{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:40:13Z","timestamp":1755870013246,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":96,"publisher":"ACM","funder":[{"name":"National Research Foundation of Korea (NRF)","award":["NRF-2021R1C1C1012172"],"award-info":[{"award-number":["NRF-2021R1C1C1012172"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,8]]},"DOI":"10.1145\/3721145.3735111","type":"proceedings-article","created":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:57:17Z","timestamp":1755867437000},"page":"495-512","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SparsePIM: An Efficient HBM-Based PIM Architecture for Sparse Matrix-Vector Multiplications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7097-2125","authenticated-orcid":false,"given":"Taewoon","family":"Kang","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6412-5352","authenticated-orcid":false,"given":"Geonwoo","family":"Choi","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6377-5482","authenticated-orcid":false,"given":"Taeweon","family":"Suh","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1706-6850","authenticated-orcid":false,"given":"Gunjae","family":"Koo","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Korea University, Seoul, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2025,8,22]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750397"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Arash Ashari Naser Sedaghati John Eisenlohr and P. Sadayappan. 2015. A model-driven blocking strategy for load balanced sparse matrix\u2013vector multiplication on GPUs. J. Parallel and Distrib. Comput. 76 (2015) 3\u201315. 10.1016\/j.jpdc.2014.11.001Special Issue on Architecture and Algorithms for Irregular Applications.","DOI":"10.1016\/j.jpdc.2014.11.001"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00034"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","unstructured":"Sergey Brin and Lawrence Page. 1998. The anatomy of a large-scale hypertextual Web search engine. Computer Networks and ISDN Systems 30 1 (1998) 107\u2013117. 10.1016\/S0169-7552(98)00110-XProceedings of the Seventh International World Wide Web Conference.","DOI":"10.1016\/S0169-7552(98)00110-X"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Kwanyeob Chae Jaegeun Song Yoonjae Choi Jiyeon Park Billy Koo Jihun Oh Shinyoung Yi Won Lee Dongha Kim Kyeongkeun Kang Eunsu Kim Juyoung Kim Sanghune Park Sungcheol Park Mijung Noh Hyo\u00a0Gyuem Rhew and Jongshin Shin. 2024. A 4-nm 1.15 TB\/s HBM3 Interface With Resistor-Tuned Offset Calibration and In Situ Margin Detection. IEEE Journal of Solid-State Circuits 59 1 (2024) 231\u2013242. 10.1109\/JSSC.2023.3330485","DOI":"10.1109\/JSSC.2023.3330485"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","unstructured":"Yuedan Chen Guoqing Xiao Fan Wu Zhuo Tang and Keqin Li. 2020. tpSpMV: A two-phase large-scale sparse matrix-vector multiplication kernel for manycore architectures. Information Sciences 523 (2020) 279\u2013295. 10.1016\/j.ins.2020.03.020","DOI":"10.1016\/j.ins.2020.03.020"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2018.8310257"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056040"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472479"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2014.23"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPADS53394.2021.00058"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Christina Giannoula Ivan Fernandez Juan\u00a0G\u00f3mez Luna Nectarios Koziris Georgios Goumas and Onur Mutlu. 2022. SparseP: Towards Efficient Sparse Matrix Vector Multiplication on Real Processing-In-Memory Architectures. Proc. ACM Meas. Anal. Comput. Syst. 6 1 Article 21 (Feb. 2022) 49\u00a0pages. 10.1145\/3508041","DOI":"10.1145\/3508041"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","unstructured":"Mohammad Hosseinabady and Jose\u00a0Luis Nunez-Yanez. 2020. A Streaming Dataflow Engine for Sparse Matrix-Vector Multiplication Using High-Level Synthesis. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 39 6 (2020) 1272\u20131285. 10.1109\/TCAD.2019.2912923","DOI":"10.1109\/TCAD.2019.2912923"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"Anil\u00a0K. Jain. 2010. Data clustering: 50 years beyond K-means. Pattern Recognition Letters 31 8 (2010) 651\u2013666. 10.1016\/j.patrec.2009.09.011Award winning papers from the 19th International Conference on Pattern Recognition (ICPR).","DOI":"10.1016\/j.patrec.2009.09.011"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","unstructured":"Hai Jin Dan Chen Long Zheng Yu Huang Pengcheng Yao Jin Zhao Xiaofei Liao and Wenbin Jiang. 2023. Accelerating Graph Convolutional Networks Through a PIM-Accelerated Approach. IEEE Trans. Comput. 72 9 (2023) 2628\u20132640. 10.1109\/TC.2023.3257514","DOI":"10.1109\/TC.2023.3257514"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313434"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMW.2017.7939084"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","unstructured":"E.F. Kaasschieter. 1988. Preconditioned conjugate gradients for solving singular systems. J. Comput. Appl. Math. 24 1 (1988) 265\u2013275. 10.1016\/0377-0427(88)90358-5","DOI":"10.1016\/0377-0427(88)90358-5"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614314"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358286"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","unstructured":"Jieui Kang Soeun Choi Eunjin Lee and Jaehyeong Sim. 2024. SpDRAM: Efficient In-DRAM Acceleration of Sparse Matrix-Vector Multiplication. IEEE Access 12 (2024) 176009\u2013176021. 10.1109\/ACCESS.2024.3505622","DOI":"10.1109\/ACCESS.2024.3505622"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2012.12"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Marat\u00a0F. Khairoutdinov and David\u00a0A. Randall. 2001. A cloud resolving model as a cloud parameterization in the NCAR Community Climate System Model: Preliminary results. Geophysical Research Letters 28 18 (2001) 3617\u20133620. 10.1029\/2001GL013552","DOI":"10.1029\/2001GL013552"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","unstructured":"Inje Kim Jonghyun Jeong Yunho Oh Myung\u00a0Kuk Yoon and Gunjae Koo. 2022. Analyzing GCN Aggregation on GPU. IEEE Access 10 (2022) 113046\u2013113060. 10.1109\/ACCESS.2022.3217222","DOI":"10.1109\/ACCESS.2022.3217222"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9567191"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2011.5746413"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Whijin Kim Hana Kim Jihye Lee Hyunji Kim and Ji-Hoon Kim. 2023. Multi-Mode SpMV Accelerator for Transprecision PageRank With Real-World Graphs. IEEE Access 11 (2023) 6261\u20136272. 10.1109\/ACCESS.2023.3237079","DOI":"10.1109\/ACCESS.2023.3237079"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Jon\u00a0M. Kleinberg. 1999. Authoritative sources in a hyperlinked environment. J. ACM 46 5 (Sept. 1999) 604\u2013632. 10.1145\/324133.324140","DOI":"10.1145\/324133.324140"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2015.23"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/1366230.1366244"},{"key":"e_1_3_3_1_38_2","doi-asserted-by":"publisher","unstructured":"Daehan Kwon Seongju Lee Kyuyoung Kim Sanghoon Oh Joonhong Park Gi-Moon Hong Dongyoon Ka Kyudong Hwang Jeongje Park Kyeongpil Kang Jungyeon Kim Junyeol Jeon Nahsung Kim Yongkee Kwon Vladimir Kornijcuk Woojae Shin Jongsoon Won Minkyu Lee Hyunha Joo Haerang Choi Guhyun Kim Byeongju An Jaewook Lee Donguc Ko Younggun Jun Ilwoong Kim Choungki Song Ilkon Kim Chanwook Park Seho Kim Chunseok Jeong Euicheol Lim Dongkyun Kim Jieun Jang Il Park Junhyun Chun and Joohwan Cho. 2023. A 1ynm 1.25V 8Gb 16Gb\/s\/Pin GDDR6-Based Accelerator-in-Memory Supporting 1TFLOPS MAC Operation and Various Activation Functions for Deep Learning Application. IEEE Journal of Solid-State Circuits 58 1 (2023) 291\u2013302. 10.1109\/JSSC.2022.3200718","DOI":"10.1109\/JSSC.2022.3200718"},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895629"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365862"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9062977"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2014.6757501"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC49657.2024.10454440"},{"key":"e_1_3_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418035"},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","unstructured":"Min Li Yulong Ao and Chao Yang. 2021. Adaptive SpMV\/SpMSpV on GPUs for Input Vectors of Varied Sparsity. IEEE Transactions on Parallel and Distributed Systems 32 7 (2021) 1842\u20131853. 10.1109\/TPDS.2020.3040150","DOI":"10.1109\/TPDS.2020.3040150"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","unstructured":"Shiqing Li Di Liu and Weichen\u00a0LiuDi Liu. 2023. Efficient FPGA-Based Sparse Matrix\u2013Vector Multiplication With Data Reuse-Aware Compression. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 42 12 (2023) 4606\u20134617. 10.1109\/TCAD.2023.3281715","DOI":"10.1109\/TCAD.2023.3281715"},{"key":"e_1_3_3_1_49_2","doi-asserted-by":"publisher","unstructured":"Shang Li Zhiyuan Yang Dhiraj Reddy Ankur Srivastava and Bruce Jacob. 2020. DRAMsim3: A Cycle-Accurate Thermal-Capable DRAM Simulator. IEEE Computer Architecture Letters 19 2 (2020) 106\u2013109. 10.1109\/LCA.2020.2973991","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_1_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3566097.3567839"},{"key":"e_1_3_3_1_51_2","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu Baoyuan","year":"2015","unstructured":"Baoyuan Liu, Min Wang, Hassan Foroosh, Marshall Tappen, and Marianna Pensky. 2015. Sparse Convolutional Neural Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_1_52_2","doi-asserted-by":"publisher","unstructured":"Marco Maggioni and Tanya Berger-Wolf. 2016. Optimization techniques for sparse matrix\u2013vector multiplication on GPUs. J. Parallel and Distrib. Comput. 93-94 (2016) 66\u201386. 10.1016\/j.jpdc.2016.03.011","DOI":"10.1016\/j.jpdc.2016.03.011"},{"key":"e_1_3_3_1_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-28"},{"key":"e_1_3_3_1_54_2","doi-asserted-by":"publisher","DOI":"10.1109\/GCON58516.2023.10183488"},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/HIPC.2009.5433184"},{"key":"e_1_3_3_1_56_2","doi-asserted-by":"publisher","unstructured":"Susumu Mashimo Thiem Van\u00a0Chu and Kenji Kise. 2017. Cost-Effective and High-Throughput Merge Network: Architecture for the Fastest FPGA Sorting Accelerator. SIGARCH Comput. Archit. News 44 4 (Jan. 2017) 8\u201313. 10.1145\/3039902.3039905","DOI":"10.1145\/3039902.3039905"},{"key":"e_1_3_3_1_57_2","unstructured":"JEDEC Standard High Bandwidth Memory\u00a0DRAM Memory. 2015. Dram specification. Standard JESD235A (2015)."},{"key":"e_1_3_3_1_58_2","unstructured":"JEDEC Standard High Bandwidth Memory\u00a0DRAM Memory. 2021. Dram specification. Standard JESD235D (2021)."},{"key":"e_1_3_3_1_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.54"},{"key":"e_1_3_3_1_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370327"},{"key":"e_1_3_3_1_61_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24037-9_58"},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00016"},{"key":"e_1_3_3_1_63_2","unstructured":"CUDA Nvidia. 2025. Cusparse library. NVIDIA Corporation Santa Clara California (2025)."},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC19947.2020.9063110"},{"key":"e_1_3_3_1_65_2","unstructured":"Cristobal Ortega Yann Falevoz and Renaud Ayrignac. 2024. PIM-AI: A Novel Architecture for High-Efficiency LLM Inference. arxiv:https:\/\/arXiv.org\/abs\/2411.17309\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2411.17309"},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00067"},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","unstructured":"Jaewon Park Jae\u00a0Hoon Lee Sang-Kil Park Ki\u00a0Chul Chun Kyomin Sohn and Sungho Kang. 2021. An In-DRAM BIST for 16 Gb DDR4 DRAM in the 2nd 10-nm-Class DRAM Process. IEEE Access 9 (2021) 33487\u201333497. 10.1109\/ACCESS.2021.3061349","DOI":"10.1109\/ACCESS.2021.3061349"},{"key":"e_1_3_3_1_68_2","doi-asserted-by":"publisher","unstructured":"Myeong-Jae Park Jinhyung Lee Kyungjun Cho Jihwan Park Junil Moon Sung-Hak Lee Tae-Kyun Kim Sanghoon Oh Seokwoo Choi Yongsuk Choi Ho\u00a0Sung Cho Taesik Yun Young\u00a0Jun Koo Jae-Seung Lee Byung-Kuk Yoon Young-Jun Park Sangmuk Oh Chang\u00a0Kwon Lee Seong-Hee Lee Hyun-Woo Kim Yucheon Ju Seung-Kyun Lim Kyo\u00a0Yun Lee Sang-Hoon Lee Woo\u00a0Sung We Seungchan Kim Seung\u00a0Min Yang Keonho Lee In-Keun Kim Younghyun Jeon Jae-Hyung Park Jong\u00a0Chan Yun Seonyeol Kim Dong-Yeol Lee Su-Hyun Oh Jung-Hyun Shin Yeonho Lee Jieun Jang and Joohwan Cho. 2023. A 192-Gb 12-High 896-GB\/s HBM3 DRAM With a TSV Auto-Calibration Scheme and Machine-Learning-Based Layout Optimization. IEEE Journal of Solid-State Circuits 58 1 (2023) 256\u2013269. 10.1109\/JSSC.2022.3193354","DOI":"10.1109\/JSSC.2022.3193354"},{"key":"e_1_3_3_1_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS45731.2020.9181266"},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2014.6844483"},{"key":"e_1_3_3_1_71_2","doi-asserted-by":"publisher","unstructured":"Mayra\u00a0Z. Rodriguez Cesar\u00a0H. Comin Dalcimar Casanova Odemir\u00a0M. Bruno Diego\u00a0R. Amancio Luciano da\u00a0F. Costa and Francisco\u00a0A. Rodrigues. 2019. Clustering algorithms: A comparative approach. PLOS ONE 14 1 (01 2019) 1\u201334. 10.1371\/journal.pone.0210236","DOI":"10.1371\/journal.pone.0210236"},{"key":"e_1_3_3_1_72_2","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611970739"},{"key":"e_1_3_3_1_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358330"},{"key":"e_1_3_3_1_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651324"},{"key":"e_1_3_3_1_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_3_1_76_2","doi-asserted-by":"publisher","unstructured":"Kristina\u00a0P. Sinaga and Miin-Shen Yang. 2020. Unsupervised K-Means Clustering Algorithm. IEEE Access 8 (2020) 80716\u201380727. 10.1109\/ACCESS.2020.2988796","DOI":"10.1109\/ACCESS.2020.2988796"},{"key":"e_1_3_3_1_77_2","doi-asserted-by":"publisher","unstructured":"Kyomin Sohn Won-Joo Yun Reum Oh Chi-Sung Oh Seong-Young Seo Min-Sang Park Dong-Hak Shin Won-Chang Jung Sang-Hoon Shin Je-Min Ryu Hye-Seung Yu Jae-Hun Jung Hyunui Lee Seok-Yong Kang Young-Soo Sohn Jung-Hwan Choi Yong-Cheol Bae Seong-Jin Jang and Gyoyoung Jin. 2017. A 1.2 V 20 nm 307 GB\/s HBM DRAM With At-Speed Wafer-Level IO Test Scheme and Adaptive Refresh Considering Temperature Distribution. IEEE Journal of Solid-State Circuits 52 1 (2017) 250\u2013260. 10.1109\/JSSC.2016.2602221","DOI":"10.1109\/JSSC.2016.2602221"},{"key":"e_1_3_3_1_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530420"},{"key":"e_1_3_3_1_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00062"},{"key":"e_1_3_3_1_80_2","doi-asserted-by":"publisher","unstructured":"Wai\u00a0Teng Tang Wen\u00a0Jun Tan Rick Siow\u00a0Mong Goh Stephen\u00a0John Turner and Weng-Fai Wong. 2015. A Family of Bit-Representation-Optimized Formats for Fast Sparse Matrix-Vector Multiplication on the GPU. IEEE Transactions on Parallel and Distributed Systems 26 9 (2015) 2373\u20132385. 10.1109\/TPDS.2014.2357437","DOI":"10.1109\/TPDS.2014.2357437"},{"key":"e_1_3_3_1_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASICON52560.2021.9620445"},{"key":"e_1_3_3_1_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582026"},{"key":"e_1_3_3_1_83_2","doi-asserted-by":"publisher","unstructured":"Hanghang Tong Christos Faloutsos and Jia-Yu Pan. 2008. Random walk with restart: fast solutions and applications. Knowledge and Information Systems 14 (2008) 327\u2013346. 10.1007\/s10115-007-0094-2","DOI":"10.1007\/s10115-007-0094-2"},{"key":"e_1_3_3_1_84_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2014.6974716"},{"key":"e_1_3_3_1_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/CANDAR.2016.0023"},{"key":"e_1_3_3_1_86_2","doi-asserted-by":"publisher","unstructured":"Sheng Wang Yuan Sun and Zhifeng Bao. 2020. On the efficiency of K-means clustering: evaluation optimization and algorithm selection. Proceedings of the VLDB Endowment 14 2 (Oct. 2020) 163\u2013175. 10.14778\/3425879.3425887","DOI":"10.14778\/3425879.3425887"},{"key":"e_1_3_3_1_87_2","doi-asserted-by":"publisher","unstructured":"Shih-Hung Weng Quan Chen and Chung-Kuan Cheng. 2012. Time-Domain Analysis of Large-Scale Circuits by Matrix Exponential Method With Adaptive Control. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 31 8 (2012) 1180\u20131193. 10.1109\/TCAD.2012.2189396","DOI":"10.1109\/TCAD.2012.2189396"},{"key":"e_1_3_3_1_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/2429384.2429469"},{"key":"e_1_3_3_1_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00055"},{"key":"e_1_3_3_1_90_2","doi-asserted-by":"publisher","unstructured":"Weidong Yang Yuqing Yang Shuya Ji Jianfei Jiang Naifeng Jing Qin Wang Zhigang Mao and Weiguang Sheng. 2024. RecPIM: Efficient In-Memory Processing for Personalized Recommendation Inference Using Near-Bank Architecture. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 43 10 (2024) 2854\u20132867. 10.1109\/TCAD.2024.3386117","DOI":"10.1109\/TCAD.2024.3386117"},{"key":"e_1_3_3_1_91_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC41405.2020.00090"},{"key":"e_1_3_3_1_92_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546797"},{"key":"e_1_3_3_1_93_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_3_1_94_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00053"},{"key":"e_1_3_3_1_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/3DIC.2013.6702348"},{"key":"e_1_3_3_1_96_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC.2013.6670336"},{"key":"e_1_3_3_1_97_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358256"}],"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\/3721145.3735111","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T13:00:10Z","timestamp":1755867610000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3721145.3735111"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,8]]},"references-count":96,"alternative-id":["10.1145\/3721145.3735111","10.1145\/3721145"],"URL":"https:\/\/doi.org\/10.1145\/3721145.3735111","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"}}]}}