{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T15:39:30Z","timestamp":1788277170813,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":209,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"JST CREST","award":["JPMJCR21D2"],"award-info":[{"award-number":["JPMJCR21D2"]}]},{"name":"JSPS KAKENHI","award":["23H00467"],"award-info":[{"award-number":["23H00467"]}]},{"name":"JST ACT-X","award":["JPMJAX25CC"],"award-info":[{"award-number":["JPMJAX25CC"]}]},{"name":"Semiconductor Research Corporation (SRC)"},{"name":"ETH Future Computing Laboratory (EFCL)"},{"name":"AI Chip Center for Emerging Smart Systems (ACCESS)"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,6]]},"DOI":"10.1145\/3797905.3800550","type":"proceedings-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T11:50:37Z","timestamp":1782993037000},"page":"618-636","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Clutch: High Performance Vector-Scalar Comparison using DRAM via Chunked Temporal Coding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-9328-3805","authenticated-orcid":false,"given":"Daichi","family":"Tokuda","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1523-3063","authenticated-orcid":false,"given":"Tatsuya","family":"Kubo","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan and RIKEN, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3310-4423","authenticated-orcid":false,"given":"Ismail Emir","family":"Yuksel","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5333-5726","authenticated-orcid":false,"given":"Ataberk","family":"Olgun","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0849-8724","authenticated-orcid":false,"given":"Haocong","family":"Luo","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0282-743X","authenticated-orcid":false,"given":"Tomoya","family":"Nagatani","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1557-4819","authenticated-orcid":false,"suffix":"Junior","given":"Geraldo Francisco","family":"De Oliveira","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9333-6077","authenticated-orcid":false,"given":"Abdullah Giray","family":"Ya\u011fl\u0131k\u00e7\u0131","sequence":"additional","affiliation":[{"name":"CISPA, Saarbr\u00fccken, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4029-0175","authenticated-orcid":false,"given":"Mohammad","family":"Sadrosadati","sequence":"additional","affiliation":[{"name":"ETH Z\u00fcrich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0075-2312","authenticated-orcid":false,"given":"Onur","family":"Mutlu","sequence":"additional","affiliation":[{"name":"ETH Zurich, Zurich, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3441-1695","authenticated-orcid":false,"given":"Shinya","family":"Takamaeda-Yamazaki","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan and RIKEN, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Akmalbek Abdusalomov Mukhriddin Mukhiddinov Oybek Djuraev Utkir Khamdamov and Taeg\u00a0Keun Whangbo. 2020. Automatic salient object extraction based on locally adaptive thresholding to generate tactile graphics. Applied Sciences (2020).","DOI":"10.3390\/app10103350"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Salma Afifi Ishan Thakkar and Sudeep Pasricha. 2024. ARTEMIS: A Mixed Analog-Stochastic In-DRAM Accelerator for Transformer Neural Networks. IEEE TCAD (2024).","DOI":"10.1109\/TCAD.2024.3446719"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750397"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2014.7040954"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Adri\u00e1n Alcolea Mercedes\u00a0E Paoletti Juan\u00a0M Haut Javier Resano and Antonio Plaza. 2020. Inference in supervised spectral classifiers for on-board hyperspectral imaging: An overview. Remote Sensing (2020).","DOI":"10.3390\/rs12030534"},{"key":"e_1_3_3_2_10_2","unstructured":"Mustafa\u00a0F Ali Akhilesh Jaiswal and Kaushik Roy. 2019. In-Memory Low-Cost Bit-Serial Addition Using Commodity DRAM Technology. TCAS-I (2019)."},{"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, et\u00a0al. 2015. Saving Memory Movements Through Vector Processing in the DRAM. In CASES."},{"key":"e_1_3_3_2_14_2","unstructured":"American Statistical Association. 2009. Data Expo 2009: Airline On-Time Performance. https:\/\/community.amstat.org\/jointscsg-section\/dataexpo\/dataexpo2009."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3299874.3317984"},{"key":"e_1_3_3_2_16_2","volume-title":"Arm Cortex-A53 MPCore Processor Technical Reference Manual","author":"Ltd. Arm","year":"2016","unstructured":"Arm Ltd.2016. Arm Cortex-A53 MPCore Processor Technical Reference Manual."},{"key":"e_1_3_3_2_17_2","unstructured":"Arm Ltd.2024. Arm Neon Intrinsics Reference. https:\/\/developer.arm.com\/architectures\/instruction-sets\/simd-isas\/neon."},{"key":"e_1_3_3_2_18_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_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783753"},{"key":"e_1_3_3_2_20_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_21_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_22_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_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2764942"},{"key":"e_1_3_3_2_24_2","unstructured":"Pierre Baldi Peter Sadowski and Daniel Whiteson. 2014. HIGGS Dataset. UCI Machine Learning Repository. https:\/\/archive.ics.uci.edu\/dataset\/280\/higgs"},{"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":"publisher","unstructured":"Jock\u00a0A. Blackard and Denis\u00a0J. Dean. 1999. Covertype. 10.24432\/C50K5Nhttps:\/\/archive.ics.uci.edu\/dataset\/31\/covertype.","DOI":"10.24432\/C50K5N"},{"key":"e_1_3_3_2_27_2","unstructured":"Casper\u00a0Solheim Bojer and Jens\u00a0Peder Meldgaard. 2021. Kaggle forecasting competitions: An overlooked learning opportunity. International Journal of Forecasting (2021)."},{"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 preprint arXiv:https:\/\/arXiv.org\/abs\/2103.00768 (2021)."},{"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","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 preprint arXiv:https:\/\/arXiv.org\/abs\/2103.00798 (2021)."},{"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","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 preprint arXiv:https:\/\/arXiv.org\/abs\/1706.03162 (2017)."},{"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":"publisher","DOI":"10.1109\/MICRO50266.2020.00081"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446095"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_3_2_41_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_42_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_43_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_44_2","volume-title":"HPCA","author":"Lima Joao Paulo\u00a0C de","year":"2026","unstructured":"Joao Paulo\u00a0C de Lima, Ben Morris, Asif\u00a0Ali Khan, Jeronimo Castrillon, and Alex\u00a0K Jones. 2026. Count2multiply: Reliable in-memory high-radix counting. In HPCA."},{"key":"e_1_3_3_2_45_2","volume-title":"CF","author":"Lima Jo\u00e3o Paulo\u00a0C. de","year":"2018","unstructured":"Jo\u00e3o Paulo\u00a0C. de Lima, Paulo\u00a0Cesar Santos, Marco A.\u00a0Z. 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_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196029"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317845"},{"key":"e_1_3_3_2_48_2","volume-title":"ICA3P","author":"Deng Wenya","year":"2023","unstructured":"Wenya Deng, Zhi Wang, Yang Guo, Jian Zhang, Zhenyu Wu, and Yaohua Wang. 2023. DAS: A DRAM-Based Annealing System for Solving Large-Scale Combinatorial Optimization Problems. In ICA3P."},{"key":"e_1_3_3_2_49_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2112.14216 (2021)."},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_2_51_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_52_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_53_2","doi-asserted-by":"crossref","unstructured":"D.\u00a0G. Elliott M. Stumm W.\u00a0M. Snelgrove et\u00a0al. 1999. Computational RAM: Implementing Processors in Memory. D&T (1999).","DOI":"10.1109\/54.748803"},{"key":"e_1_3_3_2_54_2","unstructured":"F\u00a0G\u00f6khan Ergin. 2017. Dynamic masking techniques for particle image velocimetry. Is\u0131 Bilimi ve Tekni\u011fi Dergisi (2017)."},{"key":"e_1_3_3_2_55_2","unstructured":"Franz F\u00e4rber Norman May Wolfgang Lehner Philipp Gro\u00dfe Ingo M\u00fcller Hannes Rauhe and Jonathan Dees. 2012. The SAP HANA Database\u2013An Architecture Overview. IEEE Data Eng. Bull. (2012)."},{"key":"e_1_3_3_2_56_2","unstructured":"A. Farmahini-Farahani J.\u00a0H. Ahn K. Compton and N.\u00a0S. Kim. 2014. DRAMA: An Architecture for Accelerated Processing Near Memory. CAL (2014)."},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD50377.2020.00035"},{"key":"e_1_3_3_2_59_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2104.07699 (2021)."},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00067"},{"key":"e_1_3_3_2_61_2","volume-title":"MICRO","author":"Fujiki Daichi","year":"2023","unstructured":"Daichi Fujiki. 2023. MVC: Enabling fully coherent multi-data-views through the memory hierarchy with processing in memory. In MICRO."},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173171"},{"key":"e_1_3_3_2_63_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_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358260"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00066"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2016.7446059"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037702"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"crossref","unstructured":"Esteban Garz\u00f3n Alexander Fish and Leonid Yavits. 2026. CADM: Content addressable commodity off-the-shelf DRAM-based genome classifier. Journal of Systems Architecture (2026).","DOI":"10.1016\/j.sysarc.2026.103710"},{"key":"e_1_3_3_2_69_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_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3508041"},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00031"},{"key":"e_1_3_3_2_72_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_73_2","doi-asserted-by":"crossref","unstructured":"Goetz Graefe et\u00a0al. 2011. Modern B-tree techniques. Foundations and Trends in Databases (2011).","DOI":"10.1109\/ICDE.2011.5767956"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"crossref","unstructured":"Martin Grund Jens Kr\u00fcger Hasso Plattner Alexander Zeier Philippe Cudre-Mauroux and Samuel Madden. 2010. Hyrise: a main memory hybrid storage engine. Proceedings of the VLDB Endowment (2010).","DOI":"10.14778\/1921071.1921077"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/2902961.2903512"},{"key":"e_1_3_3_2_76_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_77_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_78_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_79_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_80_2","unstructured":"Juan G\u00f3mez-Luna Izzat El\u00a0Hajj 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 preprint arXiv:https:\/\/arXiv.org\/abs\/2105.03814 (2021)."},{"key":"e_1_3_3_2_81_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_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"e_1_3_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/331532.331589"},{"key":"e_1_3_3_2_84_2","doi-asserted-by":"crossref","unstructured":"John\u00a0T Hancock and Taghi\u00a0M Khoshgoftaar. 2020. CatBoost for big data: an interdisciplinary review. Journal of big data (2020).","DOI":"10.21203\/rs.3.rs-54646\/v1"},{"key":"e_1_3_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.62"},{"key":"e_1_3_3_2_86_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_87_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_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2016.7753257"},{"key":"e_1_3_3_2_89_2","unstructured":"Jianfeng Hu and Jianliang Min. 2018. Automated detection of driver fatigue based on EEG signals using gradient boosting decision tree model. Cognitive neurodynamics (2018)."},{"key":"e_1_3_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00018"},{"key":"e_1_3_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS47924.2020.00076"},{"key":"e_1_3_3_2_92_2","unstructured":"Stratos Idreos Fabian Groffen Niels Nes Stefan Manegold K\u00a0Sjoerd Mullender Martin\u00a0L Kersten et\u00a0al. 2012. MonetDB: Two decades of research in column-oriented database architectures. IEEE Data Eng. Bull. (2012)."},{"key":"e_1_3_3_2_93_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_94_2","volume-title":"Intel Core i7-9700K Processor Datasheethttps:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/186604\/intel-core-i7-9700k-processor-12m-cache-up-to-4-90-ghz.html","author":"Corporation Intel","year":"2018","unstructured":"Intel Corporation. 2018. Intel Core i7-9700K Processor Datasheet. https:\/\/ark.intel.com\/content\/www\/us\/en\/ark\/products\/186604\/intel-core-i7-9700k-processor-12m-cache-up-to-4-90-ghz.html."},{"key":"e_1_3_3_2_95_2","doi-asserted-by":"crossref","unstructured":"Leonid Iosipoi and Anton Vakhrushev. 2022. Sketchboost: Fast gradient boosted decision tree for multioutput problems. NeurIPS (2022).","DOI":"10.52202\/068431-1843"},{"key":"e_1_3_3_2_96_2","doi-asserted-by":"crossref","unstructured":"Zuher Jahshan and Leonid Yavits. 2024. MajorK: Majority based kmer matching in commodity DRAM. CAL (2024).","DOI":"10.1109\/LCA.2024.3384259"},{"key":"e_1_3_3_2_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358297"},{"key":"e_1_3_3_2_98_2","unstructured":"JEDEC Solid State Technology Association. 2012. DDR4 SDRAM Standard. https:\/\/www.jedec.org\/standards-documents\/docs\/jesd79-4a."},{"key":"e_1_3_3_2_99_2","unstructured":"Guolin Ke Qi Meng Thomas Finley Taifeng Wang Wei Chen Weidong Ma Qiwei Ye and Tie-Yan Liu. 2017. Lightgbm: A highly efficient gradient boosting decision tree. NeurIPS (2017)."},{"key":"e_1_3_3_2_100_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_101_2","unstructured":"Alfons Kemper Thomas Neumann Florian Funke Viktor Leis and Henrik M\u00fche. 2012. HyPer: Adapting Columnar Main-Memory Data Management for Transactional AND Query Processing. IEEE Data Eng. Bull. (2012)."},{"key":"e_1_3_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1145\/3132402.3132426"},{"key":"e_1_3_3_2_103_2","unstructured":"Kashif\u00a0Nizam Khan Mikael Hirki Tapio Niemi Jukka\u00a0K Nurminen and Zhonghong Ou. 2018. Rapl in action: Experiences in using rapl for power measurements. TOMPECS (2018)."},{"key":"e_1_3_3_2_104_2","volume-title":"FPGA","author":"Khataei Alireza","year":"2025","unstructured":"Alireza Khataei and Kia Bazargan. 2025. TreeLUT: An Efficient Alternative to Deep Neural Networks for Inference Acceleration Using Gradient Boosted Decision Trees. In FPGA."},{"key":"e_1_3_3_2_105_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_106_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_107_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00026"},{"key":"e_1_3_3_2_108_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00011"},{"key":"e_1_3_3_2_109_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 preprint arXiv:https:\/\/arXiv.org\/abs\/1708.04329 (2017)."},{"key":"e_1_3_3_2_110_2","doi-asserted-by":"crossref","unstructured":"Yoongu Kim Vivek Seshadri Donghyuk Lee Jamie Liu and Onur Mutlu. 2012. A case for exploiting subarray-level parallelism (SALP) in DRAM. ISCA (2012).","DOI":"10.1109\/ISCA.2012.6237032"},{"key":"e_1_3_3_2_111_2","unstructured":"Tatsuya Kubo Daichi Tokuda Tomoya Nagatani Masayuki Usui Lei Qu Ting Cao and Shinya Takamaeda-Yamazaki. 2025. MVDRAM: Enabling GeMV Execution in Unmodified DRAM for Low-Bit LLM Acceleration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.23817 (2025)."},{"key":"e_1_3_3_2_112_2","unstructured":"Tatsuya Kubo Daichi Tokuda Lei Qu Ting Cao and Shinya Takamaeda-Yamazaki. 2025. PUDTune: Multi-Level Charging for High-Precision Calibration in Processing-Using-DRAM. CAL (2025)."},{"key":"e_1_3_3_2_113_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, Seongil O, 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_114_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2015.7113373"},{"key":"e_1_3_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2015.42"},{"key":"e_1_3_3_2_116_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_117_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"e_1_3_3_2_118_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357550"},{"key":"e_1_3_3_2_119_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00062"},{"key":"e_1_3_3_2_120_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_3_2_121_2","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898064"},{"key":"e_1_3_3_2_122_2","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465322"},{"key":"e_1_3_3_2_123_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_124_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00059"},{"key":"e_1_3_3_2_125_2","volume-title":"ISCA","author":"Liu Jiantao","year":"2025","unstructured":"Jiantao Liu, Minxuan Zhou, Yue Pan, Chien-Yi Yang, Lana Josipovi\u0107, and Tajana Rosing. 2025. OptiPIM: Optimizing Processing-in-Memory Acceleration Using Integer Linear Programming. In ISCA."},{"key":"e_1_3_3_2_126_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378497"},{"key":"e_1_3_3_2_127_2","doi-asserted-by":"crossref","unstructured":"Advait Madhavan Timothy Sherwood and Dmitri Strukov. 2014. Race logic: A hardware acceleration for dynamic programming algorithms. ISCA (2014).","DOI":"10.1109\/ISCA.2014.6853226"},{"key":"e_1_3_3_2_128_2","volume-title":"ISCA","author":"Marazzi Michele","year":"2024","unstructured":"Michele Marazzi, Tristan Sachsenweger, Flavien Solt, Peng Zeng, Kubo Takashi, Maksym Yarema, and Kaveh Razavi. 2024. Hifi-dram: Enabling high-fidelity dram research by uncovering sense amplifiers with ic imaging. In ISCA."},{"key":"e_1_3_3_2_129_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_130_2","doi-asserted-by":"crossref","unstructured":"Morten Moshagen. 2010. multiTree: A computer program for the analysis of multinomial processing tree models. Behavior Research Methods (2010).","DOI":"10.3758\/BRM.42.1.42"},{"key":"e_1_3_3_2_131_2","unstructured":"Naveen Muralimanohar Rajeev Balasubramonian and Norman\u00a0P Jouppi. 2009. CACTI 6.0: A tool to model large caches. HP laboratories (2009)."},{"key":"e_1_3_3_2_132_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMW.2013.6582088"},{"key":"e_1_3_3_2_133_2","volume-title":"IEDM","author":"Mutlu Onur","year":"2024","unstructured":"Onur Mutlu, Ataberk Olgun, Geraldo\u00a0F Oliveira, and Ismail\u00a0E Yuksel. 2024. Memory-Centric Computing: Recent Advances in Processing-in-DRAM. In IEDM."},{"key":"e_1_3_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMW61990.2025.11026935"},{"key":"e_1_3_3_2_135_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.54"},{"key":"e_1_3_3_2_136_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_137_2","volume-title":"ISCA","author":"Nam Hwayong","year":"2024","unstructured":"Hwayong Nam, Seungmin Baek, Minbok Wi, Michael\u00a0Jaemin Kim, Jaehyun Park, Chihun Song, Nam\u00a0Sung Kim, and Jung\u00a0Ho Ahn. 2024. DRAMScope: Uncovering dram microarchitecture and characteristics by issuing memory commands. In ISCA."},{"key":"e_1_3_3_2_138_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_139_2","doi-asserted-by":"crossref","unstructured":"Ataberk Olgun Juan Gomez\u00a0Luna 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_140_2","doi-asserted-by":"crossref","unstructured":"Ataberk Olgun Hasan Hassan A\u00a0Giray Ya\u011fl\u0131k\u00e7\u0131 Yahya\u00a0Can Tu\u011frul Lois Orosa Haocong Luo Minesh Patel O\u011fuz Ergin and Onur Mutlu. 2023. DRAM Bender: An extensible and versatile FPGA-based infrastructure to easily test state-of-the-art DRAM chips. TCAD (2023).","DOI":"10.1109\/TCAD.2023.3282172"},{"key":"e_1_3_3_2_141_2","volume-title":"ISCA","author":"Olgun Ataberk","year":"2021","unstructured":"Ataberk Olgun, Minesh Patel, A\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 DRAM chips. In ISCA."},{"key":"e_1_3_3_2_142_2","doi-asserted-by":"crossref","unstructured":"Geraldo\u00a0F Oliveira Juan G\u00f3mez-Luna Saugata Ghose Amirali Boroumand and Onur Mutlu. 2022. Accelerating neural network inference with processing-in-dram: From the edge to the cloud. IEEE Micro (2022).","DOI":"10.1109\/MM.2022.3202350"},{"key":"e_1_3_3_2_143_2","volume-title":"ICS","author":"Oliveira Geraldo\u00a0Francisco","year":"2025","unstructured":"Geraldo\u00a0Francisco Oliveira, Mayank Kabra, Yuxin Guo, Kangqi Chen, Abdullah\u00a0Giray Yaglikci, Melina Soysal, Mohammad Sadrosadati, Joaquin Olivares\u00a0Bueno, Saugata Ghose, Juan G\u00f3mez-Luna, et\u00a0al. 2025. Proteus: Achieving High-Performance Processing-Using-DRAM with Dynamic Bit-Precision, Adaptive Data Representation, and Flexible Arithmetic. In ICS."},{"key":"e_1_3_3_2_144_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00024"},{"key":"e_1_3_3_2_145_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-56258-2_3"},{"key":"e_1_3_3_2_146_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_147_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00069"},{"key":"e_1_3_3_2_148_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_149_2","doi-asserted-by":"publisher","DOI":"10.1145\/2967938.2967940"},{"key":"e_1_3_3_2_150_2","unstructured":"Liudmila Prokhorenkova Gleb Gusev Aleksandr Vorobev Anna\u00a0Veronika Dorogush and Andrey Gulin. 2018. CatBoost: unbiased boosting with categorical features. NeurIPS (2018)."},{"key":"e_1_3_3_2_151_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_3_2_152_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_153_2","volume-title":"SoftMC \u2014 GitHub Repositoryhttps:\/\/github.com\/CMU-SAFARI\/softmc","author":"Group SAFARI Research","year":"2017","unstructured":"SAFARI Research Group. 2017. SoftMC \u2014 GitHub Repository. https:\/\/github.com\/CMU-SAFARI\/softmc."},{"key":"e_1_3_3_2_154_2","volume-title":"DRAM Bender \u2014 GitHub Repositoryhttps:\/\/github.com\/CMU-SAFARI\/DRAM-Bender","author":"Group SAFARI Research","year":"2022","unstructured":"SAFARI Research Group. 2022. DRAM Bender \u2014 GitHub Repository. https:\/\/github.com\/CMU-SAFARI\/DRAM-Bender."},{"key":"e_1_3_3_2_155_2","doi-asserted-by":"crossref","unstructured":"Naratip Santitissadeekorn David\u00a0JB Lloyd Martin\u00a0B Short and Sylvain Delahaies. 2020. Approximate filtering of conditional intensity process for Poisson count data: Application to urban crime. Computational Statistics & Data Analysis (2020).","DOI":"10.1016\/j.csda.2019.106850"},{"key":"e_1_3_3_2_156_2","volume-title":"DATE","author":"Santos Paulo\u00a0C.","year":"2018","unstructured":"Paulo\u00a0C. Santos, Geraldo\u00a0F. Oliveira, Jo\u00e3o\u00a0P. Lima, Marco A.\u00a0Z. Alves, Luigi Carro, and Antonio C.\u00a0S. Beck. 2018. Processing in 3D Memories to Speed Up Operations on Complex Data Structures. In DATE."},{"key":"e_1_3_3_2_157_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_158_2","doi-asserted-by":"crossref","unstructured":"Vivek Seshadri Kevin Hsieh Amirali Boroumand 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_159_2","doi-asserted-by":"publisher","DOI":"10.1145\/2540708.2540725"},{"key":"e_1_3_3_2_160_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 preprint arXiv:https:\/\/arXiv.org\/abs\/1805.03502 (2018)."},{"key":"e_1_3_3_2_161_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 preprint arXiv:https:\/\/arXiv.org\/abs\/1611.09988 (2016)."},{"key":"e_1_3_3_2_162_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_3_2_163_2","unstructured":"Vivek Seshadri and Onur Mutlu. 2016. The processing using memory paradigm: In-DRAM bulk copy initialization bitwise AND and OR. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1610.09603 (2016)."},{"key":"e_1_3_3_2_164_2","doi-asserted-by":"publisher","DOI":"10.1016\/bs.adcom.2017.04.004"},{"key":"e_1_3_3_2_165_2","unstructured":"Vivek Seshadri and Onur Mutlu. 2019. In-DRAM bulk bitwise execution engine. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.09822 (2019)."},{"key":"e_1_3_3_2_166_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_167_2","doi-asserted-by":"publisher","DOI":"10.1145\/2463209.2488866"},{"key":"e_1_3_3_2_168_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_169_2","volume-title":"ISVLSI","author":"Shivanandamurthy Supreeth\u00a0Mysore","year":"2021","unstructured":"Supreeth\u00a0Mysore Shivanandamurthy, Ishan\u00a0G Thakkar, and Sayed\u00a0Ahmad Salehi. 2021. Atria: A bit-parallel stochastic arithmetic based accelerator for in-dram cnn processing. In ISVLSI."},{"key":"e_1_3_3_2_170_2","unstructured":"Assaf Shmuel Oren Glickman and Teddy Lazebnik. 2024. A Comprehensive Benchmark of Machine and Deep Learning Across Diverse Tabular Datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.14817 (2024)."},{"key":"e_1_3_3_2_171_2","doi-asserted-by":"crossref","unstructured":"Ravid Shwartz-Ziv and Amitai Armon. 2022. Tabular data: Deep learning is not all you need. Information Fusion (2022).","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"e_1_3_3_2_172_2","doi-asserted-by":"publisher","DOI":"10.1109\/FPL50879.2020.00014"},{"key":"e_1_3_3_2_173_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317867"},{"key":"e_1_3_3_2_174_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"e_1_3_3_2_175_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00052"},{"key":"e_1_3_3_2_176_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_177_2","doi-asserted-by":"crossref","unstructured":"Rui Sun Guanyu Wang Wenyu Zhang Li-Ta Hsu and Washington\u00a0Y Ochieng. 2020. A gradient boosting decision tree based GPS signal reception classification algorithm. Applied Soft Computing (2020).","DOI":"10.1016\/j.asoc.2019.105942"},{"key":"e_1_3_3_2_178_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_179_2","doi-asserted-by":"crossref","unstructured":"Purab\u00a0Ranjan Sutradhar Mark Connolly Sathwika Bavikadi Sai Manoj\u00a0Pudukotai Dinakarrao Mark\u00a0A Indovina and Amlan Ganguly. 2020. pPIM: A programmable processor-in-memory architecture with precision-scaling for deep learning. CAL (2020).","DOI":"10.1109\/LCA.2020.3011643"},{"key":"e_1_3_3_2_180_2","volume-title":"Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing: Hardware Architectures","author":"Thakkar Ishan\u00a0G","year":"2023","unstructured":"Ishan\u00a0G Thakkar, Supreeth\u00a0M Shivanandamurthy, and Sayed\u00a0Ahmad Salehi. 2023. Low-Latency, Energy-Efficient In-DRAM CNN Acceleration with Bit-Parallel Unary Computing. In Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing: Hardware Architectures."},{"key":"e_1_3_3_2_181_2","doi-asserted-by":"crossref","unstructured":"Daichi Tokuda and Shinya Takamaeda-Yamazaki. 2025. DF-BETA: An FPGA-based Memory Locality Aware Decision Forest Accelerator via Bit-Level Early Termination. ACM TRETS (2025).","DOI":"10.1145\/3706114"},{"key":"e_1_3_3_2_182_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480071"},{"key":"e_1_3_3_2_183_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_184_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00058"},{"key":"e_1_3_3_2_185_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00051"},{"key":"e_1_3_3_2_186_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00036"},{"key":"e_1_3_3_2_187_2","doi-asserted-by":"crossref","unstructured":"Thomas Willhalm Nicolae Popovici Yazan Boshmaf Hasso Plattner Alexander Zeier and Jan Schaffner. 2009. SIMD-scan: ultra fast in-memory table scan using on-chip vector processing units. Proceedings of the VLDB Endowment (2009).","DOI":"10.14778\/1687627.1687671"},{"key":"e_1_3_3_2_188_2","volume-title":"ISCA","author":"Wu Di","year":"2020","unstructured":"Di Wu, Jingjie Li, Ruokai Yin, Hsuan Hsiao, Younghyun Kim, and Joshua San\u00a0Miguel. 2020. UGEMM: Unary computing architecture for GEMM applications. In ISCA."},{"key":"e_1_3_3_2_189_2","unstructured":"Lingxi Wu Rasool Sharifi Ashish Venkat and Kevin Skadron. 2022. DRAM-CAM: General-purpose bit-serial exact pattern matching. CAL (2022)."},{"key":"e_1_3_3_2_190_2","doi-asserted-by":"publisher","DOI":"10.1145\/2771937.2771945"},{"key":"e_1_3_3_2_191_2","volume-title":"Xilinx Power Estimator User Guide","author":"Inc. Xilinx,","year":"2022","unstructured":"Xilinx, Inc.2022. Xilinx Power Estimator User Guide. v2022.1."},{"key":"e_1_3_3_2_192_2","volume-title":"MICRO","author":"Xin Xin","year":"2021","unstructured":"Xin Xin, Yanan Guo, Youtao Zhang, and Jun Yang. 2021. SAM: accelerating strided memory accesses. In MICRO."},{"key":"e_1_3_3_2_193_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00033"},{"key":"e_1_3_3_2_194_2","unstructured":"Li Y. Xu W. Chen H. Jiang J. and Li X.2021. A Novel Framework Based on Mask R\u2011CNN and Histogram Thresholding for Scalable Segmentation of New and Old Rural Buildings. Remote Sensing (2021)."},{"key":"e_1_3_3_2_195_2","volume-title":"ICCD","author":"Y\u00fcksel Ismail\u00a0Emir","year":"2025","unstructured":"Ismail\u00a0Emir Y\u00fcksel, Ataberk Olgun, F\u00a0Nisa Bostanci, O\u011fuzhan Canpolat, Geraldo\u00a0F Oliveira, Mohammad Sadrosadati, A\u00a0Giray Ya\u011flik\u00e7i, Onur Mutlu, et\u00a0al. 2025. In-DRAM True Random Number Generation Using Simultaneous Multiple-Row Activation: An Experimental Study of Real DRAM Chips. In ICCD."},{"key":"e_1_3_3_2_196_2","volume-title":"ISCA","author":"Yuksel Ismail\u00a0Emir","year":"2025","unstructured":"Ismail\u00a0Emir Yuksel, Akash Sood, Ataberk Olgun, O\u011fuzhan Canpolat, Haocong Luo, Nisa Bostanci, Mohammad Sadrosadati, Giray Yaglikci, and Onur Mutlu. 2025. PuDHammer: Experimental Analysis of Read Disturbance Effects of Processing-using-DRAM in Real DRAM Chips. In ISCA."},{"key":"e_1_3_3_2_197_2","unstructured":"Ismail\u00a0Emir Yuksel Yahya\u00a0Can Tugrul F Bostanci Abdullah\u00a0Giray Yaglikci Ataberk Olgun Geraldo\u00a0F Oliveira Melina Soysal Haocong Luo Juan\u00a0Gomez Luna Mohammad Sadrosadati et\u00a0al. 2023. PULSAR: Simultaneous many-row activation for reliable and high-performance computing in off-the-shelf DRAM chips. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2312.02880 (2023)."},{"key":"e_1_3_3_2_198_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN58291.2024.00024"},{"key":"e_1_3_3_2_199_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00030"},{"key":"e_1_3_3_2_200_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_201_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_3_2_202_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00053"},{"key":"e_1_3_3_2_203_2","doi-asserted-by":"crossref","unstructured":"Tianning Zhang Weihuan He Hui Zheng Yaoping Cui Hongquan Song and Shenglei Fu. 2021. Satellite-based ground PM2. 5 estimation using a gradient boosting decision tree. Chemosphere (2021).","DOI":"10.1016\/j.chemosphere.2020.128801"},{"key":"e_1_3_3_2_204_2","doi-asserted-by":"crossref","unstructured":"Wanhu Zhang Junqi Yu Anjun Zhao and Xinwei Zhou. 2021. Predictive model of cooling load for ice storage air-conditioning system by using GBDT. Energy reports (2021).","DOI":"10.1016\/j.egyr.2021.03.017"},{"key":"e_1_3_3_2_205_2","doi-asserted-by":"crossref","unstructured":"YD Zhang L Liao Q Yu WG Ma and KH Li. 2021. Using the gradient boosting decision tree (GBDT) algorithm for a train delay prediction model considering the delay propagation feature. Advances in Production Engineering & Management (2021).","DOI":"10.14743\/apem2021.3.400"},{"key":"e_1_3_3_2_206_2","doi-asserted-by":"crossref","unstructured":"Dong Zhong Qinglei Cao George Bosilca and Jack Dongarra. 2022. Using long vector extensions for MPI reductions. Parallel Comput. (2022).","DOI":"10.1016\/j.parco.2021.102871"},{"key":"e_1_3_3_2_207_2","volume-title":"ICCAD","author":"Zhou Ranyang","year":"2022","unstructured":"Ranyang Zhou, Arman Roohi, Durga Misra, and Shaahin Angizi. 2022. ReD-LUT: Reconfigurable in-DRAM LUTs enabling massive parallel computation. In ICCAD."},{"key":"e_1_3_3_2_208_2","doi-asserted-by":"crossref","unstructured":"Ranyang Zhou Sepehr Tabrizchi Arman Roohi and Shaahin Angizi. 2022. Lt-pim: An lut-based processing-in-dram architecture with rowhammer self-tracking. CAL (2022).","DOI":"10.1109\/LCA.2022.3220084"},{"key":"e_1_3_3_2_209_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2013.6670336"},{"key":"e_1_3_3_2_210_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358256"}],"event":{"name":"ICS '26: 2026 International Conference on Supercomputing","location":"Belfast United Kingdom","acronym":"ICS '26","sponsor":["SIGHPC ACM Special Interest Group on High Performance Computing, Special Interest Group on High Performance Computing","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 40th ACM International Conference on Supercomputing"],"original-title":[],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T13:07:57Z","timestamp":1782997677000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3797905.3800550"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":209,"alternative-id":["10.1145\/3797905.3800550","10.1145\/3797905"],"URL":"https:\/\/doi.org\/10.1145\/3797905.3800550","relation":{},"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}