{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:45:15Z","timestamp":1772725515124,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,4,27]],"date-time":"2024-04-27T00:00:00Z","timestamp":1714176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,27]]},"DOI":"10.1145\/3620666.3651328","type":"proceedings-article","created":{"date-parts":[[2024,4,24]],"date-time":"2024-04-24T12:08:21Z","timestamp":1713960501000},"page":"1033-1047","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["TinyForge: A Design Space Exploration to Advance Energy and Silicon Area Trade-offs in tinyML Compute Architectures with Custom Latch Arrays"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7012-4135","authenticated-orcid":false,"given":"Massimo","family":"Giordano","sequence":"first","affiliation":[{"name":"Stanford University, Stanford, California, United States of America"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4923-825X","authenticated-orcid":false,"given":"Rohan","family":"Doshi","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0466-5072","authenticated-orcid":false,"given":"Qianyun","family":"Lu","sequence":"additional","affiliation":[{"name":"Stanford University, Stanford, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3417-8782","authenticated-orcid":false,"given":"Boris","family":"Murmann","sequence":"additional","affiliation":[{"name":"University of Hawaii, Honolulu, Hawaii, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,4,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Peter Torelli, Jeremy Holleman, Nat Jeffries, Csaba Kiraly, Pietro Montino, David Kanter, Sebastian Ahmed, and Danilo Pau. Mlperf tiny benchmark. arXiv preprint arXiv:2106.07597","author":"Banbury Colby","year":"2021","unstructured":"Colby Banbury, Vijay Janapa Reddi, Peter Torelli, Jeremy Holleman, Nat Jeffries, Csaba Kiraly, Pietro Montino, David Kanter, Sebastian Ahmed, and Danilo Pau. Mlperf tiny benchmark. arXiv preprint arXiv:2106.07597, 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of machine learning and systems, 3:517--532","author":"Banbury Colby","year":"2021","unstructured":"Colby Banbury, Chuteng Zhou, Igor Fedorov, Ramon Matas, Urmish Thakker, Dibakar Gope, Vijay Janapa Reddi, Matthew Mattina, and Paul Whatmough. Micronets: Neural network architectures for deploying tinyml applications on commodity microcontrollers. Proceedings of machine learning and systems, 3:517--532, 2021."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.410741"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3349567.3351726"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2950386"},{"key":"e_1_3_2_1_6_1","volume-title":"DNNOff: offloading DNN-based intelligent IoT applications in mobile edge computing","author":"Chen Xing","year":"2021","unstructured":"Xing Chen, Ming Li, Hao Zhong, Yun Ma, and Ching-Hsien Hsu. DNNOff: offloading DNN-based intelligent IoT applications in mobile edge computing. IEEE transactions on industrial informatics, 18(4):2820--2829, 2021."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365766"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3476984"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067643"},{"key":"e_1_3_2_1_11_1","volume-title":"Dmazerunner: Executing perfectly nested loops on dataflow accelerators. ACM Transactions on Embedded Computing Systems (TECS), 18(5s):1--27","author":"Dave Shail","year":"2019","unstructured":"Shail Dave, Youngbin Kim, Sasikanth Avancha, Kyoungwoo Lee, and Aviral Shrivastava. Dmazerunner: Executing perfectly nested loops on dataflow accelerators. ACM Transactions on Embedded Computing Systems (TECS), 18(5s):1--27, 2019."},{"key":"e_1_3_2_1_12_1","volume-title":"A fast and elitist multiobjective genetic algorithm: Nsga-ii","author":"Deb Kalyanmoy","year":"2002","unstructured":"Kalyanmoy Deb, Amrit Pratap, Sameer Agarwal, and TAMT Meyarivan. A fast and elitist multiobjective genetic algorithm: Nsga-ii. IEEE transactions on evolutionary computation, 6(2):182--197, 2002."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067422"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2021.100461"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Hidehiro Fujiwara Haruki Mori Wei-Chang Zhao Mei-Chen Chuang Rawan Naous Chao-Kai Chuang Takeshi Hashizume Dar Sun Chia-Fu Lee Kerem Akarvardar Saman Adham Tan-Li Chou Mahmut Ersin Sinangil Yih Wang Yu-Der Chih Yen-Huei Chen Hung-Jen Liao and Tsung-Yung Jonathan Chang. A 5-nm 254-TOPS\/W 221-TOPS\/mm2 Fully-Digital Computing-in-Memory Macro Supporting Wide-Range Dynamic-Voltage-Frequency Scaling and Simultaneous MAC and Write Operations. In 2022 IEEE International Solid- State Circuits Conference (ISSCC) volume 65 pages 1--3 February 2022.","DOI":"10.1109\/ISSCC42614.2022.9731754"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.23919\/VLSICircuits52068.2021.9492347"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2020.101831"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42615.2023.10067610"},{"key":"e_1_3_2_1_19_1","unstructured":"Vijay Janapa Reddi Christine Cheng David Kanter Peter Mattson Guenther Schmuelling Carole-Jean Wu Brian Anderson Maximilien Breughe Mark Charlebois William Chou Ramesh Chukka Cody Coleman Sam Davis Pan Deng Greg Diamos Jared Duke Dave Fick J. Scott Gardner Itay Hubara Sachin Idgunji Thomas B. Jablin Jeff Jiao Tom St. John Pankaj Kanwar David Lee Jeffery Liao Anton Lokhmotov Francisco Massa Peng Meng Paulius Micikevicius Colin Osborne Gennady Pekhimenko Arun Tejusve Raghunath Rajan Dilip Sequeira Ashish Sirasao Fei Sun Hanlin Tang Michael Thomson Frank Wei Ephrem Wu Lingjie Xu Koichi Yamada Bing Yu George Yuan Aaron Zhong Peizhao Zhang and Yuchen Zhou. MLPerf Inference Benchmark. Technical report November 2019."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2515510"},{"key":"e_1_3_2_1_21_1","unstructured":"Michael Jiang. TSMC chip contract price increases by up to 20% smashing the market and reversing misgivings."},{"key":"e_1_3_2_1_22_1","volume-title":"Tinybert: Distilling bert for natural language understanding","author":"Jiao Xiaoqi","year":"2020","unstructured":"Xiaoqi Jiao, Yichun Yin, Lifeng Shang, Xin Jiang, Xiao Chen, Linlin Li, Fang Wang, and Qun Liu. Tinybert: Distilling bert for natural language understanding, 2020."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2021.3110747"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"e_1_3_2_1_25_1","first-page":"5338","volume-title":"International Conference on Machine Learning","author":"Koh Pang Wei","year":"2020","unstructured":"Pang Wei Koh, Thao Nguyen, Yew Siang Tang, Stephen Mussmann, Emma Pierson, Been Kim, and Percy Liang. Concept bottleneck models. In International Conference on Machine Learning, pages 5338--5348. PMLR, 2020."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870426"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00016"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553453"},{"key":"e_1_3_2_1_30_1","volume-title":"Fog computing: Focusing on mobile users at the edge. arXiv preprint arXiv:1502.01815","author":"Luan Tom H.","year":"2015","unstructured":"Tom H. Luan, Longxiang Gao, Zhi Li, Yang Xiang, Guiyi Wei, and Limin Sun. Fog computing: Focusing on mobile users at the edge. arXiv preprint arXiv:1502.01815, 2015."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2020.2974843"},{"key":"e_1_3_2_1_32_1","volume-title":"August","author":"Mei Linyan","year":"2020","unstructured":"Linyan Mei, Pouya Houshmand, Vikram Jain, Sebastian Giraldo, and Marian Verhelst. ZigZag: A Memory-Centric Rapid DNN Accelerator Design Space Exploration Framework, August 2020."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2017.7870353"},{"key":"e_1_3_2_1_34_1","volume-title":"Ms marco: A human generated machine reading comprehension dataset. choice, 2640:660","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. Ms marco: A human generated machine reading comprehension dataset. choice, 2640:660, 2016."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_2_1_36_1","first-page":"1","volume-title":"Xinwen Fu. On Misconception of Hardware and Cost in IoT Security and Privacy. In ICC 2019 - 2019 IEEE International Conference on Communications (ICC)","author":"Pearson Bryan","year":"2019","unstructured":"Bryan Pearson, Lan Luo, Yue Zhang, Rajib Dey, Zhen Ling, Mostafa Bassiouni, and Xinwen Fu. On Misconception of Hardware and Cost in IoT Security and Privacy. In ICC 2019 - 2019 IEEE International Conference on Communications (ICC), pages 1--7, May 2019."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.4018\/978-1-5225-4044-1.ch007"},{"key":"e_1_3_2_1_38_1","first-page":"257","volume-title":"Proceedings of the 7th Annual conference on Genetic and Evolutionary Computation","author":"Carlo","year":"2005","unstructured":"Carlo R. Raquel and Prospero C. Naval Jr. An effective use of crowding distance in multiobjective particle swarm optimization. In Proceedings of the 7th Annual conference on Genetic and Evolutionary Computation, pages 257--264, 2005."},{"key":"e_1_3_2_1_39_1","volume-title":"Np-completeness of the active time scheduling problem. arXiv preprint arXiv:2112.03255","author":"Saha Sagnik","year":"2021","unstructured":"Sagnik Saha and Manish Purohit. Np-completeness of the active time scheduling problem. arXiv preprint arXiv:2112.03255, 2021."},{"key":"e_1_3_2_1_40_1","volume-title":"Scale-sim: Systolic cnn accelerator simulator. arXiv preprint arXiv:1811.02883","author":"Samajdar Ananda","year":"2018","unstructured":"Ananda Samajdar, Yuhao Zhu, Paul Whatmough, Matthew Mattina, and Tushar Krishna. Scale-sim: Systolic cnn accelerator simulator. arXiv preprint arXiv:1811.02883, 2018."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCNCW.2012.6215496"},{"key":"e_1_3_2_1_43_1","unstructured":"Irina Sizova. GAP9 processor."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASC.2019.2957196"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ASPDAC.2015.7058985"},{"key":"e_1_3_2_1_46_1","volume-title":"Power, area, and performance optimization of standard cell memory arrays through controlled placement. ACM Transactions on Design Automation of Electronic Systems (TODAES), 21(4):1--25","author":"Teman Adam","year":"2016","unstructured":"Adam Teman, Davide Rossi, Pascal Meinerzhagen, Luca Benini, and Andreas Burg. Power, area, and performance optimization of standard cell memory arrays through controlled placement. ACM Transactions on Design Automation of Electronic Systems (TODAES), 21(4):1--25, 2016."},{"key":"e_1_3_2_1_47_1","volume-title":"Well-read students learn better: On the importance of pre-training compact models","author":"Turc Iulia","year":"2019","unstructured":"Iulia Turc, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. Well-read students learn better: On the importance of pre-training compact models, 2019."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942127"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2010.42"},{"key":"e_1_3_2_1_50_1","unstructured":"Yu Emma Wang Gu-Yeon Wei and David Brooks. Benchmarking TPU GPU and CPU Platforms for Deep Learning October 2019."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2021.3105028"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00048"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"e_1_3_2_1_54_1","volume-title":"SMAUG: End-to-end full-stack simulation infrastructure for deep learning workloads. ACM Transactions on Architecture and Code Optimization (TACO), 17(4):1--26","author":"Xi Sam","year":"2020","unstructured":"Sam Xi, Yuan Yao, Kshitij Bhardwaj, Paul Whatmough, Gu-Yeon Wei, and David Brooks. SMAUG: End-to-end full-stack simulation infrastructure for deep learning workloads. ACM Transactions on Architecture and Code Optimization (TACO), 17(4):1--26, 2020."},{"key":"e_1_3_2_1_55_1","first-page":"287","volume-title":"Ahmed Louri. Adapt-Flow: A Flexible DNN Accelerator Architecture for Heterogeneous Dataflow Implementation. In Proceedings of the Great Lakes Symposium on VLSI 2022","author":"Yang Jiaqi","year":"2022","unstructured":"Jiaqi Yang, Hao Zheng, and Ahmed Louri. Adapt-Flow: A Flexible DNN Accelerator Architecture for Heterogeneous Dataflow Implementation. In Proceedings of the Great Lakes Symposium on VLSI 2022, pages 287--292, 2022."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"}],"event":{"name":"ASPLOS '24: 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3","location":"La Jolla CA USA","acronym":"ASPLOS '24","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture","SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 3"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651328","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:42Z","timestamp":1750291422000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3620666.3651328"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,27]]},"references-count":56,"alternative-id":["10.1145\/3620666.3651328","10.1145\/3620666"],"URL":"https:\/\/doi.org\/10.1145\/3620666.3651328","relation":{},"subject":[],"published":{"date-parts":[[2024,4,27]]},"assertion":[{"value":"2024-04-27","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}