{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:32:44Z","timestamp":1763724764985,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":36,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,27]],"date-time":"2024-10-27T00:00:00Z","timestamp":1729987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2324854"],"award-info":[{"award-number":["2324854"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,27]]},"DOI":"10.1145\/3676536.3676724","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T12:53:56Z","timestamp":1744203236000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MapFormer: Attention-based multi-DNN manager for throughout & power co-optimization on embedded devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6804-135X","authenticated-orcid":false,"given":"Andreas","family":"Karatzas","sequence":"first","affiliation":[{"name":"School of Electrical, Computer, and Biomedical Engineering, Southern Illinois University, Carbondale, IL, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0985-3045","authenticated-orcid":false,"given":"Iraklis","family":"Anagnostopoulos","sequence":"additional","affiliation":[{"name":"School of Electrical, Computer, and Biomedical Engineering, Southern Illinois University, Carbondale, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"ARM-CO-UP: ARM CO operative U tilization of P rocessors. ACM Transactions on Design Automation of Electronic Systems","author":"Aghapour Ehsan","year":"2024","unstructured":"Ehsan Aghapour, Dolly Sapra, Andy Pimentel, and Anuj Pathania. 2024. ARM-CO-UP: ARM CO operative U tilization of P rocessors. ACM Transactions on Design Automation of Electronic Systems (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2772822"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071134"},{"key":"e_1_3_2_1_4_1","volume-title":"Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691","author":"Dao Tri","year":"2023","unstructured":"Tri Dao. 2023. Flashattention-2: Faster attention with better parallelism and work partitioning. arXiv preprint arXiv:2307.08691 (2023)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2024.3386067"},{"key":"e_1_3_2_1_6_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358312"},{"volume-title":"2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT). IEEE.","author":"Myeonggyun","key":"e_1_3_2_1_8_1","unstructured":"Myeonggyun Han et al. 2019. Mosaic: Heterogeneity-, communication-, and constraint-aware model slicing and execution for accurate and efficient inference. In 2019 28th International Conference on Parallel Architectures and Compilation Techniques (PACT). IEEE."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/IGSC51522.2020.9290876"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-SoC.2019.8920374"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00147"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Duseok Kang et al. 2020. Scheduling of deep learning applications onto heterogeneous processors in an embedded device. IEEE Access (2020).","DOI":"10.1109\/ACCESS.2020.2977496"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247989"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/2517765"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3103503"},{"key":"e_1_3_2_1_16_1","volume-title":"On-device neural net inference with mobile gpus. arXiv preprint arXiv:1907.01989","author":"Lee Juhyun","year":"2019","unstructured":"Juhyun Lee, Nikolay Chirkov, Ekaterina Ignasheva, Yury Pisarchyk, Mogan Shieh, Fabio Riccardi, Raman Sarokin, Andrei Kulik, and Matthias Grundmann. 2019. On-device neural net inference with mobile gpus. arXiv preprint arXiv:1907.01989 (2019)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3088861"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3095028"},{"key":"e_1_3_2_1_19_1","unstructured":"Google LLC. 2024. Google Lookout. https:\/\/play.google.com\/store\/apps\/details?id=com.google.android.apps.accessibility.reveal&hl=en_US&gl=US. Accessed: 2024-05-05."},{"key":"e_1_3_2_1_20_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_1_21_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_22_1","unstructured":"Tomas Mikolov et al. 2013. Distributed representations of words and phrases and their compositionality. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-49292-5_4"},{"key":"e_1_3_2_1_24_1","unstructured":"NVIDIA. 2024. NVIDIA Jetson Xavier Series. https:\/\/www.nvidia.com\/en-us\/autonomous-machines\/embedded-systems\/jetson-xavier-series\/. Accessed: 2024-05-05."},{"key":"e_1_3_2_1_25_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAdTE.2013.6524743"},{"key":"e_1_3_2_1_27_1","unstructured":"Semiengineering. 2023. ML Moves From Servers To Smart Phones. https:\/\/semiengineering.com\/ml-moves-from-servers-to-smart-phones\/. Accessed: 2024-05-05."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Ourania Spantidi et al. 2022. Targeting DNN Inference via Efficient Utilization of Heterogeneous Precision DNN Accelerators. IEEE Transactions on Emerging Topics in Computing (2022).","DOI":"10.1109\/TETC.2022.3178730"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10228-y"},{"key":"e_1_3_2_1_30_1","volume-title":"Positional encoding to control output sequence length. arXiv preprint arXiv:1904.07418","author":"Takase Sho","year":"2019","unstructured":"Sho Takase and Naoaki Okazaki. 2019. Positional encoding to control output sequence length. arXiv preprint arXiv:1904.07418 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.11.004"},{"key":"e_1_3_2_1_32_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_33_1","first-page":"19511","article-title":"Learning search space partition for black-box optimization using monte carlo tree search","volume":"33","author":"Wang Linnan","year":"2020","unstructured":"Linnan Wang, Rodrigo Fonseca, and Yuandong Tian. 2020. Learning search space partition for black-box optimization using monte carlo tree search. Advances in Neural Information Processing Systems 33 (2020), 19511--19522.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2021.06.001"},{"key":"e_1_3_2_1_35_1","volume-title":"Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur) 53, 3","author":"Wang Yaqing","year":"2020","unstructured":"Yaqing Wang, Quanming Yao, James T Kwok, and Lionel M Ni. 2020. Generalizing from a few examples: A survey on few-shot learning. ACM computing surveys (csur) 53, 3 (2020), 1--34."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASID.2018.8693202"}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"],"location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24"},"container-title":["Proceedings of the 43rd IEEE\/ACM International Conference on Computer-Aided Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676724","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676724","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3676724","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:43:57Z","timestamp":1750290237000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3676724"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":36,"alternative-id":["10.1145\/3676536.3676724","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3676724","relation":{},"subject":[],"published":{"date-parts":[[2024,10,27]]},"assertion":[{"value":"2025-04-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}