{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T22:26:11Z","timestamp":1775082371566,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819584048","type":"print"},{"value":"9789819584055","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-8405-5_24","type":"book-chapter","created":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:15:28Z","timestamp":1775074528000},"page":"440-461","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning and\u00a0Data Statistics Based Scalability Bottleneck Detection"],"prefix":"10.1007","author":[{"given":"Yuhan","family":"Cao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoming","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,4,2]]},"reference":[{"key":"24_CR1","unstructured":"MPIP: A light-weight MPI profiler (2020). https:\/\/software.llnl.gov\/mpiP\/"},{"key":"24_CR2","doi-asserted-by":"publisher","unstructured":"Abubaker, N., Karsavuran, M.O., Aykanat, C.: Scaling stratified stochastic gradient descent for distributed matrix completion. IEEE Trans. Knowl. Data Eng. 35(10), 10603\u201310615 (2023). https:\/\/doi.org\/10.1109\/TKDE.2023.3253791, https:\/\/ieeexplore.ieee.org\/document\/10061560\/","DOI":"10.1109\/TKDE.2023.3253791"},{"key":"24_CR3","doi-asserted-by":"publisher","unstructured":"Adhianto, L., et al.: HPCTOOLKIT: tools for performance analysis of optimized parallel programs. Concurr. Comput. Pract. Exp. 22(6), 685\u2013701 (2010). https:\/\/doi.org\/10.1002\/CPE.1553","DOI":"10.1002\/CPE.1553"},{"issue":"2","key":"24_CR4","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1109\/TPDS.2022.3221085","volume":"34","author":"A Afzal","year":"2023","unstructured":"Afzal, A., Hager, G., Wellein, G.: The role of idle waves, desynchronization, and bottleneck evasion in the performance of parallel programs. IEEE Trans. Parallel Distrib. Syst. 34(2), 623\u2013638 (2023). https:\/\/doi.org\/10.1109\/TPDS.2022.3221085","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"24_CR5","doi-asserted-by":"publisher","unstructured":"Amaris, M., Camargo, R., Cordeiro, D., et al.: Evaluating execution time predictions on GPU kernels using an analytical model and machine learning techniques. J. Parallel Distributed Comput. 171, 66\u201378 (2023). https:\/\/doi.org\/10.1016\/j.jpdc.2022.09.002, https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0743731522001903","DOI":"10.1016\/j.jpdc.2022.09.002"},{"key":"24_CR6","doi-asserted-by":"publisher","unstructured":"Andrade, T.N.C., Lima, G., Lima, V.M.C., Bem-Amor, S., Hawila, I., Cucu-Grosjean, L.: On the impact of hardware-related events on the execution of real-time programs. Des. Autom. Embed. Syst. 27(4), 275\u2013302 (2023). https:\/\/doi.org\/10.1007\/s10617-023-09281-9, https:\/\/link.springer.com\/10.1007\/s10617-023-09281-9","DOI":"10.1007\/s10617-023-09281-9"},{"key":"24_CR7","doi-asserted-by":"publisher","unstructured":"Barnes, B.J., Rountree, B., Lowenthal, D.K., et\u00a0al.: A regression-based approach to scalability prediction. In: Proceedings of the 22nd Annual International Conference on Supercomputing, pp. 368\u2013377. ACM, Island of Kos Greece (2008). https:\/\/doi.org\/10.1145\/1375527.1375580","DOI":"10.1145\/1375527.1375580"},{"key":"24_CR8","doi-asserted-by":"publisher","unstructured":"Barry, D., Danalis, A., Dongarra, J.: Automated data analysis for defining performance metrics from raw hardware events. In: 2024 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 716\u2013725. IEEE, San Francisco (2024). https:\/\/doi.org\/10.1109\/IPDPSW63119.2024.00134, https:\/\/ieeexplore.ieee.org\/document\/10596509\/","DOI":"10.1109\/IPDPSW63119.2024.00134"},{"issue":"6","key":"24_CR9","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1007\/s11704-018-7239-1","volume":"13","author":"J Chen","year":"2019","unstructured":"Chen, J., Zhou, W., Dong, Y., et al.: Analyzing time-dimension communication characterizations for representative scientific applications on supercomputer systems. Front. Comput. Sci. 13(6), 1228\u20131242 (2019). https:\/\/doi.org\/10.1007\/s11704-018-7239-1","journal-title":"Front. Comput. Sci."},{"issue":"1","key":"24_CR10","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPDS.2019.2929781","volume":"31","author":"K Criswell","year":"2020","unstructured":"Criswell, K., Adegbija, T.: A survey of phase classification techniques for characterizing variable application behavior. IEEE Trans. Parallel Distrib. Syst. 31(1), 224\u2013236 (2020a). https:\/\/doi.org\/10.1109\/TPDS.2019.2929781","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"24_CR11","doi-asserted-by":"publisher","unstructured":"Criswell, K., Adegbija, T.: A survey of phase classification techniques for characterizing variable application behavior. IEEE Trans. Parallel Distrib. Syst. 31(1), 224\u2013236 (2020). https:\/\/doi.org\/10.1109\/TPDS.2019.2929781, https:\/\/ieeexplore.ieee.org\/document\/8769866\/","DOI":"10.1109\/TPDS.2019.2929781"},{"key":"24_CR12","doi-asserted-by":"publisher","unstructured":"Ding, N., Lee, V.W., Xue, W., et al.: APMT: an automatic hardware counter-based performance modeling tool for HPC applications. CCF Trans. High Perf. Comput. 2(2), 135\u2013148 (2020). https:\/\/doi.org\/10.1007\/s42514-020-00035-8, https:\/\/link.springer.com\/10.1007\/s42514-020-00035-8","DOI":"10.1007\/s42514-020-00035-8"},{"key":"24_CR13","doi-asserted-by":"publisher","unstructured":"Ghosh, S., Gupta, V.: EventGraD: event-triggered communication in parallel stochastic gradient descent. In: 2020 IEEE\/ACM Workshop on Machine Learning in High Performance Computing Environments (MLHPC) and Workshop on Artificial Intelligence and Machine Learning for Scientific Applications (AI4S), pp.\u00a01\u20138. IEEE, GA, USA (2020). https:\/\/doi.org\/10.1109\/MLHPCAI4S51975.2020.00008, https:\/\/ieeexplore.ieee.org\/document\/9409306\/","DOI":"10.1109\/MLHPCAI4S51975.2020.00008"},{"key":"24_CR14","unstructured":"GRAPH500: Graph500 (2017). https:\/\/graph500.org\/"},{"issue":"7","key":"24_CR15","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1109\/TPDS.2020.3045983","volume":"32","author":"M Hao","year":"2021","unstructured":"Hao, M., et al.: Fine-grained powercap allocation for power-constrained systems based on multi-objective machine learning. IEEE Trans. Parallel Distrib. Syst. 32(7), 1789\u20131801 (2021). https:\/\/doi.org\/10.1109\/TPDS.2020.3045983","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"24_CR16","doi-asserted-by":"publisher","unstructured":"Helal, A.E., Jung, C., Feng, W.c., et\u00a0al.: CommAnalyzer: automated estimation of communication cost and scalability on HPC clusters from sequential code. In: Proceedings of the 27th International Symposium on High-Performance Parallel and Distributed Computing, pp. 80\u201391. ACM, Tempe Arizona (2018). https:\/\/doi.org\/10.1145\/3208040.3208042","DOI":"10.1145\/3208040.3208042"},{"key":"24_CR17","doi-asserted-by":"publisher","unstructured":"Hoefler, T., Snir, M.: Generic topology mapping strategies for large-scale parallel architectures. In: Proceedings of the International Conference on Supercomputing, pp. 75\u201384. ICS \u201911, Association for Computing Machinery, New York (2011). https:\/\/doi.org\/10.1145\/1995896.1995909","DOI":"10.1145\/1995896.1995909"},{"key":"24_CR18","unstructured":"HPCG: High Performance Conjugate Gradients (2020). https:\/\/www.hpcg-benchmark.org\/"},{"key":"24_CR19","doi-asserted-by":"publisher","unstructured":"Hutter, E., Solomonik, E.: Application performance modeling via tensor completion. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314. ACM, Denver (2023). https:\/\/doi.org\/10.1145\/3581784.3607069","DOI":"10.1145\/3581784.3607069"},{"key":"24_CR20","doi-asserted-by":"publisher","unstructured":"Jin, Y., et al.: SCALANA: automating scaling loss detection with graph analysis. In: SC20: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314. IEEE, Atlanta (2020). https:\/\/doi.org\/10.1109\/SC41405.2020.00032, https:\/\/ieeexplore.ieee.org\/document\/9355294\/","DOI":"10.1109\/SC41405.2020.00032"},{"key":"24_CR21","doi-asserted-by":"publisher","unstructured":"Li, P., Guo, Y., Luo, Y., et\u00a0al.: Graph neural networks based memory inefficiency detection using selective sampling. In: SC22: International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 1\u201314. IEEE, Dallas (2022). https:\/\/doi.org\/10.1109\/SC41404.2022.00090, https:\/\/ieeexplore.ieee.org\/document\/10046134\/","DOI":"10.1109\/SC41404.2022.00090"},{"key":"24_CR22","doi-asserted-by":"publisher","unstructured":"Li, Z., Chen, Z., Tang, Y., et\u00a0al.: Muse: a runtime incrementally reconfigurable network adapting to HPC real-time traffic. In: 2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 765\u2013779 (2024). https:\/\/doi.org\/10.1109\/IPDPS57955.2024.00073","DOI":"10.1109\/IPDPS57955.2024.00073"},{"issue":"5","key":"24_CR23","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1109\/TPDS.2018.2872992","volume":"30","author":"AF Lorenzon","year":"2019","unstructured":"Lorenzon, A.F., de Oliveira, C.C., Souza, J.D., et al.: Aurora: seamless optimization of openmp applications. IEEE Trans. Parallel Distrib. Syst. 30(5), 1007\u20131021 (2019). https:\/\/doi.org\/10.1109\/TPDS.2018.2872992","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"24_CR24","doi-asserted-by":"publisher","unstructured":"Lozano, E.S.A., Gerstlauer, A.: Learning-based phase-aware multi-core CPU workload forecasting. ACM Trans. Des. Autom. Electron. Syst. 28(2) (2022). https:\/\/doi.org\/10.1145\/3564929","DOI":"10.1145\/3564929"},{"key":"24_CR25","doi-asserted-by":"publisher","unstructured":"Luo, J., Yan, T., Xu, Q., et\u00a0al.: Siesta: synthesizing proxy applications for MPI programs. In: 2024 IEEE International Conference on Cluster Computing (CLUSTER), pp. 14\u201326. IEEE, Kobe (2024). https:\/\/doi.org\/10.1109\/CLUSTER59578.2024.00009, https:\/\/ieeexplore.ieee.org\/document\/10740841\/","DOI":"10.1109\/CLUSTER59578.2024.00009"},{"key":"24_CR26","unstructured":"NPB: NAS parallel benchmarks (2020). https:\/\/www.nas.nasa.gov\/software\/npb.html"},{"key":"24_CR27","doi-asserted-by":"publisher","unstructured":"Qi, X., et\u00a0al.: Highrpm: combining integrated measurement and sofware power modeling for high-resolution power monitoring. In: Proceedings of the 52nd International Conference on Parallel Processing, pp. 369\u2013379. ICPP \u201923, Association for Computing Machinery, New York (2023). https:\/\/doi.org\/10.1145\/3605573.3605649","DOI":"10.1145\/3605573.3605649"},{"key":"24_CR28","doi-asserted-by":"publisher","unstructured":"Ritter, M., Geis, A., Wehrstein, J., et\u00a0al.: Noise-resilient empirical performance modeling with deep neural networks. In: 2021 IEEE International Parallel and Distributed Processing Symposium (IPDPS), pp. 23\u201334. IEEE, Portland (2021). https:\/\/doi.org\/10.1109\/IPDPS49936.2021.00012, https:\/\/ieeexplore.ieee.org\/document\/9460451\/","DOI":"10.1109\/IPDPS49936.2021.00012"},{"issue":"2","key":"24_CR29","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1177\/1094342006064482","volume":"20","author":"SS Shende","year":"2006","unstructured":"Shende, S.S., Malony, A.D.: The tau parallel performance system. Int. J. High Perform. Comput. Appl. 20(2), 287\u2013311 (2006). https:\/\/doi.org\/10.1177\/1094342006064482","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"24_CR30","doi-asserted-by":"publisher","unstructured":"Sun, J., Sun, G., Zhan, S., et al.: Automated performance modeling of HPC applications using machine learning. IEEE Trans. Comput. 69(5), 749\u2013763 (2020). https:\/\/doi.org\/10.1109\/TC.2020.2964767, https:\/\/ieeexplore.ieee.org\/document\/8956059\/","DOI":"10.1109\/TC.2020.2964767"},{"key":"24_CR31","doi-asserted-by":"publisher","unstructured":"Wang, R., Lu, K., Chen, J., et\u00a0al.: Brief introduction of tianhe exascale prototype system. Tsinghua Sci. Technol. 26(3), 361\u2013369 (2021). https:\/\/doi.org\/10.26599\/TST.2020.9010009","DOI":"10.26599\/TST.2020.9010009"},{"issue":"10","key":"24_CR32","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MC.2016.311","volume":"49","author":"X Wu","year":"2016","unstructured":"Wu, X., Taylor, V., Cook, J., et al.: Using performance-power modeling to improve energy efficiency of HPC applications. Computer 49(10), 20\u201329 (2016). https:\/\/doi.org\/10.1109\/MC.2016.311","journal-title":"Computer"},{"key":"24_CR33","doi-asserted-by":"publisher","unstructured":"Xuan, Z., You, X., Yang, H., et\u00a0al.: Retrospection on the performance analysis tools for large-scale HPC programs. In: 2024 IEEE 31st International Conference on High Performance Computing, Data, and Analytics (HiPC), pp. 34\u201344. IEEE, Bangalore (2024). https:\/\/doi.org\/10.1109\/HiPC62374.2024.00013, https:\/\/ieeexplore.ieee.org\/document\/10884289\/","DOI":"10.1109\/HiPC62374.2024.00013"},{"key":"24_CR34","doi-asserted-by":"publisher","unstructured":"Zhang, W., Cheng, A.M.K., Subhlok, J.: DwarfCode: a performance prediction tool for parallel applications. IEEE Trans. Comput. 65(2), 495\u2013507 (2016). https:\/\/doi.org\/10.1109\/TC.2015.2417526, http:\/\/ieeexplore.ieee.org\/document\/7098397\/","DOI":"10.1109\/TC.2015.2417526"},{"key":"24_CR35","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Liu, Y., Jiao, P., et al.: Automatic multi-parameter performance modeling of HPC applications on a new sunway supercomputer. IEEE Trans. Parallel Distrib. Syst. 34(11), 2965\u20132977 (2023). https:\/\/doi.org\/10.1109\/TPDS.2023.3317296, https:\/\/ieeexplore.ieee.org\/document\/10255321\/","DOI":"10.1109\/TPDS.2023.3317296"},{"key":"24_CR36","doi-asserted-by":"publisher","unstructured":"Zhou, W., Zhang, J., Sun, J., et\u00a0al.: Using small-scale history data to predict large-scale performance of HPC application. In: 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 787\u2013795. IEEE, New Orleans (2020). https:\/\/doi.org\/10.1109\/IPDPSW50202.2020.00135, https:\/\/ieeexplore.ieee.org\/document\/9150406\/","DOI":"10.1109\/IPDPSW50202.2020.00135"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Architectures for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-8405-5_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T20:15:30Z","timestamp":1775074530000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-8405-5_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819584048","9789819584055"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-8405-5_24","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"2 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICA3PP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Algorithms and Architectures for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhengzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ieee-cybermatics.org\/2025\/ica3pp\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}