{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:00:29Z","timestamp":1750309229273,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":17,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T00:00:00Z","timestamp":1737331200000},"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":[[2025,1,20]]},"DOI":"10.1145\/3658617.3697567","type":"proceedings-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T14:32:21Z","timestamp":1741098741000},"page":"491-497","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Fail-Slow Detection Framework for HBM Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7346-5418","authenticated-orcid":false,"given":"Zikang","family":"Xu","sequence":"first","affiliation":[{"name":"XiaMen Univ., XiaMen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6450-8485","authenticated-orcid":false,"given":"Yiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"XiaMen Univ., XiaMen, China"},{"name":"Peng Cheng Lab, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2673-5868","authenticated-orcid":false,"given":"Zhirong","family":"Shen","sequence":"additional","affiliation":[{"name":"XiaMen Univ., XiaMen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/dsn-w.2017.39"},{"key":"e_1_3_2_1_2_1","volume-title":"IEEE Conference Proceedings, IEEE Conference Proceedings (Jan","author":"Baseman Elisabeth","year":"2016","unstructured":"Elisabeth Baseman, DeBardeleben Nathan, Ferreira Kurt, Scott Levy, Raasch Steven, Sridharan Vilas, Taniya Siddiqua, and Qiang Guan. 2016. Improving DRAM Fault Characterization through Machine Learning. IEEE Conference Proceedings, IEEE Conference Proceedings (Jan 2016)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/sc41405.2020.00065"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/2744769.2744923"},{"key":"e_1_3_2_1_5_1","volume-title":"When HLS Meets FPGA HBM: Benchmarking and Bandwidth Optimization","author":"Choi Young-Kyu","year":"2020","unstructured":"Young-Kyu Choi, Yuze Chi, Jie Wang, Licheng Guo, and Jason Cong. 2020. When HLS Meets FPGA HBM: Benchmarking and Bandwidth Optimization. Cornell University - arXiv, Cornell University - arXiv (Oct 2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"Fail-Slow at Scale: Evidence of Hardware Performance Faults in Large Production Systems. login Usenix Mag., login Usenix Mag. (Jan","author":"Gunawi S.","year":"2018","unstructured":"HaryadiS. Gunawi, RizaO. Suminto, Russell Sears, Sundararaman Swaminathan, Xing Lin, and Robert Ricci. 2018. Fail-Slow at Scale: Evidence of Hardware Performance Faults in Large Production Systems. login Usenix Mag., login Usenix Mag. (Jan 2018)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/2987550.2987583"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2150976.2150989"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/imw.2017.7939084"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240302.3240315"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/hotchips.2019.8875654"},{"key":"e_1_3_2_1_12_1","volume-title":"Perseus: A Fail-Slow Detection Framework for Cloud Storage Systems. In USENIX Conference on File and Storage Technologies. https:\/\/api.semanticscholar.org\/CorpusID:267790674","author":"Lu Ruiming","year":"2023","unstructured":"Ruiming Lu, Erci Xu, Yiming Zhang, Fengyi Zhu, Zhaosheng Zhu, Mengtian Wang, Zongpeng Zhu, Guangtao Xue, Jiwu Shu, Minglu Li, and Jiesheng Wu. 2023. Perseus: A Fail-Slow Detection Framework for Cloud Storage Systems. In USENIX Conference on File and Storage Technologies. https:\/\/api.semanticscholar.org\/CorpusID:267790674"},{"key":"e_1_3_2_1_13_1","unstructured":"Ruiming Lu Erci Xu Yiming Zhang Zhaosheng Zhu Mengtian Wang Zongpeng Zhu Guangtao Xue Minglu Li and Jiesheng Wu. [n. d.]. NVMe SSD Failures in the Field: the Fail-Stop and the Fail-Slow. ([n. d.])."},{"key":"e_1_3_2_1_14_1","volume-title":"RAIDShield: characterizing, monitoring, and proactively protecting against disk failures. File and Storage Technologies, File and Storage Technologies (Feb","author":"Ma Ao","year":"2015","unstructured":"Ao Ma, Rachel Traylor, Fred Douglis, Mark Chamness, Guanlin Lu, Darren Sawyer, Surendar Chandra, and WindsorW. Hsu. 2015. RAIDShield: characterizing, monitoring, and proactively protecting against disk failures. File and Storage Technologies, File and Storage Technologies (Feb 2015)."},{"key":"e_1_3_2_1_15_1","unstructured":"NVIDIA. 2024. NVIDIA A100. https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2503210.2503257"},{"key":"e_1_3_2_1_17_1","volume-title":"2024 USENIX Annual Technical Conference (USENIX ATC 24)","author":"Wu Ronglong","year":"2024","unstructured":"Ronglong Wu, Shuyue Zhou, Jiahao Lu, Zhirong Shen, Zikang Xu, Jiwu Shu, Kunlin Yang, Feilong Lin, and Yiming Zhang. 2024. Removing Obstacles before Breaking Through the Memory Wall: A Close Look at HBM Errors in the Field. In 2024 USENIX Annual Technical Conference (USENIX ATC 24). USENIX Association, Santa Clara, CA, 851--867. https:\/\/www.usenix.org\/conference\/atc24\/presentation\/wu-ronglong"}],"event":{"name":"ASPDAC '25: 30th Asia and South Pacific Design Automation Conference","sponsor":["SIGDA ACM Special Interest Group on Design Automation","IEICE","IPSJ","IEEE CAS","IEEE CEDA"],"location":"Tokyo Japan","acronym":"ASPDAC '25"},"container-title":["Proceedings of the 30th Asia and South Pacific Design Automation Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697567","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3658617.3697567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:19Z","timestamp":1750290259000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3658617.3697567"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,20]]},"references-count":17,"alternative-id":["10.1145\/3658617.3697567","10.1145\/3658617"],"URL":"https:\/\/doi.org\/10.1145\/3658617.3697567","relation":{},"subject":[],"published":{"date-parts":[[2025,1,20]]},"assertion":[{"value":"2025-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}