{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T16:36:35Z","timestamp":1781886995119,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":41,"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":[{"name":"US National Science Foundation (NSF)","award":["CNS-1955353"],"award-info":[{"award-number":["CNS-1955353"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CSR-2308530"],"award-info":[{"award-number":["CSR-2308530"]}],"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\/3676536.3697138","type":"proceedings-article","created":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T13:26:26Z","timestamp":1744205186000},"page":"1-7","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Heterogeneous Manycore In-Memory Computing Architectures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8170-1161","authenticated-orcid":false,"given":"Chukwufumnanya","family":"Ogbogu","sequence":"first","affiliation":[{"name":"Washington State University, Pullman, WA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9517-1280","authenticated-orcid":false,"given":"Gaurav","family":"Narang","sequence":"additional","affiliation":[{"name":"Washington State University, Pullman, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7668-2824","authenticated-orcid":false,"given":"Biresh Kumar","family":"Joardar","sequence":"additional","affiliation":[{"name":"University of Houston, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3848-5301","authenticated-orcid":false,"given":"Janardhan Rao","family":"Doppa","sequence":"additional","affiliation":[{"name":"Washington State University, Pullman, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5930-8531","authenticated-orcid":false,"given":"Partha Pratim","family":"Pande","sequence":"additional","affiliation":[{"name":"Washington State University, Pullman, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.12.038"},{"key":"e_1_3_2_1_2_1","volume-title":"PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning. in IEEE International Symposium on High-Performance Computer Architecture (HPCA).","author":"Song L.","unstructured":"L. Song, X. Qian, L. Hai and Y. Chen. 2017. PipeLayer: A Pipelined ReRAM-Based Accelerator for Deep Learning. in IEEE International Symposium on High-Performance Computer Architecture (HPCA)."},{"key":"e_1_3_2_1_3_1","volume-title":"In-Memory Computing in Emerging Memory Technologies for Machine Learning: An Overview. in IEEE Design Automation Conference (DAC).","author":"Roy K.","unstructured":"K. Roy, I. Chakraborty, M. Ali, A. Ankit and A. Agrawal. 2020. In-Memory Computing in Emerging Memory Technologies for Machine Learning: An Overview. in IEEE Design Automation Conference (DAC)."},{"key":"e_1_3_2_1_4_1","volume-title":"ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars Ali. in International Symposium on Computer Architecture (ISCA).","author":"Shafiee A.","year":"2016","unstructured":"A. Shafiee et al. 2016. ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars Ali. in International Symposium on Computer Architecture (ISCA)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-42110-y"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JXCDC.2019.2923745"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/2561828.2561832"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"X. Peng et al. 2020. Benchmarking monolithic 3D integration for compute-in-memory accelerators: overcoming ADC bottlenecks and maintaining scalability to 7nm or beyond. in IEDM.","DOI":"10.1109\/IEDM13553.2020.9372091"},{"key":"e_1_3_2_1_9_1","first-page":"485","article-title":"3-d heterogeneous integration of rram-based compute-in-memory: Impact of integration parameters on inference accuracy","author":"Kaul A.","year":"2022","unstructured":"A. Kaul et al. 2022. 3-d heterogeneous integration of rram-based compute-in-memory: Impact of integration parameters on inference accuracy. IEEE Transactions on Electron Devices, pp. 485--92.","journal-title":"IEEE Transactions on Electron Devices"},{"key":"e_1_3_2_1_10_1","article-title":"AccuReD: High Accuracy Training of CNNs on ReRAM\/GPU Heterogeneous 3D Architecture","author":"Joardar B. K.","year":"2020","unstructured":"B. K. Joardar et al. 2020. AccuReD: High Accuracy Training of CNNs on ReRAM\/GPU Heterogeneous 3D Architecture. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.","journal-title":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442442.3452055"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218732"},{"issue":"1","key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3604802","article-title":"A Survey of Design and Optimization for Systolic Array-based DNN Accelerators","volume":"56","author":"Xu R.","year":"2023","unstructured":"R. Xu et al. 2023. A Survey of Design and Optimization for Systolic Array-based DNN Accelerators. ACM Computing Surveys, vol. 56, no. 1, pp. 1--37.","journal-title":"ACM Computing Surveys"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503465"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2024.3433427"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.5555\/3488766.3488792"},{"key":"e_1_3_2_1_17_1","volume-title":"TEFLON: Thermally Efficient Dataflow-Aware 3D NoC for Accelerating CNN Inferencing on Manycore PIM Architectures. ACM Transactions on Embedded Computing Systems.","author":"Narang G.","year":"2024","unstructured":"G. Narang, C. Ogbogu, J. Doppa and P. Pande. 2024. TEFLON: Thermally Efficient Dataflow-Aware 3D NoC for Accelerating CNN Inferencing on Manycore PIM Architectures. ACM Transactions on Embedded Computing Systems."},{"key":"e_1_3_2_1_18_1","volume-title":"Florets for Chiplets: Data Flow-aware High-Performance and Energy-efficient Network-on-Interposer for CNN Inference Tasks. ACM Transactions on Embedded Computing Systems","volume":"21","author":"Sharma H.","unstructured":"H. Sharma, L. Pfromm, R. Topaloglu, J. Doppa, U. Ogras, A. Kalyanraman and P. Pande. 2023. Florets for Chiplets: Data Flow-aware High-Performance and Energy-efficient Network-on-Interposer for CNN Inference Tasks. ACM Transactions on Embedded Computing Systems, vol. 22(5s), pp. 1--21."},{"key":"e_1_3_2_1_19_1","volume-title":"Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks. in 45th Annual International Symposium on Computer Architecture (ISCA).","author":"Eckert C.","year":"2018","unstructured":"C. Eckert et al. 2018. Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks. in 45th Annual International Symposium on Computer Architecture (ISCA)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSI.2021.3138057"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2023.3327748"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2021.3127517"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_2_1_24_1","volume-title":"S. Datta and A. Raychowdhury.","author":"Keshavarzi A.","year":"2020","unstructured":"A. Keshavarzi, K. Ni, W. Van Den Hoek, S. Datta and A. Raychowdhury. 2020. FerroElectronics for Edge Intelligence. IEEE Micro, vol. 40."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TED.2020.2964640"},{"key":"e_1_3_2_1_26_1","volume-title":"Domain-Specific STT-MRAM-Based In-Memory Computing: A Survey. IEEE Access","volume":"12","author":"Yusuf A.","unstructured":"A. Yusuf, T. Adegbija and D. Gajaria. 2024. Domain-Specific STT-MRAM-Based In-Memory Computing: A Survey. IEEE Access, vol. 12."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"X. Peng et al. 2020. DNN+NeuroSim V2.0: An end-to-end benchmarking framework for compute-in-memory accelerators for on-chip training. arXiv:2003.06471.","DOI":"10.1109\/TCAD.2020.3043731"},{"key":"e_1_3_2_1_28_1","first-page":"1","volume-title":"IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED)","author":"Ogbogu C.","unstructured":"C. Ogbogu, M. Soumen, B. Joardar, J. Doppa, D. Heo, K. Chakrabarty and P. Pande. 2023. Energy-Efficient ReRAM-Based ML Training via Mixed Pruning and Reconfigurable ADC. IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED), pp. 1--6."},{"key":"e_1_3_2_1_29_1","first-page":"1","volume-title":"2020 57th ACM\/IEEE Design Automation Conference (DAC)","author":"Lee S.","unstructured":"S. Lee, G. Jung, M. E. Fouda, J. Lee, A. Eltawil and F. Kurdahi. 2020. Learning to Predict IR Drop with Effective Training for ReRAM-based Neural Network Hardware. In 2020 57th ACM\/IEEE Design Automation Conference (DAC), pp. 1--6."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322271"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310400"},{"key":"e_1_3_2_1_32_1","volume-title":"Hybrid Analog-Digital In-Memory Computing. in IEEE\/ACM International Conference On Computer Aided Design (ICCAD).","author":"Haq Rashed M. R.","unstructured":"M. R. Haq Rashed, S. K. Jha and R. Ewetz. 2021. Hybrid Analog-Digital In-Memory Computing. in IEEE\/ACM International Conference On Computer Aided Design (ICCAD)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2022.3197516"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774549"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","unstructured":"S. Bandyopadhyay S. Saha U. Maulik and K. Deb. 2008. A simulated annealing-based multiobjective optimization algorithm: AMOSA. IEEE transactions on evolutionary computation vol. 12(3) pp. 269--283.","DOI":"10.1109\/TEVC.2007.900837"},{"key":"e_1_3_2_1_36_1","unstructured":"T. Lin Y. Wang X. Liu and X. Qiu. 2021. A Survey of Transformers. in ArXiv preprint ArXiv:2106.04554."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"crossref","unstructured":"P. Dhingra et al. 2024. HeTraX: Energy Efficient 3D Heterogeneous Manycore Architecture for Transformer Acceleration. arXiv preprint arXiv:2408.03397.","DOI":"10.1145\/3665314.3670814"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"crossref","unstructured":"S. Sridharan J. Stevens K. Roy and A. Raghunathan. 2023. X-Former: In-Memory Acceleration of Transformers. IEEE TVLSI.","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"M. Zhou W. Xu J. Kang and T. Rosing. 2022. TransPIM: A Memory-based Acceleration via Software-Hardware Co-Design for Transformer. in HPCA Korea.","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"e_1_3_2_1_40_1","volume-title":"HAIMA: A Hybrid SRAM and DRAM Accelerator-in-Memory Architecture for Transformer. in DAC.","author":"Ding Y.","year":"2023","unstructured":"Y. Ding et al. 2023. HAIMA: A Hybrid SRAM and DRAM Accelerator-in-Memory Architecture for Transformer. in DAC."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Y. Luo and S. Yu. 2024. H3D-Transformer: A Heterogeneous 3D (H3D) Computing Platform for Transformer Model Acceleration on Edge Devices. in ACM TOADES.","DOI":"10.1145\/3649219"}],"event":{"name":"ICCAD '24: 43rd IEEE\/ACM International Conference on Computer-Aided Design","location":"Newark Liberty International Airport Marriott New York NY USA","acronym":"ICCAD '24","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE CAS","IEEE CEDA","IEEE EDS"]},"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\/3676536.3697138","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3697138","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676536.3697138","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:45Z","timestamp":1750295925000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676536.3697138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,27]]},"references-count":41,"alternative-id":["10.1145\/3676536.3697138","10.1145\/3676536"],"URL":"https:\/\/doi.org\/10.1145\/3676536.3697138","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"}}]}}