{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T23:39:30Z","timestamp":1793144370337,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["CNS-2339901, CNS-2312785"],"award-info":[{"award-number":["CNS-2339901, CNS-2312785"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3676641.3715987","type":"proceedings-article","created":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T16:47:32Z","timestamp":1743094052000},"page":"1203-1217","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":58,"title":["Systematic CXL Memory Characterization and Performance Analysis at Scale"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2490-5176","authenticated-orcid":false,"given":"Jinshu","family":"Liu","sequence":"first","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6160-425X","authenticated-orcid":false,"given":"Hamid","family":"Hadian","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5024-2065","authenticated-orcid":false,"given":"Yuyue","family":"Wang","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3911-1512","authenticated-orcid":false,"given":"Daniel S.","family":"Berger","sequence":"additional","affiliation":[{"name":"Microsoft and University of Washington, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7226-1598","authenticated-orcid":false,"given":"Marie","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Samsung, San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7120-7426","authenticated-orcid":false,"given":"Xun","family":"Jian","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9152-0321","authenticated-orcid":false,"given":"Sam H.","family":"Noh","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3155-0203","authenticated-orcid":false,"given":"Huaicheng","family":"Li","sequence":"additional","affiliation":[{"name":"Virginia Tech, Blacksburg, VA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"A Benchmark Suite for Cloud Services. https:\/\/github.com\/parsaepfl\/cloudsuite."},{"key":"e_1_3_2_1_2_1","unstructured":"Compute Express Link. https:\/\/www.computeexpresslink.org."},{"key":"e_1_3_2_1_3_1","unstructured":"CXL Memory eXpander Controller (MXC). https:\/\/www.montagetech.com\/MXC."},{"key":"e_1_3_2_1_4_1","unstructured":"CZ120 Memory Expansion Module. https:\/\/www.micron.com\/products\/memory\/cxl-memory."},{"key":"e_1_3_2_1_5_1","unstructured":"GPT-2. https:\/\/en.wikipedia.org\/wiki\/GPT-2."},{"key":"e_1_3_2_1_6_1","unstructured":"Intel Memory Latency Checker (Intel MLC). https:\/\/www.intel.co m\/content\/www\/us\/en\/download\/736633\/intel-memory-latencychecker-intel-mlc.html."},{"key":"e_1_3_2_1_7_1","unstructured":"JEDEC Memory Module Reference Base Standard - for Compute Express Link (CXL). https:\/\/www.jedec.org\/standards-documents\/docs\/jesd319."},{"key":"e_1_3_2_1_8_1","unstructured":"Leo CXL Smart Memory Controllers. https:\/\/www.asteralabs.com\/pro ducts\/leo\/leo-cxl-memory-connectivity-controllers\/."},{"key":"e_1_3_2_1_9_1","unstructured":"LLM Inference in C\/C. https:\/\/github.com\/ggerganov\/llama.cpp."},{"key":"e_1_3_2_1_10_1","unstructured":"PCIe 6.0 Will Run So Hot That It Needs Thermal Throttling. https: \/\/tinyurl.com\/pciegen6-2."},{"key":"e_1_3_2_1_11_1","unstructured":"PCIe 6.0's Thermal Throttling Plans Could Slam Brakes on Performance. https:\/\/tinyurl.com\/pciegen6-1."},{"key":"e_1_3_2_1_12_1","unstructured":"Phoronix. https:\/\/www.phoronix.com\/."},{"key":"e_1_3_2_1_13_1","unstructured":"Redis. https:\/\/redis.io."},{"key":"e_1_3_2_1_14_1","unstructured":"Reference Implementations of MLPerf Inference Benchmarks. https: \/\/github.com\/mlperf."},{"key":"e_1_3_2_1_15_1","unstructured":"Samsung Unveils CXL Memory Module Box: Up to 16 TB at 60 GB\/s. https:\/\/www.anandtech.com\/show\/21333\/samsung-unveils-cxlmemory-module-box-up-to-16-tb-at-60-gbs."},{"key":"e_1_3_2_1_16_1","unstructured":"Scoreboarding. https:\/\/en.wikipedia.org\/wiki\/Scoreboarding."},{"key":"e_1_3_2_1_17_1","unstructured":"SK hynix CXL 2.0 Memory Expansion Modules Launched with 96GB of DDR5. https:\/\/www.servethehome.com\/sk-hynix-cxl-2-0-memoryexpansion-modules-launched-with-96gb-of-ddr5\/."},{"key":"e_1_3_2_1_18_1","volume-title":"CPU 2017","author":"SPEC","year":"2017","unstructured":"SPEC CPU 2017. https:\/\/www.spec.org\/cpu2017."},{"key":"e_1_3_2_1_19_1","unstructured":"The PBBS Benchmark Suite (V2). https:\/\/cmuparlay.github.io\/pbbsbe nch\/."},{"key":"e_1_3_2_1_20_1","unstructured":"Top-down Microarchitecture Analysis Method. https:\/\/www.intel.co m\/content\/www\/us\/en\/docs\/vtune-profiler\/cookbook\/2023-0\/topdown-microarchitecture-analysis-method.html."},{"key":"e_1_3_2_1_21_1","unstructured":"VoltDB. https:\/\/www.voltdb.com."},{"key":"e_1_3_2_1_22_1","volume-title":"https:\/\/github.com\/sbeamer\/gapbs.git","author":"Benchmark Suite GAP","year":"2021","unstructured":"GAP Benchmark Suite. https:\/\/github.com\/sbeamer\/gapbs.git, 2021."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2023.3241586"},{"key":"e_1_3_2_1_24_1","volume-title":"Kai Li. The PARSEC Benchmark Suite: Characterization and Architectural Implications. In IEEE International Conference on Parallel Architectures and Compilation Techniques (PACT)","author":"Bienia Christian","year":"2008","unstructured":"Christian Bienia, Sanjeev Kumar, Jaswinder Pal Singh, and Kai Li. The PARSEC Benchmark Suite: Characterization and Architectural Implications. In IEEE International Conference on Parallel Architectures and Compilation Techniques (PACT), 2008."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/2896377.2901453"},{"key":"e_1_3_2_1_26_1","volume-title":"Thomas Willhalm. Quantifying the Performance Impact of Memory Latency and Bandwidth for Big Data Workloads. In IEEE International Symposium on Workload Characterization (IISWC)","author":"Clapp Russell","year":"2015","unstructured":"Russell Clapp, Martin Dimitrov, Karthik Kumar, Vish Viswanathan, and Thomas Willhalm. Quantifying the Performance Impact of Memory Latency and Bandwidth for Big Data Workloads. In IEEE International Symposium on Workload Characterization (IISWC), 2015."},{"key":"e_1_3_2_1_27_1","volume-title":"July","author":"Sharma Debendra Das","year":"2024","unstructured":"Debendra Das Sharma, Robert Blankenship, and Daniel Berger. An Introduction to the Compute Express Link (CXL) Interconnect. ACM Comput. Surv., 56(11), July 2024."},{"key":"e_1_3_2_1_28_1","volume-title":"Simulation and Application Profiling. In 57th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO-57)","author":"Esmaili-Dokht Pouya","year":"2024","unstructured":"Pouya Esmaili-Dokht, Francesco Sgherzi, Valeria Soldera Girelli, Isaac Boixaderas, Mariana Carmin, Alireza Momeni, Adria Armejach, Estanislao Mercadal, German Llort, Petar Radojkovic, Miquel Moreto, Judit Gimenez, Xavier Martorell, Eduard Ayguade, Jesus Labarta, Emanuele Confalonieri, Rishabh Dubey, and Jason Adlard. A Mess of Memory System Benchmarking, Simulation and Application Profiling. In 57th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO-57), 2024."},{"key":"e_1_3_2_1_29_1","volume-title":"Onur Mutlu. Demystifying Complex Workload-DRAM Interactions: An Experimental Study. In Proceedings of the 2019 ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS)","author":"Ghose Saugata","year":"2019","unstructured":"Saugata Ghose, Tianshi Li, Nastaran Hajinazar, Damla Senol Cali, and Onur Mutlu. Demystifying Complex Workload-DRAM Interactions: An Experimental Study. In Proceedings of the 2019 ACM International Conference on Measurement and Modeling of Computer Systems (SIGMETRICS), 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"Bo Huang. The HiBench Benchmark Suite: Characterization of the MapReduce-Based Data Analysis. In Proceedings of the 26th International Conference on Data Engineering (ICDE)","author":"Huang Shengsheng","year":"2010","unstructured":"Shengsheng Huang, Jie Huang, Jinquan Dai, Tao Xie, and Bo Huang. The HiBench Benchmark Suite: Characterization of the MapReduce-Based Data Analysis. In Proceedings of the 26th International Conference on Data Engineering (ICDE), 2010."},{"key":"e_1_3_2_1_31_1","volume-title":"DRAM, Disk","author":"Jacob Bruce","year":"2007","unstructured":"Bruce Jacob, Spencer Ng, and David Wang. Memory Systems: Cache, DRAM, Disk. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 2007."},{"key":"e_1_3_2_1_32_1","volume-title":"Young Ik Eom. Memtis: Efficient Memory Tiering with Dynamic Page Classification and Page Size Determination. In Proceedings of the 29th ACM Symposium on Operating Systems Principles (SOSP)","author":"Lee Taehyung","year":"2023","unstructured":"Taehyung Lee, Sumit Kumar Monga, Changwoo Min, and Young Ik Eom. Memtis: Efficient Memory Tiering with Dynamic Page Classification and Page Size Determination. In Proceedings of the 29th ACM Symposium on Operating Systems Principles (SOSP), 2023."},{"key":"e_1_3_2_1_33_1","volume-title":"Amy Tai. A Case Against CXL Memory Pooling. In The 22nd ACMWorkshop on Hot Topics in Networks (HotNets '23)","author":"Levis Philip","year":"2023","unstructured":"Philip Levis, Kun Lin, and Amy Tai. A Case Against CXL Memory Pooling. In The 22nd ACMWorkshop on Hot Topics in Networks (HotNets '23), 2023."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_2_1_35_1","volume-title":"Dissecting CXL Memory Performance at Scale: Analysis, Modeling, and Optimization. https:\/\/arxiv.org\/abs\/2409.14317","author":"Liu Jinshu","year":"2024","unstructured":"Jinshu Liu, Hamid Hadian, Hanchen Xu, Daniel S. Berger, and Huaicheng Li. Dissecting CXL Memory Performance at Scale: Analysis, Modeling, and Optimization. https:\/\/arxiv.org\/abs\/2409.14317, 2024."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"e_1_3_2_1_37_1","unstructured":"Vinicius Petrucci Eishan Mirakhur Nikesh Agarwal Su Wei Lim Vishal Tanna Rita Gupta and MaheshWagh. CXL Memory Expansion: A Closer Look on Actual Platform. https:\/\/www.micron.com\/conte nt\/dam\/micron\/global\/public\/products\/white-paper\/cxl-memoryexpansion-a-close-look-on-actual-platform.pdf."},{"key":"e_1_3_2_1_38_1","volume-title":"HW\/SW Co-Designed Interconnect Stack for Rack-Scale Memory Disaggregation. In 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO-53)","author":"Pinto Christian","year":"2020","unstructured":"Christian Pinto, Dimitris Syrivelis, Michele Gazzetti, Panos Koutsovasilis, Andrea Reale, Kostas Katrinis, and Peter Hofstee. Thymesis- Flow: A Software-Defined, HW\/SW Co-Designed Interconnect Stack for Rack-Scale Memory Disaggregation. In 53rd Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO-53), 2020."},{"key":"e_1_3_2_1_39_1","volume-title":"Shen and Cong Li. Runtime Estimation of Application Memory Latency for Performance Analysis and Optimization. In The International Symposium on Memory Systems (MEMSYS)","author":"Huanxing","year":"2020","unstructured":"Huanxing Shen and Cong Li. Runtime Estimation of Application Memory Latency for Performance Analysis and Optimization. In The International Symposium on Memory Systems (MEMSYS), 2020."},{"key":"e_1_3_2_1_40_1","volume-title":"Shiratake. Scaling and Performance Challenges of Future DRAM. In IEEE International Memory Workshop (IMW)","author":"Shigeru","year":"2020","unstructured":"Shigeru Shiratake. Scaling and Performance Challenges of Future DRAM. In IEEE International Memory Workshop (IMW), 2020."},{"key":"e_1_3_2_1_41_1","volume-title":"Nam Sung Kim. Demystifying CXL Memory with Genuine CXL-Ready Systems and Devices. In 56th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO-56)","author":"Sun Yan","year":"2023","unstructured":"Yan Sun, Yifan Yuan, Zeduo Yu, Zeduo Yu, Reese Kuper, Chihun Song, Jinghan Huang, Houxiang Ji, Siddharth Agarwal, Jiaqi Lou, Ipoom Jeong, Ren Wang, Jung Ho Ahn, Tianyin Xu, and Nam Sung Kim. Demystifying CXL Memory with Genuine CXL-Ready Systems and Devices. In 56th Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO-56), 2023."},{"key":"e_1_3_2_1_42_1","volume-title":"Jianjun Chen. Exploring Performance and Cost Optimization with ASIC-Based CXL Memory. In Proceedings of the 2024 EuroSys Conference (EuroSys)","author":"Tang Yupeng","year":"2024","unstructured":"Yupeng Tang, Ping Zhou, Wenhui Zhang, Henry Hu, Qirui Yang, Hao Xiang, Tongping Liu, Jiaxin Shan, Ruoyun Huang, Cheng Zhao, Cheng Chen, Hui Zhang, Fei Liu, Shuai Zhang, Xiaoning Ding, and Jianjun Chen. Exploring Performance and Cost Optimization with ASIC-Based CXL Memory. In Proceedings of the 2024 EuroSys Conference (EuroSys), 2024."},{"key":"e_1_3_2_1_43_1","volume-title":"Ivy Peng. A Quantitative Approach for Adopting Disaggregated Memory in HPC Systems. In Proceedings of International Conference on High Performance Computing, Networking, Storage and Analysis (SC)","author":"Wahlgren Jacob","year":"2023","unstructured":"Jacob Wahlgren, Gabin Schieffer, Maya Gokhale, and Ivy Peng. A Quantitative Approach for Adopting Disaggregated Memory in HPC Systems. In Proceedings of International Conference on High Performance Computing, Networking, Storage and Analysis (SC), 2023."},{"key":"e_1_3_2_1_44_1","volume-title":"Akshitha Sriraman. Designing Cloud Servers for Lower Carbon. In Proceedings of the 51st Annual International Symposium on Computer Architecture (ISCA)","author":"Wang Jaylen","year":"2024","unstructured":"Jaylen Wang, Daniel S. Berger, Fiodar Kazhamiaka, Celine Irvene, Chaojie Zhang, Esha Choukse, Kali Frost, Rodrigo Fonseca, Brijesh Warrier, Chetan Bansal, Jonathan Stern, Ricardo Bianchini, and Akshitha Sriraman. Designing Cloud Servers for Lower Carbon. In Proceedings of the 51st Annual International Symposium on Computer Architecture (ISCA), 2024."},{"key":"e_1_3_2_1_45_1","volume-title":"Yasin. A Top-Down Method for Performance Analysis and Counters Architecture. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS)","author":"Ahmad","year":"2014","unstructured":"Ahmad Yasin. A Top-Down Method for Performance Analysis and Counters Architecture. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2014."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC50251.2020.00019"},{"key":"e_1_3_2_1_47_1","volume-title":"Asaf Cidon. Managing Memory Tiers with CXL in Virtualized Environments. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI)","author":"Zhong Yuhong","year":"2024","unstructured":"Yuhong Zhong, Daniel S. Berger, Carl Waldspurger, Ryan Wee, Ishwar Agarwal, Rajat Agarwal, Frank Hady, Karthik Kumar, Mark D. Hill, Mosharaf Chowdhury, and Asaf Cidon. Managing Memory Tiers with CXL in Virtualized Environments. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI), 2024."}],"event":{"name":"ASPLOS '25: 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Rotterdam Netherlands","acronym":"ASPLOS '25","sponsor":["SIGPLAN ACM Special Interest Group on Programming Languages","SIGOPS ACM Special Interest Group on Operating Systems","SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 30th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3715987","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3676641.3715987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:13:25Z","timestamp":1755774805000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3676641.3715987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":47,"alternative-id":["10.1145\/3676641.3715987","10.1145\/3676641"],"URL":"https:\/\/doi.org\/10.1145\/3676641.3715987","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}