{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T17:37:52Z","timestamp":1784828272274,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":17,"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\/"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2308530"],"award-info":[{"award-number":["CNS-2308530"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1955353"],"award-info":[{"award-number":["CNS-1955353"]}],"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":[[2024,8,5]]},"DOI":"10.1145\/3665314.3670814","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":["HeTraX: Energy Efficient 3D Heterogeneous Manycore Architecture for Transformer Acceleration"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0422-3365","authenticated-orcid":false,"given":"Pratyush","family":"Dhingra","sequence":"first","affiliation":[{"name":"Washington State University, Pullman, WA, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3848-5301","authenticated-orcid":false,"given":"Jana","family":"Doppa","sequence":"additional","affiliation":[{"name":"Washington State University, Pullman, WA, United States"}],"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, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,9,9]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"T. Lin Y. Wang X. Liu and X. Qiu. 2021. A Survey of Transformers. arXiv preprint ArXiv:2106.04554 (2021)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"A. Shafiee et al. 2016. ISAAC: a convolutional neural network accelerator with in-situ analog arithmetic in crossbars. In ISCA.","DOI":"10.1109\/ISCA.2016.12"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Z. He et al. 2019. Noise Injection Adaption: End-to-End ReRAM Crossbar Non-ideal Effect Adaption for Neural Network Mapping. In DAC.","DOI":"10.1145\/3316781.3317870"},{"key":"e_1_3_2_1_4_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.","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"e_1_3_2_1_5_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_6_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. ACM TOADES (2024).","DOI":"10.1145\/3649219"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"X. Yang et al. 2020. ReTransformer: ReRAM-based Processing-in-Memory Architecture for Transformer Acceleration. In ICCAD.","DOI":"10.1145\/3400302.3415640"},{"key":"e_1_3_2_1_8_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 (2023).","DOI":"10.1109\/TVLSI.2023.3282046"},{"key":"e_1_3_2_1_9_1","unstructured":"https:\/\/ddr-phy.org\/. [Online]."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"crossref","unstructured":"B. Joardar et al. 2019. Learning-Based Application-Agnostic 3D NoC Design for Heterogeneous Manycore Systems. IEEE TC 68 (2018).","DOI":"10.1109\/TC.2018.2889053"},{"key":"e_1_3_2_1_11_1","unstructured":"J. Cong et al. 2004. A thermal-driven floorplanning algorithm for 3D ICs. In ICCAD."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"V. Kandiah et al. 2021. AccelWattch: A Power Modeling Framework for Modern GPUs. MICRO-54 (2021).","DOI":"10.1145\/3466752.3480063"},{"key":"e_1_3_2_1_13_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. IEEE TCAD 40 (2020).","DOI":"10.1109\/TCAD.2020.3043731"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"N. Jiang et al. 2013. Detailed and Flexible Cycle-Accurate Network-on-Chip Simulator. In ISPASS.","DOI":"10.1109\/ISPASS.2013.6557149"},{"key":"e_1_3_2_1_15_1","volume":"201","author":"Gopireddy B.","unstructured":"B. Gopireddy and J. Torrellas. 2019. Designing Vertical Processors in Monolithic 3D. In ISCA.","journal-title":"J. Torrellas."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"A. Wang et al. 2018. GLUE:A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018).","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"S. Van Huylenbroeck et al. 2016. Small Pitch High Aspect Ratio Via-Last TSV Module. IEEE ECTC (2016).","DOI":"10.1109\/ECTC.2016.155"}],"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\/3665314.3670814","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665314.3670814","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3665314.3670814","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\/3665314.3670814"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,5]]},"references-count":17,"alternative-id":["10.1145\/3665314.3670814","10.1145\/3665314"],"URL":"https:\/\/doi.org\/10.1145\/3665314.3670814","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"}}]}}