{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:37:08Z","timestamp":1772725028561,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":56,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,30]]},"DOI":"10.1145\/3695794.3695795","type":"proceedings-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T04:06:53Z","timestamp":1733976413000},"page":"1-12","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["PIM-Potential: Broadening the Acceleration Reach of PIM Architectures"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5272-2396","authenticated-orcid":false,"given":"Johnathan","family":"Alsop","sequence":"first","affiliation":[{"name":"AMD Inc., Santa Clara, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9552-0508","authenticated-orcid":false,"given":"Shaizeen","family":"Aga","sequence":"additional","affiliation":[{"name":"AMD Inc., Santa Clara, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4129-0310","authenticated-orcid":false,"given":"Mohamed","family":"Ibrahim","sequence":"additional","affiliation":[{"name":"AMD Inc., Santa Clara, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9980-9720","authenticated-orcid":false,"given":"Mahzabeen","family":"Islam","sequence":"additional","affiliation":[{"name":"AMD Inc., Santa Clara, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2973-9479","authenticated-orcid":false,"given":"Nuwan","family":"Jayasena","sequence":"additional","affiliation":[{"name":"AMD Inc., Santa Clara, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0694-7740","authenticated-orcid":false,"given":"Andrew","family":"McCrabb","sequence":"additional","affiliation":[{"name":"University of Michigan, Ann Arbor, MI, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"2013. JEDEC High Bandwidth Memory (HBM) DRAM. https:\/\/www.jedec.org\/standards-documents\/docs\/jesd235a."},{"key":"e_1_3_3_2_3_2","unstructured":"2022. JEDEC Publishes HBM3 Update to High Bandwidth Memory (HBM) Standard. https:\/\/www.jedec.org\/news\/pressreleases\/jedec-publishes-hbm3-update-high-bandwidth-memory-hbm-standard."},{"key":"e_1_3_3_2_4_2","unstructured":"2022. rocprofiler developer tool. https:\/\/github.com\/ROCm-Developer-Tools\/rocprofiler."},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC.2018.8573480"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357532"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750386"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2749469.2750385"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Junwhan Ahn Sungjoo Yoo Onur Mutlu and Kiyoung Choi. 2015. PIM-enabled instructions: A low-overhead locality-aware processing-in-memory architecture. ACM SIGARCH Computer Architecture News 43 3S (2015) 336\u2013348.","DOI":"10.1145\/2872887.2750385"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783753"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3078597.3078616"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173177"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322266"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Amirali Boroumand Saugata Ghose Minesh Patel Hasan Hassan Brandon Lucia Kevin Hsieh Krishna\u00a0T Malladi Hongzhong Zheng and Onur Mutlu. 2016. LazyPIM: An efficient cache coherence mechanism for processing-in-memory. IEEE Computer Architecture Letters 16 1 (2016) 46\u201350.","DOI":"10.1109\/LCA.2016.2577557"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"crossref","unstructured":"Preston Briggs Keith\u00a0D Cooper and Linda Torczon. 1994. Improvements to graph coloring register allocation. ACM Transactions on Programming Languages and Systems (TOPLAS) 16 3 (1994) 428\u2013455.","DOI":"10.1145\/177492.177575"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3323165.3323191"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Fred\u00a0C Chow and John\u00a0L Hennessy. 1990. The priority-based coloring approach to register allocation. ACM Transactions on Programming Languages and Systems (TOPLAS) 12 4 (1990) 501\u2013536.","DOI":"10.1145\/88616.88621"},{"key":"e_1_3_3_2_19_2","unstructured":"Criteo. [n. d.]. Criteo Terabyte Click Logs dataset. https:\/\/ailab.criteo.com\/criteo-1tb-click-logs-dataset\/."},{"key":"e_1_3_3_2_20_2","unstructured":"Timothy\u00a0A Davis et\u00a0al. 2015. SuiteSparse: A suite of sparse matrix software. https:\/\/people.engr.tamu.edu\/davis\/suitesparse.html"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2621934.2621936"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"crossref","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. Proceedings of the ACM on Measurement and Analysis of Computing Systems 6 1 (2022) 1\u201349.","DOI":"10.1145\/3508041"},{"key":"e_1_3_3_2_24_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 10 (2022) 52565\u201352608.","DOI":"10.1109\/ACCESS.2022.3174101"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472456.3472512"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Jin\u00a0Hyun Kim Shin-Haeng Kang Sukhan Lee Hyeonsu Kim Yuhwan Ro Seungwon Lee David Wang Jihyun Choi Jinin So YeonGon Cho et\u00a0al. 2022. Aquabolt-XL HBM2-PIM LPDDR5-PIM with in-memory processing and AXDIMM with acceleration buffer. IEEE Micro 42 3 (2022) 20\u201330.","DOI":"10.1109\/MM.2022.3164651"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS52781.2021.9567191"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358284"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS55958.2022.9895629"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ECTC.2016.348"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731711"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Won\u00a0Jun Lee Chang\u00a0Hyun Kim Yoonah Paik Jongsun Park Il Park and Seon\u00a0Wook Kim. 2019. Design of processing-\u201cinside\u201d-memory optimized for dram behaviors. IEEE Access 7 (2019) 82633\u201382648.","DOI":"10.1109\/ACCESS.2019.2924240"},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"e_1_3_3_2_37_2","unstructured":"Yueting Li Tianshuo Bai Xinyi Xu Yundong Zhang Bi Wu Hao Cai Biao Pan and Weisheng Zhao. 2022. A Survey of MRAM-Centric Computing: From Near Memory to In Memory. IEEE Transactions on Emerging Topics in Computing (2022)."},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Sparsh Mittal. 2018. A survey of ReRAM-based architectures for processing-in-memory and neural networks. Machine learning and knowledge extraction 1 1 (2018) 75\u2013114.","DOI":"10.3390\/make1010005"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.54"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807591.2807626"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Ravi Nair Samuel\u00a0F Antao Carlo Bertolli Pradip Bose Jose\u00a0R Brunheroto Tong Chen C-Y Cher Carlos\u00a0HA Costa Jun Doi Constantinos Evangelinos et\u00a0al. 2015. Active memory cube: A processing-in-memory architecture for exascale systems. IBM Journal of Research and Development 59 2\/3 (2015) 17\u20131.","DOI":"10.1147\/JRD.2015.2409732"},{"key":"e_1_3_3_2_42_2","unstructured":"Maxim Naumov Dheevatsa Mudigere Hao-Jun\u00a0Michael Shi Jianyu Huang Narayanan Sundaraman Jongsoo Park Xiaodong Wang Udit Gupta Carole-Jean Wu Alisson\u00a0G Azzolini et\u00a0al. 2019. Deep learning recommendation model for personalization and recommendation systems. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1906.00091 (2019)."},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480080"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC55918.2022.00033"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00027"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00052"},{"key":"e_1_3_3_2_48_2","unstructured":"Chirag Sudarshan. 2024. Processing-in-Memory DRAM Architectures for Neural Network Applications. Ph.\u00a0D. Dissertation. Rheinland-Pf\u00e4lzische Technische Universit\u00e4t Kaiserslautern-Landau."},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15074-6_23"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9937832"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"crossref","unstructured":"Yangzihao Wang Yuechao Pan Andrew Davidson Yuduo Wu Carl Yang Leyuan Wang Muhammad Osama Chenshan Yuan Weitang Liu Andy\u00a0T Riffel et\u00a0al. 2017. Gunrock: GPU graph analytics. ACM Transactions on Parallel Computing (TOPC) 4 1 (2017) 1\u201349.","DOI":"10.1145\/3108140"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"Lucas\u00a0C Wilcox Georg Stadler Carsten Burstedde and Omar Ghattas. 2010. A high-order discontinuous Galerkin method for wave propagation through coupled elastic\u2013acoustic media. J. Comput. Phys. 229 24 (2010) 9373\u20139396.","DOI":"10.1016\/j.jcp.2010.09.008"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"crossref","unstructured":"Yue Xi Bin Gao Jianshi Tang An Chen Meng-Fan Chang Xiaobo\u00a0Sharon Hu Jan Van Der\u00a0Spiegel He Qian and Huaqiang Wu. 2020. In-memory learning with analog resistive switching memory: A review and perspective. Proc. IEEE 109 1 (2020) 14\u201342.","DOI":"10.1109\/JPROC.2020.3004543"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/2600212.2600213"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2018.00053"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358269"},{"key":"e_1_3_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358256"}],"event":{"name":"MEMSYS '24: The International Symposium on Memory Systems","location":"Washington DC USA","acronym":"MEMSYS '24"},"container-title":["Proceedings of the International Symposium on Memory Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695794.3695795","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695794.3695795","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:10:06Z","timestamp":1750295406000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695794.3695795"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"references-count":56,"alternative-id":["10.1145\/3695794.3695795","10.1145\/3695794"],"URL":"https:\/\/doi.org\/10.1145\/3695794.3695795","relation":{},"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"2024-12-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}