{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:08:19Z","timestamp":1778080099429,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,5]],"date-time":"2024-08-05T00:00:00Z","timestamp":1722816000000},"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":[[2024,8,5]]},"DOI":"10.1145\/3665314.3670841","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T19:31:18Z","timestamp":1725910278000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["PiQi: Partially Quantized DNN Inference on HMPSoCs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0291-7555","authenticated-orcid":false,"given":"Ehsan","family":"Aghapour","sequence":"first","affiliation":[{"name":"University of Amsterdam, Amsterdam, North holland, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8447-872X","authenticated-orcid":false,"given":"Yixian","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3590-0394","authenticated-orcid":false,"given":"Dolly","family":"Sapra","sequence":"additional","affiliation":[{"name":"University Van Amsterdam, Amsterdam, North Holland, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2043-4469","authenticated-orcid":false,"given":"Andy","family":"Pimentel","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, North Holland, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5813-7021","authenticated-orcid":false,"given":"Anuj","family":"Pathania","sequence":"additional","affiliation":[{"name":"University of Amsterdam, Amsterdam, North-Holland, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Ehsan Aghapour et al. 2022. CPU-GPU Layer-Switched Low Latency CNN Inference. In DSD.","DOI":"10.1109\/DSD57027.2022.00051"},{"key":"e_1_3_2_1_2_1","volume-title":"PELSI: Power-Efficient Layer-Switched Inference. In RTCSA.","author":"Ehsan Aghapour","year":"2023","unstructured":"Ehsan Aghapour et al. 2023. PELSI: Power-Efficient Layer-Switched Inference. In RTCSA."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3656472"},{"key":"e_1_3_2_1_4_1","volume-title":"Edge Devices: Extended Version.","author":"Hyunho Ahn","year":"2023","unstructured":"Hyunho Ahn et al. 2023. Performance Characterization of using Quantization for DNN Inference on Edge Devices: Extended Version."},{"key":"e_1_3_2_1_5_1","volume-title":"Coelho et al","author":"Claudionor","year":"2021","unstructured":"Claudionor N. Coelho et al. 2021. Automatic heterogeneous quantization of deep neural networks for low-latency inference on the edge for particle detectors. Nature Machine Intelligence (2021)."},{"key":"e_1_3_2_1_6_1","unstructured":"Xiaotian Guo et al. 2023. Automated Exploration and Implementation of Distributed CNN Inference at the Edge. IoT Journal (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Ramyad Hadidi et al. 2019. Characterizing the Deployment of Deep Neural Networks on Commercial Edge Devices. In IISWC.","DOI":"10.1109\/IISWC47752.2019.9041955"},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 55th Annual Design Automation Conference (DAC '18)","author":"Shubham","unstructured":"Shubham Jain et al. 2018. Compensated-DNN: Energy Efficient Low-Precision Deep Neural Networks by Compensating Quantization Errors. In Proceedings of the 55th Annual Design Automation Conference (DAC '18)."},{"key":"e_1_3_2_1_9_1","volume-title":"A fast and elitist multi-objective genetic algorithm: NSGA-II. TEVC","author":"Kalyanmoy Deb","year":"2002","unstructured":"Deb Kalyanmoy. 2002. A fast and elitist multi-objective genetic algorithm: NSGA-II. TEVC (2002)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"Andreas Karatzas et al. 2023. OmniBoost: Boosting Throughput of Heterogeneous Embedded Devices under Multi-DNN Workload. In DAC.","DOI":"10.1109\/DAC56929.2023.10247989"},{"key":"e_1_3_2_1_11_1","volume-title":"Layer: Low Latency On-Device Inference Using Cooperative Single-Layer Acceleration and Processor-Friendly Quantization. in EuroSys.","author":"Youngsok Kim","year":"2019","unstructured":"Youngsok Kim et al. 2019. Layer: Low Latency On-Device Inference Using Cooperative Single-Layer Acceleration and Processor-Friendly Quantization. in EuroSys."},{"key":"e_1_3_2_1_12_1","unstructured":"Kyuho J. Lee. 2021. Architecture of neural processing unit for deep neural networks. In Hardware Accelerator Systems for Artificial Intelligence and Machine Learning. Elsevier."},{"key":"e_1_3_2_1_13_1","volume-title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction. arXiv:2102.05426","author":"Yuhang Li","year":"2021","unstructured":"Yuhang Li et al. 2021. BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction. arXiv:2102.05426"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"Markus Nagel et al. 2019. Data-Free Quantization Through Weight Equalization and Bias Correction. In ICCV.","DOI":"10.1109\/ICCV.2019.00141"},{"key":"e_1_3_2_1_15_1","unstructured":"Markus Nagel et al. 2021. A White Paper on Neural Network Quantization. arXiv:2106.08295"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Jie Tang et al. 2017. Enabling Deep Learning on IoT Devices. Computer (2017).","DOI":"10.1109\/MC.2017.3641648"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of the 54th Annual Design Automation Conference","author":"Hokchhay","year":"2017","unstructured":"Hokchhay Tann et al. 2017. Hardware-Software Codesign of Accurate, Multiplier-Free Deep Neural Networks. In Proceedings of the 54th Annual Design Automation Conference 2017."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Satoki Tsuji et al. 2022. Greedy search algorithm for partial quantization of convolutional neural networks inspired by submodular optimization. Neural Computing and Applications (2022).","DOI":"10.1007\/s00521-021-06752-7"},{"key":"e_1_3_2_1_19_1","unstructured":"Peisong Wang et al. 2023. Optimization-Based Post-Training Quantization With Bit-Split and Stitching. TPAMI (2023)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Siqi Wang et al. 2020. High-Throughput CNN Inference on Embedded ARM Big.LITTLE Multicore Processors. TCAD (2020).","DOI":"10.1109\/TCAD.2019.2944584"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Siqi Wang et al. 2020. Neural Network Inference on Mobile SoCs. IEEE Design Test (2020).","DOI":"10.1109\/MDAT.2020.2968258"}],"event":{"name":"ISLPED '24: 29th ACM\/IEEE International Symposium on Low Power Electronics and Design","location":"Newport Beach CA USA","acronym":"ISLPED '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE EDA"]},"container-title":["Proceedings of the 29th ACM\/IEEE International Symposium on Low Power Electronics and Design"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665314.3670841","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665314.3670841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:51Z","timestamp":1750294671000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3665314.3670841"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":21,"alternative-id":["10.1145\/3665314.3670841","10.1145\/3665314"],"URL":"https:\/\/doi.org\/10.1145\/3665314.3670841","relation":{},"subject":[],"published":{"date-parts":[[2024,8,5]]},"assertion":[{"value":"2024-09-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}