{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:49:59Z","timestamp":1761709799122,"version":"3.40.3"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030633929"},{"type":"electronic","value":"9783030633936"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-63393-6_24","type":"book-chapter","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T09:04:28Z","timestamp":1608627868000},"page":"366-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Performance Evaluation of Python Based Data Analytics Frameworks in Summit: Early Experiences"],"prefix":"10.1007","author":[{"given":"Benjam\u00edn","family":"Hern\u00e1ndez","sequence":"first","affiliation":[]},{"given":"Suhas","family":"Somnath","sequence":"additional","affiliation":[]},{"given":"Junqi","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Joe","family":"Eaton","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Entschev","sequence":"additional","affiliation":[]},{"given":"John","family":"Kirkham","sequence":"additional","affiliation":[]},{"given":"Zahra","family":"Ronaghi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,12,18]]},"reference":[{"issue":"5","key":"24_CR1","first-page":"1","volume":"1695","author":"G Csardi","year":"2006","unstructured":"Csardi, G., Nepusz, T., et al.: The igraph software package for complex network research. InterJ. Complex Syst. 1695(5), 1\u20139 (2006)","journal-title":"InterJ. Complex Syst."},{"key":"24_CR2","unstructured":"Dask Development Team. Chunks - DASK (2020). https:\/\/docs.dask.org\/en\/latest\/array-chunks.html. Accessed 26 May 2020"},{"key":"24_CR3","unstructured":"Dask Distributed. Managing computation (2016). https:\/\/distributed.readthedocs.io\/en\/latest\/manage-computation.html#dask-collections-to-futures. Accessed 22 Sep 2020"},{"key":"24_CR4","unstructured":"Econtal. sgesvd\\_buffersize int32 overflow with CUDA (2019). https:\/\/github.com\/cupy\/cupy\/issues\/2351. Accessed 26 May 2020"},{"key":"24_CR5","unstructured":"Python Software Foundation and JetBrains. Python software foundation survey (2019). https:\/\/www.jetbrains.com\/lp\/python-developers-survey-2019. Accessed 26 May 2020"},{"key":"24_CR6","unstructured":"Hagberg, A., Swart, P., Chult, D.S.: Exploring network structure, dynamics, and function using networkx. Technical report, Los Alamos National Lab. (LANL), Los Alamos, NM (United States) (2008)"},{"key":"24_CR7","unstructured":"Hern\u00e1ndez, B.: Recipes to build, install and execute NVIDIA RAPIDS framework on Summit supercomputer (2020). https:\/\/github.com\/benjha\/nvrapids_olcf. Accessed 26 May 2020"},{"issue":"3","key":"24_CR8","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/MCSE.2007.55","volume":"9","author":"JD Hunter","year":"2007","unstructured":"Hunter, J.D.: Matplotlib: a 2D graphics environment. Comput. Sci. Eng. 9(3), 90\u201395 (2007)","journal-title":"Comput. Sci. Eng."},{"key":"24_CR9","unstructured":"Kluyver, T.,et al.: Jupyter notebooks-a publishing format for reproducible computational workflows. In: ELPUB, pp. 87\u201390 (2016)"},{"key":"24_CR10","unstructured":"Lu, H., Hern\u00e1ndez, B., Sommath, S., Yin, J.: Nvidia rapids on summit supercomputer: early experiences. In: Nvidia GPU Technology Conference (2020)"},{"key":"24_CR11","unstructured":"Martin, A.M., Townsend, K.P., Miller-Bains, K., Burr E.M.: 2019 Oak Ridge Leadership Computing Facility User Survey. Findings and Recommendations. Technical report, Scientific Assessment & Workforce Development, February 2020"},{"key":"24_CR12","unstructured":"McKinney, W., et al.: pandas: a foundational python library for data analysis and statistics. Python High Perform. Sci. Comput. 14(9), (2011)"},{"key":"24_CR13","unstructured":"NVIDIA. GPUDirect Storage: A Direct Path Between Storage and GPU Memory (2019). https:\/\/developer.nvidia.com\/blog\/gpudirect-storage\/. Accessed 14 Sept 2020"},{"key":"24_CR14","unstructured":"NVIDIA. Open GPU Data Science-RAPIDS 2020. https:\/\/rapids.ai. Accessed 26 May 2020"},{"key":"24_CR15","unstructured":"NVIDIA. Optimize groupby-agg in dask\\_cudf (2020). https:\/\/github.com\/rapidsai\/cudf\/pull\/6248"},{"key":"24_CR16","unstructured":"Okuta,R., Unno, Y., Nishino, D., Hido, S., Loomis, C.: Cupy: a numpy-compatible library for Nvidia GPU calculations. In: Proceedings of Workshop on Machine Learning Systems (LearningSys) in the Thirty-first Annual Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"24_CR17","doi-asserted-by":"crossref","unstructured":"Oral, S., et al.: End-to-end i\/o portfolio for the summit supercomputing ecosystem. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC 2019, New York, NY, USA. Association for Computing Machinery (2019)","DOI":"10.1145\/3295500.3356157"},{"key":"24_CR18","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F.: Scikit-learn: Machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"issue":"4","key":"24_CR19","doi-asserted-by":"publisher","first-page":"193","DOI":"10.3390\/info11040193","volume":"11","author":"R Sebastian","year":"2020","unstructured":"Sebastian, R., Joshua, P., Corey, N.: Machine learning in python: Main developments and technology trends in data science, machine learning, and artificial intelligence. Information 11(4), 193 (2020)","journal-title":"Information"},{"issue":"3\/4","key":"24_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1147\/JRD.2019.2963637","volume":"64","author":"S Roberts","year":"2020","unstructured":"Roberts, S., Mann, C., Marroquin, C.: Redefining IBM power system design for coral. IBM J. Res. Dev. 64(3\/4), 1\u201310 (2020)","journal-title":"IBM J. Res. Dev."},{"key":"24_CR21","doi-asserted-by":"crossref","unstructured":"Rocklin, M.: Dask: parallel computation with blocked algorithms and task scheduling. In: Huff, K., Bergstra, J., (eds.) Proceedings of the 14th Python in Science Conference, pp. 130\u2013136 (2015)","DOI":"10.25080\/Majora-7b98e3ed-013"},{"key":"24_CR22","unstructured":"Schmidt, D., Yin, J., Matheson, M., Messer, B., Shankar, M.: Defining big data analytics benchmarks for next generation supercomputers (2018)"},{"key":"24_CR23","doi-asserted-by":"crossref","unstructured":"Shamis, P., et al.: UCX: an open source framework for HPC network APIs and beyond. In: IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 40\u201343 (2015)","DOI":"10.1109\/HOTI.2015.13"},{"key":"24_CR24","unstructured":"Vazhkudai, S.S.: The design, deployment, and evaluation of the coral pre-exascale systems. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018. IEEE Press (2018)"},{"key":"24_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/978-3-030-34356-9_26","volume-title":"High Performance Computing","author":"V Vergara Larrea","year":"2019","unstructured":"Vergara Larrea, V., et al.: Scaling the summit: deploying the world\u2019s fastest supercomputer. In: Weiland, M., Juckeland, G., Alam, S., Jagode, H. (eds.) ISC High Performance 2019. LNCS, vol. 11887, pp. 330\u2013351. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-34356-9_26"},{"issue":"3","key":"24_CR26","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"Virtanen, P., et al.: Scipy 1.0: fundamental algorithms for scientific computing in python. Nat. Meth. 17(3), 261\u2013272 (2020)","journal-title":"Nat. Meth."},{"issue":"2","key":"24_CR27","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MCSE.2011.37","volume":"13","author":"S van der Walt","year":"2011","unstructured":"van der Walt, S., Colbert, S.C., Varoquaux, G.: The numpy array: a structure for efficient numerical computation. Comput. Sci. Eng. 13(2), 22\u201330 (2011)","journal-title":"Comput. Sci. Eng."}],"container-title":["Communications in Computer and Information Science","Driving Scientific and Engineering Discoveries Through the Convergence of HPC, Big Data and AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-63393-6_24","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,24]],"date-time":"2021-04-24T03:04:51Z","timestamp":1619233491000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-63393-6_24"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030633929","9783030633936"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-63393-6_24","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"18 December 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SMC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Smoky Mountains Computational Sciences and Engineering Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Oak Ridge, TN","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"smc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/smc.ornl.gov\/","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":"easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"94","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":"36","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":"1","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":"38% - 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":"3.75","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":"3","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}