{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T12:48:40Z","timestamp":1777121320150,"version":"3.51.4"},"reference-count":91,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Syst."],"published-print":{"date-parts":[[2026,5,31]]},"abstract":"<jats:p>\n                    Advances in memory technologies (\n                    <jats:italic toggle=\"yes\">e<\/jats:italic>\n                    .\n                    <jats:italic toggle=\"yes\">g<\/jats:italic>\n                    ., HBM, DRAM, NVM) and interconnects (\n                    <jats:italic toggle=\"yes\">e<\/jats:italic>\n                    .\n                    <jats:italic toggle=\"yes\">g<\/jats:italic>\n                    ., CXL) have significantly enhanced the flexibility of utilizing memory resources in modern computer systems. As this trend continues, memory resources are poised to become fully composable in the near future. This increasing flexibility also accelerates the demand for effective tiered memory systems capable of performing well across diverse scenarios and workloads. However, the effectiveness of existing tiered memory systems heavily depends on system configuration (e.g., the ratio of fast tier to capacity tier), memory access patterns, and page sizes (base vs. huge). Their reliance on simple heuristics and static thresholds for detecting page hotness, and limited consideration of page sizes, results in suboptimal (often pathological) page placement decisions. To build a robust and effective system, tiered memory management must holistically account for overall memory access patterns in conjunction with the tiering environment.\n                  <\/jats:p>\n                  <jats:p>\n                    We present\n                    <jats:sc>Memtis<\/jats:sc>\n                    , a tiered memory system that adopts informed decision-making for page placement and page size determination.\n                    <jats:sc>Memtis<\/jats:sc>\n                    leverages access distribution of allocated pages to optimally approximate the hot data set to the fast tier capacity. Moreover,\n                    <jats:sc>Memtis<\/jats:sc>\n                    dynamically determines the page size that allows applications to use huge pages while avoiding their drawbacks by detecting inefficient use of fast tier memory and splintering them if necessary. To further enhance its practicality across diverse scenarios,\n                    <jats:sc>Memtis<\/jats:sc>\n                    effectively supports the dynamic allocation of fast tier memory if there is a specific performance requirement, such as a target hit ratio. Our evaluation shows that\n                    <jats:sc>Memtis<\/jats:sc>\n                    outperforms existing tiered memory systems under various workloads and tiering configurations by up to 169.0%, showing its robustness.\n                  <\/jats:p>","DOI":"10.1145\/3777549","type":"journal-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T11:37:52Z","timestamp":1763811472000},"page":"1-35","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Harnessing Page Access Frequency Distribution for Efficient Memory Tiering"],"prefix":"10.1145","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6935-9981","authenticated-orcid":false,"given":"Taehyung","family":"Lee","sequence":"first","affiliation":[{"name":"Sungkyunkwan University - Natural Sciences Campus","place":["Suwon-si, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8622-8628","authenticated-orcid":false,"given":"Sumit","family":"Monga","sequence":"additional","affiliation":[{"name":"Virginia Tech","place":["Blacksburg, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6141-8054","authenticated-orcid":false,"given":"Young Ik","family":"Eom","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University - Suwon Campus","place":["Suwon, Korea (the Republic of)"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6225-5357","authenticated-orcid":false,"given":"Changwoo","family":"Min","sequence":"additional","affiliation":[{"name":"Igalia","place":["A Coru\u00f1a, Spain"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,24]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Reto Achermann and Ashish Panwar. 2019. Mitosis workload BTree. Retrieved 13 September from https:\/\/github.com\/mitosis-project\/mitosis-workload-btree"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378468"},{"issue":"1","key":"e_1_3_2_4_2","first-page":"143","article-title":"Zipf\u2019s law and the internet.","volume":"3","author":"Adamic Lada A.","year":"2002","unstructured":"Lada A. Adamic and Bernardo A. Huberman. 2002. Zipf\u2019s law and the internet. Glottometrics 3, 1 (2002), 143\u2013150.","journal-title":"Glottometrics"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037706"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00050"},{"key":"e_1_3_2_7_2","unstructured":"Anandtech. 2018. Intel Launches Optane DIMMs Up To 512GB: Apache Pass Is Here! Retrieved from https:\/\/www.anandtech.com\/show\/12828\/intel-launches-optane-dimms-up-to-512gb-apache-pass-is-here"},{"key":"e_1_3_2_8_2","first-page":"1","article-title":"Pareto distribution","author":"Arnold Barry C.","year":"2014","unstructured":"Barry C. Arnold. 2014. Pareto distribution. Wiley StatsRef: Statistics Reference Online (2014), 1\u201310.","journal-title":"Wiley StatsRef: Statistics Reference Online"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3123939.3123975"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414630"},{"key":"e_1_3_2_11_2","unstructured":"Piotr Balcer. 2022. Disaggregated Memory - In Pursuit of Scale and Efficiency. Retrieved 13 September from https:\/\/pmem.io\/blog\/2022\/01\/disaggregated-memory-in-pursuit-of-scale-and-efficiency\/"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2485922.2485943"},{"key":"e_1_3_2_13_2","unstructured":"Scott Beamer Krste Asanovic and David A. Patterson. 2015. The GAP benchmark suite. arXiv:1508.03619. Retrieved from https:\/\/arxiv.org\/abs\/1508.03619"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3409964.3461814"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3520263.3534650"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS49936.2021.00011"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.63"},{"key":"e_1_3_2_18_2","unstructured":"CXL Consortium. 2022. Compute Express Link Specification 3.0. Retrieved 13 September from https:\/\/www.computeexpresslink.org\/download-the-specification"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/1807128.1807152"},{"key":"e_1_3_2_20_2","unstructured":"Jonathan Corbet. 2022. CXL 1: Management and tiering. Retrieved 13 September from https:\/\/lwn.net\/Articles\/894598\/"},{"key":"e_1_3_2_21_2","unstructured":"Standard Performance Evaluation Corporation. 2022. SPEC CPU 2017. Retrieved 13 September from https:\/\/www.spec.org\/cpu2017\/"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/2901318.2901344"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582031"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.5555\/2643634.2643659"},{"key":"e_1_3_2_25_2","unstructured":"Alessandro Goncalves. 2022. Make Sense of Memory Tiering. Retrieved 13 September from https:\/\/www.snia.org\/educational-library\/make-sense-memory-tiering-2022"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582021"},{"key":"e_1_3_2_27_2","first-page":"733","volume-title":"Proceedings of the 2017 USENIX Annual Technical Conference","author":"Guo Fan","year":"2017","unstructured":"Fan Guo, Yongkun Li, Yinlong Xu, Song Jiang, and John C. S. Lui. 2017. SmartMD: A high performance deduplication engine with mixed pages. In Proceedings of the 2017 USENIX Annual Technical Conference. 733\u2013744. Retrieved from https:\/\/www.usenix.org\/conference\/atc17\/technical-sessions\/presentation\/guo-fan"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/2731186.2731191"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2020.3036686"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378465"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080245"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446745"},{"key":"e_1_3_2_33_2","first-page":"715","volume-title":"Proceedings of the 2021 USENIX Annual Technical Conference","author":"Kim Jonghyeon","year":"2021","unstructured":"Jonghyeon Kim, Wonkyo Choe, and Jeongseob Ahn. 2021. Exploring the design space of page management for multi-tiered memory systems. In Proceedings of the 2021 USENIX Annual Technical Conference. 715\u2013728. Retrieved from https:\/\/www.usenix.org\/conference\/atc21\/presentation\/kim-jonghyeon"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2019.00012"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357543"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2018.00050"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459898.3463907"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772751"},{"key":"e_1_3_2_39_2","first-page":"705","volume-title":"Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation","author":"Kwon Youngjin","year":"2016","unstructured":"Youngjin Kwon, Hangchen Yu, Simon Peter, Christopher J. Rossbach, and Emmett Witchel. 2016. Coordinated and efficient huge page management with ingens. In Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation. 705\u2013721. Retrieved from https:\/\/www.usenix.org\/conference\/osdi16\/technical-sessions\/presentation\/kwon"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304053"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2016.7838026"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigComp54360.2022.00059"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3575693.3578835"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3343737.3343745"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3516807.3516822"},{"key":"e_1_3_2_46_2","unstructured":"Chih-Jen Lin. 2021. LIBLINEAR \u2013 A Library for Large Linear Classification v2.43. Retrieved 13 September from https:\/\/www.csie.ntu.edu.tw\/cjlin\/liblinear\/"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSM.2010.2096437"},{"key":"e_1_3_2_48_2","first-page":"593","volume-title":"Proceedings of the 2022 USENIX Annual Technical Conference","author":"Mansi Mark","year":"2022","unstructured":"Mark Mansi, Bijan Tabatabai, and Michael M. Swift. 2022. CBMM: Financial advice for kernel memory managers. In Proceedings of the 2022 USENIX Annual Technical Conference. 593\u2013608. Retrieved from https:\/\/www.usenix.org\/conference\/atc22\/presentation\/mansi"},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00072"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3582016.3582063"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319647.3325839"},{"key":"e_1_3_2_52_2","unstructured":"Timothy Prickett Morgan. 2022. The future of system memory is mostly CXL. Retrieved 13 September from https:\/\/www.nextplatform.com\/2022\/07\/05\/the-future-of-system-memory-is-mostly-cxl\/"},{"key":"e_1_3_2_53_2","first-page":"45","article-title":"Introducing the graph 500","volume":"19","author":"Murphy Richard C.","year":"2010","unstructured":"Richard C. Murphy, Kyle B. Wheeler, Brian W. Barrett, and James A. Ang. 2010. Introducing the graph 500. Cray Users Group 19 (2010), 45\u201374.","journal-title":"Cray Users Group"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/1060289.1060299"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3461648.3463844"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/1713254.1713276"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1145\/3445814.3446709"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304064"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173203"},{"key":"e_1_3_2_60_2","unstructured":"SeongJae Park. 2021. Introduce Data Access MONitor (DAMON). Retrieved 13 September from https:\/\/lwn.net\/Articles\/849708\/"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531466"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/3565885"},{"key":"e_1_3_2_63_2","unstructured":"Industry Perspectives. 2015. Don\u2019t Forget About Memory: DRAM\u2019s Surprising Role in the High Cost of Data Centers. Retrieved 13 September from https:\/\/www.datacenterknowledge.com\/archives\/2015\/11\/12\/dont-forget-memory-drams-surprising-role-high-cost-data-centers"},{"key":"e_1_3_2_64_2","unstructured":"Chris Petersen. 2021. Software Defined Memory: A Meta perspective. Retrieved 13 September from https:\/\/www.opencompute.org\/events\/past-events\/2021-ocp-global-summit"},{"key":"e_1_3_2_65_2","unstructured":"Phoronix. 2022. MGLRU Looks Like One Of The Best Linux Kernel Innovations Of The Year. Retrieved 13 September from https:\/\/www.phoronix.com\/news\/MGLRU-LPC-2022"},{"key":"e_1_3_2_66_2","unstructured":"The Next Platform. 2020. CXL and Gen-Z Iron Out a Coherent Interconnect Strategy. Retrieved 13 September from https:\/\/www.nextplatform.com\/2020\/04\/03\/cxl-and-gen-z-iron-out-a-coherent-interconnect-strategy\/"},{"key":"e_1_3_2_67_2","unstructured":"pmem.io. 2019. Using the memmap Kernel Option. Retrieved 13 September from https:\/\/docs.pmem.io\/persistent-memory\/getting-started-guide\/creating-development-environments\/linux-environments\/linux-memmap"},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.39"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480062"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/3477132.3483550"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00057"},{"key":"e_1_3_2_72_2","unstructured":"Rafa\u0142 Rudnicki. 2022. Memory Tiering (Part 1). Retrieved 13 September from https:\/\/pmem.io\/blog\/2022\/06\/memory-tiering-part-1"},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1145\/3205289.3208064"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.20"},{"key":"e_1_3_2_75_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2014.56"},{"key":"e_1_3_2_76_2","volume-title":"Proceedings of the Role of Reactor Physics toward a Sustainable Future","author":"Tramm John R.","year":"2014","unstructured":"John R. Tramm, Andrew R. Siegel, Tanzima Islam, and Martin Schulz. 2014. XSBench - The development and verification of a performance abstraction for monte carlo reactor analysis. In Proceedings of the Role of Reactor Physics toward a Sustainable Future. Retrieved from https:\/\/www.mcs.anl.gov\/papers\/P5064-0114.pdf"},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522713"},{"key":"e_1_3_2_78_2","article-title":"Automatic NUMA balancing","author":"Riel Rik van","year":"2014","unstructured":"Rik van Riel and Vinod Chegu. 2014. Automatic NUMA balancing. Red Hat Summit (2014).","journal-title":"Red Hat Summit"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741964"},{"key":"e_1_3_2_80_2","unstructured":"Vishal Verma. 2022. Tiering-0.8. Retrieved 13 September from https:\/\/git.kernel.org\/pub\/scm\/linux\/kernel\/git\/vishal\/tiering.git\/log\/?h=tiering-0.8"},{"key":"e_1_3_2_81_2","doi-asserted-by":"publisher","DOI":"10.1145\/3694715.3695968"},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1145\/3314221.3314650"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3310133"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507731"},{"key":"e_1_3_2_85_2","unstructured":"Network World. 2018. Facebook and Amazon are causing a memory shortage. Retrieved 13 September from https:\/\/www.networkworld.com\/article\/3247775\/facebook-and-amazon-are-causing-a-memory-shortage.html"},{"key":"e_1_3_2_86_2","first-page":"19","volume-title":"Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation","author":"Xiang Lingfeng","year":"2024","unstructured":"Lingfeng Xiang, Zhen Lin, Weishu Deng, Hui Lu, Jia Rao, Yifan Yuan, and Ren Wang. 2024. Nomad: Non-exclusive memory tiering via transactional page migration. In Proceedings of the 18th USENIX Symposium on Operating Systems Design and Implementation. USENIX Association, 19\u201335. Retrieved from https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/xiang"},{"key":"e_1_3_2_87_2","unstructured":"Zi Yan. 2017. mm: page migration enhancement for thp. Retrieved 13 September from https:\/\/lwn.net\/Articles\/723764\/"},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304024"},{"key":"e_1_3_2_89_2","unstructured":"Yu Zhao. 2022. Multigenerational LRU Framework. Retrieved 13 September from https:\/\/lwn.net\/Articles\/880393\/"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.5555\/3691938.3691941"},{"key":"e_1_3_2_91_2","unstructured":"Alexander Zhu. 2022. [RFC 0\/3] THP Shrinker. Retrieved 13 September from https:\/\/lwn.net\/ml\/linux-kernel\/cover.1661461643.git.alexlzhu@fb.com\/"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.5555\/3489146.3489203"}],"container-title":["ACM Transactions on Computer Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3777549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T12:24:38Z","timestamp":1777119878000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3777549"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,24]]},"references-count":91,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,5,31]]}},"alternative-id":["10.1145\/3777549"],"URL":"https:\/\/doi.org\/10.1145\/3777549","relation":{},"ISSN":["0734-2071","1557-7333"],"issn-type":[{"value":"0734-2071","type":"print"},{"value":"1557-7333","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,24]]},"assertion":[{"value":"2025-05-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-04","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}