{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T01:53:11Z","timestamp":1773193991275,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["1730158, 1540112, 1541349, 1826967, 2112167, 2100237, 2120019, 2003279, 2211386, 2052809, 1911095"],"award-info":[{"award-number":["1730158, 1540112, 1541349, 1826967, 2112167, 2100237, 2120019, 2003279, 2211386, 2052809, 1911095"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","award":["PRISM, CoCoSys, JUMP 2.0"],"award-info":[{"award-number":["PRISM, CoCoSys, JUMP 2.0"]}],"id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["RPSIM, CoCosSys, JUMP 2.0"],"award-info":[{"award-number":["RPSIM, CoCosSys, JUMP 2.0"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Swiss National Science Foundation","award":["215747"],"award-info":[{"award-number":["215747"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731041","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"867-883","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["OptiPIM: Optimizing Processing-in-Memory Acceleration Using Integer Linear Programming"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9663-3186","authenticated-orcid":false,"given":"Jiantao","family":"Liu","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5523-7270","authenticated-orcid":false,"given":"Minxuan","family":"Zhou","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6358-0394","authenticated-orcid":false,"given":"Yue","family":"Pan","sequence":"additional","affiliation":[{"name":"University of California, San Diego, La Jolla, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8518-3370","authenticated-orcid":false,"given":"Chien-Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6659-8533","authenticated-orcid":false,"given":"Lana","family":"Josipovi\u0107","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Z\u00fcrich, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6954-997X","authenticated-orcid":false,"given":"Tajana","family":"Rosing","sequence":"additional","affiliation":[{"name":"UCSD, La Jolla, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS61541.2024.00012"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304049"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640366"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","unstructured":"Prasanth Chatarasi Hyoukjun Kwon Angshuman Parashar Michael Pellauer Tushar Krishna and Vivek Sarkar. 2021. Marvel: A Data-Centric Approach for Mapping Deep Learning Operators on Spatial Accelerators. ACM Trans. Archit. Code Optim. 19 1 Article 6 (Dec. 2021). 10.1145\/3485137","DOI":"10.1145\/3485137"},{"key":"e_1_3_3_2_6_2","series-title":"(OSDI \u201918)","first-page":"578","volume-title":"13th USENIX Symposium on Operating Systems Design and Implementation","author":"Chen Tianqi","year":"2018","unstructured":"Tianqi Chen, Thierry Moreau, Ziheng Jiang, Lianmin Zheng, Eddie Yan, Haichen Shen, Meghan Cowan, Leyuan Wang, Yuwei Hu, Luis Ceze, Carlos Guestrin, and Arvind Krishnamurthy. 2018. TVM: An Automated End-to-End Optimizing Compiler for Deep Learning. In 13th USENIX Symposium on Operating Systems Design and Implementation(OSDI \u201918). Carlsbad, CA, USA, 578\u2013594. https:\/\/www.usenix.org\/conference\/osdi18\/presentation\/chen"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","unstructured":"Tsu-Wu\u00a0J. Chou and George\u00a0E. Collins. 1982. Algorithms for the Solution of Systems of Linear Diophantine Equations. SIAM J. Comput. 11 4 (Nov. 1982) 687\u2013708. 10.1137\/0211057 arXiv:10.1137\/0211057","DOI":"10.1137\/0211057"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD57390.2023.10323777"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3623278.3624772"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_2_11_2","unstructured":"Jacob Devlin Ming-Wei Chang Kenton Lee and Kristina Toutanova. 2019. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arxiv:https:\/\/arXiv.org\/abs\/1810.04805\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00040"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358260"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","unstructured":"Amir Gholami Zhewei Yao Sehoon Kim Coleman Hooper Michael\u00a0W. Mahoney and Kurt Keutzer. 2024. AI and Memory Wall. IEEE Micro 44 3 (May 2024) 33\u201339. 10.1109\/MM.2024.3373763","DOI":"10.1109\/MM.2024.3373763"},{"key":"e_1_3_3_2_15_2","unstructured":"Aaron Grattafiori et\u00a0al. 2024. The Llama 3 Herd of Models. arxiv:https:\/\/arXiv.org\/abs\/2407.21783\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_3_2_16_2","unstructured":"Gurobi Optimization LLC. 2023. Gurobi Optimizer Reference Manual. https:\/\/www.gurobi.com"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446762"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623797"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS55109.2022.00039"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00050"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00029"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322237"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","unstructured":"Mingu Kang Sujan\u00a0K. Gonugondla and Naresh\u00a0R. Shanbhag. 2020. Deep In-Memory Architectures in SRAM: An Analog Approach to Approximate Computing. Proc. IEEE 108 12 (Dec. 2020) 2251\u20132275. 10.1109\/JPROC.2020.3034117","DOI":"10.1109\/JPROC.2020.3034117"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3400302.3415639"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE54114.2022.9774568"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey\u00a0E. Hinton. 2017. ImageNet classification with deep convolutional neural networks. Commun. ACM 60 6 (May 2017) 84\u201390. 10.1145\/3065386","DOI":"10.1145\/3065386"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895629"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365862"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370308"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640376"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_3_2_40_2","volume-title":"Torch-MLIR","unstructured":"LLVM. [n. d.]. Torch-MLIR. https:\/\/github.com\/llvm\/torch-mlir"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00062"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","unstructured":"Haocong Luo Yahya\u00a0Can Tu\u011frul F.\u00a0Nisa Bostanc\u0131 Ataberk Olgun A.\u00a0Giray Ya\u011fl\u0131k\u00e7\u0131 and Onur Mutlu. 2024. Ramulator 2.0: A Modern Modular and Extensible DRAM Simulator. IEEE Computer Architecture Letters 23 1 (Jan. 2024) 112\u2013116. 10.1109\/LCA.2023.3333759","DOI":"10.1109\/LCA.2023.3333759"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624869"},{"key":"e_1_3_3_2_44_2","unstructured":"NVIDIA. [n. d.]. TensorRT: High-Performance Deep Learning Inference Optimizer and Runtime. https:\/\/github.com\/NVIDIA\/TensorRT Accessed: 2025-02-16."},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063110"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00024"},{"key":"e_1_3_3_2_47_2","unstructured":"GUROBI OPTIMIZATION. 2025. Gurobi Academic License Program: Free Licenses for Academics | Gurobi - Gurobi Optimization. https:\/\/www.gurobi.com\/academia\/academic-program-and-licenses\/. Accessed: 2025."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_3_2_49_2","volume-title":"Polybench: The polyhedral benchmark suite","author":"Pouchet Louis-No\u00ebl","year":"2012","unstructured":"Louis-No\u00ebl Pouchet. 2012. Polybench: The polyhedral benchmark suite. https:\/\/web.cs.ucla.edu\/\u00a0pouchet\/software\/polybench\/"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198568209.001.0001"},{"key":"e_1_3_3_2_51_2","unstructured":"RDson. 2024. Llama-3-14B-Instruct-v1. https:\/\/huggingface.co\/RDson\/Llama-3-14B-Instruct-v1. Accessed: 2024."},{"key":"e_1_3_3_2_52_2","volume-title":"Discrete Mathematics and Its Applications (5th ed.)","author":"Rosen Kenneth\u00a0H.","year":"2002","unstructured":"Kenneth\u00a0H. Rosen. 2002. Discrete Mathematics and Its Applications (5th ed.). McGraw-Hill Higher Education."},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3587135.3592206"},{"key":"e_1_3_3_2_54_2","unstructured":"Amit Sabne. 2020. XLA : Compiling Machine Learning for Peak Performance."},{"key":"e_1_3_3_2_55_2","unstructured":"SAITPublic. 2025. PIMSimulator. https:\/\/github.com\/SAITPublic\/PIMSimulator Accessed: 2025-02-16."},{"key":"e_1_3_3_2_56_2","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arxiv:https:\/\/arXiv.org\/abs\/1409.1556\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247928"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3617232.3624865"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"e_1_3_3_2_61_2","unstructured":"Nicolas Vasilache Oleksandr Zinenko Theodoros Theodoridis Priya Goyal Zachary DeVito William\u00a0S. Moses Sven Verdoolaege Andrew Adams and Albert Cohen. 2018. Tensor Comprehensions: Framework-Agnostic High-Performance Machine Learning Abstractions. arxiv:https:\/\/arXiv.org\/abs\/1802.04730\u00a0[cs.PL] https:\/\/arxiv.org\/abs\/1802.04730"},{"key":"e_1_3_3_2_62_2","unstructured":"Jie Wang and Jason Cong. 2021. Search for Optimal Systolic Arrays: A Comprehensive Automated Exploration Framework and Lessons Learned. arxiv:https:\/\/arXiv.org\/abs\/2111.14252\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2111.14252"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"publisher","unstructured":"Junpeng Wang Mengke Ge Bo Ding Qi Xu Song Chen and Yi Kang. 2024. NicePIM: Design Space Exploration for Processing-In-Memory DNN Accelerators With 3-D Stacked-DRAM. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 43 5 (May 2024) 1456\u20131469. 10.1109\/TCAD.2023.3342605","DOI":"10.1109\/TCAD.2023.3342605"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00096"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378514"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00021"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731041","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731041","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T10:58:32Z","timestamp":1750503512000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731041"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":66,"alternative-id":["10.1145\/3695053.3731041","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731041","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}