTC\u201918). 1283\u20131288."},{"key":"e_1_3_1_42_2","first-page":"1","volume-title":"IEEE International Electron Devices Meeting (IEDM\u201909)","year":"2009","unstructured":"G. Katti, A. Mercha, J. V. Olmen, C. Huyghebaert, A. Jourdain, M. Stucchi, M. Rakowski, I. Debusschere, P. Soussan, W. Dehaene, K. D. Meyer, Y. Travaly, E. Beyne, S. Biesemans, and B. Swinnen. 2009. 3D stacked ICs using Cu TSVs and die to wafer hybrid collective bonding. In IEEE International Electron Devices Meeting (IEDM\u201909). 1\u20134."},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2020.3031290"},{"key":"e_1_3_1_44_2","first-page":"58","volume-title":"IEEE International Symposium on High Performance Computer Architecture (HPCA\u201920)","author":"Qin E.","year":"2020","unstructured":"E. Qin, A. Samajdar, H. Kwon, V. Nadella, S. Srinivasan, D. Das, B. Kaul, and T. Krishna. 2020. SIGMA: A sparse and irregular GEMM accelerator with flexible interconnects for DNN training. In IEEE International Symposium on High Performance Computer Architecture (HPCA\u201920). 58\u201370."},{"key":"e_1_3_1_45_2","first-page":"1","volume-title":"International Symposium on Computer Architecture (ISCA\u201923)","year":"2023","unstructured":"Y. Qin, Y. Wang, D. Deng, Z. Zhao, X. Yang, L. Liu, S. Wei, Y. Hu, and A. S. Yin. 2023. FACT: FFN-attention co-optimized transformer architecture with eager correlation prediction. In International Symposium on Computer Architecture (ISCA\u201923). 1\u201314."},{"key":"e_1_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415640"}],"container-title":["ACM Transactions on Design Automation of Electronic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649219","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649219","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:47Z","timestamp":1750295867000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649219"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,22]]},"references-count":45,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,5,31]]}},"alternative-id":["10.1145\/3649219"],"URL":"https:\/\/doi.org\/10.1145\/3649219","relation":{},"ISSN":["1084-4309","1557-7309"],"issn-type":[{"value":"1084-4309","type":"print"},{"value":"1557-7309","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,22]]},"assertion":[{"value":"2023-06-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-02-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}