{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:59:05Z","timestamp":1767322745290,"version":"3.48.0"},"publisher-location":"Cham","reference-count":30,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032105066","type":"print"},{"value":"9783032105073","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\/978-3-032-10507-3_11","type":"book-chapter","created":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:54:10Z","timestamp":1767322450000},"page":"205-223","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep RC: A Scalable Data Engineering and\u00a0Deep Learning Pipeline"],"prefix":"10.1007","author":[{"given":"Arup Kumar","family":"Sarker","sequence":"first","affiliation":[]},{"given":"Aymen","family":"Alsaadi","sequence":"additional","affiliation":[]},{"given":"Alexander James","family":"Halpern","sequence":"additional","affiliation":[]},{"given":"Prabhath","family":"Tangella","sequence":"additional","affiliation":[]},{"given":"Mikhail","family":"Titov","sequence":"additional","affiliation":[]},{"given":"Niranda","family":"Perera","sequence":"additional","affiliation":[]},{"given":"Mills","family":"Staylor","sequence":"additional","affiliation":[]},{"given":"Gregor","family":"von Laszewski","sequence":"additional","affiliation":[]},{"given":"Shantenu","family":"Jha","sequence":"additional","affiliation":[]},{"given":"Geoffrey","family":"Fox","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,2]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Abeykoon, V., et al.: Data engineering for HPC with python. In: 2020 IEEE\/ACM 9th Workshop on Python for High-Performance and Scientific Computing (PyHPC), pp. 13\u201321. IEEE (2020)","DOI":"10.1109\/PyHPC51966.2020.00007"},{"issue":"10","key":"11_CR2","doi-asserted-by":"publisher","first-page":"5293","DOI":"10.5194\/hess-21-5293-2017","volume":"21","author":"N Addor","year":"2017","unstructured":"Addor, N., Newman, A.J., Mizukami, N., Clark, M.P.: The camels data set: catchment attributes and meteorology for large-sample studies. Hydrol. Earth Syst. Sci. 21(10), 5293\u20135313 (2017)","journal-title":"Hydrol. Earth Syst. Sci."},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Babuji, Y., et al.: Parsl: pervasive parallel programming in python. In: Proceedings of the 28th International Symposium on High-Performance Parallel and Distributed Computing, pp. 25\u201336 (2019)","DOI":"10.1145\/3307681.3325400"},{"key":"11_CR4","first-page":"430","volume":"4","author":"P Barham","year":"2022","unstructured":"Barham, P., et al.: Pathways: asynchronous distributed dataflow for ML. Proc. Mach. Learn. Syst. 4, 430\u2013449 (2022)","journal-title":"Proc. Mach. Learn. Syst."},{"key":"11_CR5","unstructured":"Carbone, P., Katsifodimos, A., Ewen, S., Markl, V., Haridi, S., Tzoumas, K.: Apache flink: stream and batch processing in a single engine. Bull. Tech. Committee Data Eng. 38(4) (2015)"},{"key":"11_CR6","unstructured":"Dean, J.: Introducing pathways: a next-generation AI architecture (2021). https:\/\/blog.google\/technology\/ai\/introducing-pathways-next-generation-ai-architecture\/. Accessed 17 Apr 2024"},{"key":"11_CR7","doi-asserted-by":"publisher","unstructured":"DeCandia, G., et al.: Dynamo: amazon\u2019s highly available key-value store. In: Proceedings of Twenty-First ACM SIGOPS Symposium on Operating Systems Principles, SOSP 2007, pp. 205\u2013220. Association for Computing Machinery, New York (2007). https:\/\/doi.org\/10.1145\/1294261.1294281","DOI":"10.1145\/1294261.1294281"},{"key":"11_CR8","unstructured":"NVIDIA Developer: Nvidia collective communications library (NCCL) (2022). https:\/\/developer.nvidia.com\/nccl. Accessed 10 Aug 2024"},{"key":"11_CR9","unstructured":"Facebookincubator: Gloo: collective communications library with various primitives for multi-machine training (2023). https:\/\/github.com\/facebookincubator\/gloo. Accessed 01 Apr 2023"},{"key":"11_CR10","unstructured":"Goel, P.: Accelerated data analytics: Speed up data exploration with rapids CUDF (2023). https:\/\/developer.nvidia.com\/blog\/accelerated-data-analytics-speed-up-data-exploration-with-rapids-cudf\/. Accessed 10 Oct 2024"},{"key":"11_CR11","unstructured":"He, J., Chen, Y.J., Idamekorala, A., Fox, G.: Science time series: deep learning in hydrology. arXiv preprint arXiv:2410.15218 (2024)"},{"issue":"9","key":"11_CR12","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1101\/gr.107524.110","volume":"20","author":"A McKenna","year":"2010","unstructured":"McKenna, A.: The genome analysis toolkit: a mapreduce framework for analyzing next-generation DNA sequencing data. Genome Res. 20(9), 1297\u2013303 (2010). https:\/\/doi.org\/10.1101\/gr.107524.110","journal-title":"Genome Res."},{"key":"11_CR13","doi-asserted-by":"publisher","unstructured":"Merzky, A., Turilli, M., Titov, M., Al-Saadi, A., Jha, S.: Design and performance characterization of radical-pilot on leadership-class platforms. IEEE Trans. Parallel Distrib. Syst. 33(04), 818\u2013829 (2022). https:\/\/doi.org\/10.1109\/TPDS.2021.3105994","DOI":"10.1109\/TPDS.2021.3105994"},{"key":"11_CR14","unstructured":"Moritz, P., et al.: Ray: a distributed framework for emerging $$\\{$$AI$$\\}$$ applications. In: 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2018), pp. 561\u2013577 (2018)"},{"key":"11_CR15","unstructured":"Olivares, K.G., Chall\u00fa, C., Garza, A., Canseco, M.M., Dubrawski, A.: NeuralForecast: user friendly state-of-the-art neural forecasting models. PyCon Salt Lake City, Utah, US 2022 (2022). https:\/\/github.com\/Nixtla\/neuralforecast"},{"key":"11_CR16","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates, Inc. (2019). http:\/\/papers.neurips.cc\/paper\/9015-pytorch-an-imperative-style-high-performance-deep-learning-library.pdf"},{"key":"11_CR17","doi-asserted-by":"publisher","first-page":"1384619","DOI":"10.3389\/fhpcp.2024.1384619","volume":"2","author":"N Perera","year":"2024","unstructured":"Perera, N., et al.: Supercharging distributed computing environments for high-performance data engineering. Front. High Perform. Comput. 2, 1384619 (2024)","journal-title":"Front. High Perform. Comput."},{"key":"11_CR18","doi-asserted-by":"crossref","unstructured":"Perera, N., et al.: In-depth analysis on parallel processing patterns for high-performance dataframes. Future Gener. Comput. Syst. (2023)","DOI":"10.1016\/j.future.2023.07.007"},{"key":"11_CR19","unstructured":"Rivanna: University of Virginia\u2019s high-performance computing (HPC) system (2019). https:\/\/www.rc.virginia.edu\/userinfo\/rivanna\/overview\/"},{"key":"11_CR20","doi-asserted-by":"crossref","unstructured":"Rocklin, M.: Dask: parallel computation with blocked algorithms and task scheduling. In: Proceedings of the 14th Python in Science Conference, vol.\u00a0130, p.\u00a0136. Citeseer (2015)","DOI":"10.25080\/Majora-7b98e3ed-013"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Sarker, A.K., et al.: Radical-cylon: a heterogeneous data pipeline for scientific computing. In: Workshop on Job Scheduling Strategies for Parallel Processing, pp. 84\u2013102. Springer (2024)","DOI":"10.1007\/978-3-031-74430-3_5"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Sarker, A.K., Lin, F.X.: Incremental perception on real time 3D data. In: Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications, pp. 68\u201373 (2022)","DOI":"10.1145\/3508396.3512875"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Shamis, P., et al.: UCX: an open source framework for HPC network APIs and beyond. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 40\u201343. IEEE (2015)","DOI":"10.1109\/HOTI.2015.13"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Shan, K., et al.: Hybrid cloud and HPC approach to high-performance dataframes. In: 2022 IEEE International Conference on Big Data (Big Data), pp. 2728\u20132736. IEEE (2022)","DOI":"10.1109\/BigData55660.2022.10020958"},{"key":"11_CR25","unstructured":"Team, T.: Tensorflow: large-scale machine learning on heterogeneous systems (2015). http:\/\/tensorflow.org\/"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Widanage, C., et al.: High performance data engineering everywhere. In: 2020 IEEE International Conference on Smart Data Services (SMDS), pp. 122\u2013132. IEEE (2020)","DOI":"10.1109\/SMDS49396.2020.00022"},{"key":"11_CR27","unstructured":"Yuan, J., et al.: Oneflow: redesign the distributed deep learning framework from scratch. arXiv preprint arXiv:2110.15032 (2021)"},{"issue":"11","key":"11_CR28","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/2934664","volume":"59","author":"M Zaharia","year":"2016","unstructured":"Zaharia, M., et al.: Apache spark: a unified engine for big data processing. Commun. ACM 59(11), 56\u201365 (2016)","journal-title":"Commun. ACM"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, H., et al.: Informer: beyond efficient transformer for long sequence time-series forecasting. In: The Thirty-Fifth AAAI Conference on Artificial Intelligence, AAAI 2021, Virtual Conference, vol.\u00a035, pp. 11106\u201311115. AAAI Press (2021)","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"11_CR30","unstructured":"ZMQ: High-level messaging patterns (2021). https:\/\/zguide.zeromq.org\/docs\/chapter2\/#High-Level-Messaging-Patterns. Accessed 05 Apr 2024"}],"container-title":["Lecture Notes in Computer Science","Job Scheduling Strategies for Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-10507-3_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T02:54:13Z","timestamp":1767322453000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-10507-3_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032105066","9783032105073"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-10507-3_11","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 January 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"JSSPP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Workshop on Job Scheduling Strategies for Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"3 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"jsspp2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/jsspp.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}