{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T07:59:25Z","timestamp":1776931165190,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,18]]},"DOI":"10.1145\/3725843.3756089","type":"proceedings-article","created":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T17:19:56Z","timestamp":1760721596000},"page":"1448-1461","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DRAM Fault Classification through Large-Scale Field Monitoring for Robust Memory RAS Management"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0475-9911","authenticated-orcid":false,"given":"Hoiju","family":"Chung","sequence":"first","affiliation":[{"name":"SK hynix America, San Jose, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1330-0528","authenticated-orcid":false,"given":"Euisang","family":"Oh","sequence":"additional","affiliation":[{"name":"SK hynix America, San Jose, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4801-8969","authenticated-orcid":false,"given":"Seungmin","family":"Baek","sequence":"additional","affiliation":[{"name":"SK hynix America, San Jose, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1793-6587","authenticated-orcid":false,"given":"Hyeongshin","family":"Yoon","sequence":"additional","affiliation":[{"name":"SK hynix America, San Jose, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8049-4388","authenticated-orcid":false,"given":"Jaesung","family":"Yoo","sequence":"additional","affiliation":[{"name":"SK hynix America, San Jose, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6392-3826","authenticated-orcid":false,"given":"Sanghwan","family":"Lee","sequence":"additional","affiliation":[{"name":"SK hynix America, San Jose, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5350-5170","authenticated-orcid":false,"given":"Yongjun","family":"Lee","sequence":"additional","affiliation":[{"name":"Microsoft, Mountain View, California, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2958-1375","authenticated-orcid":false,"given":"Arhatha","family":"Bramhanand","sequence":"additional","affiliation":[{"name":"Microsoft, Redmond, Washington, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7954-6512","authenticated-orcid":false,"given":"Brett","family":"Dodds","sequence":"additional","affiliation":[{"name":"Microsoft, Boise, Idaho, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7531-3365","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0442-5634","authenticated-orcid":false,"given":"Nam Sung","family":"Kim","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Urbana, Illinois, USA"}]}],"member":"320","published-online":{"date-parts":[[2025,10,17]]},"reference":[{"key":"e_1_3_3_2_2_2","unstructured":"JEDEC Solid State\u00a0Technology Association et\u00a0al. 2012. JEDEC Standard: DDR4 SDRAM. JEDEC Standard JESD79-4 (2012)."},{"key":"e_1_3_3_2_3_2","unstructured":"JEDEC Solid State\u00a0Technology Association et\u00a0al. 2014. JEDEC Standard: Low Power Double Data Rate 4 (LPDDR4). JEDEC Standard JESD209-4 (2014)."},{"key":"e_1_3_3_2_4_2","unstructured":"JEDEC Solid State\u00a0Technology Association et\u00a0al. 2019. JEDEC Standard: Low Power Double Data Rate 5 (LPDDR5). JEDEC Standard JESD209-5 (2019)."},{"key":"e_1_3_3_2_5_2","unstructured":"JEDEC Solid State\u00a0Technology Association et\u00a0al. 2020. JEDEC Standard: DDR5 SDRAM. JEDEC Standard JESD79-5 (2020)."},{"key":"e_1_3_3_2_6_2","unstructured":"JEDEC Solid State\u00a0Technology Association et\u00a0al. 2022. JEDEC Standard: High Bandwidth Memory DRAM (HBM3). JEDEC Standard JESD238 (2022)."},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"crossref","unstructured":"A. Avizienis J.-C. Laprie B. Randell and C. Landwehr. 2004. Basic concepts and taxonomy of dependable and secure computing. IEEE Transactions on Dependable and Secure Computing 1 1 (2004) 11\u201333.","DOI":"10.1109\/TDSC.2004.2"},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071066"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN-S65789.2025.00039"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"T. Calin M. Nicolaidis and R. Velazco. 1996. Upset hardened memory design for submicron CMOS technology. IEEE Transactions on Nuclear Science 43 6 (1996) 2874\u20132878.","DOI":"10.1109\/23.556880"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00052"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2014.63"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/3422575.3422803"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357526.3357527"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD53106.2021.00077"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531465"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3502181.3531465"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Sudhanva Gurumurthi Kijun Lee Munseon Jang Vilas Sridharan Aaron Nygren Yesin Ryu Kyomin Sohn Taekyun Kim and Hoeju Chung. 2021. HBM3 RAS: Enhancing Resilience at Scale. IEEE Computer Architecture Letters 20 2 (2021) 158\u2013161.","DOI":"10.1109\/LCA.2021.3117150"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Andy\u00a0A. Hwang Ioan\u00a0A. Stefanovici and Bianca Schroeder. 2012. Cosmic rays don\u2019t strike twice: understanding the nature of DRAM errors and the implications for system design. SIGARCH Comput. Archit. News 40 1 (March 2012) 111\u2013122.","DOI":"10.1145\/2189750.2150989"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2150989"},{"key":"e_1_3_3_2_21_2","unstructured":"Intel. 2023. 4th Gen Intel\u00ae Xeon\u00ae Scalable Processors: Reliability Availability and Serviceability. Technical Paper Rev1.0 (2023)."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614294"},{"key":"e_1_3_3_2_23_2","unstructured":"Uksong Kang Hak-Soo Yu Churoo Park Hongzhong Zheng John Halbert Kuljit Bains Sungjin Jang and Joo\u00a0Sun Choi. 2014. Co-architecting controllers and DRAM to enhance DRAM process scaling. 14 (2014)."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Byunghoon Kim Young-Seon Jeong Seung\u00a0Hoon Tong et\u00a0al. 2015. A Regularized Singular Value Decomposition-Based Approach for Failure Pattern Classification on Fail Bit Map in a DRAM Wafer. IEEE Transactions on Semiconductor Manufacturing 28 1 (2015) 41\u201349.","DOI":"10.1109\/TSM.2014.2388192"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2015.7056025"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC.2012.6176869"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"Chang-Kyo Lee Hyung-Joon Chi Jin-Seok Heo Jung-Hwan Park Jin-Hun Jang Dongkeon Lee Jae-Hoon Jung et\u00a0al. 2021. An 8.5-Gb\/s\/Pin 12-Gb LPDDR5 SDRAM With a Hybrid-Bank Architecture Low Power and Speed-Boosting Techniques. 56 1 (2021) 212\u2013224.","DOI":"10.1109\/JSSC.2020.3017775"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/IRPS48228.2024.10529404"},{"key":"e_1_3_3_2_29_2","first-page":"01","volume-title":"SC22: International Conference for High Performance Computing, Networking, Storage and Analysis","author":"Li Cong","year":"2022","unstructured":"Cong Li, Yu Zhang, Jialei Wang, Hang Chen, Xian Liu, Tai Huang, et\u00a0al. 2022. From Correctable Memory Errors to Uncorrectable Memory Errors: What Error Bits Tell. In SC22: International Conference for High Performance Computing, Networking, Storage and Analysis. 01\u201314."},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN.2015.57"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.38"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00083"},{"key":"e_1_3_3_2_33_2","unstructured":"NVIDIA. 2023. NVIDIA GH200 Grace Hopper Superchip. https:\/\/www.nvidia.com\/en-us\/data-center\/grace-hopper-superchip\/?ncid=no-ncid"},{"key":"e_1_3_3_2_34_2","unstructured":"NVIDIA. 2024. NVIDIA GB300 NVL72: Built for the age of AI reasoning. https:\/\/www.nvidia.com\/en-us\/data-center\/gb300-nvl72\/?ncid=no-ncid"},{"key":"e_1_3_3_2_35_2","unstructured":"NVIDIA. 2025. Cloud and Data Center Solutions: NVIDIA Grace. https:\/\/www.nvidia.com\/en-us\/data-center\/grace-cpu\/?ncid=no-ncid"},{"key":"e_1_3_3_2_36_2","unstructured":"OCP-FMFM. 2025. OCP Fleetscale Memory Fault Management (FMFM). https:\/\/www.opencompute.org\/wiki\/Hardware_Management\/FMFM"},{"key":"e_1_3_3_2_37_2","unstructured":"OCP-HWFM. 2025. OCP Hardware Management\/Hardware Fault Management (HWFM). https:\/\/www.opencompute.org\/wiki\/Hardware_Management\/Hardware_Fault_Management"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"crossref","unstructured":"Tae-Young Oh Hoeju Chung Jun-Young Park Ki-Won Lee Seunghoon Oh Su-Yeon Doo et\u00a0al. 2015. A 3.2 Gbps\/pin 8 Gbit 1.0 V LPDDR4 SDRAM With Integrated ECC Engine for Sub-1 V DRAM Core Operation. IEEE Journal of Solid-State Circuits 50 1 (2015) 178\u2013190.","DOI":"10.1109\/JSSC.2014.2353799"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731562"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Yesin Ryu Sung-Gi Ahn Jae\u00a0Hoon Lee Jaewon Park Yong\u00a0Ki Kim Hyochang Kim et\u00a0al. 2023. A 16 GB 1024 GB\/s HBM3 DRAM With Source-Synchronized Bus Design and On-Die Error Control Scheme for Enhanced RAS Features. IEEE Journal of Solid-State Circuits 58 4 (2023) 1051\u20131061.","DOI":"10.1109\/JSSC.2022.3232096"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLSITechnologyandCir46769.2022.9830391"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Bianca Schroeder and Garth\u00a0A Gibson. 2009. A large-scale study of failures in high-performance computing systems. IEEE transactions on Dependable and Secure Computing 7 4 (2009) 337\u2013350.","DOI":"10.1109\/TDSC.2009.4"},{"key":"e_1_3_3_2_43_2","doi-asserted-by":"crossref","unstructured":"Bianca Schroeder Eduardo Pinheiro and Wolf-Dietrich Weber. 2009. DRAM errors in the wild: a large-scale field study. ACM SIGMETRICS Performance Evaluation Review 37 1 (2009) 193\u2013204.","DOI":"10.1145\/2492101.1555372"},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/DFT.2017.8244428"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Vilas Sridharan Nathan DeBardeleben Sudhanva Gurumurthi et\u00a0al. 2015. Memory errors in modern systems: The good the bad and the ugly. ACM SIGARCH Computer Architecture News 43 1 (2015) 297\u2013310.","DOI":"10.1145\/2786763.2694348"},{"key":"e_1_3_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.5555\/2388996.2389100"},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503257"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/DSN53405.2022.00037"}],"event":{"name":"MICRO 2025: 58th IEEE\/ACM International Symposium on Microarchitecture","location":"Seoul Korea","acronym":"MICRO 2025","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 58th IEEE\/ACM International Symposium on Microarchitecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3725843.3756089","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T21:46:37Z","timestamp":1769463997000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3725843.3756089"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,17]]},"references-count":47,"alternative-id":["10.1145\/3725843.3756089","10.1145\/3725843"],"URL":"https:\/\/doi.org\/10.1145\/3725843.3756089","relation":{},"subject":[],"published":{"date-parts":[[2025,10,17]]},"assertion":[{"value":"2025-10-17","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}