{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T17:31:16Z","timestamp":1769794276238,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,6]]},"DOI":"10.1145\/3767110.3767133","type":"proceedings-article","created":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:36:01Z","timestamp":1769747761000},"page":"197-206","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Scalable Analytical Memory Modeling of AI Accelerators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2072-7060","authenticated-orcid":false,"given":"Md Azahar","family":"Alam","sequence":"first","affiliation":[{"name":"Computer Science and Engineering, The University of Toledo, Toledo, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4755-7821","authenticated-orcid":false,"given":"Nandakishore","family":"Santhi","sequence":"additional","affiliation":[{"name":"Los Alamos National Laboratory, Los Alamos, NM, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6295-3569","authenticated-orcid":false,"given":"Kishwar","family":"Ahmed","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, The University of Toledo, Toledo, OH, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3392717.3392761"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476221"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPCCC47392.2019.8958760"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422575.3422806"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Nathan Binkert Bradford Beckmann Gabriel Black Steven\u00a0K. Reinhardt Ali Saidi Arkaprava Basu Joel Hestness Derek\u00a0R. Hower Tushar Krishna Somayeh Sardashti Rathijit Sen Korey Sewell Muhammad Shoaib Nilay Vaish Mark\u00a0D. Hill and David\u00a0A. Wood. 2011. The gem5 simulator. SIGARCH Comput. Archit. News 39 2 (Aug. 2011) 1\u20137. doi:10.1145\/2024716.2024718","DOI":"10.1145\/2024716.2024718"},{"key":"e_1_3_3_2_7_2","volume-title":"An Analytical Model of Locality and Caching","author":"Brehob M.","year":"1999","unstructured":"M. Brehob and R. Enbody. 1999. An Analytical Model of Locality and Caching. Technical Report MSU-CSE-99-31. Michigan State University."},{"key":"e_1_3_3_2_8_2","first-page":"150","volume-title":"Proc. of the 17th ACM Int\u2019l Conf. on Supercomputing (ICS)","author":"Cascaval C.","year":"2003","unstructured":"C. Cascaval and D.\u00a0A. Padua. 2003. Estimating Cache Misses and Locality Using Stack Distances. In Proc. of the 17th ACM Int\u2019l Conf. on Supercomputing (ICS). 150\u2013159. doi:10.1145\/782814.782836"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/2541940.2541967"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.58"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2016.7418007"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"crossref","unstructured":"Chen Ding and Yutao Zhong. 2003. Predicting whole-program locality through reuse distance analysis. SIGPLAN Not. 38 5 (May 2003) 245\u2013257. doi:10.1145\/780822.781159","DOI":"10.1145\/780822.781159"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/781131.781159"},{"key":"e_1_3_3_2_14_2","first-page":"19","volume-title":"Proceedings of the International Conference on Parallel Architectures and Compilation Techniques (PACT)","author":"Eyerman Stijn","year":"2009","unstructured":"Stijn Eyerman and Lieven Eeckhout. 2009. Characterizing memory behavior of SPEC CPU benchmarks on Intel\u2019s Core microarchitecture. In Proceedings of the International Conference on Parallel Architectures and Compilation Techniques (PACT). 19\u201328."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2018.00039"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640379"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589350"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Norman\u00a0P. Jouppi Cliff Young Nishant Patil David Patterson Ganesh Agrawal Raminder Bajwa Sarah Bates Sushant Bhatia Nick Boden Andrew Borchers Richard Boyle Peter Cantin Chi Chao Chris Clark Jonathan Coriell Michael Daley Matt Dau Jeff Dean Bill Gelb Theodore\u00a0V. Ghaemmaghami Ravi Gottipati Will Gulland Robert Hagmann Russell\u00a0C. Ho David H\u00f6gberg Jie Hu Robert Hundt Donald Hurt Jay Ibarz Alistair Jaffey Alistair Jaworski Andreas Kaplan Hitesh Khaitan Alexander Koch Nagarajan Kumar Sean Lacy Justin Laudon John Law Donghyuk Le Callie Leary Zhewei Liu Kevin Lucke Andrew Lundin Greg MacKean Andrew Maggiore Michael Mahony Kaveh Miller Rajesh Nagarajan Rajesh Narayanaswami Rahul Ni Keenan Nix Thomas Norrie Michelle O\u2019Mernick Navin Penukonda Adrienne Phelps Jacqueline Ross Ali Salek Eshrat Samadiani Christopher Severn Gennady Sizikov Mark Snelham Jim Souter Daniel Steinberg Adam Swing Mike Tan Gary Thorson Bill Tian Howard Toma Emily Tuttle Vijay Vasudevan Richard Walter Will Wang Evan Wilcox and Dong\u00a0Hyuk Yoon. 2017. In\u2010datacenter performance analysis of a tensor processing unit. CoRR. Available: http:\/\/arxiv.org\/abs\/1704.04760.","DOI":"10.1145\/3140659.3080246"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"M. Kiani and A. Rajabzadeh. 2018. Efficient Cache Performance Modeling in GPUs Using Reuse Distance Analysis. ACM Trans. on Architecture and Code Optimization 15 4 (2018) 24. doi:10.1145\/3291051","DOI":"10.1145\/3291051"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Yoongu Kim Weikun Yang and Onur Mutlu. 2016. Ramulator: A Fast and Extensible DRAM Simulator. IEEE Comput. Archit. Lett. 15 1 (Jan. 2016) 45\u201349. doi:10.1109\/LCA.2015.2414456","DOI":"10.1109\/LCA.2015.2414456"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00033"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358252"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO61859.2024.00016"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/CICC53496.2022.9772870"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-01771-1"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"R.\u00a0L. Mattson J. Gecsei D.\u00a0R. Slutz and I.\u00a0L. Traiger. 1970. Evaluation Techniques for Storage Hierarchies. IBM Systems Journal 9 2 (1970) 78\u2013117. doi:10.1147\/sj.92.0078","DOI":"10.1147\/sj.92.0078"},{"key":"e_1_3_3_2_27_2","first-page":"217","volume-title":"IEEE Transactions on Parallel and Distributed Systems","author":"Mei Xinxin","year":"2019","unstructured":"Xinxin Mei, Xiaowen Chu, and Feng Liu. 2019. Demystifying GPU microarchitecture through microbenchmarking. In IEEE Transactions on Parallel and Distributed Systems , Vol.\u00a030. IEEE, 217\u2013230."},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC53511.2021.00028"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_3_2_30_2","unstructured":"Anurag Parashar Michael Rhu Anoop Mukkara Anthony Puglielli Radhika Venkatesan Brad Khailany Joel\u00a0S. Emer Stephen\u00a0W. Keckler and William\u00a0J. Dally. 2017. SCNN: An accelerator for compressed\u2010sparse convolutional neural networks. CoRR. Available: http:\/\/arxiv.org\/abs\/1708.04485."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"crossref","unstructured":"Paul Rosenfeld Elliott Cooper-Balis and Bruce Jacob. 2011. DRAMSim2: A Cycle Accurate Memory System Simulator. IEEE Comput. Archit. Lett. 10 1 (Jan. 2011) 16\u201319. doi:10.1109\/L-CA.2011.4","DOI":"10.1109\/L-CA.2011.4"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS48437.2020.00016"},{"key":"e_1_3_3_2_33_2","unstructured":"Ananda Samajdar Yuhao Zhu Paul Whatmough Matthew Mattina and Tushar Krishna. 2018. SCALE-Sim: Systolic CNN Accelerator Simulator. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1811.02883 (2018)."},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9891914"},{"key":"e_1_3_3_2_35_2","doi-asserted-by":"crossref","unstructured":"Guangyuan Sun Sungmin Kang and Seung-Won Jun. 2022. Burstz: Eliminating the Communication Bottleneck of Scientific Computing Accelerators via Accelerated Compression. ACM Transactions on Reconfigurable Technology and Systems (TRETS) 15 2 (2022) 1\u201334.","DOI":"10.1145\/3476831"},{"key":"e_1_3_3_2_36_2","volume-title":"Probability and Statistics for Engineers and Scientists (9th ed.)","author":"Walpole Ronald\u00a0E","year":"2012","unstructured":"Ronald\u00a0E Walpole, Raymond\u00a0H Myers, Sharon\u00a0L Myers, and Keying\u00a0E Ye. 2012. Probability and Statistics for Engineers and Scientists (9th ed.). Pearson."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00010"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2427631.2427632"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"e_1_3_3_2_40_2","unstructured":"Xilinx. 2018. Xilinx ML Suite. https:\/\/github.com\/Xilinx\/ml-suite. Accessed: 2025-06-18."},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"crossref","unstructured":"Lei Yang Ryan\u00a0M. Radway Yu-Hung Chen Ting-Fang Wu Hao Liu Emad Ansari Vivek Chandra Souvik Mitra and Emmanuel Beign\u00e9. 2022. Three-Dimensional Stacked Neural Network Accelerator Architectures for AR\/VR Applications. IEEE Micro 42 6 (2022) 116\u2013124.","DOI":"10.1109\/MM.2022.3202254"}],"event":{"name":"MemSys '25: International Symposium on Memory Systems","location":"Washington USA","acronym":"MemSys '25"},"container-title":["Proceedings of the International Symposium on Memory Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3767110.3767133","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T04:36:58Z","timestamp":1769747818000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3767110.3767133"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,6]]},"references-count":40,"alternative-id":["10.1145\/3767110.3767133","10.1145\/3767110"],"URL":"https:\/\/doi.org\/10.1145\/3767110.3767133","relation":{},"subject":[],"published":{"date-parts":[[2025,10,6]]},"assertion":[{"value":"2026-01-29","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}