{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:02:09Z","timestamp":1742943729784,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":33,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819708611"},{"type":"electronic","value":"9789819708628"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-0862-8_9","type":"book-chapter","created":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T08:03:04Z","timestamp":1709193784000},"page":"126-145","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeletePop: A DLT Execution Time Predictor Based on\u00a0Comprehensive Modeling"],"prefix":"10.1007","author":[{"given":"Yongzhe","family":"He","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueyuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"En","family":"Shao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangming","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ninghui","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,1]]},"reference":[{"key":"9_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/3-540-39997-6_1","volume-title":"Job Scheduling Strategies for Parallel Processing","author":"K Aida","year":"2000","unstructured":"Aida, K.: Effect of job size characteristics on job scheduling performance. In: Feitelson, D.G., Rudolph, L. (eds.) JSSPP 2000. LNCS, vol. 1911, pp. 1\u201317. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-39997-6_1"},{"doi-asserted-by":"publisher","unstructured":"Arafa, Y., et al.: Hybrid, scalable, trace-driven performance modeling of GPGPUs. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2021, pp. 1\u201315. Association for Computing Machinery. https:\/\/doi.org\/10.1145\/3458817.3476221","key":"9_CR2","DOI":"10.1145\/3458817.3476221"},{"doi-asserted-by":"publisher","unstructured":"Bai, Y., et al.: Gradient compression supercharged high-performance data parallel DNN training. In: Proceedings of the ACM SIGOPS 28th Symposium on Operating Systems Principles CD-ROM, pp. 359\u2013375. ACM (2021). https:\/\/doi.org\/10.1145\/3477132.3483553","key":"9_CR3","DOI":"10.1145\/3477132.3483553"},{"doi-asserted-by":"publisher","unstructured":"Dadu, V., Nowatzki, T.: TaskStream: accelerating task-parallel workloads by recovering program structure. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 1\u201313. ACM (2022). https:\/\/doi.org\/10.1145\/3503222.3507706","key":"9_CR4","DOI":"10.1145\/3503222.3507706"},{"unstructured":"Dean, J., et al.: Large scale distributed deep networks. In: Advances in Neural Information Processing Systems, vol. 25. Curran Associates Inc. (2012)","key":"9_CR5"},{"doi-asserted-by":"publisher","unstructured":"Gautam, J.V., Prajapati, H.B., Dabhi, V.K., Chaudhary, S.: A survey on job scheduling algorithms in big data processing. In: 2015 IEEE International Conference on Electrical, Computer and Communication Technologies (ICECCT), pp. 1\u201311 (2015). https:\/\/doi.org\/10.1109\/ICECCT.2015.7226035","key":"9_CR6","DOI":"10.1109\/ICECCT.2015.7226035"},{"unstructured":"Goldsborough, P.: A Tour of TensorFlow (2016)","key":"9_CR7"},{"unstructured":"Hindman, B., et al.: Mesos: a platform for fine-grained resource sharing in the data center. In: Proceedings of the 8th USENIX Conference on Networked Systems Design and Implementation, NSDI 2011, pp. 295\u2013308. USENIX Association (2011)","key":"9_CR8"},{"issue":"3","key":"9_CR9","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/s42514-019-00018-4","volume":"1","author":"MH Javed","year":"2019","unstructured":"Javed, M.H., Ibrahim, K.Z., Lu, X.: Performance analysis of deep learning workloads using roofline trajectories. CCF Trans. High Perform. Comput. 1(3), 224\u2013239 (2019). https:\/\/doi.org\/10.1007\/s42514-019-00018-4","journal-title":"CCF Trans. High Perform. Comput."},{"unstructured":"Jia, Z., Zaharia, M., Aiken, A.: Beyond data and model parallelism for deep neural networks, vol. 1, pp. 1\u201313 (2019)","key":"9_CR10"},{"unstructured":"Kaufman, S., et al.: A learned performance model for tensor processing units 3, 387\u2013400","key":"9_CR11"},{"issue":"3","key":"9_CR12","doi-asserted-by":"publisher","first-page":"2287","DOI":"10.1007\/s10586-020-03144-9","volume":"23","author":"Y Kim","year":"2020","unstructured":"Kim, Y., Choi, H., Lee, J., Kim, J.-S., Jei, H., Roh, H.: Towards an optimized distributed deep learning framework for a heterogeneous multi-GPU cluster. Cluster Comput. 23(3), 2287\u20132300 (2020). https:\/\/doi.org\/10.1007\/s10586-020-03144-9","journal-title":"Cluster Comput."},{"unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25. Curran Associates Inc. (2012)","key":"9_CR13"},{"unstructured":"Kwon, W., Yu, G.I., Jeong, E., Chun, B.G.: Nimble: lightweight and parallel GPU task scheduling for deep learning, vol. 33, pp. 8343\u20138354 (2020)","key":"9_CR14"},{"issue":"1","key":"9_CR15","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1109\/TPDS.2019.2928289","volume":"31","author":"A Li","year":"2020","unstructured":"Li, A., et al.: Evaluating modern GPU interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirect. IEEE Trans. Parallel Distrib. Syst. 31(1), 94\u2013110 (2020). https:\/\/doi.org\/10.1109\/TPDS.2019.2928289","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"doi-asserted-by":"publisher","unstructured":"Li, M.: Scaling distributed machine learning with the parameter server. In: Proceedings of the 2014 International Conference on Big Data Science and Computing, BigDataScience 2014, p. 1. Association for Computing Machinery (2014). https:\/\/doi.org\/10.1145\/2640087.2644155","key":"9_CR16","DOI":"10.1145\/2640087.2644155"},{"doi-asserted-by":"publisher","unstructured":"Narayanan, D., et al.: PipeDream: generalized pipeline parallelism for DNN training. In: Proceedings of the 27th ACM Symposium on Operating Systems Principles, SOSP 2019, pp. 1\u201315. Association for Computing Machinery (2019). https:\/\/doi.org\/10.1145\/3341301.3359646","key":"9_CR17","DOI":"10.1145\/3341301.3359646"},{"key":"9_CR18","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.jpdc.2020.11.005","volume":"149","author":"S Ouyang","year":"2021","unstructured":"Ouyang, S., Dong, D., Xu, Y., Xiao, L.: Communication optimization strategies for distributed deep neural network training: a survey. J. Parallel Distrib. Comput. 149, 52\u201365 (2021). https:\/\/doi.org\/10.1016\/j.jpdc.2020.11.005","journal-title":"J. Parallel Distrib. Comput."},{"unstructured":"Park, J.H., et al.: HetPipe: enabling large DNN training on (Whimpy) heterogeneous GPU clusters through integration of pipelined model parallelism and data parallelism. In: Proceedings of the 2020 USENIX Conference on USENIX Annual Technical Conference, vol. 21, pp. 307\u2013321. USENIX Association (2020)","key":"9_CR19"},{"issue":"2","key":"9_CR20","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.jpdc.2008.09.002","volume":"69","author":"P Patarasuk","year":"2009","unstructured":"Patarasuk, P., Yuan, X.: Bandwidth optimal all-reduce algorithms for clusters of workstations. J. Parallel Distrib. Comput. 69(2), 117\u2013124 (2009). https:\/\/doi.org\/10.1016\/j.jpdc.2008.09.002","journal-title":"J. Parallel Distrib. Comput."},{"doi-asserted-by":"publisher","unstructured":"Robson, E., Xu, C., Wills, L.W.: ProSE: the architecture and design of a protein discovery engine. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 655\u2013668. ACM (2022). https:\/\/doi.org\/10.1145\/3503222.3507722","key":"9_CR21","DOI":"10.1145\/3503222.3507722"},{"doi-asserted-by":"publisher","unstructured":"Sanders, P., Mehlhorn, K., Dietzfelbinger, M., Dementiev, R.: Sequential and Parallel Algorithms and Data Structures: The Basic Toolbox. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-25209-0","key":"9_CR22","DOI":"10.1007\/978-3-030-25209-0"},{"doi-asserted-by":"publisher","unstructured":"Schwarzkopf, M., Konwinski, A., Abd-El-Malek, M., Wilkes, J.: Omega: flexible, scalable schedulers for large compute clusters. In: Proceedings of the 8th ACM European Conference on Computer Systems, EuroSys 2013, pp. 351\u2013364. Association for Computing Machinery (2013). https:\/\/doi.org\/10.1145\/2465351.2465386","key":"9_CR23","DOI":"10.1145\/2465351.2465386"},{"doi-asserted-by":"publisher","unstructured":"Simakov, N.A., et al.: Slurm simulator: improving slurm scheduler performance on large HPC systems by utilization of multiple controllers and node sharing. In: Proceedings of the Practice and Experience on Advanced Research Computing, PEARC 2018, pp. 1\u20138. Association for Computing Machinery (2018). https:\/\/doi.org\/10.1145\/3219104.3219111","key":"9_CR24","DOI":"10.1145\/3219104.3219111"},{"doi-asserted-by":"publisher","unstructured":"Song, L., Mao, J., Zhuo, Y., Qian, X., Li, H., Chen, Y.: HyPar: towards hybrid parallelism for deep learning accelerator array. In: 2019 IEEE International Symposium on High Performance Computer Architecture (HPCA), pp. 56\u201368. IEEE (2019). https:\/\/doi.org\/10.1109\/HPCA.2019.00027","key":"9_CR25","DOI":"10.1109\/HPCA.2019.00027"},{"doi-asserted-by":"publisher","unstructured":"Vavilapalli, V.K., et al.: Apache hadoop YARN: yet another resource negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing, SOCC 2013, pp. 1\u201316. Association for Computing Machinery (2013). https:\/\/doi.org\/10.1145\/2523616.2523633","key":"9_CR26","DOI":"10.1145\/2523616.2523633"},{"issue":"4","key":"9_CR27","doi-asserted-by":"publisher","first-page":"24","DOI":"10.9790\/4200-0704012428","volume":"7","author":"A Verma","year":"2017","unstructured":"Verma, A., Dahiya, P.K.: PCIe bus: a state-of-the-art-review. IOSR J. VLSI Sig. Process. 7(4), 24\u201328 (2017). https:\/\/doi.org\/10.9790\/4200-0704012428","journal-title":"IOSR J. VLSI Sig. Process."},{"doi-asserted-by":"publisher","unstructured":"Wette, P., Schwabe, A., Splietker, M., Karl, H.: Extending Hadoop\u2019s yarn scheduler load simulator with a highly realistic network & traffic model. In: Proceedings of the 2015 1st IEEE Conference on Network Softwarization (NetSoft), pp. 1\u20132 (2015). https:\/\/doi.org\/10.1109\/NETSOFT.2015.7116169","key":"9_CR28","DOI":"10.1109\/NETSOFT.2015.7116169"},{"doi-asserted-by":"publisher","unstructured":"Yang, K., Cao, R., Zhou, Y., Zhang, J., Shao, E., Tan, G.: Deep reinforcement agent for failure-aware job scheduling in high-performance computing. In: 2021 IEEE 27th International Conference on Parallel and Distributed Systems (ICPADS), pp. 442\u2013449 (2021). https:\/\/doi.org\/10.1109\/ICPADS53394.2021.00061","key":"9_CR29","DOI":"10.1109\/ICPADS53394.2021.00061"},{"doi-asserted-by":"publisher","unstructured":"Yang, X., et al.: Integrating dynamic pricing of electricity into energy aware scheduling for HPC systems. In: Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, SC 2013, pp. 1\u201311 (2013). https:\/\/doi.org\/10.1145\/2503210.2503264","key":"9_CR30","DOI":"10.1145\/2503210.2503264"},{"doi-asserted-by":"publisher","unstructured":"Yang, Y., et al.: INFless: a native serverless system for low-latency, high-throughput inference. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 768\u2013781. ACM (2022). https:\/\/doi.org\/10.1145\/3503222.3507709","key":"9_CR31","DOI":"10.1145\/3503222.3507709"},{"issue":"8","key":"9_CR32","doi-asserted-by":"publisher","first-page":"1878","DOI":"10.1109\/TPDS.2020.2978045","volume":"31","author":"P Zhang","year":"2020","unstructured":"Zhang, P., Fang, J., Yang, C., Huang, C., Tang, T., Wang, Z.: Optimizing streaming parallelism on heterogeneous many-core architectures. IEEE Trans. Parallel Distrib. Syst. 31(8), 1878\u20131896 (2020). https:\/\/doi.org\/10.1109\/TPDS.2020.2978045","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"doi-asserted-by":"publisher","unstructured":"Zheng, Z., et al.: AStitch: enabling a new multi-dimensional optimization space for memory-intensive ML training and inference on modern SIMT architectures. In: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, pp. 359\u2013373. ACM (2022). https:\/\/doi.org\/10.1145\/3503222.3507723","key":"9_CR33","DOI":"10.1145\/3503222.3507723"}],"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\/978-981-97-0862-8_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,29]],"date-time":"2024-02-29T08:16:42Z","timestamp":1709194602000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-0862-8_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819708611","9789819708628"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-0862-8_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 March 2024","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":"Tianjin","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ica3pp2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tjutanklab.com\/ica3pp2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Online submission system","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"439","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":"145","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":"33% - 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":"5","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)"}}]}}