{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T11:28:58Z","timestamp":1763724538214,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T00:00:00Z","timestamp":1624320000000},"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":[],"published-print":{"date-parts":[[2021,6,22]]},"DOI":"10.1145\/3453688.3461499","type":"proceedings-article","created":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T23:13:29Z","timestamp":1624058009000},"page":"241-246","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Computing Utilization Enhancement for Chiplet-based Homogeneous Processing-in-Memory Deep Learning Processors"],"prefix":"10.1145","author":[{"given":"Bo","family":"Jiao","sequence":"first","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Haozhe","family":"Zhu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Jinshan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Shunli","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Xiaoyang","family":"Kang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Mingyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]},{"given":"Chixiao","family":"Chen","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2021,6,22]]},"reference":[{"key":"e_1_3_2_3_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2013.90"},{"key":"e_1_3_2_3_2_1","first-page":"136","volume-title":"a 12nm programmable convolution-efficient neural-processing-unit chip achieving 825tops,\" in 2020 IEEE International Solid- State Circuits Conference - (ISSCC)","author":"Jiao Y.","year":"2020","unstructured":"Y. Jiao, et al., \"a 12nm programmable convolution-efficient neural-processing-unit chip achieving 825tops,\" in 2020 IEEE International Solid- State Circuits Conference - (ISSCC), 2020, pp. 136--140."},{"key":"e_1_3_2_3_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062985"},{"key":"e_1_3_2_3_4_1","first-page":"728","volume-title":"Cost-effective design of scalable high-performance systems using active and passive interposers,\" in 2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD)","author":"Stow D.","year":"2017","unstructured":"D. Stow, Y. Xie, T. Siddiqua, and G. H. Loh, \"Cost-effective design of scalable high-performance systems using active and passive interposers,\" in 2017 IEEE\/ACM International Conference on Computer-Aided Design (ICCAD), 2017, pp. 728--735."},{"key":"e_1_3_2_3_5_1","first-page":"44","volume-title":"AMD Chiplet Architecture for High-Performance Server and Desktop Products,\" in IEEE International Solid- State Circuits Conference - (ISSCC)","author":"Naffziger S.","year":"2020","unstructured":"S. Naffziger, K. Lepak, M. Paraschou and M. Subramony, \"AMD Chiplet Architecture for High-Performance Server and Desktop Products,\" in IEEE International Solid- State Circuits Conference - (ISSCC), 2020, pp. 44--45."},{"key":"e_1_3_2_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2019.2960488"},{"key":"e_1_3_2_3_7_1","volume-title":"Hot Chips: A Symposium on High Performance Chips","author":"Zaruba F.","year":"2020","unstructured":"F. Zaruba, F. Schuiki and L. Benini, \"Manticore: A 4096-core RISC-V Chiplet Architecture for Ultra-efficient Floating-point Computing\", in Hot Chips: A Symposium on High Performance Chips, 2020."},{"key":"e_1_3_2_3_8_1","volume-title":"Simba: Scaling deep-learning inference with multi-chip-module-based architecture,\" in Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture","author":"Shao Y. S.","year":"2019","unstructured":"Y. S. Shao, et al., \"Simba: Scaling deep-learning inference with multi-chip-module-based architecture,\" in Proceedings of the 52nd Annual IEEE\/ACM International Symposium on Microarchitecture, 2019, p. 14--27."},{"key":"e_1_3_2_3_9_1","first-page":"541","volume-title":"PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning,\" in IEEE International Symposium on High Performance Computer Architecture (HPCA)","author":"Song L.","year":"2017","unstructured":"L. Song, X. Qian, H. Li and Y. Chen, \"PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning,\" in IEEE International Symposium on High Performance Computer Architecture (HPCA), 2017, pp. 541--552."},{"key":"e_1_3_2_3_10_1","first-page":"40","volume-title":"zeppelin': An soc for multichip architectures,\" in 2018 IEEE International Solid - State Circuits Conference - (ISSCC)","author":"Beck N.","year":"2018","unstructured":"N. Beck, S. White, M. Paraschou, and S. Naffziger, \"\"zeppelin': An soc for multichip architectures,\" in 2018 IEEE International Solid - State Circuits Conference - (ISSCC), 2018, pp. 40--42."},{"key":"e_1_3_2_3_11_1","first-page":"726","volume-title":"Modular routing design for chiplet-based systems,\" in ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA)","author":"Yin J.","year":"2018","unstructured":"J. Yin, et al., \"Modular routing design for chiplet-based systems,\" in ACM\/IEEE 45th Annual International Symposium on Computer Architecture (ISCA), 2018, pp. 726--738."},{"key":"e_1_3_2_3_12_1","first-page":"1","volume-title":"A versatile and flexible chiplet-based system design for heterogeneous manycore architectures,\" in 2020 57th ACM\/IEEE Design Automation Conference (DAC)","author":"Zheng H.","year":"2020","unstructured":"H. Zheng, K. Wang, and A. Louri, \"A versatile and flexible chiplet-based system design for heterogeneous manycore architectures,\" in 2020 57th ACM\/IEEE Design Automation Conference (DAC), 2020, pp. 1--6."},{"key":"e_1_3_2_3_13_1","first-page":"14","volume-title":"ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars,\" in ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA)","author":"Shafiee A.","year":"2016","unstructured":"A. Shafiee et al., \"ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars,\" in ACM\/IEEE 43rd Annual International Symposium on Computer Architecture (ISCA), 2016, pp. 14--26."},{"key":"e_1_3_2_3_14_1","first-page":"1","volume-title":"In-datacenter performance analysis of a tensor processing unit,\" in ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA)","author":"Jouppi N. P.","year":"2017","unstructured":"N. P. Jouppi, et al., \"In-datacenter performance analysis of a tensor processing unit,\" in ACM\/IEEE 44th Annual International Symposium on Computer Architecture (ISCA), 2017, pp. 1--12,"},{"key":"e_1_3_2_3_15_1","first-page":"1","volume-title":"ACM\/IEEE Design Automation Conference (DAC)","author":"Chen C.","year":"2018","unstructured":"C. Chen, et al., \"Exploring the Programmability for Deep Learning Processors:from Architecture to Tensorization,\"in ACM\/IEEE Design Automation Conference (DAC), 2018, pp. 1--6."},{"key":"e_1_3_2_3_16_1","volume-title":"TVM: end-to-end compilation stack for deep learning,\" in SysML Conference","author":"Chen T.","year":"2018","unstructured":"T. Chen, et al., \"TVM: end-to-end compilation stack for deep learning,\" in SysML Conference, 2018."},{"key":"e_1_3_2_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2616357"},{"key":"e_1_3_2_3_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062958"}],"event":{"name":"GLSVLSI '21: Great Lakes Symposium on VLSI 2021","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"Virtual Event USA","acronym":"GLSVLSI '21"},"container-title":["Proceedings of the 2021 Great Lakes Symposium on VLSI"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3453688.3461499","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3453688.3461499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:28:46Z","timestamp":1750195726000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3453688.3461499"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,22]]},"references-count":18,"alternative-id":["10.1145\/3453688.3461499","10.1145\/3453688"],"URL":"https:\/\/doi.org\/10.1145\/3453688.3461499","relation":{},"subject":[],"published":{"date-parts":[[2021,6,22]]},"assertion":[{"value":"2021-06-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}