{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T12:18:31Z","timestamp":1767183511235,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,23]],"date-time":"2024-06-23T00:00:00Z","timestamp":1719100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,23]]},"DOI":"10.1145\/3649329.3656239","type":"proceedings-article","created":{"date-parts":[[2024,11,7]],"date-time":"2024-11-07T19:27:22Z","timestamp":1731007642000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["ICGMM: CXL-enabled Memory Expansion with Intelligent Caching Using Gaussian Mixture Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1834-5612","authenticated-orcid":false,"given":"Hanqiu","family":"Chen","sequence":"first","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0212-6704","authenticated-orcid":false,"given":"Yitu","family":"Wang","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0580-5716","authenticated-orcid":false,"given":"Vitorio","family":"Cargnini","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, San Jose, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2608-7322","authenticated-orcid":false,"given":"Mohammadreza","family":"Soltaniyeh","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, San Jose, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3415-709X","authenticated-orcid":false,"given":"Dongyang","family":"Li","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, San Jose, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5420-1361","authenticated-orcid":false,"given":"Gongjin","family":"Sun","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, San Jose, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4281-9674","authenticated-orcid":false,"given":"Pradeep","family":"Subedi","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, San Jose, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1573-1377","authenticated-orcid":false,"given":"Andrew","family":"Chang","sequence":"additional","affiliation":[{"name":"Samsung Semiconductor, San Jose, CA, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1486-8412","authenticated-orcid":false,"given":"Yiran","family":"Chen","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2541-8767","authenticated-orcid":false,"given":"Cong","family":"Hao","sequence":"additional","affiliation":[{"name":"Georgia Institute of Technology, Atlanta, GA, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,11,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"RiseLab Medium Post","author":"Amir","year":"2021","unstructured":"Amir Gholami et al. Ai and memory wall. RiseLab Medium Post, 2021."},{"key":"e_1_3_2_1_2_1","volume-title":"NVIDIA Developer Blog","author":"Kharya Paresh","year":"2021","unstructured":"Paresh Kharya and Ali Alvi. Using deepspeed and megatron to train megatron-turing nlg 530b, the world's largest and most powerful generative language model. NVIDIA Developer Blog, 2021."},{"key":"e_1_3_2_1_3_1","volume-title":"CVPR","author":"Minxue","year":"2022","unstructured":"Minxue Tang et al. Fedcor: Correlation-based active client selection strategy for heterogeneous federated learning. In CVPR, 2022."},{"key":"e_1_3_2_1_4_1","volume-title":"ICCAD","author":"Yitu","year":"2021","unstructured":"Yitu Wang et al. Rerec: In-reram acceleration with access-aware mapping for personalized recommendation. In ICCAD, 2021."},{"key":"e_1_3_2_1_5_1","volume-title":"https:\/\/www.computeexpresslink.org\/","author":"Compute Express","year":"2022","unstructured":"Compute Express Link (CXL). https:\/\/www.computeexpresslink.org\/, 2022. Accessed: 2023-11-14."},{"key":"e_1_3_2_1_6_1","volume-title":"MICRO","author":"Sharma Debendra Das","year":"2022","unstructured":"Debendra Das Sharma. Compute express link (cxl): Enabling heterogeneous data-centric computing with heterogeneous memory hierarchy. MICRO, 2022."},{"key":"e_1_3_2_1_7_1","volume-title":"ASPLOS","author":"Huaicheng","year":"2023","unstructured":"Huaicheng Li et al. Pond: Cxl-based memory pooling systems for cloud platforms. In ASPLOS, 2023."},{"key":"e_1_3_2_1_8_1","volume":"202","author":"Yitu Wang","unstructured":"Yitu Wang et al. Ems-i: An efficient memory system design with specialized caching mechanism for recommendation inference. ACM Transactions on Embedded Computing Systems, 2023.","journal-title":"ACM Transactions on Embedded Computing Systems"},{"key":"e_1_3_2_1_9_1","volume":"14","author":"Shiyu Li","unstructured":"Shiyu Li et al. Ndrec: A near-data processing system for training large-scale recommendation models. IEEE Transactions on Computers, pages 1--14, 2024.","journal-title":"IEEE Transactions on Computers, pages 1--"},{"key":"e_1_3_2_1_10_1","volume-title":"USENIX ATC","author":"Shao-Peng","year":"2023","unstructured":"Shao-Peng Yang et al. Overcoming the memory wall with {CXL-Enabled}{SSDs}. In USENIX ATC, 2023."},{"key":"e_1_3_2_1_11_1","volume-title":"Operating systems: Three easy pieces","author":"Arpaci-Dusseau Remzi H","year":"2018","unstructured":"Remzi H Arpaci-Dusseau and Andrea C Arpaci-Dusseau. Operating systems: Three easy pieces. 2018."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/1089733.1089735"},{"key":"e_1_3_2_1_13_1","volume-title":"CISS","author":"Chen","year":"2018","unstructured":"Chen Zhong et al. A deep reinforcement learning-based framework for content caching. In CISS, 2018."},{"key":"e_1_3_2_1_14_1","volume-title":"MICRO","author":"Zhan","year":"2019","unstructured":"Zhan Shi et al. Applying deep learning to the cache replacement problem. In MICRO, 2019."},{"key":"e_1_3_2_1_15_1","volume-title":"ICML","author":"Evan","year":"2020","unstructured":"Evan Liu et al. An imitation learning approach for cache replacement. In ICML, 2020."},{"key":"e_1_3_2_1_16_1","volume-title":"FAST","author":"Juncheng","year":"2023","unstructured":"Juncheng Yang et al. {GL-Cache}: Group-level learning for efficient and high-performance caching. In FAST, 2023."},{"key":"e_1_3_2_1_17_1","volume-title":"CoRR","author":"Udit","year":"2019","unstructured":"Udit Gupta et al. The architectural implications of facebook's dnn-based personalized recommendation. CoRR, 2019."},{"key":"e_1_3_2_1_18_1","volume-title":"PACT","author":"Christian","year":"2008","unstructured":"Christian Bienia et al. The parsec benchmark suite: Characterization and architectural implications. In PACT, 2008."},{"key":"e_1_3_2_1_19_1","unstructured":"https:\/\/github.com\/akopytov\/sysbench 2023. Accessed: 2023-11-15."},{"key":"e_1_3_2_1_20_1","volume-title":"HotStorage","author":"Giuseppe","year":"2018","unstructured":"Giuseppe Vietri et al. Driving cache replacement with {ML-based}{LeCaR}. In HotStorage, 2018."},{"key":"e_1_3_2_1_21_1","volume-title":"Gaussian mixture models. Encyclopedia of biometrics","author":"Reynolds Douglas A","year":"2009","unstructured":"Douglas A Reynolds et al. Gaussian mixture models. Encyclopedia of biometrics, 2009."},{"key":"e_1_3_2_1_22_1","volume-title":"Smartssd: Fpga accelerated near-storage data analytics on ssd","author":"Lee Joo Hwan","year":"2020","unstructured":"Joo Hwan Lee et al. Smartssd: Fpga accelerated near-storage data analytics on ssd. 2020."},{"key":"e_1_3_2_1_23_1","unstructured":"John McCalpin. Stream: Sustainable memory bandwidth in high performance computers. http:\/\/www.cs.virginia.edu\/stream\/ 2006."},{"key":"e_1_3_2_1_24_1","unstructured":"memtier_benchmark 2023. Accessed: 2023-11-15."}],"event":{"name":"DAC '24: 61st ACM\/IEEE Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEEE-CEDA","SIGBED ACM Special Interest Group on Embedded Systems"],"location":"San Francisco CA USA","acronym":"DAC '24"},"container-title":["Proceedings of the 61st ACM\/IEEE Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656239","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3649329.3656239","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:55Z","timestamp":1750295875000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3649329.3656239"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,23]]},"references-count":24,"alternative-id":["10.1145\/3649329.3656239","10.1145\/3649329"],"URL":"https:\/\/doi.org\/10.1145\/3649329.3656239","relation":{},"subject":[],"published":{"date-parts":[[2024,6,23]]},"assertion":[{"value":"2024-11-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}