{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T15:10:08Z","timestamp":1751037008075,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,6,29]],"date-time":"2025-06-29T00:00:00Z","timestamp":1751155200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2326894, 2425655"],"award-info":[{"award-number":["2326894, 2425655"]}],"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":[[2025,6,30]]},"DOI":"10.1145\/3716368.3735222","type":"proceedings-article","created":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:00:26Z","timestamp":1751032826000},"page":"200-207","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CADOSys: Cache Aware Design Space Optimization for Spatial ML Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7092-2401","authenticated-orcid":false,"given":"Ruihao","family":"Li","sequence":"first","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0425-3335","authenticated-orcid":false,"given":"Siyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1581-8166","authenticated-orcid":false,"given":"Krishna","family":"Kavi","sequence":"additional","affiliation":[{"name":"University of North Texas, Denton, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7754-1874","authenticated-orcid":false,"given":"Gayatri","family":"Mehta","sequence":"additional","affiliation":[{"name":"University of North Texas, Denton, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7556-3069","authenticated-orcid":false,"given":"Neeraja J.","family":"Yadwadkar","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8747-5214","authenticated-orcid":false,"given":"Lizy K.","family":"John","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin, Austin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,29]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_3_2_2_2","DOI":"10.1109\/MICRO.2016.7783725"},{"key":"e_1_3_3_2_3_2","volume-title":"ISCA","author":"Cai Jingwei","year":"2023","unstructured":"Jingwei Cai, et\u00a0al. 2023. Inter-layer scheduling space definition and exploration for tiled accelerators. In ISCA."},{"key":"e_1_3_3_2_4_2","volume-title":"ISCA","author":"Chen Yu-Hsin","year":"2016","unstructured":"Yu-Hsin Chen, et\u00a0al. 2016. Eyeriss: A spatial architecture for energy-efficient dataflow for convolutional neural networks. In ISCA."},{"unstructured":"Abhimanyu Dubey et\u00a0al. 2024. The llama 3 herd of models. arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024).","key":"e_1_3_3_2_5_2"},{"key":"e_1_3_3_2_6_2","volume-title":"ISCA","author":"Firoozshahian Amin","year":"2023","unstructured":"Amin Firoozshahian, et\u00a0al. 2023. MTIA: First Generation Silicon Targeting Meta\u2019s Recommendation Systems. In ISCA."},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_7_2","DOI":"10.1145\/3445814.3446762"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_8_2","DOI":"10.1145\/3613424.3623797"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_9_2","DOI":"10.1109\/ISPASS55109.2022.00041"},{"key":"e_1_3_3_2_10_2","volume-title":"ISCA","author":"Huang Qijing","year":"2021","unstructured":"Qijing Huang, et\u00a0al. 2021. Cosa: Scheduling by constrained optimization for spatial accelerators. In ISCA."},{"key":"e_1_3_3_2_11_2","volume-title":"ISCA","author":"Huang Qijing","year":"2024","unstructured":"Qijing Huang, et\u00a0al. 2024. Mind the Gap: Attainable Data Movement and Operational Intensity Bounds for Tensor Algorithms. In ISCA."},{"key":"e_1_3_3_2_12_2","volume-title":"ISCA","author":"Jouppi Norm","year":"2023","unstructured":"Norm Jouppi, et\u00a0al. 2023. Tpu v4: An optically reconfigurable supercomputer for machine learning with hardware support for embeddings. In ISCA."},{"key":"e_1_3_3_2_13_2","volume-title":"ISCA","author":"Jouppi Norman\u00a0P","year":"2017","unstructured":"Norman\u00a0P Jouppi, et\u00a0al. 2017. In-datacenter performance analysis of a tensor processing unit. In ISCA."},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_14_2","DOI":"10.1145\/3400302.3415639"},{"key":"e_1_3_3_2_15_2","volume-title":"DATE","author":"Khan Sadaf","year":"2024","unstructured":"Sadaf Khan, et\u00a0al. 2024. DeepSeq: Deep Sequential Circuit Learning. In DATE."},{"unstructured":"Joyjit Kundu et\u00a0al. 2024. A System Level Performance Evaluation for Superconducting Digital Systems. arXiv:https:\/\/arXiv.org\/abs\/2411.08645 (2024).","key":"e_1_3_3_2_16_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_17_2","DOI":"10.1109\/HPCA51647.2021.00016"},{"key":"e_1_3_3_2_18_2","volume-title":"DATE","author":"Li Jiajun","year":"2018","unstructured":"Jiajun Li, et\u00a0al. 2018. SmartShuttle: Optimizing off-chip memory accesses for deep learning accelerators. In DATE."},{"key":"e_1_3_3_2_19_2","volume-title":"DATE","author":"Lin Zhe","year":"2022","unstructured":"Zhe Lin, et\u00a0al. 2022. Powergear: Early-stage power estimation in FPGA HLS via heterogeneous edge-centric GNNs. In DATE."},{"doi-asserted-by":"crossref","unstructured":"Sparsh Mittal. 2017. A survey of techniques for cache partitioning in multicore processors. CSUR (2017).","key":"e_1_3_3_2_20_2","DOI":"10.1145\/3062394"},{"key":"e_1_3_3_2_21_2","volume-title":"ISCA","author":"Mudigere Dheevatsa","year":"2022","unstructured":"Dheevatsa Mudigere, et\u00a0al. 2022. Software-hardware co-design for fast and scalable training of deep learning recommendation models. In ISCA."},{"unstructured":"Maxim Naumov et\u00a0al. 2020. Deep learning training in facebook data centers: Design of scale-up and scale-out systems. arXiv:https:\/\/arXiv.org\/abs\/2003.09518 (2020).","key":"e_1_3_3_2_22_2"},{"unstructured":"Maxim Naumov et\u00a0al. 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv:https:\/\/arXiv.org\/abs\/1906.00091 (2019).","key":"e_1_3_3_2_23_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_24_2","DOI":"10.1109\/ISPASS.2019.00042"},{"unstructured":"Nadav Rotem et\u00a0al. 2018. Glow: Graph lowering compiler techniques for neural networks. arXiv:https:\/\/arXiv.org\/abs\/1805.00907 (2018).","key":"e_1_3_3_2_25_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_26_2","DOI":"10.1109\/HPCA56546.2023.10071095"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_27_2","DOI":"10.1109\/ISPASS48437.2020.00016"},{"unstructured":"Ananda Samajdar et\u00a0al. 2018. Scale-sim: Systolic cnn accelerator simulator. arXiv:https:\/\/arXiv.org\/abs\/1811.02883 (2018).","key":"e_1_3_3_2_28_2"},{"unstructured":"Vivienne Sze et\u00a0al. 2017. Efficient processing of deep neural networks: A tutorial and survey. Proc. IEEE (2017).","key":"e_1_3_3_2_29_2"},{"unstructured":"Ashish Vaswani et\u00a0al. 2017. Attention is all you need. NeurIPS (2017).","key":"e_1_3_3_2_30_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_31_2","DOI":"10.1145\/3613424.3623793"},{"unstructured":"Wayne\u00a0Xin Zhao et\u00a0al. 2023. A survey of large language models. arXiv:https:\/\/arXiv.org\/abs\/2303.18223 (2023).","key":"e_1_3_3_2_32_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_33_2","DOI":"10.1145\/3613424.3623792"},{"doi-asserted-by":"publisher","key":"e_1_3_3_2_34_2","DOI":"10.1109\/HPCA53966.2022.00042"}],"event":{"sponsor":["SIGDA ACM Special Interest Group on Design Automation"],"acronym":"GLSVLSI '25","name":"GLSVLSI '25: Great Lakes Symposium on VLSI 2025","location":"New Orleans LA USA"},"container-title":["Proceedings of the Great Lakes Symposium on VLSI 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3716368.3735222","content-type":"text\/html","content-version":"vor","intended-application":"syndication"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T14:37:37Z","timestamp":1751035057000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716368.3735222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,29]]},"references-count":33,"alternative-id":["10.1145\/3716368.3735222","10.1145\/3716368"],"URL":"https:\/\/doi.org\/10.1145\/3716368.3735222","relation":{},"subject":[],"published":{"date-parts":[[2025,6,29]]},"assertion":[{"value":"2025-06-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}