{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:02:45Z","timestamp":1755907365592,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":18,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,12]],"date-time":"2024-06-12T00:00:00Z","timestamp":1718150400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2231620"],"award-info":[{"award-number":["2231620"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,12]]},"DOI":"10.1145\/3649476.3658732","type":"proceedings-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T12:29:41Z","timestamp":1718022581000},"page":"57-62","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A DRAM-based Near-Memory Architecture for Accelerated and Energy-Efficient Execution of Transformers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6649-8487","authenticated-orcid":false,"given":"Gian","family":"Singh","sequence":"first","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9278-2959","authenticated-orcid":false,"given":"Sarma","family":"Vrudhula","sequence":"additional","affiliation":[{"name":"School of Computing and Augmented Intelligence, Arizona State University, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,6,12]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"AMD. 2015. High-Bandwidth Memory (HBM). https:\/\/www.amd.com\/system\/files\/documents\/high-bandwidth-memory-hbm.pdf."},{"key":"e_1_3_2_1_2_1","unstructured":"K. Chandrasekar 2024. DRAMPower: Open-source DRAM Power and Energy Estimation Tool . http:\/\/www.drampower.info\/."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Q. Deng 2018. DrAcc: a DRAM based accelerator for accurate CNN inference. In DAC\u201918.","DOI":"10.1145\/3195970.3196029"},{"key":"e_1_3_2_1_4_1","unstructured":"J. Devlin 2018. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. CoRR abs\/1810.04805 (2018). arXiv:1810.04805"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Y. Ding 2023. HAIMA: A Hybrid SRAM and DRAM Accelerator-in-Memory Architecture for Transformer. In DAC.","DOI":"10.1109\/DAC56929.2023.10247913"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"J. Gomez-Luna 2022. Benchmarking a New Paradigm: Experimental Analysis and Characterization of a Real Processing-in-Memory System. IEEE Access (2022).","DOI":"10.1109\/ACCESS.2022.3174101"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"N. Hajinazar 2021. SIMDRAM: A Framework for Bit-Serial SIMD Processing using DRAM. In ASPLOS\u201921.","DOI":"10.1145\/3445814.3446749"},{"key":"e_1_3_2_1_8_1","volume-title":"Colonnade: A Reconfigurable SRAM-Based Digital Bit-Serial Compute-In-Memory Macro for Processing Neural Networks. JSSC 56, 7","author":"Kim","year":"2021","unstructured":"H. Kim 2021. Colonnade: A Reconfigurable SRAM-Based Digital Bit-Serial Compute-In-Memory Macro for Processing Neural Networks. JSSC 56, 7 (2021)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"crossref","unstructured":"J.H. Kim 2021. Aquabolt-XL: Samsung HBM2-PIM with in-memory Processing for ML Accelerators and Beyond. In 2021 HCS.","DOI":"10.1109\/HCS52781.2021.9567191"},{"key":"e_1_3_2_1_10_1","volume-title":"BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs\/1910.13461","author":"Lewis","year":"2019","unstructured":"M. Lewis 2019. BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension. CoRR abs\/1910.13461 (2019). arXiv:1910.13461"},{"volume-title":"DRISA: a DRAM-based Reconfigurable In-Situ Accelerator","author":"Li","key":"e_1_3_2_1_11_1","unstructured":"S. Li 2017. DRISA: a DRAM-based Reconfigurable In-Situ Accelerator. In IEEE\/ACM MICRO\u201917."},{"volume-title":"Threshold logic and its applications","author":"Muroga","key":"e_1_3_2_1_12_1","unstructured":"S. Muroga. 1971. Threshold logic and its applications. Wiley-Interscience, NY."},{"key":"e_1_3_2_1_13_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arxiv:2303.08774\u00a0[cs.CL]"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"crossref","unstructured":"V. Seshadri 2017. Ambit: in-memory accelerator for bulk bitwise operations using commodity DRAM technology. In MICRO\u201917.","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_2_1_15_1","volume-title":"X-Former: In-Memory Acceleration of Transformers. TVLSI","author":"Sridharan","year":"2023","unstructured":"S. Sridharan 2023. X-Former: In-Memory Acceleration of Transformers. TVLSI (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2024.3357597"},{"key":"e_1_3_2_1_17_1","volume-title":"Vesti: Energy-Efficient In-Memory Computing Accelerator for Deep Neural Networks. TVLSI\u201920","author":"Yin 0.","year":"2020","unstructured":"S. Yin 2020. Vesti: Energy-Efficient In-Memory Computing Accelerator for Deep Neural Networks. TVLSI\u201920 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"M. Zhou 2022. TransPIM: A Memory-based Acceleration via Software-Hardware Co-Design for Transformer. In HPCA.","DOI":"10.1109\/HPCA53966.2022.00082"}],"event":{"name":"GLSVLSI '24: Great Lakes Symposium on VLSI 2024","sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"location":"Clearwater FL USA","acronym":"GLSVLSI '24"},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658732","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649476.3658732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T02:31:00Z","timestamp":1755829860000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649476.3658732"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,12]]},"references-count":18,"alternative-id":["10.1145\/3649476.3658732","10.1145\/3649476"],"URL":"https:\/\/doi.org\/10.1145\/3649476.3658732","relation":{},"subject":[],"published":{"date-parts":[[2024,6,12]]},"assertion":[{"value":"2024-06-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}