{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:09:40Z","timestamp":1750219780635,"version":"3.41.0"},"reference-count":23,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,12,31]],"date-time":"2022-12-31T00:00:00Z","timestamp":1672444800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Queue"],"published-print":{"date-parts":[[2022,12,31]]},"abstract":"<jats:p>As artificial intelligence becomes a pervasive tool for the billions of IoT (Internet of things) devices at the edge, the data movement bottleneck imposes severe limitations on the performance and autonomy of these systems. PiM (processing-in-memory) is emerging as a way of mitigating the data movement bottleneck while satisfying the stringent performance, energy efficiency, and accuracy requirements of edge imaging applications that rely on CNNs (convolutional neural networks).<\/jats:p>","DOI":"10.1145\/3580503","type":"journal-article","created":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T23:04:47Z","timestamp":1675119887000},"page":"9-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["To PiM or Not to PiM"],"prefix":"10.1145","volume":"20","author":[{"given":"Gabriel","family":"Falcao","sequence":"first","affiliation":[{"name":"Instituto de Telecomunica\u00e7\u00f5es"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o Dinis","family":"Ferreira","sequence":"additional","affiliation":[{"name":"University of Coimbra"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,1,30]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Bonawitz K. Kairouz P. McMahan B. Ramage D. 2021. Federated learning and privacy: building privacy-preserving systems for machine learning and data science on decentralized data. acmqueue 19(5) 87?114; https:\/\/dl.acm.org\/doi\/10.1145\/3494834.3500240.","key":"e_1_2_1_1_1","DOI":"10.1145\/3494834.3500240"},{"doi-asserted-by":"publisher","key":"e_1_2_1_2_1","DOI":"10.1145\/3007787.3001140"},{"doi-asserted-by":"publisher","key":"e_1_2_1_3_1","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"doi-asserted-by":"publisher","key":"e_1_2_1_4_1","DOI":"10.1145\/3123939.3123953"},{"doi-asserted-by":"publisher","key":"e_1_2_1_5_1","DOI":"10.1109\/MICRO56248.2022.00067"},{"doi-asserted-by":"publisher","key":"e_1_2_1_6_1","DOI":"10.1109\/MC.2020.3034951"},{"doi-asserted-by":"publisher","key":"e_1_2_1_7_1","DOI":"10.1145\/3352460.3358260"},{"doi-asserted-by":"publisher","key":"e_1_2_1_8_1","DOI":"10.1145\/3445814.3446749"},{"doi-asserted-by":"publisher","key":"e_1_2_1_9_1","DOI":"10.1145\/3282307"},{"key":"e_1_2_1_10_1","first-page":"1","article-title":"Quantized neural networks: training neural networks with low precision weights and activations","volume":"18","author":"Hubara I.","year":"2017","unstructured":"Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., Bengio, Y. 2017. Quantized neural networks: training neural networks with low precision weights and activations. Journal of Machine Learning Research 18, 1-30; https:\/\/www.jmlr.org\/papers\/volume18\/16-456\/16-456.pdf.","journal-title":"Journal of Machine Learning Research"},{"doi-asserted-by":"publisher","key":"e_1_2_1_11_1","DOI":"10.1145\/3079856.3080246"},{"key":"e_1_2_1_12_1","volume-title":"IEEE International Solid-state Circuits Conference (ISSCC), 350-352; https:\/\/ieeexplore.ieee.org\/document\/9365862","author":"Kwon Y.-C.","year":"2021","unstructured":"Kwon, Y.-C., Lee, S., Lee, J., Kwon, S.-H., Ryu, J., Son, J.-P., Seongil, O., Yu, H.-S., Lee, H., Kim, S. 2021. 25.4 A 20nm 6GB function-in-memory DRAM, based on HBM2 with a 1.2 TFLOPS programmable computing unit using bank-level parallelism, for machine learning applications. In IEEE International Solid-state Circuits Conference (ISSCC), 350-352; https:\/\/ieeexplore.ieee.org\/document\/9365862."},{"doi-asserted-by":"publisher","key":"e_1_2_1_13_1","DOI":"10.1109\/SiPS.2017.8110024"},{"key":"e_1_2_1_14_1","volume-title":"A modern primer on processing in memory. arXiv","author":"Mutlu O.","year":"2012","unstructured":"Mutlu, O., Ghose, S., G\u00f3mez-Luna, J., Ausavarungnirun, R. 2020. A modern primer on processing in memory. arXiv; https:\/\/arxiv.org\/abs\/2012.03112."},{"volume-title":"Handling limited resources in mobile computing via closed-loop approximate computations","author":"Pandey P.","unstructured":"Pandey, P., Pompili, D. 2019. Handling limited resources in mobile computing via closed-loop approximate computations. IEEE Pervasive Computing 18 (1), 39?48; https:\/\/ieeexplore.ieee.org\/document\/8705029.","key":"e_1_2_1_15_1"},{"unstructured":"Radojkovic P. Carpenter P. Esmaili-Dokht P. Cimadomo R. Charles H.-P. Sebastian A. Amato P. 2021. Processing in memory: the tipping point. European Technology Platform for High-performance Computing white paper; https:\/\/www.etp4hpc.eu\/pujades\/files\/ETP4HPC_WP_Processing-In-Memory_FINAL.pdf.","key":"e_1_2_1_16_1"},{"doi-asserted-by":"publisher","key":"e_1_2_1_17_1","DOI":"10.1145\/3429945"},{"volume-title":"The digitization of the world?from edge to core. IDC White Paper","author":"Reinsel D.","unstructured":"Reinsel, D., Gantz, J., Rydning, J. 2018. The digitization of the world?from edge to core. IDC White Paper, I. D. Corporation; https:\/\/www.seagate.com\/files\/www-content\/our-story\/trends\/files\/idc-seagate-dataage-whitepaper.pdf.","key":"e_1_2_1_18_1"},{"key":"e_1_2_1_20_1","volume-title":"13th ACM International Systems and Storage Conference.","author":"Satyanarayanan M.","year":"2020","unstructured":"Satyanarayanan, M. 2020. Edge computing: a new disruptive force. Keynote address, 13th ACM International Systems and Storage Conference."},{"doi-asserted-by":"publisher","key":"e_1_2_1_21_1","DOI":"10.1145\/3123939.3124544"},{"doi-asserted-by":"publisher","key":"e_1_2_1_22_1","DOI":"10.1145\/3007787.3001139"},{"doi-asserted-by":"publisher","key":"e_1_2_1_23_1","DOI":"10.1109\/MM.2020.2975764"},{"doi-asserted-by":"crossref","unstructured":"Zheng H. Hu H. Han Z. 2020. Preserving user privacy for machine learning: local differential privacy or federated machine learning? IEEE Intelligent Systems 35(4) 5?14; https:\/\/ieeexplore.ieee.org\/document\/9144394.","key":"e_1_2_1_24_1","DOI":"10.1109\/MIS.2020.3010335"}],"container-title":["Queue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580503","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3580503","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:42Z","timestamp":1750178262000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3580503"}},"subtitle":["The case for in-memory inferencing of quantized CNNs at the edge"],"short-title":[],"issued":{"date-parts":[[2022,12,31]]},"references-count":23,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,12,31]]}},"alternative-id":["10.1145\/3580503"],"URL":"https:\/\/doi.org\/10.1145\/3580503","relation":{},"ISSN":["1542-7730","1542-7749"],"issn-type":[{"type":"print","value":"1542-7730"},{"type":"electronic","value":"1542-7749"}],"subject":[],"published":{"date-parts":[[2022,12,31]]},"assertion":[{"value":"2023-01-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}