{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T08:45:31Z","timestamp":1743151531597,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031408427"},{"type":"electronic","value":"9783031408434"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-40843-4_17","type":"book-chapter","created":{"date-parts":[[2023,8,24]],"date-time":"2023-08-24T12:02:32Z","timestamp":1692878552000},"page":"221-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Understanding System Resilience for\u00a0Converged Computing of\u00a0Cloud, Edge, and\u00a0HPC"],"prefix":"10.1007","author":[{"given":"Luanzheng","family":"Guo","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jay","family":"Lofstead","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Ren","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ignacio","family":"Laguna","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gokcen","family":"Kestor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Line","family":"Pouchard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dossay","family":"Oryspayev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyeran","family":"Jeon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,25]]},"reference":[{"unstructured":"Exascale Computing Project CANDLE. https:\/\/www.exascaleproject.org\/research-group\/data-analytics-and-optimization\/","key":"17_CR1"},{"unstructured":"NVIDIA SDK. https:\/\/developer.nvidia.com\/hpc-sdk","key":"17_CR2"},{"unstructured":"Slurm Fault Tolerant Workload Management. https:\/\/ieeexplore.ieee.org\/stamp\/stamp.jsp?tp= &arnumber=1303290","key":"17_CR3"},{"unstructured":"Stress-ng. https:\/\/github.com\/ColinIanKing\/stress-ng","key":"17_CR4"},{"doi-asserted-by":"crossref","unstructured":"Ahn, D.H., et al.: Scalable composition and analysis techniques for massive scientific workflows. In: e-Science (2022)","key":"17_CR5","DOI":"10.1109\/eScience55777.2022.00018"},{"doi-asserted-by":"crossref","unstructured":"AlZain, M.A., Soh, B., Pardede, E.: A new approach using redundancy technique to improve security in cloud computing. In: CyberSec, pp. 230\u2013235. IEEE (2012)","key":"17_CR6","DOI":"10.1109\/CyberSec.2012.6246174"},{"key":"17_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1007\/978-3-319-14325-5_47","volume-title":"Euro-Par 2014: Parallel Processing Workshops","author":"J Calhoun","year":"2014","unstructured":"Calhoun, J., Olson, L., Snir, M.: FlipIt: an LLVM based fault injector for HPC. In: Lopes, L., et al. (eds.) Euro-Par 2014. LNCS, vol. 8805, pp. 547\u2013558. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-14325-5_47"},{"doi-asserted-by":"crossref","unstructured":"Chakrabarti, D.R., Boehm, H.J., Bhandari, K.: Atlas: leveraging locks for non-volatile memory consistency. In: ACM OOPSLA (2014)","key":"17_CR8","DOI":"10.1145\/2660193.2660224"},{"key":"17_CR9","first-page":"89","volume":"13","author":"JJ Dongarra","year":"1997","unstructured":"Dongarra, J.J., Meuer, H.W., Strohmaier, E., et al.: Top500 supercomputer sites. Supercomputer 13, 89\u2013111 (1997)","journal-title":"Supercomputer"},{"doi-asserted-by":"crossref","unstructured":"Georgakoudis, G., Laguna, I., Nikolopoulos, D.S., Schulz, M.: REFINE: realistic fault injection via compiler-based instrumentation for accuracy, portability and speed. In: ACM\/IEEE SC, pp. 1\u201314 (2017)","key":"17_CR10","DOI":"10.1145\/3126908.3126972"},{"doi-asserted-by":"crossref","unstructured":"Guo, L., Georgakoudis, G., Parasyris, K., Laguna, I., Li, D.: MATCH: an MPI fault tolerance benchmark suite. In: 2020 IEEE International Symposium on Workload Characterization (IISWC), pp. 60\u201371. IEEE (2020)","key":"17_CR11","DOI":"10.1109\/IISWC50251.2020.00015"},{"doi-asserted-by":"crossref","unstructured":"Guo, L., Li, D.: MOARD: modeling application resilience to transient faults on data objects. In: IPDPS (2019)","key":"17_CR12","DOI":"10.1109\/IPDPS.2019.00096"},{"key":"17_CR13","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.jpdc.2021.02.015","volume":"152","author":"L Guo","year":"2021","unstructured":"Guo, L., Li, D., Laguna, I.: Paris: predicting application resilience using machine learning. J. Parallel Distrib. Comput. 152, 111\u2013124 (2021)","journal-title":"J. Parallel Distrib. Comput."},{"doi-asserted-by":"crossref","unstructured":"Guo, L., Li, D., Laguna, I., Schulz, M.: Fliptracker: understanding natural error resilience in HPC applications. In: SC (2018)","key":"17_CR14","DOI":"10.1109\/SC.2018.00011"},{"key":"17_CR15","first-page":"1318","volume":"72","author":"B Javadi","year":"2012","unstructured":"Javadi, B., Abawajy, J., Buyya, R.: Failure-aware resource provisioning for hybrid cloud infrastructure. JPDC 72, 1318\u20131331 (2012)","journal-title":"JPDC"},{"doi-asserted-by":"crossref","unstructured":"Jhawar, R., Piuri, V., Santambrogio, M.: A comprehensive conceptual system-level approach to fault tolerance in cloud computing. In: IEEE ISC, pp. 1\u20135 (2012)","key":"17_CR16","DOI":"10.1109\/SysCon.2012.6189503"},{"doi-asserted-by":"crossref","unstructured":"Kestor, G., Krishnamoorthy, S., Ma, W.: Localized fault recovery for nested fork-join programs. In: IEEE IPDPS (2017)","key":"17_CR17","DOI":"10.1109\/IPDPS.2017.75"},{"unstructured":"Kunkel, J., Bent, J., Lofstead, J., Markomanolis, G.S.: Establishing the IO-500 benchmark. White Paper (2016)","key":"17_CR18"},{"doi-asserted-by":"crossref","unstructured":"Laguna, I., Schulz, M., Richards, D.F., Calhoun, J., Olson, L.: IPAS: intelligent protection against silent output corruption in scientific applications. In: IEEE CGO, pp. 227\u2013238 (2016)","key":"17_CR19","DOI":"10.1145\/2854038.2854059"},{"doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: A visual comparison of silent error propagation. IEEE TVCG (2022)","key":"17_CR20","DOI":"10.1109\/TVCG.2022.3230636"},{"doi-asserted-by":"crossref","unstructured":"Mohammed, B., Kiran, M., Maiyama, K.M., Kamala, M.M., Awan, I.U.: Failover strategy for fault tolerance in cloud computing environment. Software (2017)","key":"17_CR21","DOI":"10.1109\/UIC-ATC-ScalCom-CBDCom-IoP-SmartWorld.2016.0094"},{"doi-asserted-by":"crossref","unstructured":"Mukherjee, S., Weaver, C., Emer, J., Reinhardt, S., Austin, T.: A systematic methodology to compute the architectural vulnerability factors for a high-performance microprocessor. In: Proceedings of IEEE\/ACM MICRO (2003)","key":"17_CR22","DOI":"10.1109\/MM.2003.1261389"},{"doi-asserted-by":"crossref","unstructured":"Nicolae, B., et al.: VeloC: towards high performance adaptive asynchronous checkpointing at large scale. In: IEEE IPDPS (2019)","key":"17_CR23","DOI":"10.1109\/IPDPS.2019.00099"},{"doi-asserted-by":"crossref","unstructured":"Oukid, I., et al.: FPTree: a hybrid SCM-DRAM persistent and concurrent B-Tree for storage class memory. In: SIGMOD (2016)","key":"17_CR24","DOI":"10.1145\/2882903.2915251"},{"doi-asserted-by":"crossref","unstructured":"Peterson, J.L., et al.: Enabling machine learning-ready HPC ensembles with merlin. FGCS 131(C), 255\u2013268 (2022)","key":"17_CR25","DOI":"10.1016\/j.future.2022.01.024"},{"doi-asserted-by":"crossref","unstructured":"Reis, G.A., Chang, J., Vachharajani, N., Rangan, R., August, D.I.: SWIFT: software implemented fault tolerance. In: IEEE CGO, pp. 243\u2013254 (2005)","key":"17_CR26","DOI":"10.1109\/CGO.2005.34"},{"doi-asserted-by":"crossref","unstructured":"Ren, J., Wu, K., Li, D.: Exploring non-volatility of non-volatile memory for high performance computing under failures. In: IEEE CLUSTER, pp. 237\u2013247 (2020)","key":"17_CR27","DOI":"10.1109\/CLUSTER49012.2020.00034"},{"doi-asserted-by":"crossref","unstructured":"Rorabaugh, D., Guevara, M., Llamas, R., Kitson, J., Vargas, R., Taufer, M.: SOMOSPIE: a modular SOil MOisture SPatial inference engine based on data-driven decisions. In: eScience, pp. 1\u201310 (2019)","key":"17_CR28","DOI":"10.1109\/eScience.2019.00008"},{"doi-asserted-by":"crossref","unstructured":"Saadi, A.A., et al.: Impeccable: integrated modeling pipeline for COVID cure by assessing better leads. In: ICPP, pp. 1\u201312 (2021)","key":"17_CR29","DOI":"10.1145\/3472456.3473524"},{"doi-asserted-by":"crossref","unstructured":"Shahzad, F., Thies, J., Kreutzer, M., Zeiser, T., Hager, G., Wellein, G.: CRAFT: a library for easier application-level checkpoint\/restart and automatic fault tolerance. IEEE TPDS (2018)","key":"17_CR30","DOI":"10.1109\/TPDS.2018.2866794"},{"issue":"10","key":"17_CR31","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1109\/12.324541","volume":"43","author":"KG Shin","year":"1994","unstructured":"Shin, K.G., Kim, H.: A time redundancy approach to TMR failures using fault-state likelihoods. IEEE Trans. Comput. 43(10), 1151\u20131162 (1994)","journal-title":"IEEE Trans. Comput."},{"doi-asserted-by":"crossref","unstructured":"Wang, J., Bao, W., Zhu, X., Yang, L.T., Xiang, Y.: FESTAL: fault-tolerant elastic scheduling algorithm for real-time tasks in virtualized clouds. IEEE TC (2014)","key":"17_CR32","DOI":"10.1109\/TC.2014.2366751"},{"doi-asserted-by":"crossref","unstructured":"Wei, J., Thomas, A., Li, G., Pattabiraman, K.: Quantifying the accuracy of high-level fault injection techniques for hardware faults. In: IEEE\/IFIP DSN, pp. 375\u2013382 (2014)","key":"17_CR33","DOI":"10.1109\/DSN.2014.2"},{"doi-asserted-by":"crossref","unstructured":"Yu, L., Li, D., Mittal, S., Vetter, J.S.: Quantitatively modeling application resiliency with data vulnerability factor. In: SC (2014)","key":"17_CR34","DOI":"10.1109\/SC.2014.62"}],"container-title":["Lecture Notes in Computer Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-40843-4_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T20:15:31Z","timestamp":1729973731000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-40843-4_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031408427","9783031408434"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-40843-4_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"25 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISC High Performance","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on High Performance Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hamburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Germany","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 May 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 May 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"supercomputing2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isc-hpc.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Linklings","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"49","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"70% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}