{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:34:42Z","timestamp":1768030482002,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":75,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"US Army Research Office","award":["W911NF22C0082"],"award-info":[{"award-number":["W911NF22C0082"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1907863"],"award-info":[{"award-number":["CNS-1907863"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,9,30]]},"DOI":"10.1145\/3695794.3695801","type":"proceedings-article","created":{"date-parts":[[2024,12,12]],"date-time":"2024-12-12T04:06:53Z","timestamp":1733976413000},"page":"61-77","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["UpDown: A Novel Architecture for Unlimited Memory Parallelism"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-1600-1459","authenticated-orcid":false,"given":"Andronicus","family":"Rajasukumar","sequence":"first","affiliation":[{"name":"University of Chicago, Chicago, IL, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7469-6130","authenticated-orcid":false,"given":"Tianchi","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7269-9155","authenticated-orcid":false,"given":"Ruiqi","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1204-206X","authenticated-orcid":false,"given":"Andrew A.","family":"Chien","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, IL, United States and Argonne National Laboratory, Lemont, IL, USA"}]}],"member":"320","published-online":{"date-parts":[[2024,12,11]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"[n. d.]. Synopsys teaching resources. https:\/\/www.synopsys.com\/community\/university-program\/teaching-resources.html."},{"key":"e_1_3_3_2_3_2","unstructured":"2022. AGILE: ADVANCED GRAPHIC INTELLIGENCE LOGICAL COMPUTING ENVIRONMENT Program. https:\/\/www.iarpa.gov\/research-programs\/agile."},{"key":"e_1_3_3_2_4_2","unstructured":"2023. NVIDIA H100 Tensor Core GPU Architecture. NVIDIA (2023). https:\/\/resources.nvidia.com\/en-us-tensor-core"},{"key":"e_1_3_3_2_5_2","unstructured":"2024. Intel\u00ae 64 and IA-32 Architectures Optimization Reference Manual Volume 1. Intel (2024). https:\/\/cdrdv2.intel.com\/v1\/dl\/getContent\/671488"},{"key":"e_1_3_3_2_6_2","unstructured":"Sriram Aananthakrishnan Nesreen\u00a0K. Ahmed Vincent Cave Marcelo Cintra Yigit Demir Kristof\u00a0Du Bois Stijn Eyerman Joshua\u00a0B. Fryman Ivan Ganev Wim Heirman Hans-Christian Hoppe Jason Howard Ibrahim Hur MidhunChandra Kodiyath Samkit Jain Daniel\u00a0S. Klowden Marek\u00a0M. Landowski Laurent Montigny Ankit More Przemyslaw Ossowski Robert Pawlowski Nick Pepperling Fabrizio Petrini Mariusz Sikora Balasubramanian Seshasayee Shaden Smith Sebastian Szkoda Sanjaya Tayal Jesmin\u00a0Jahan Tithi Yves Vandriessche and Izajasz\u00a0P. Wrosz. 2020. PIUMA: Programmable Integrated Unified Memory Architecture. http:\/\/arxiv.org\/abs\/2010.06277 arXiv:https:\/\/arXiv.org\/abs\/2010.06277 [cs]."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/77726.255132"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/77726.255132"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/DODUGC.2003.1253421"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/325164.325116"},{"key":"e_1_3_3_2_11_2","unstructured":"David Brooks. 2018. What\u2019s the future of technology scaling?https:\/\/www.sigarch.org\/whats-the-future-of-technology-scaling\/"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Tien-Fu Chen and Jean-Loup Baer. 1995. Effective hardware-based data prefetching for high-performance processors. IEEE Trans. Comput. 44 5 (1995) 609\u2013623. 10.1109\/12.381947 https:\/\/dl.acm.org\/doi\/10.1109\/12.381947","DOI":"10.1109\/12.381947"},{"key":"e_1_3_3_2_13_2","unstructured":"George\u00a0Cozma Chester\u00a0Lam. 2022. AMD\u2019s Zen 4 Part 2: Memory Subsystem and Conclusion. Chips and Cheese (November 2022). https:\/\/chipsandcheese.com\/2022\/11\/08\/amds-zen-4-part-2-memory-subsystem-and-conclusion\/"},{"key":"e_1_3_3_2_14_2","unstructured":"Daniel Chiang. 2024. SK Hynix to reveal 16-layer HBM3E to main the lead. DigiTimesAsia (February 2024). https:\/\/www.digitimes.com\/news\/a20240222PD215\/sk-hynix-hbm-dram-2024-production.html"},{"key":"e_1_3_3_2_15_2","volume-title":"UpDown Accelerator Instruction Set Architecture (ISA) v2.4","author":"Chien Andrew","year":"2024","unstructured":"Andrew Chien, Andronicus Rajasukumar, Marziyeh Nourian, Yuqing Wang, Tianshuo Su, Chen Zou, and Yuanwei Fang. 2024. UpDown Accelerator Instruction Set Architecture (ISA) v2.4. Technical Report TR-2024-03. University of Chicago. https:\/\/newtraell.cs.uchicago.edu\/research\/publications\/techreports\/TR-2024-03"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/30350.30372"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830809"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123983"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/191995.192029"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/1062261.1062268"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"crossref","unstructured":"John\u00a0WC Fu Janak\u00a0H Patel and Bob\u00a0L Janssens. 1992. Stride directed prefetching in scalar processors. ACM SIGMICRO Newsletter 23 1-2 (1992) 102\u2013110.","DOI":"10.1145\/144965.145006"},{"key":"e_1_3_3_2_22_2","unstructured":"Chester\u00a0Lam George\u00a0Cozma. 2022. Graviton 3: First Impressions. Chips and Cheese (May 2022). https:\/\/chipsandcheese.com\/2022\/05\/29\/graviton-3-first-impressions\/"},{"key":"e_1_3_3_2_23_2","unstructured":"Kourosh Gharachorloo. [n. d.]. MEMORY CONSISTENCY MODELS FOR SHARED-MEMORY MULTIPROCESSORS. ([n. d.])."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Kourosh Gharachorloo Anoop Gupta and John Hennessy. 1992. Hiding memory latency using dynamic scheduling in shared-memory multiprocessors. ACM SIGARCH Computer Architecture News 20 2 (May 1992) 22\u201333. 10.1145\/146628.139678https:\/\/dl.acm.org\/doi\/10.1145\/146628.139678","DOI":"10.1145\/146628.139678"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Karl-Erwin Grosspietsch. 1992. Associative processors and memories: A survey. IEEE Micro 12 3 (1992) 12\u201319.","DOI":"10.1109\/40.141599"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830800"},{"key":"e_1_3_3_2_27_2","volume-title":"Computer Architecture: A Quantitative Approach (5 ed.)","author":"Hennessy John\u00a0L.","year":"2012","unstructured":"John\u00a0L. Hennessy and David\u00a0A. Patterson. 2012. Computer Architecture: A Quantitative Approach (5 ed.). Morgan Kaufmann, Amsterdam."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183549"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2003.1183549"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/1006209.1006211"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/IMW.2017.7939084"},{"key":"e_1_3_3_2_32_2","unstructured":"Jack Kang. 2017. SiFive U54-MC Coreplex: Multicore 64-bit Application Processor class RISC-V CPU. https:\/\/static.dev.sifive.com\/slides\/SiFive-U54-MC.pdf"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/285930.285979"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3626183.3659975"},{"key":"e_1_3_3_2_35_2","unstructured":"Chester Lam. 2021. Popping the Hood on Golden Cove. Chips and Cheese (December 2021). https:\/\/chipsandcheese.com\/2021\/12\/02\/popping-the-hood-on-golden-cove\/"},{"key":"e_1_3_3_2_36_2","unstructured":"Chester Lam. 2022. Sunny Cove: Intel\u2019s Lost Generation. Chips and Cheese (June 2022). https:\/\/chipsandcheese.com\/2022\/06\/07\/sunny-cove-intels-lost-generation\/"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","unstructured":"Jaekyu Lee Hyesoon Kim and Richard Vuduc. 2012. When Prefetching Works When It Doesn\u2019t and Why. ACM Trans. Archit. Code Optim. 9 1 Article 2 (mar 2012) 29\u00a0pages. 10.1145\/2133382.2133384https:\/\/dl.acm.org\/doi\/10.1145\/2133382.2133384","DOI":"10.1145\/2133382.2133384"},{"key":"e_1_3_3_2_38_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 https:\/\/dl.acm.org\/doi\/10.1109\/LCA.2020.2973991","DOI":"10.1109\/LCA.2020.2973991"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","unstructured":"John D.\u00a0C. Little. 1961. A Proof for the Queuing Formula: L = \u03bb W. Oper. Res. 9 3 (jun 1961) 383\u2013387. 10.1287\/opre.9.3.383 https:\/\/dl.acm.org\/doi\/10.1287\/opre.9.3.383","DOI":"10.1287\/opre.9.3.383"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2008.15"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","unstructured":"Jason Lowe-Power Abdul\u00a0Mutaal Ahmad Ayaz Akram Mohammad Alian Rico Amslinger Matteo Andreozzi Adri\u00e0 Armejach Nils Asmussen Brad Beckmann Srikant Bharadwaj Gabe Black Gedare Bloom Bobby\u00a0R. Bruce Daniel\u00a0Rodrigues Carvalho Jeronimo Castrillon Lizhong Chen Nicolas Derumigny Stephan Diestelhorst Wendy Elsasser Carlos Escuin Marjan Fariborz Amin Farmahini-Farahani Pouya Fotouhi Ryan Gambord Jayneel Gandhi Dibakar Gope Thomas Grass Anthony Gutierrez Bagus Hanindhito Andreas Hansson Swapnil Haria Austin Harris Timothy Hayes Adrian Herrera Matthew Horsnell Syed Ali\u00a0Raza Jafri Radhika Jagtap Hanhwi Jang Reiley Jeyapaul Timothy\u00a0M. Jones Matthias Jung Subash Kannoth Hamidreza Khaleghzadeh Yuetsu Kodama Tushar Krishna Tommaso Marinelli Christian Menard Andrea Mondelli Miquel Moreto Tiago M\u00fcck Omar Naji Krishnendra Nathella Hoa Nguyen Nikos Nikoleris Lena\u00a0E. Olson Marc Orr Binh Pham Pablo Prieto Trivikram Reddy Alec Roelke Mahyar Samani Andreas Sandberg Javier Setoain Boris Shingarov Matthew\u00a0D. Sinclair Tuan Ta Rahul Thakur Giacomo Travaglini Michael Upton Nilay Vaish Ilias Vougioukas William Wang Zhengrong Wang Norbert Wehn Christian Weis David\u00a0A. Wood Hongil Yoon and \u00c9der\u00a0F. Zulian. 2020. The gem5 Simulator: Version 20.0+. 10.48550\/arXiv.2007.03152arXiv:https:\/\/arXiv.org\/abs\/2007.03152 [cs].","DOI":"10.48550\/arXiv.2007.03152"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2008.4541126"},{"key":"e_1_3_3_2_43_2","volume-title":"STREAM: Sustainable Memory Bandwidth in High Performance Computers","author":"McCalpin John\u00a0D.","year":"1991","unstructured":"John\u00a0D. McCalpin. 1991-2007. STREAM: Sustainable Memory Bandwidth in High Performance Computers. Technical Report. University of Virginia, Charlottesville, Virginia. http:\/\/www.cs.virginia.edu\/stream\/ A continually updated technical report. http:\/\/www.cs.virginia.edu\/stream\/."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-40843-4_30"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS.2009.5161108"},{"key":"e_1_3_3_2_46_2","unstructured":"Hassan Mujtaba. 2022. Intel Sapphire Rapids \u20184th Gen Xeon\u2019 CPU Delidded By Der8auer Unveils Extreme Core Count Die With 56 Golden Cove Cores. WCCFTech (January 2022). https:\/\/wccf.tech\/189cd"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00010"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/165123.165158"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527400"},{"key":"e_1_3_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/RAICS51191.2020.9332500"},{"key":"e_1_3_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2011.7477494"},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"publisher","unstructured":"Steven\u00a0A. Przybylski. 1990. Cache and memory hierarchy design. (1 1990). 10.1016\/B978-0-08-050059-1.50006-2","DOI":"10.1016\/B978-0-08-050059-1.50006-2"},{"key":"e_1_3_3_2_53_2","unstructured":"Andronicus Rajasukumar Jiya Su Yuqing Wang Tianshuo Su Marziyeh Nourian Jose M\u00a0Monsalve Diaz Tianchi Zhang Jianru Ding Wenyi Wang Ziyi Zhang Moubarak Jeje Henry Hoffmann Yanjing Li and Andrew\u00a0A. Chien. 2024. UpDown: Programmable fine-grained Events for Scalable Performance on Irregular Applications. arxiv:https:\/\/arXiv.org\/abs\/2407.20773\u00a0[cs.AR] https:\/\/arxiv.org\/abs\/2407.20773"},{"key":"e_1_3_3_2_54_2","unstructured":"Cliff Robinson. 2021. AMD Zen 3 at Hot Chips 33. https:\/\/www.servethehome.com\/amd-zen-3-at-hot-chips-33\/"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527379"},{"key":"e_1_3_3_2_56_2","doi-asserted-by":"publisher","unstructured":"Peter Sewell Susmit Sarkar Scott Owens Francesco\u00a0Zappa Nardelli and Magnus\u00a0O. Myreen. 2010. x86-TSO: a rigorous and usable programmer\u2019s model for x86 multiprocessors. Commun. ACM 53 7 (July 2010) 89\u201397. 10.1145\/1785414.1785443https:\/\/dl.acm.org\/doi\/10.1145\/1785414.1785443","DOI":"10.1145\/1785414.1785443"},{"key":"e_1_3_3_2_57_2","unstructured":"Anton Shilov. 2023. Micron Publishes Updated DRAM Roadmap: 32 Gb DDR5 DRAMs GDDR7 HBMNext. AnandTech (July 2023). https:\/\/www.anandtech.com\/show\/18982\/micron-publishes-updated-dram-roadmap-32-gb-ddr5-drams-gddr7-hbmnext"},{"key":"e_1_3_3_2_58_2","unstructured":"Anton Shilov. 2023. Micron Unveils HBM3 Gen2 Memory: 1.2 TB\/sec Memory Stacks For HPC and AI Processors. AnandTech (July 2023). https:\/\/www.anandtech.com\/show\/18981\/micron-unveils-hbm3-gen2-12-tbs-per-stack-at-92-gts-speed"},{"key":"e_1_3_3_2_59_2","unstructured":"Siarhei Siamashka. 2017. tinymembench. https:\/\/github.com\/ssvb\/tinymembench."},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"publisher","unstructured":"J.E. Smith and A.R. Pleszkun. 1988. Implementing precise interrupts in pipelined processors. IEEE Trans. Comput. 37 5 (1988) 562\u2013573. 10.1109\/12.4607 https:\/\/dl.acm.org\/doi\/10.1109\/12.4607","DOI":"10.1109\/12.4607"},{"key":"e_1_3_3_2_61_2","doi-asserted-by":"crossref","unstructured":"James\u00a0E Smith. 1982. Decoupled access\/execute computer architectures. ACM SIGARCH Computer Architecture News 10 3 (1982) 112\u2013119.","DOI":"10.1145\/1067649.801719"},{"key":"e_1_3_3_2_62_2","unstructured":"Ryan Smith. 2023. AMD: EPYC \"Genoa-X\" CPUs With 1.1GB of L3 Cache Now Available. AnandTech (June 2023). https:\/\/www.anandtech.com\/show\/18914\/amd-epyc-genoax-cpus-with-11gb-of-l3-cache-shipping-now"},{"key":"e_1_3_3_2_63_2","unstructured":"Ryan Smith. 2024. NVIDIA Blackwell Architecture and B200\/B100 Accelerators Announced: Going Bigger With Smaller Data. AnandTech (March 2024). https:\/\/www.anandtech.com\/show\/21310\/nvidia-blackwell-architecture-and-b200b100-accelerators-announced-going-bigger-with-smaller-data"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.5555\/266800.266804"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"publisher","unstructured":"Aaron Stillmaker and Bevan Baas. 2017. Scaling equations for the accurate prediction of CMOS device performance from 180nm to 7nm. Integration 58 (2017) 74\u201381. 10.1016\/j.vlsi.2017.02.002","DOI":"10.1016\/j.vlsi.2017.02.002"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","unstructured":"Aaron Stillmaker and Bevan Baas. 2019. Corrigendum to \u201cScaling Equations for the Accurate Prediction of CMOS Device Performance from 180nm to 7nm\u201d [Integr. VLSI J. 58 (2017) 74\u201381]. Integr. VLSI J. 67 C (jul 2019) 170. 10.1016\/j.vlsi.2019.04.006 https:\/\/dl.acm.org\/doi\/10.1016\/j.vlsi.2019.04.006","DOI":"10.1016\/j.vlsi.2019.04.006"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"publisher","unstructured":"M.B. Taylor J. Kim J. Miller D. Wentzlaff F. Ghodrat B. Greenwald H. Hoffman P. Johnson Jae-Wook Lee W. Lee A. Ma A. Saraf M. Seneski N. Shnidman V. Strumpen M. Frank S. Amarasinghe and A. Agarwal. 2002. The Raw microprocessor: a computational fabric for software circuits and general-purpose programs. IEEE Micro 22 2 (2002) 25\u201335. 10.1109\/MM.2002.997877 https:\/\/dl.acm.org\/doi\/10.1109\/MM.2002.997877","DOI":"10.1109\/MM.2002.997877"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASIC.2001.954697"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","unstructured":"R.\u00a0M. Tomasulo. 1967. An Efficient Algorithm for Exploiting Multiple Arithmetic Units. IBM Journal of Research and Development 11 1 (1967) 25\u201333. 10.1147\/rd.111.0025 https:\/\/dl.acm.org\/doi\/10.1147\/rd.111.0025","DOI":"10.1147\/rd.111.0025"},{"key":"e_1_3_3_2_70_2","volume-title":"Procs. of the 23rd International Symposium on Computer Architecture","author":"VanderWiel Steve","year":"1996","unstructured":"Steve VanderWiel and David\u00a0J Lilja. 1996. A survey of data prefetching techniques. In Procs. of the 23rd International Symposium on Computer Architecture. Citeseer."},{"key":"e_1_3_3_2_71_2","unstructured":"Krishnaswamy Viswanathan. 2024. Intel\u00ae memory latency Checker v3.11. https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/articles\/tool\/intelr-memory-latency-checker.html"},{"key":"e_1_3_3_2_72_2","unstructured":"Luming Wang Xu Zhang Songyue Wang Zhuolun Jiang Tianyue Lu Mingyu Chen Siwei Luo and Keji Huang. 2024. Asynchronous Memory Access Unit: Exploiting Massive Parallelism for Far Memory Access. http:\/\/arxiv.org\/abs\/2404.11044 arXiv:https:\/\/arXiv.org\/abs\/2404.11044 [cs]."},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322229"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/2830772.2830807"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173197"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1997.621492"}],"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\/3695794.3695801","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695794.3695801","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695794.3695801","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\/3695794.3695801"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"references-count":75,"alternative-id":["10.1145\/3695794.3695801","10.1145\/3695794"],"URL":"https:\/\/doi.org\/10.1145\/3695794.3695801","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"}}]}}