{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T15:53:23Z","timestamp":1782921203059,"version":"3.54.5"},"reference-count":103,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CCF-2329096"],"award-info":[{"award-number":["CCF-2329096"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,31]]},"DOI":"10.1109\/hpca68181.2026.11408599","type":"proceedings-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T20:47:22Z","timestamp":1772657242000},"page":"1-16","source":"Crossref","is-referenced-by-count":2,"title":["The Memory Processing Unit: A Generalized Interface for End-to-End In-Memory Execution"],"prefix":"10.1109","author":[{"given":"Minh S. Q.","family":"Truong","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqiu","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dawei","family":"Xiong","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amol","family":"Shah","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Glass","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abraham","family":"Farrell","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James A.","family":"Bain","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"L. Richard","family":"Carley","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saugata","family":"Ghose","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Samsung SmartSSD"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.21"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2172\/2006312"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714956"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/2872887.2750385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2019.2907886"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196092"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196009"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317764"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304049"},{"key":"ref11","volume-title":"RACER Artifacts - GitHub Repository","author":"Research Group","year":"2021"},{"key":"ref12","volume-title":"MASTODON - GitHub Repository","author":"Research Group","year":"2026"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1968.229158"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TC.1982.1676015"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/irps45951.2020.9129313"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2717764.2717782"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1454115.1454128"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1086\/260062"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/nature08940"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173177"},{"key":"ref21","article-title":"CAPE: A ContentAddressable Processing Engine","author":"Caminal","year":"2021","journal-title":"in HPCA"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1002\/adma.201301940"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00083"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358328"},{"key":"ref25","article-title":"Challenges for Future Computing Systems","author":"Dally","year":"2015","journal-title":"keynote talk at HiPEAC"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527431"},{"key":"ref28","article-title":"Neural Cache: Bit-Serial InCache Acceleration of Deep Neural Networks","author":"Eckert","year":"2018","journal-title":"in ISCA"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/VLSI-SOC46417.2020.9344103"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1966.5273"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322257"},{"key":"ref32","article-title":"The Programmable Logic-in-Memory (PLiM) Computer","author":"Gaillardon","year":"2016","journal-title":"in DATE"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480078"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358260"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00066"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2934048"},{"key":"ref37","volume-title":"In-Place Associative Computing","author":"Technology"},{"key":"ref38","article-title":"Gemini \u00ae APU: Enabling High Performance Billion-Scale Similarity Search","author":"Technology","year":"2020","journal-title":"White Paper"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240811"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446749"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927083"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.7873\/date.2015.1136"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/STHERM.2010.5444290"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322237"},{"key":"ref46","journal-title":"Intel Xeon Gold 6544Y"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TVLSI.2017.2776954"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/JSSC.2016.2515510"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2015.7169194"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2021.3097700"},{"key":"ref51","article-title":"Quantifying the Cost of Data Movement in Scientific Applications","author":"Kestor","year":"2013","journal-title":"in IISWC"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.23919\/VLSICircuits52068.2021.9492362"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3622781.3674189"},{"key":"ref54","author":"Khan","year":"2024","journal-title":"The Landscape of Compute-Near-Memory and Compute-in-Memory: A Research and Commercial Overview"},{"key":"ref55","article-title":"Innovation With SmartSSD for Green Computing","author":"Ki","year":"2022","journal-title":"talk at SNIA PMCS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-10"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2014.2357292"},{"key":"ref58","article-title":"MemristorBased IMPLY Logic Design Procedure","author":"Kvatinsky","year":"2011","journal-title":"in ICCD"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tvlsi.2013.2282132"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42613.2021.9365862"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/12.599898"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-023-01010-1"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3533737.3535093"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tc.2024.3477981"},{"key":"ref65","article-title":"A 1ynm 1.25 V 8Gb, $16 \\text{Gb} \/ \\mathrm{s} \/$ Pin GDDR6-Based Accelerator-in-Memory Supporting 1TFLOPS MAC Operation and Various Activation Functions for Deep-Learning Applications","author":"Lee","year":"2022","journal-title":"in ISSCC"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.46506\/jica.2021.2.1.043"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1016\/j.mejo.2014.06.006"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744870"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123977"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/2897937.2898064"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS46596.2019.8965179"},{"key":"ref72","article-title":"SharedPIM: Enabling Concurrent Computation and Data Flow for Faster Processing-in-DRAM","author":"Mamdouh","year":"2024","journal-title":"arXiv:2408.15489 [cs.AR]"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3323476"},{"key":"ref74","volume-title":"cuBLAS: Basic Linear Algebra on ZVIDIA GPUs"},{"key":"ref75","volume-title":"GeForce RTX 4090"},{"key":"ref76","volume-title":"CUDA Toolkit Documentation: Profiler User\u2019s Guide","year":"2025"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3110993"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00024"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00060"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00069"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1038\/nature14441"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/1964218.1964225"},{"key":"ref83","volume-title":"HBM Processing in Memory"},{"key":"ref84","volume-title":"Samsung Electronics Develops SecondGeneration SmartSSD Computational Storage Drive With Upgraded Processing Functionality","year":"2022"},{"key":"ref85","volume-title":"The Structural Simulation Toolkit","author":"National Laboratories"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00081"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3124544"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/bs.adcom.2017.04.004"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/3579990.3580009"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.55"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btw753"},{"key":"ref93","volume-title":"Edlib","author":"\u0160o\u0161i\u0107","year":"2024"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-8379-3_8"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546754"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480071"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2022.3171765"},{"key":"ref99","volume-title":"Technology"},{"key":"ref100","article-title":"Attention Is All You Need","author":"Vaswani","year":"2017","journal-title":"in NIPS"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2015.7357122"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342278"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174244"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173167"}],"event":{"name":"2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)","location":"Sydney, Australia","start":{"date-parts":[[2026,1,31]]},"end":{"date-parts":[[2026,2,4]]}},"container-title":["2026 IEEE International Symposium on High Performance Computer Architecture (HPCA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11408404\/11408433\/11408599.pdf?arnumber=11408599","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T06:36:22Z","timestamp":1772692582000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408599\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":103,"URL":"https:\/\/doi.org\/10.1109\/hpca68181.2026.11408599","relation":{},"subject":[],"published":{"date-parts":[[2026,1,31]]}}}