{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:37:17Z","timestamp":1772725037462,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":274,"publisher":"ACM","funder":[{"name":"Semiconductor Research Corporation (SRC)"},{"name":"ETH Future Computing Laboratory (EFCL)"},{"name":"AI Chip Center for Emerging Smart Systems (ACCESS), sponsored by InnoHK funding, Hong Kong SAR"},{"name":"European Union?s Horizon programme for research and innovation [101047160 - BioPIM]"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1145\/3721145.3730420","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:17Z","timestamp":1755867437000},"page":"473-494","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Proteus: Achieving High-Performance Processing-Using-DRAM with Dynamic Bit-Precision, Adaptive Data Representation, and Flexible Arithmetic"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1557-4819","authenticated-orcid":false,"given":"Geraldo Francisco","family":"de Oliveira Junior","sequence":"first","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, CH-ZH, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2304-3124","authenticated-orcid":false,"given":"Mayank","family":"Kabra","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, CH-ZH, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0169-3864","authenticated-orcid":false,"given":"Yuxin","family":"Guo","sequence":"additional","affiliation":[{"name":"Cambridge University, Department of Computer Science, Cambridge, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8624-4497","authenticated-orcid":false,"given":"Kangqi","family":"Chen","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, CH-ZH, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9333-6077","authenticated-orcid":false,"given":"Abdullah Giray","family":"Yaglikci","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, CH-ZH, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2378-6737","authenticated-orcid":false,"given":"Melina","family":"Soysal","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, CH-ZH, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4029-0175","authenticated-orcid":false,"given":"Mohammad","family":"Sadrosadati","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, CH-ZH, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2584-5491","authenticated-orcid":false,"given":"Joaquin","family":"Olivares Bueno","sequence":"additional","affiliation":[{"name":"Universidad de C\u00f3rdoba, Electrical and Computer Engineering, C\u00f3rdoba, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9138-0613","authenticated-orcid":false,"given":"Saugata","family":"Ghose","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Siebel School of Computing and Data Science, Champaign, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6514-1571","authenticated-orcid":false,"given":"Juan","family":"G\u00f3mez-Luna","sequence":"additional","affiliation":[{"name":"NVIDIA Research, Zurich, CH-ZH, Switzerland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0075-2312","authenticated-orcid":false,"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, CH-ZH, Switzerland"}]}],"member":"320","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_3_2_6_2","volume-title":"ISCA","author":"Akin Berkin","year":"2015","unstructured":"Berkin Akin, Franz Franchetti, and James\u00a0C Hoe. 2015. Data Reorganization in Memory Using 3D-Stacked DRAM. In ISCA."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2014.7040954"},{"key":"e_1_3_3_2_8_2","volume-title":"ISCA","author":"Alameldeen Alaa\u00a0R","year":"2004","unstructured":"Alaa\u00a0R Alameldeen and David\u00a0A Wood. 2004. Adaptive Cache Compression for High-Performance Processors. In ISCA."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123982"},{"key":"e_1_3_3_2_10_2","volume-title":"TCAS-I","author":"Ali Mustafa\u00a0F","year":"2019","unstructured":"Mustafa\u00a0F Ali, Akhilesh Jaiswal, and Kaushik Roy. 2019. In-Memory Low-Cost Bit-Serial Addition Using Commodity DRAM Technology. In TCAS-I."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.3850\/9783981537079_0093"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818950.2818953"},{"key":"e_1_3_3_2_13_2","volume-title":"CASES","author":"Alves M.\u00a0A.\u00a0Z.","year":"2015","unstructured":"M.\u00a0A.\u00a0Z. Alves, P.\u00a0C. Santos, F.\u00a0B. Moreira, and opthers. 2015. Saving Memory Movements Through Vector Processing in the DRAM. In CASES."},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299874.3317984"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942101"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Aman Arora Atharva Bhamburkar Aatman Borda Tanmay Anand Rishabh Sehgal Bagus Hanindhito Pierre-Emmanuel Gaillardon Jaydeep Kulkarni and Lizy\u00a0K John. 2023. CoMeFa: Deploying Compute-in-Memory on FPGAs for Deep Learning Acceleration. Trans. Reconfigurable Technol. Syst. (2023).","DOI":"10.1145\/3603504"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"H. Asghari-Moghaddam A. Farmahini-Farahani K. Morrow et\u00a0al. 2016. Near-DRAM Acceleration with Single-ISA Heterogeneous Processing in Standard Memory Modules. IEEE Micro (2016).","DOI":"10.1109\/MM.2016.8"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783753"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Erfan Azarkhish Christoph Pfister Davide Rossi Igor Loi and Luca Benini. 2016. Logic-Base Interconnect Design for Near Memory Computing in the Smart Memory Cube. IEEE VLSI (2016).","DOI":"10.1109\/TVLSI.2016.2570283"},{"key":"e_1_3_3_2_20_2","volume-title":"EMS","author":"Azarkhish Erfan","year":"2016","unstructured":"Erfan Azarkhish, Davide Rossi, Igor Loi, and Luca Benini. 2016. A Case for Near Memory Computation Inside the Smart Memory Cube. In EMS."},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"Erfan Azarkhish Davide Rossi Igor Loi and Luca Benini. 2018. Neurostream: Scalable and Energy Efficient Deep Learning with Smart Memory Cubes. TPDS (2018).","DOI":"10.1109\/TPDS.2017.2752706"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2764942"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","unstructured":"R. Balasubramonian J. Chang T. Manning et\u00a0al. 2014. Near-Data Processing: Insights from a MICRO-46 Workshop. IEEE Micro (2014).","DOI":"10.1109\/MM.2014.55"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Orest\u00a0J Bedrij. 1962. Carry-Select Adder. IEEE TC (1962).","DOI":"10.1109\/IRETELC.1962.5407919"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480133"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Nathan Binkert Bradford Beckmann Gabriel Black Steven\u00a0K. Reinhardt Ali Saidi Arkaprava Basu Joel Hestness Derek\u00a0R. Hower Tushar Krishna Somayeh Sardashti Rathijit Sen Korey Sewell Muhammad Shoaib Nilay Vaish Mark\u00a0D. Hill and David\u00a0A. Wood. 2011. The gem5 Simulator. Comput. Archit. News (2011).","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Andrew\u00a0D Booth. 1951. A Signed Binary mMultiplication Technique. The Quarterly Journal of Mechanics and Applied Mathematics (1951).","DOI":"10.1093\/qjmam\/4.2.236"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.5555\/AAI28263242"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT52795.2021.00019"},{"key":"e_1_3_3_2_30_2","unstructured":"Amirali Boroumand Saugata Ghose Berkin Akin Ravi Narayanaswami Geraldo\u00a0F Oliveira Xiaoyu Ma Eric Shiu and Onur Mutlu. 2021. Mitigating Edge Machine Learning Inference Bottlenecks: An Empirical Study on Accelerating Google Edge Models. arXiv:2103.00768 [cs.AR]."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173177"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Amirali Boroumand Saugata Ghose Brandon Lucia Kevin Hsieh Krishna Malladi Hongzhong Zheng and Onur Mutlu. 2017. LazyPIM: An Efficient Cache Coherence Mechanism for Processing-in-Memory. CAL (2017).","DOI":"10.1109\/LCA.2016.2577557"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Amirali Boroumand Saugata Ghose Geraldo\u00a0F Oliveira and Onur Mutlu. 2021. Polynesia: Enabling Effective Hybrid Transactional\/Analytical Databases with Specialized Hardware\/Software Co-Design. arXiv:2103.00798 [cs.AR].","DOI":"10.1109\/ICDE53745.2022.00270"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE53745.2022.00270"},{"key":"e_1_3_3_2_35_2","volume-title":"ISCA","author":"Boroumand Amirali","year":"2019","unstructured":"Amirali Boroumand, Saugata Ghose, Minesh Patel, Hasan Hassan, Brandon Lucia, Rachata Ausavarungnirun, Kevin Hsieh, Nastaran Hajinazar, Krishna\u00a0T Malladi, Hongzhong Zheng, et\u00a0al. 2019. CoNDA: Efficient Cache Coherence Support for Near-Data Accelerators. In ISCA."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"crossref","unstructured":"Amirali Boroumand Saugata Ghose Minesh Patel Hasan Hassan Brandon Lucia Nastaran Hajinazar Kevin Hsieh Krishna\u00a0T Malladi Hongzhong Zheng and Onur Mutlu. 2017. LazyPIM: Efficient Support for Cache Coherence in Processing-in-Memory Architectures. arXiv:1706.03162 [cs.AR].","DOI":"10.1109\/LCA.2016.2577557"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00087"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Brent and Kung. 1982. A Regular Layout for Parallel Adders. IEEE TC (1982).","DOI":"10.1109\/TC.1982.1675982"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.5555\/520549.822763"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2002.995718"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.21236\/ADA458537"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00081"},{"key":"e_1_3_3_2_43_2","volume-title":"ISCA","author":"Caminal Helena","year":"2022","unstructured":"Helena Caminal, Yannis Chronis, Tianshu Wu, Jignesh\u00a0M Patel, and Jos\u00e9\u00a0F Mart\u00ednez. 2022. Accelerating Database Analytic Query Workloads Using an Associative Processor. In ISCA."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33182-4_5"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3497776.3517773"},{"key":"e_1_3_3_2_46_2","volume-title":"CASES","author":"Canis Andrew","year":"2013","unstructured":"Andrew Canis, Jongsok Choi, Blair Fort, Ruolong Lian, Qijing Huang, Nazanin Calagar, Marcel Gort, Jia\u00a0Jun Qin, Mark Aldham, Tomasz Czajkowski, et\u00a0al. 2013. From Software to Accelerators with LegUp High-Level Synthesis. In CASES."},{"key":"e_1_3_3_2_47_2","unstructured":"Kevin\u00a0K Chang. 2017. Understanding and Improving the Latency of DRAM-Based Memory Systems. Ph.\u00a0D. Dissertation. Carnegie Mellon University."},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/2896377.2901453"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446095"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3078505.3078590"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2014.6835946"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306797"},{"key":"e_1_3_3_2_53_2","volume-title":"ISCA","author":"Chi Ping","year":"2016","unstructured":"Ping Chi, Shuangchen Li, Cong Xu, Tao Zhang, Jishen Zhao, Yongpan Liu, Yu Wang, and Yuan Xie. 2016. PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory. In ISCA."},{"key":"e_1_3_3_2_54_2","unstructured":"Seunghwan Cho Haerang Choi Eunhyeok Park Hyunsung Shin and Sungjoo Yoo. 2020. McDRAM v2: In-Dynamic Random Access Memory Systolic Array Accelerator to Address the Large Model Problem in Deep Neural Networks on the Edge. IEEE Access (2020)."},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/1120725.1121055"},{"key":"e_1_3_3_2_56_2","unstructured":"Guohao Dai Tianhao Huang Yuze Chi Jishen Zhao Guangyu Sun Yongpan Liu Yu Wang Yuan Xie and Huazhong Yang. 2018. GraphH: A Processing-in-Memory Architecture for Large-Scale Graph Processing. TCAD (2018)."},{"key":"e_1_3_3_2_57_2","volume-title":"CF","author":"Lima Jo\u00e3o Paulo\u00a0C de","year":"2018","unstructured":"Jo\u00e3o Paulo\u00a0C de Lima, Paulo\u00a0Cesar Santos, Marco\u00a0AZ Alves, Antonio Beck, and Luigi Carro. 2018. Design Space Exploration for PIM Architectures in 3D-Stacked Memories. In CF."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196029"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317845"},{"key":"e_1_3_3_2_60_2","unstructured":"Robert\u00a0H. Dennard. 1968. Field-Effect Transistor Memory. US Patent 3 387 286."},{"key":"e_1_3_3_2_61_2","unstructured":"Alain Denzler Rahul Bera Nastaran Hajinazar Gagandeep Singh Geraldo\u00a0F Oliveira Juan G\u00f3mez-Luna and Onur Mutlu. 2021. Casper: Accelerating Stencil Computation using Near-Cache Processing. arXiv:2112.14216 [cs.AR]."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_2_63_2","volume-title":"ISCA","author":"Drumond Mario","year":"2017","unstructured":"Mario Drumond, Alexandros Daglis, Nooshin Mirzadeh, Dmitrii Ustiugov, Javier Picorel, Babak Falsafi, Boris Grot, and Dionisios Pnevmatikatos. 2017. The Mondrian Data Engine. In ISCA."},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.7873\/DATE2014.065"},{"key":"e_1_3_3_2_65_2","volume-title":"ISCA","author":"Eckert Charles","year":"2018","unstructured":"Charles Eckert, Xiaowei Wang, Jingcheng Wang, Arun Subramaniyan, Ravi Iyer, Dennis Sylvester, David Blaauw, and Reetuparna Das. 2018. Neural Cache: Bit-Serial In-Cache Acceleration of Deep Neural Networks. In ISCA."},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"crossref","unstructured":"D.\u00a0G. Elliott M. Stumm W.\u00a0M. Snelgrove et\u00a0al. 1999. Computational RAM: Implementing Processors in Memory. Design and Test of Computers (1999).","DOI":"10.1109\/54.748803"},{"key":"e_1_3_3_2_67_2","volume-title":"PATMOS","author":"Ergin O\u011fuz","year":"2006","unstructured":"O\u011fuz Ergin. 2006. Exploiting Narrow Values for Energy Efficiency in the Register Files of Superscalar Microprocessors. In PATMOS."},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2004.29"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"crossref","unstructured":"Oguz Ergin Osman Unsal Xavier Vera and Antonio Gonzalez. 2006. Exploiting Narrow Values for Soft Error Tolerance. CAL (2006).","DOI":"10.1109\/L-CA.2006.12"},{"key":"e_1_3_3_2_70_2","doi-asserted-by":"crossref","unstructured":"Oguz Ergin Osman Unsal Xavier Vera and Antonio Gonzalez. 2008. Reducing Soft Errors Through Operand Width Aware Policies. TDSC (2008).","DOI":"10.1109\/TDSC.2008.18"},{"key":"e_1_3_3_2_71_2","unstructured":"A. Farmahini-Farahani J.\u00a0H. Ahn K. Compton and N.\u00a0S. Kim. 2014. DRAMA: An Architecture for Accelerated Processing Near Memory. Computer Architecture Letters (2014)."},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD50377.2020.00035"},{"key":"e_1_3_3_2_74_2","unstructured":"Jo\u00e3o\u00a0Dinis Ferreira Gabriel Falcao Juan G\u00f3mez-Luna Mohammed Alser Lois Orosa Mohammad Sadrosadati Jeremie\u00a0S Kim Geraldo\u00a0F Oliveira Taha Shahroodi Anant Nori et\u00a0al. 2021. pLUTo: In-DRAM Lookup Tables to Enable Massively Parallel General-Purpose Computation. arXiv:2104.07699 [cs.AR]."},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00067"},{"key":"e_1_3_3_2_76_2","unstructured":"Nadeem Firasta Mark Buxton Paula Jinbo Kaveh Nasri and Shihjong Kuo. 2008. Intel AVX: New Frontiers in Performance Improvements and Energy Efficiency. white paper."},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173171"},{"key":"e_1_3_3_2_78_2","volume-title":"ISCA","author":"Fujiki Daichi","year":"2019","unstructured":"Daichi Fujiki, Scott Mahlke, and Reetuparna Das. 2019. Duality Cache for Data Parallel Acceleration. In ISCA."},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358260"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446059"},{"key":"e_1_3_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_3_2_82_2","volume-title":"ASPLOS","author":"Ghiasi Nika\u00a0Mansouri","year":"2022","unstructured":"Nika\u00a0Mansouri Ghiasi, Jisung Park, Harun Mustafa, Jeremie Kim, Ataberk Olgun, Arvid Gollwitzer, Damla\u00a0Senol Cali, Can Firtina, Haiyu Mao, Nour\u00a0Almadhoun Alserr, et\u00a0al. 2022. GenStore: A High-Performance and Energy-Efficient In-Storage Computing System for Genome Sequence Analysis. In ASPLOS."},{"key":"e_1_3_3_2_83_2","unstructured":"Saugata Ghose Amirali Boroumand Jeremie\u00a0S Kim Juan G\u00f3mez-Luna and Onur Mutlu. 2019. Processing-in-Memory: A Workload-Driven Perspective. IBM JRD (2019)."},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-90385-9_5"},{"key":"e_1_3_3_2_85_2","volume-title":"SIGMETRICS","author":"Ghose S.","year":"2020","unstructured":"S. Ghose, T. Li, N. Hajinazar, D.\u00a0Senol Cali, and O. Mutlu. 2020. Demystifying Complex Workload\u2013DRAM Interactions: An Experimental Study. In SIGMETRICS."},{"key":"e_1_3_3_2_86_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219617.3219661"},{"key":"e_1_3_3_2_87_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508041"},{"key":"e_1_3_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00031"},{"key":"e_1_3_3_2_89_2","doi-asserted-by":"crossref","unstructured":"Maya Gokhale Bill Holmes and Ken Iobst. 1995. Processing in Memory: The Terasys Massively Parallel PIM Array. Computer (1995).","DOI":"10.1109\/2.375174"},{"key":"e_1_3_3_2_90_2","volume-title":"CUT","author":"G\u00f3mez-Luna Juan","year":"2021","unstructured":"Juan G\u00f3mez-Luna, Izzat El\u00a0Hajj, Ivan Fernandez, Christina Giannoula, Geraldo\u00a0F Oliveira, and Onur Mutlu. 2021. Benchmarking Memory-Centric Computing Systems: Analysis of Real Processing-in-Memory Hardware. In CUT."},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"crossref","unstructured":"Juan G\u00f3mez-Luna Izzat El\u00a0Hajj Ivan Fernandez Christina Giannoula Geraldo\u00a0F Oliveira and Onur Mutlu. 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_3_2_92_2","doi-asserted-by":"crossref","unstructured":"Juan G\u00f3mez-Luna Izzat\u00a0El Hajj Ivan Fern\u00e1ndez Christina Giannoula Geraldo\u00a0F. Oliveira and Onur Mutlu. 2021. Benchmarking a New Paradigm: An Experimental Analysis of a Real Processing-in-Memory Architecture. arXiv:2105.03814 [cs.AR].","DOI":"10.1109\/ACCESS.2022.3174101"},{"key":"e_1_3_3_2_93_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-017-9314-z"},{"key":"e_1_3_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/2902961.2903512"},{"key":"e_1_3_3_2_95_2","volume-title":"ISCA","author":"Gu Peng","year":"2020","unstructured":"Peng Gu, Xinfeng Xie, Yufei Ding, Guoyang Chen, Weifeng Zhang, Dimin Niu, and Yuan Xie. 2020. iPIM: Programmable In-Memory Image Processing Accelerator using Near-Bank Architecture. In ISCA."},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"crossref","unstructured":"CC Guest and Thomas\u00a0K Gaylord. 1980. Truth-Table Look-Up Optical Processing Utilizing Binary and Residue Arithmetic. Applied Optics (1980).","DOI":"10.1364\/AO.19.001201"},{"key":"e_1_3_3_2_97_2","volume-title":"WoNDP","author":"Guo Qi","year":"2014","unstructured":"Qi Guo, Nikolaos Alachiotis, Berkin Akin, Fazle Sadi, Guanglin Xu, Tze\u00a0Meng Low, Larry Pileggi, James\u00a0C Hoe, and Franz Franchetti. 2014. 3D-Stacked Memory-Side Acceleration: Accelerator and System Design. In WoNDP."},{"key":"e_1_3_3_2_98_2","doi-asserted-by":"crossref","unstructured":"Ramyad Hadidi Lifeng Nai Hyojong Kim and Hyesoon Kim. 2017. CAIRO: A Compiler-Assisted Technique for Enabling Instruction-Level Offloading of Processing-in-Memory. TACO (2017).","DOI":"10.1145\/3155287"},{"key":"e_1_3_3_2_99_2","doi-asserted-by":"crossref","unstructured":"Marcus H\u00e4hnel Bj\u00f6rn D\u00f6bel Marcus V\u00f6lp and Hermann H\u00e4rtig. 2012. Measuring Energy Consumption for Short Code Paths Using RAPL. SIGMETRICS (2012).","DOI":"10.1145\/2425248.2425252"},{"key":"e_1_3_3_2_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"e_1_3_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.1145\/331532.331589"},{"key":"e_1_3_3_2_102_2","volume-title":"ISCA","author":"Han Song","year":"2016","unstructured":"Song Han, Xingyu Liu, Huizi Mao, Jing Pu, Ardavan Pedram, Mark\u00a0A Horowitz, and William\u00a0J Dally. 2016. EIE: Efficient Inference Engine on Compressed Deep Neural Network. In ISCA."},{"key":"e_1_3_3_2_103_2","unstructured":"Hasan Hassan. 2022. Improving DRAM Performance Reliability and Security by Rigorously Understanding Intrinsic DRAM Operation. Ph.\u00a0D. Dissertation. ETH Z\u00fcrich."},{"key":"e_1_3_3_2_104_2","unstructured":"Hasan Hassan Ataberk Olgun A\u00a0Giray Yaglikci Haocong Luo and Onur Mutlu. 2022. A Case for Self-Managing DRAM Chips: Improving Performance Efficiency Reliability and Security via Autonomous in-DRAM Maintenance Operations. arXiv:2207.13358 [cs.AR]."},{"key":"e_1_3_3_2_105_2","volume-title":"ISCA","author":"Hassan Hasan","year":"2019","unstructured":"Hasan Hassan, Minesh Patel, Jeremie\u00a0S Kim, A\u00a0Giray Yaglikci, Nandita Vijaykumar, Nika\u00a0Mansouri Ghiasi, Saugata Ghose, and Onur Mutlu. 2019. CROW: A Low-Cost Substrate for Improving DRAM Performance, Energy Efficiency, and Reliability. In ISCA."},{"key":"e_1_3_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446096"},{"key":"e_1_3_3_2_107_2","doi-asserted-by":"crossref","unstructured":"Zhezhi He Li Yang Shaahin Angizi Adnan\u00a0Siraj Rakin and Deliang Fan. 2020. Sparse BD-Net: A Multiplication-Less DNN with Sparse Binarized Depth-Wise Separable Convolution. JETC (2020).","DOI":"10.1145\/3369391"},{"key":"e_1_3_3_2_108_2","volume-title":"The Odyssey","year":"2006","unstructured":"Homer. 2006. The Odyssey. Penguin Classics."},{"key":"e_1_3_3_2_109_2","volume-title":"ISCA","author":"Hsieh Kevin","year":"2016","unstructured":"Kevin Hsieh, Eiman Ebrahimi, Gwangsun Kim, Niladrish Chatterjee, Mike O\u2019Connor, Nandita Vijaykumar, Onur Mutlu, and Stephen\u00a0W Keckler. 2016. Transparent Offloading and Mapping (TOM) Enabling Programmer-Transparent Near-Data Processing in GPU Systems. In ISCA."},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2016.7753257"},{"key":"e_1_3_3_2_111_2","volume-title":"DSN","author":"Hu Jie","year":"2006","unstructured":"Jie Hu, Shuai Wang, and Sotirios\u00a0G Ziavras. 2006. In-Register Duplication: Exploiting Narrow-Width Value for Improving Register File Reliability. In DSN."},{"key":"e_1_3_3_2_112_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00018"},{"key":"e_1_3_3_2_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00076"},{"key":"e_1_3_3_2_114_2","volume-title":"ISCA","author":"Imani Mohsen","year":"2019","unstructured":"Mohsen Imani, Saransh Gupta, Yeseong Kim, and Tajana Rosing. 2019. FloatPIM: In-Memory Acceleration of Deep Neural Network Training with High Precision. In ISCA."},{"key":"e_1_3_3_2_115_2","unstructured":"Intel Corp.[n. d.]. 10th Generation Intel Core Processor Family Datasheet. https:\/\/tinyurl.com\/4fh5ze38."},{"key":"e_1_3_3_2_116_2","unstructured":"Intel Corp.[n. d.]. 6th Generation Intel Core Processor Family Datasheet. http:\/\/www.intel.com\/content\/www\/us\/en\/processors\/core\/."},{"key":"e_1_3_3_2_117_2","volume-title":"Intel\u00ae 64 and IA-32 Architectures Software Developer\u2019s Manual, Vol. 3","author":"Corp. Intel","year":"2016","unstructured":"Intel Corp.2016. Intel\u00ae 64 and IA-32 Architectures Software Developer\u2019s Manual, Vol. 3."},{"key":"e_1_3_3_2_118_2","volume-title":"ISCA","author":"Ipek Engin","year":"2008","unstructured":"Engin Ipek, Onur Mutlu, Jos\u00e9\u00a0F Mart\u00ednez, and Rich Caruana. 2008. Self-Optimizing Memory Controllers: A Reinforcement Learning Approach. In ISCA."},{"key":"e_1_3_3_2_119_2","volume-title":"CASES","author":"Islam Mafijul\u00a0Md","year":"2010","unstructured":"Mafijul\u00a0Md Islam and Per Stenstrom. 2010. Characterization and Exploitation of Narrow-Width Loads: The Narrow-Width Cache Approach. In CASES."},{"key":"e_1_3_3_2_120_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358297"},{"key":"e_1_3_3_2_121_2","volume-title":"DATE","author":"Jang Myeongjae","year":"2022","unstructured":"Myeongjae Jang, Jinkwon Kim, Jesung Kim, and Soontae Kim. 2022. ENCORE Compression: Exploiting Narrow-width Values for Quantized Deep Neural Networks. In DATE."},{"key":"e_1_3_3_2_122_2","volume-title":"JESD79-5: DDR5 SDRAM Standard","year":"2020","unstructured":"JEDEC. 2020. JESD79-5: DDR5 SDRAM Standard."},{"key":"e_1_3_3_2_123_2","volume-title":"USSR Academy of Sciences","author":"Karatsuba Anatolii\u00a0Alekseevich","year":"1962","unstructured":"Anatolii\u00a0Alekseevich Karatsuba and Yu\u00a0P Ofman. 1962. Multiplication of Many-Digital Numbers by Automatic Computers. In USSR Academy of Sciences."},{"key":"e_1_3_3_2_124_2","doi-asserted-by":"crossref","unstructured":"I\u00a0Burak Karsli Pedro Reviriego M\u00a0Fatih Balli Oguz Ergin and Juan\u00a0Antonio Maestro. 2012. Enhanced Duplication: A Technique to Correct Soft Errors in Narrow Values. CAL (2012).","DOI":"10.1109\/L-CA.2012.6"},{"key":"e_1_3_3_2_125_2","unstructured":"Liu Ke Xuan Zhang Jinin So Jong-Geon Lee Shin-Haeng Kang Sukhan Lee Songyi Han Yeongon Cho Jin\u00a0Hyun Kim Yongsuk Kwon et\u00a0al. 2021. Near-Memory Processing in Action: Accelerating Personalized Recommendation with AxDIMM. IEEE Micro (2021)."},{"key":"e_1_3_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544426"},{"key":"e_1_3_3_2_127_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132402.3132426"},{"key":"e_1_3_3_2_128_2","doi-asserted-by":"publisher","DOI":"10.1145\/605397.605420"},{"key":"e_1_3_3_2_129_2","volume-title":"ISCA","author":"Kim Duckhwan","year":"2016","unstructured":"Duckhwan Kim, Jaeha Kung, Sek Chai, Sudhakar Yalamanchili, and Saibal Mukhopadhyay. 2016. Neurocube: A Programmable Digital Neuromorphic Architecture with High-Density 3D Memory. In ISCA."},{"key":"e_1_3_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2018.00051"},{"key":"e_1_3_3_2_131_2","unstructured":"Jeremie\u00a0S. Kim. 2020. Improving DRAM Performance Security and Reliability by Understanding and Exploiting DRAM Timing Parameter Margins. Ph.\u00a0D. Dissertation. Carnegie Mellon University."},{"key":"e_1_3_3_2_132_2","unstructured":"Jeremie\u00a0S Kim Damla\u00a0Senol Cali Hongyi Xin Donghyuk Lee Saugata Ghose Mohammed Alser Hasan Hassan Oguz Ergin Can Alkan and Onur Mutlu. 2018. GRIM-Filter: Fast Seed Location Filtering in DNA Read Mapping Using Processing-in-Memory Technologies. BMC Genomics (2018)."},{"key":"e_1_3_3_2_133_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00026"},{"key":"e_1_3_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00011"},{"key":"e_1_3_3_2_135_2","unstructured":"Jeremie\u00a0S Kim Damla Senol Hongyi Xin Donghyuk Lee Saugata Ghose Mohammed Alser Hasan Hassan Oguz Ergin Can Alkan and Onur Mutlu. 2017. GRIM-Filter: Fast Seed Filtering in Read Mapping using Emerging Memory Technologies. arXiv:1708.04329 [q-bio.GN]."},{"key":"e_1_3_3_2_136_2","volume-title":"ISCA","author":"Kim Yoongu","year":"2012","unstructured":"Yoongu Kim, Vivek Seshadri, Donghyuk Lee, Jamie Liu, and Onur Mutlu. 2012. A Case for Exploiting Subarray-Level Parallelism (SALP) in DRAM. In ISCA."},{"key":"e_1_3_3_2_137_2","doi-asserted-by":"crossref","unstructured":"Yoongu Kim Weikun Yang and Onur Mutlu. 2016. Ramulator: A Fast and Extensible DRAM Simulator. CAL (2016).","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_3_2_138_2","doi-asserted-by":"crossref","unstructured":"Peter\u00a0M Kogge and Harold\u00a0S Stone. 1973. A Parallel Algorithm for the Efficient Solution of a General Class of Recurrence Equations. IEEE TC (1973).","DOI":"10.1109\/TC.1973.5009159"},{"key":"e_1_3_3_2_139_2","doi-asserted-by":"publisher","DOI":"10.1145\/2228360.2228581"},{"key":"e_1_3_3_2_140_2","volume-title":"ISSCC","author":"Kwon Young-Cheon","year":"2021","unstructured":"Young-Cheon Kwon, Suk\u00a0Han Lee, Jaehoon Lee, Sang-Hyuk Kwon, Je\u00a0Min Ryu, Jong-Pil Son, O Seongil, Hak-Soo Yu, Haesuk Lee, Soo\u00a0Young Kim, et\u00a0al. 2021. A 20nm 6GB Function-in-Memory DRAM, Based on HBM2 with a 1.2 TFLOPS Programmable Computing Unit using Bank-Level Parallelism, for Machine Learning Applications. In ISSCC."},{"key":"e_1_3_3_2_141_2","doi-asserted-by":"crossref","unstructured":"Richard\u00a0E Ladner and Michael\u00a0J Fischer. 1980. Parallel Prefix Computation. JACM (1980).","DOI":"10.1145\/322217.322232"},{"key":"e_1_3_3_2_142_2","doi-asserted-by":"crossref","unstructured":"Marcel Lapointe Huu\u00a0Tue Huynh and Paul Fortier. 1993. Systematic Design of Pipelined Recursive Filters. TC (1993).","DOI":"10.1109\/12.214688"},{"key":"e_1_3_3_2_143_2","volume-title":"BSDCan","author":"Lattner Chris","year":"2008","unstructured":"Chris Lattner. 2008. LLVM and Clang: Next Generation Compiler Technology. In BSDCan."},{"key":"e_1_3_3_2_144_2","unstructured":"Donghyuk Lee. 2016. Reducing DRAM Latency at Low Cost by Exploiting Heterogeneity. Ph.\u00a0D. Dissertation. Carnegie Mellon University."},{"key":"e_1_3_3_2_145_2","unstructured":"Donghyuk Lee Saugata Ghose Gennady Pekhimenko Samira Khan and Onur Mutlu. 2016. Simultaneous Multi-Layer Access: Improving 3D-Stacked Memory Bandwidth at Low Cost. TACO (2016)."},{"key":"e_1_3_3_2_146_2","volume-title":"SIGMETRICS","author":"Lee Donghyuk","year":"2017","unstructured":"Donghyuk Lee, Samira Khan, Lavanya Subramanian, Rachata Ausavarungnirun, Gennady Pekhimenko, Vivek Seshadri, Saugata Ghose, and Onur Mutlu. 2017. Reducing DRAM Latency by Exploiting Design-Induced Latency Variation in Modern DRAM Chips. In SIGMETRICS."},{"key":"e_1_3_3_2_147_2","doi-asserted-by":"publisher","DOI":"10.1145\/3078505.3078533"},{"key":"e_1_3_3_2_148_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056057"},{"key":"e_1_3_3_2_149_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2013.6522354"},{"key":"e_1_3_3_2_150_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.51"},{"key":"e_1_3_3_2_151_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757501"},{"key":"e_1_3_3_2_152_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00093"},{"key":"e_1_3_3_2_153_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.42"},{"key":"e_1_3_3_2_154_2","volume-title":"ISCA","author":"Lee Sukhan","year":"2021","unstructured":"Sukhan Lee, Shin-haeng Kang, Jaehoon Lee, Hyeonsu Kim, Eojin Lee, Seungwoo Seo, Hosang Yoon, Seungwon Lee, Kyounghwan Lim, Hyunsung Shin, et\u00a0al. 2021. Hardware Architecture and Software Stack for PIM Based on Commercial DRAM Technology: Industrial Product. In ISCA."},{"key":"e_1_3_3_2_155_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"e_1_3_3_2_156_2","doi-asserted-by":"crossref","unstructured":"Orian Leitersdorf Dean Leitersdorf Jonathan Gal Mor Dahan Ronny Ronen and Shahar Kvatinsky. 2023. AritPIM: High-Throughput In-Memory Arithmetic. IEEE Trans. Emerg. Topics Comput. (2023).","DOI":"10.1109\/TETC.2023.3268137"},{"key":"e_1_3_3_2_157_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357550"},{"key":"e_1_3_3_2_158_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00062"},{"key":"e_1_3_3_2_159_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_3_2_160_2","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898064"},{"key":"e_1_3_3_2_161_2","unstructured":"Hongyeol Lim and Giho Park. 2017. Triple Engine Processor (TEP): A Heterogeneous Near-Memory Processor for Diverse Kernel Operations. TACO (2017)."},{"key":"e_1_3_3_2_162_2","volume-title":"ISSCC","author":"Lim Kyu-Nam","year":"2012","unstructured":"Kyu-Nam Lim, Woong-Ju Jang, Hyung-Sik Won, Kang-Yeol Lee, Hyungsoo Kim, Dong-Whee Kim, Mi-Hyun Cho, Seung-Lo Kim, Jong-Ho Kang, Keun-Woo Park, et\u00a0al. 2012. A 1.2 V 23nm 6F2 4Gb DDR3 SDRAM with Local-Bitline Sense Amplifier, Hybrid LIO Sense Amplifier and Dummy-Less Array Architecture. In ISSCC."},{"key":"e_1_3_3_2_163_2","volume-title":"ISCA","author":"Lipasti Mikko\u00a0H","year":"2004","unstructured":"Mikko\u00a0H Lipasti, Brian\u00a0R Mestan, and Erika Gunadi. 2004. Physical Register Inlining. In ISCA."},{"key":"e_1_3_3_2_164_2","volume-title":"ISCA","author":"Liu Jamie","year":"2013","unstructured":"Jamie Liu, Ben Jaiyen, Yoongu Kim, Chris Wilkerson, Onur Mutlu, J Liu, B Jaiyen, Y Kim, C Wilkerson, and O Mutlu. 2013. An Experimental Study of Data Retention Behavior in Modern DRAM Devices: Implications for Retention Time Profiling Mechanisms. In ISCA."},{"key":"e_1_3_3_2_165_2","volume-title":"ISCA","author":"Liu Jamie","year":"2012","unstructured":"Jamie Liu, Ben Jaiyen, Richard Veras, and Onur Mutlu. 2012. RAIDR: Retention-Aware Intelligent DRAM Refresh. In ISCA."},{"key":"e_1_3_3_2_166_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00059"},{"key":"e_1_3_3_2_167_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378497"},{"key":"e_1_3_3_2_168_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2002.1176266"},{"key":"e_1_3_3_2_169_2","volume-title":"WoNDP","author":"Loh Gabriel\u00a0H","year":"2013","unstructured":"Gabriel\u00a0H Loh, Nuwan Jayasena, M Oskin, Mark Nutter, David Roberts, Mitesh Meswani, Dong\u00a0Ping Zhang, and Mike Ignatowski. 2013. A Processing in Memory Taxonomy and a Case for Studying Fixed-Function PIM. In WoNDP."},{"key":"e_1_3_3_2_170_2","doi-asserted-by":"publisher","DOI":"10.5555\/2692607"},{"key":"e_1_3_3_2_171_2","doi-asserted-by":"crossref","unstructured":"Hiroshi Makino Yasunobu Nakase Hiroaki Suzuki Hiroyuki Morinaka Hirofumi Shinohara and Koichiro Mashiko. 1996. An 8.8-ns 54\/SPL Times\/54-bit Multiplier with High Speed Redundant Binary Architecture. JSSC (1996).","DOI":"10.1109\/4.509863"},{"key":"e_1_3_3_2_172_2","volume-title":"ISCA","author":"Matam Kiran\u00a0Kumar","year":"2019","unstructured":"Kiran\u00a0Kumar Matam, Gunjae Koo, Haipeng Zha, Hung-Wei Tseng, and Murali Annavaram. 2019. GraphSSD: Graph Semantics Aware SSD. In ISCA."},{"key":"e_1_3_3_2_173_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSID.2017.14"},{"key":"e_1_3_3_2_174_2","doi-asserted-by":"publisher","DOI":"10.1145\/871506.871574"},{"key":"e_1_3_3_2_175_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.33"},{"key":"e_1_3_3_2_176_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMW.2013.6582088"},{"key":"e_1_3_3_2_177_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3323476"},{"key":"e_1_3_3_2_178_2","doi-asserted-by":"crossref","unstructured":"Onur Mutlu Saugata Ghose Juan G\u00f3mez-Luna and Rachata Ausavarungnirun. 2019. Processing Data Where It Makes Sense: Enabling In-Memory Computation. MicPro (2019).","DOI":"10.1145\/3299874.3322805"},{"key":"e_1_3_3_2_179_2","volume-title":"Emerging Computing: From Devices to Systems \u2014 Looking Beyond Moore and Von Neumann","author":"Mutlu Onur","year":"2021","unstructured":"Onur Mutlu, Saugata Ghose, Juan G\u00f3mez-Luna, and Rachata Ausavarungnirun. 2021. A Modern Primer on Processing in Memory. In Emerging Computing: From Devices to Systems \u2014 Looking Beyond Moore and Von Neumann. Springer."},{"key":"e_1_3_3_2_180_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2007.40"},{"key":"e_1_3_3_2_181_2","unstructured":"Onur Mutlu and Lavanya Subramanian. 2014. Research Problems and Opportunities in Memory Systems. SUPERFRI (2014)."},{"key":"e_1_3_3_2_182_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.54"},{"key":"e_1_3_3_2_183_2","unstructured":"R. Nair S.\u00a0F. Antao C. Bertolli P. Bose et\u00a0al. 2015. Active Memory Cube: A Processing-in-Memory Architecture for Exascale Systems. IBM JRD (2015)."},{"key":"e_1_3_3_2_184_2","volume-title":"ISSCC","author":"Niu Dimin","year":"2022","unstructured":"Dimin Niu, Shuangchen Li, Yuhao Wang, Wei Han, Zhe Zhang, Yijin Guan, Tianchan Guan, Fei Sun, Fei Xue, Lide Duan, et\u00a0al. 2022. 184QPS\/W 64Mb\/mm2 3D Logic-to-DRAM Hybrid Bonding with Process-Near-Memory Engine for Recommendation System. In ISSCC."},{"key":"e_1_3_3_2_185_2","unstructured":"NVIDIA. 2020. NVIDIA A100 Tensor Core GPU Architecture. White Paper. https:\/\/tinyurl.com\/53a8easc."},{"key":"e_1_3_3_2_186_2","unstructured":"NVIDIA Corp.[n. d.]. NVIDIA Management Library (NVML). https:\/\/developer.nvidia.com\/nvidia-management-library-nvml."},{"key":"e_1_3_3_2_187_2","unstructured":"NVIDIA Corp.[n. d.]. NVIDIA\/cutlass: CUDA Templates for Linear Algebra Subroutines. https:\/\/github.com\/NVIDIA\/cutlass."},{"key":"e_1_3_3_2_188_2","doi-asserted-by":"publisher","DOI":"10.5555\/AAI29605208"},{"key":"e_1_3_3_2_189_2","doi-asserted-by":"crossref","unstructured":"Ataberk Olgun F Bostanci Geraldo\u00a0F Oliveira Yahya\u00a0Can Tugrul Rahul Bera A\u00a0Giray Yaglikci Hasan Hassan Oguz Ergin and Onur Mutlu. 2024. Sectored DRAM: A Practical Energy-Efficient and High-Performance Fine-Grained DRAM Architecture. TACO (2024).","DOI":"10.1145\/3673653"},{"key":"e_1_3_3_2_190_2","doi-asserted-by":"crossref","unstructured":"Ataberk Olgun Juan\u00a0Gomez Luna Konstantinos Kanellopoulos Behzad Salami Hasan Hassan Oguz Ergin and Onur Mutlu. 2022. PiDRAM: A Holistic End-to-End FPGA-Based Framework for Processing-in-DRAM. TACO (2022).","DOI":"10.1145\/3563697"},{"key":"e_1_3_3_2_191_2","volume-title":"ISCA","author":"Olgun Ataberk","year":"2021","unstructured":"Ataberk Olgun, Minesh Patel, Abdullah\u00a0Giray Ya\u011fl\u0131k\u00e7\u0131, Haocong Luo, Jeremie\u00a0S. Kim, F.\u00a0Nisa Bostanc\u0131, Nandita Vijaykumar, O\u011fuz Ergin, and Onur Mutlu. 2021. QUAC-TRNG: High-Throughput True Random Number Generation Using Quadruple Row Activation in Commodity DRAMs. In ISCA."},{"key":"e_1_3_3_2_192_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30117-2_112"},{"key":"e_1_3_3_2_193_2","doi-asserted-by":"crossref","unstructured":"Joaqu\u00edn Olivares Javier Hormigo Julio Villalba Ignacio Benavides and Emilio\u00a0L Zapata. 2006. SAD Computation based on Online Arithmetic for Motion Estimation. Microprocessors and Microsystems (2006).","DOI":"10.1016\/j.micpro.2005.12.006"},{"key":"e_1_3_3_2_194_2","doi-asserted-by":"crossref","unstructured":"Geraldo\u00a0F. Oliveira Juan G\u00f3mez-Luna Lois Orosa Saugata Ghose Nandita Vijaykumar Ivan Fernandez Mohammad Sadrosadati and Onur Mutlu. 2021. DAMOV: A New Methodology and Benchmark Suite for Evaluating Data Movement Bottlenecks. IEEE Access (2021).","DOI":"10.1109\/ACCESS.2021.3110993"},{"key":"e_1_3_3_2_195_2","unstructured":"Geraldo\u00a0F Oliveira Mayank Kabra Yuxin Guo Kangqi Chen A\u00a0Giray Ya\u011fl\u0131k\u00e7\u0131 Melina Soysal Mohammad Sadrosadati Joaquin Olivares Bueno Saugata Ghose Juan G\u00f3mez-Luna et\u00a0al. 2025. Proteus: Enabling High-Performance Processing-Using-DRAM with Dynamic Bit-Precision Adaptive Data Representation and Flexible Arithmetic. arXiv:2501.17466 [cs.AR]."},{"key":"e_1_3_3_2_196_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00024"},{"key":"e_1_3_3_2_197_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56258-2_3"},{"key":"e_1_3_3_2_198_2","doi-asserted-by":"crossref","unstructured":"Yusuf Onur\u00a0Ko\u00e7berber Yusuf Osmanl\u0131o\u011flu and O\u011fuz Ergin. 2009. Exploiting Narrow Values for Faster Parity Generation. Microelectronics International (2009).","DOI":"10.1108\/13565360910981526"},{"key":"e_1_3_3_2_199_2","volume-title":"ISCA","author":"Orosa Lois","year":"2021","unstructured":"Lois Orosa, Yaohua Wang, Mohammad Sadrosadati, Jeremie Kim, Minesh Patel, Ivan Puddu, Haocong Luo, Kaveh Razavi, Juan G\u00f3mez-Luna, Hasan Hassan, Nika\u00a0Mansouri Ghiasi, Saugata Ghose, and Onur Mutlu. 2021. CODIC: A Low-Cost Substrate for Enabling Custom In-DRAM Functionalities and Optimizations. In ISCA."},{"key":"e_1_3_3_2_200_2","doi-asserted-by":"publisher","DOI":"10.1145\/1531542.1531570"},{"key":"e_1_3_3_2_201_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2010.5647631"},{"key":"e_1_3_3_2_202_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00069"},{"key":"e_1_3_3_2_203_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_3_2_204_2","unstructured":"Minesh Patel. 2022. Enabling Effective Error Mitigation In Memory Chips That Use On-Die Error-Correcting Codes. Ph.\u00a0D. Dissertation. ETH Z\u00fcrich."},{"key":"e_1_3_3_2_205_2","doi-asserted-by":"crossref","unstructured":"D. Patterson T. Anderson N. Cardwell et\u00a0al. 1997. A Case for Intelligent RAM. IEEE Micro (1997).","DOI":"10.1109\/40.592312"},{"key":"e_1_3_3_2_206_2","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967940"},{"key":"e_1_3_3_2_207_2","unstructured":"Gennady Pekhimenko. 2016. Practical Data Compression for Modern Memory Hierarchies. Ph.\u00a0D. Dissertation. Carnegie Mellon University."},{"key":"e_1_3_3_2_208_2","doi-asserted-by":"crossref","unstructured":"Gennady Pekhimenko Evgeny Bolotin Mike O\u2019Connor Onur Mutlu Todd\u00a0C Mowry and Stephen\u00a0W Keckler. 2015. Toggle-Aware Compression for GPUs. CAL (2015).","DOI":"10.1109\/HPCA.2016.7446064"},{"key":"e_1_3_3_2_209_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446064"},{"key":"e_1_3_3_2_210_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056021"},{"key":"e_1_3_3_2_211_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540724"},{"key":"e_1_3_3_2_212_2","doi-asserted-by":"publisher","DOI":"10.1145\/2370816.2370870"},{"key":"e_1_3_3_2_213_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071070"},{"key":"e_1_3_3_2_214_2","doi-asserted-by":"crossref","unstructured":"Dhananjay\u00a0S. Phatak and Israel Koren. 1994. Hybrid Signed-Digit Number Systems: A Unified Framework for Redundant Number Representations with Bounded Carry Propagation Chains. TC (1994).","DOI":"10.1109\/12.295850"},{"key":"e_1_3_3_2_215_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2013.6645550"},{"key":"e_1_3_3_2_216_2","unstructured":"Louis-No\u00ebl Pouchet. [n. d.]. PolyBench: The Polyhedral Benchmark Suite. https:\/\/www.cs.colostate.edu\/\u00a0pouchet\/software\/polybench\/."},{"key":"e_1_3_3_2_217_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_3_2_218_2","unstructured":"Seyyed Hossein\u00a0SeyyedAghaei Rezaei Mehdi Modarressi Rachata Ausavarungnirun Mohammad Sadrosadati Onur Mutlu and Masoud Daneshtalab. 2020. NoM: Network-on-Memory for Inter-Bank Data Transfer in Highly-Banked Memories. CAL (2020)."},{"key":"e_1_3_3_2_219_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2013.6494996"},{"key":"e_1_3_3_2_220_2","unstructured":"SAFARI Research Group. [n. d.]. DAMOV Benchmark Suite and Simulation Framework. https:\/\/github.com\/CMU-SAFARI\/DAMOV."},{"key":"e_1_3_3_2_221_2","unstructured":"SAFARI Research Group. [n. d.]. MIMDRAM Simulation Framework. https:\/\/github.com\/CMU-SAFARI\/MIMDRAM."},{"key":"e_1_3_3_2_222_2","unstructured":"SAFARI Research Group. [n. d.]. Proteus Simulation Framework. https:\/\/github.com\/CMU-SAFARI\/Proteus."},{"key":"e_1_3_3_2_223_2","unstructured":"Adrian Sampson. [n. d.]. LLVM for Grad Students. https:\/\/tinyurl.com\/y3tyb7z2."},{"key":"e_1_3_3_2_224_2","volume-title":"DATE","author":"Santos Paulo\u00a0C","year":"2018","unstructured":"Paulo\u00a0C Santos, Geraldo\u00a0F Oliveira, Jo\u00e3o\u00a0P Lima, Marco\u00a0AZ Alves, Luigi Carro, and Antonio\u00a0CS Beck. 2018. Processing in 3D Memories to Speed Up Operations on Complex Data Structures. In DATE."},{"key":"e_1_3_3_2_225_2","volume-title":"DATE","author":"Santos P.\u00a0C.","year":"2017","unstructured":"P.\u00a0C. Santos, G.\u00a0F. Oliveira, D.\u00a0G. Tom\u00e9, M.\u00a0A.\u00a0Z. Alves, E.\u00a0C. Almeida, and L. Carro. 2017. Operand Size Reconfiguration for Big Data Processing in Memory. In DATE."},{"key":"e_1_3_3_2_226_2","doi-asserted-by":"publisher","DOI":"10.5555\/2987964"},{"key":"e_1_3_3_2_227_2","doi-asserted-by":"publisher","DOI":"10.1145\/232973.232984"},{"key":"e_1_3_3_2_228_2","unstructured":"Vivek Seshadri. 2016. Simple DRAM and Virtual Memory Abstractions to Enable Highly Efficient Memory Subsystems. Ph.\u00a0D. Dissertation. Carnegie Mellon University."},{"key":"e_1_3_3_2_229_2","doi-asserted-by":"crossref","unstructured":"Vivek Seshadri Kevin Hsieh Amirali Boroum Donghyuk Lee Michael\u00a0A Kozuch Onur Mutlu Phillip\u00a0B Gibbons and Todd\u00a0C Mowry. 2015. Fast Bulk Bitwise AND and OR in DRAM. CAL (2015).","DOI":"10.1109\/LCA.2015.2434872"},{"key":"e_1_3_3_2_230_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_3_2_231_2","unstructured":"Vivek Seshadri Yoongu Kim Chris Fallin Donghyuk Lee Rachata Ausavarungnirun Gennady Pekhimenko Yixin Luo Onur Mutlu Phillip\u00a0B Gibbons Michael\u00a0A Kozuch et\u00a0al. 2018. RowClone: Accelerating Data Movement and Initialization Using DRAM. arXiv:1805.03502 [cs.AR]."},{"key":"e_1_3_3_2_232_2","unstructured":"Vivek Seshadri Donghyuk Lee Thomas Mullins Hasan Hassan Amirali Boroumand Jeremie Kim Michael\u00a0A Kozuch Onur Mutlu Phillip\u00a0B Gibbons and Todd\u00a0C Mowry. 2016. Buddy-RAM: Improving the Performance and Efficiency of Bulk Bitwise Operations Using DRAM. arXiv:1611.09988 [cs.AR]."},{"key":"e_1_3_3_2_233_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_3_2_234_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830820"},{"key":"e_1_3_3_2_235_2","unstructured":"Vivek Seshadri and Onur Mutlu. 2016. The Processing Using Memory Paradigm: In-DRAM Bulk Copy Initialization Bitwise AND and OR. arXiv:1610.09603 [cs.AR]."},{"key":"e_1_3_3_2_236_2","doi-asserted-by":"publisher","DOI":"10.1016\/bs.adcom.2017.04.004"},{"key":"e_1_3_3_2_237_2","unstructured":"Vivek Seshadri and Onur Mutlu. 2019. In-DRAM Bulk Bitwise Execution Engine. arXiv:1905.09822 [cs.AR]."},{"key":"e_1_3_3_2_238_2","volume-title":"ISCA","author":"Shafiee Ali","year":"2016","unstructured":"Ali Shafiee, Anirban Nag, Naveen Muralimanohar, Rajeev Balasubramonian, John\u00a0Paul Strachan, Miao Hu, R.\u00a0Stanley Williams, and Vivek Srikumar. 2016. ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars. In ISCA."},{"key":"e_1_3_3_2_239_2","doi-asserted-by":"publisher","DOI":"10.1145\/2463209.2488866"},{"key":"e_1_3_3_2_240_2","doi-asserted-by":"crossref","unstructured":"Hyunsung Shin Dongyoung Kim Eunhyeok Park Sungho Park Yongsik Park and Sungjoo Yoo. 2018. McDRAM: Low Latency and Energy-Efficient Matrix Computations in DRAM. IEEE TCADICS (2018).","DOI":"10.1109\/TCAD.2018.2857044"},{"key":"e_1_3_3_2_241_2","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676771"},{"key":"e_1_3_3_2_242_2","volume-title":"CACTI 3.0: An Integrated Cache Timing, Power, and Area Model","author":"Shivakumar Premkishore","year":"2001","unstructured":"Premkishore Shivakumar and Norman\u00a0P Jouppi. 2001. CACTI 3.0: An Integrated Cache Timing, Power, and Area Model. Technical Report 2001\/2. Compaq Computer Corporation."},{"key":"e_1_3_3_2_243_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317867"},{"key":"e_1_3_3_2_244_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL50879.2020.00014"},{"key":"e_1_3_3_2_245_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_3_2_246_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00052"},{"key":"e_1_3_3_2_247_2","unstructured":"Standard Performance Evaluation Corp.[n. d.]. SPEC CPU2017 Benchmarks. http:\/\/www.spec.org\/cpu2017\/."},{"key":"e_1_3_3_2_248_2","doi-asserted-by":"publisher","DOI":"10.1145\/349299.349317"},{"key":"e_1_3_3_2_249_2","doi-asserted-by":"crossref","unstructured":"Harold\u00a0S Stone. 1970. A Logic-in-Memory Computer. IEEE TC (1970).","DOI":"10.1109\/TC.1970.5008902"},{"key":"e_1_3_3_2_250_2","volume-title":"ISCA","author":"Subramaniyan Arun","year":"2017","unstructured":"Arun Subramaniyan and Reetuparna Das. 2017. Parallel Automata Processor. In ISCA."},{"key":"e_1_3_3_2_251_2","volume-title":"ISCA","author":"Sun Weiyi","year":"2021","unstructured":"Weiyi Sun, Zhaoshi Li, Shouyi Yin, Shaojun Wei, and Leibo Liu. 2021. ABC-DIMM: Alleviating the Bottleneck of Communication in DIMM-Based Near-Memory Processing with Inter-DIMM Broadcast. In ISCA."},{"key":"e_1_3_3_2_252_2","doi-asserted-by":"crossref","unstructured":"Tsugio Takahashi Tomonori Sekiguchi Riichiro Takemura Seiji Narui Hiroki Fujisawa Shinichi Miyatake Makoto Morino Koji Arai Satoru Yamada Shoji Shukuri et\u00a0al. 2001. A Multigigabit DRAM Technology with 6F2 Open-Bitline Cell Distributed Overdriven Sensing and Stacked-Flash Fuse. JSSC (2001).","DOI":"10.1109\/4.962294"},{"key":"e_1_3_3_2_253_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480071"},{"key":"e_1_3_3_2_254_2","doi-asserted-by":"crossref","unstructured":"Minh\u00a0SQ Truong Liting Shen Alexander Glass Alison Hoffmann L\u00a0Richard Carley James\u00a0A Bain and Saugata Ghose. 2022. Adapting the RACER Architecture to Integrate Improved In-ReRAM Logic Primitives. JETCAS (2022).","DOI":"10.1109\/JETCAS.2022.3171765"},{"key":"e_1_3_3_2_255_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00058"},{"key":"e_1_3_3_2_256_2","volume-title":"DATE","author":"Wang Shuai","year":"2009","unstructured":"Shuai Wang, Jie Hu, Sotirios\u00a0G Ziavras, and Sung\u00a0Woo Chung. 2009. Exploiting Narrow-Width Values for Thermal-Aware Register File Designs. In DATE."},{"key":"e_1_3_3_2_257_2","doi-asserted-by":"publisher","DOI":"10.1109\/Trustcom\/BigDataSE\/ICESS.2017.308"},{"key":"e_1_3_3_2_258_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00036"},{"key":"e_1_3_3_2_259_2","volume-title":"USENIX ATC","author":"Wilson Paul\u00a0R","year":"1999","unstructured":"Paul\u00a0R Wilson, Scott\u00a0F Kaplan, and Yannis Smaragdakis. 1999. The Case for Compressed Caching in Virtual Memory Systems. In USENIX ATC."},{"key":"e_1_3_3_2_260_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247818"},{"key":"e_1_3_3_2_261_2","doi-asserted-by":"publisher","DOI":"10.1145\/2771937.2771945"},{"key":"e_1_3_3_2_262_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00033"},{"key":"e_1_3_3_2_263_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2009.5306783"},{"key":"e_1_3_3_2_264_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN58291.2024.00024"},{"key":"e_1_3_3_2_265_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00030"},{"key":"e_1_3_3_2_266_2","volume-title":"ISCA","author":"Zha Yue","year":"2020","unstructured":"Yue Zha and Jing Li. 2020. Hyper-AP: Enhancing Associative Processing Through A Full-Stack Optimization. In ISCA."},{"key":"e_1_3_3_2_267_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_3_2_268_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00053"},{"key":"e_1_3_3_2_269_2","volume-title":"ISCA","author":"Zhang Tao","year":"2014","unstructured":"Tao Zhang, Ke Chen, Cong Xu, Guangyu Sun, Tao Wang, and Yuan Xie. 2014. Half-DRAM: A High-Bandwidth and Low-Power DRAM Architecture from the Rethinking of Fine-Grained Activation. In ISCA."},{"key":"e_1_3_3_2_270_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"e_1_3_3_2_271_2","doi-asserted-by":"publisher","DOI":"10.1145\/3531437.3539721"},{"key":"e_1_3_3_2_272_2","volume-title":"DATE","author":"Zhou Ranyang","year":"2023","unstructured":"Ranyang Zhou, Sepehr Tabrizchi, Mehrdad Morsali, Arman Roohi, and Shaahin Angizi. 2023. P-PIM: A Parallel Processing-in-DRAM Framework Enabling Row Hammer Protection. In DATE."},{"key":"e_1_3_3_2_273_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2013.6670336"},{"key":"e_1_3_3_2_274_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358256"},{"key":"e_1_3_3_2_275_2","unstructured":"William\u00a0K Zuravleff and Timothy Robinson. 1997. Controller for a Synchronous DRAM That Maximizes Throughput by Allowing Memory Requests and Commands to Be Issued Out of Order."}],"event":{"name":"ICS '25: 2025 International Conference on Supercomputing","location":"Salt Lake City USA","acronym":"ICS '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 39th ACM International Conference on Supercomputing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3721145.3730420","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T05:53:28Z","timestamp":1764136408000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721145.3730420"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":274,"alternative-id":["10.1145\/3721145.3730420","10.1145\/3721145"],"URL":"https:\/\/doi.org\/10.1145\/3721145.3730420","relation":{},"subject":[],"published":{"date-parts":[[2025,6,8]]},"assertion":[{"value":"2025-08-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}