{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:36:52Z","timestamp":1768030612848,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","license":[{"start":{"date-parts":[[2018,8,13]],"date-time":"2018-08-13T00:00:00Z","timestamp":1534118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1440677"],"award-info":[{"award-number":["1440677"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["1446054"],"award-info":[{"award-number":["1446054"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2018,8,13]]},"DOI":"10.1145\/3225058.3225128","type":"proceedings-article","created":{"date-parts":[[2018,8,8]],"date-time":"2018-08-08T19:13:06Z","timestamp":1533755586000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Task-parallel Analysis of Molecular Dynamics Trajectories"],"prefix":"10.1145","author":[{"given":"Ioannis","family":"Paraskevakos","sequence":"first","affiliation":[{"name":"Rutgers University, Piscataway, New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andre","family":"Luckow","sequence":"additional","affiliation":[{"name":"Ludwig-Maximilians-University, Munich, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mahzad","family":"Khoshlessan","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Chantzialexiou","sequence":"additional","affiliation":[{"name":"Rutgers University, New Jersey, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas E.","family":"Cheatham","sequence":"additional","affiliation":[{"name":"University of Utah, Salt Lake City, Utah, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oliver","family":"Beckstein","sequence":"additional","affiliation":[{"name":"Arizona State University, Tempe, Arizona, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Geoffrey C.","family":"Fox","sequence":"additional","affiliation":[{"name":"Indiana University, Bloomington, Indiana, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shantenu","family":"Jha","sequence":"additional","affiliation":[{"name":"Rutgers University, Brookhaven National Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2018,8,13]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2016. Scikit-Learn: Nearest Neighbors. http:\/\/scikit-learn.org\/stable\/modules\/neighbors.html.  2016. Scikit-Learn: Nearest Neighbors. http:\/\/scikit-learn.org\/stable\/modules\/neighbors.html."},{"key":"e_1_3_2_1_2_1","volume-title":"2016 IEEE 12th International Conference on e-Science (e-Science). 361--370","author":"Balasubramanian V.","unstructured":"V. Balasubramanian , I. Bethune , A. Shkurti , E. Breitmoser , E. Hruska , C. Clementi , C. Laughton , and S. Jha . 2016. ExTASY: Scalable and flexible coupling of MD simulations and advanced sampling techniques . In 2016 IEEE 12th International Conference on e-Science (e-Science). 361--370 . V. Balasubramanian, I. Bethune, A. Shkurti, E. Breitmoser, E. Hruska, C. Clementi, C. Laughton, and S. Jha. 2016. ExTASY: Scalable and flexible coupling of MD simulations and advanced sampling techniques. In 2016 IEEE 12th International Conference on e-Science (e-Science). 361--370."},{"key":"e_1_3_2_1_3_1","volume-title":"Harnessing the Power of Many: Extensible Toolkit for Scalable Ensemble Applications. IPDPS 2018 (accepted)","author":"Balasubramanian Vivek","year":"2018","unstructured":"Vivek Balasubramanian , Matteo Turilli , Weiming Hu , Matthieu Lefebvre , Wenjie Lei , Guido Cervone , Jeroen Tromp , and Shantenu Jha . 2018 . Harnessing the Power of Many: Extensible Toolkit for Scalable Ensemble Applications. IPDPS 2018 (accepted) (2018). https:\/\/arxiv.org\/abs\/1710.08491. Vivek Balasubramanian, Matteo Turilli, Weiming Hu, Matthieu Lefebvre, Wenjie Lei, Guido Cervone, Jeroen Tromp, and Shantenu Jha. 2018. Harnessing the Power of Many: Extensible Toolkit for Scalable Ensemble Applications. IPDPS 2018 (accepted) (2018). https:\/\/arxiv.org\/abs\/1710.08491."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2015.7"},{"key":"e_1_3_2_1_5_1","volume-title":"Computational Approaches for Cancer Workshop, SC'17","author":"Jumana","year":"2017","unstructured":"Jumana Dakka and et al. 2017. High-throughput Binding Affinity Calculations at Extreme Scales . accepted Computational Approaches for Cancer Workshop, SC'17 ( 2017 ). http:\/\/arxiv.org\/abs\/1712.09168. Jumana Dakka and et al. 2017. High-throughput Binding Affinity Calculations at Extreme Scales. accepted Computational Approaches for Cancer Workshop, SC'17 (2017). http:\/\/arxiv.org\/abs\/1712.09168."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2005.03.010"},{"key":"e_1_3_2_1_7_1","volume-title":"MapReduce: Simplified Data Processing on Large Clusters. In OSDI'04: Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation. USENIX Association","author":"Dean Jeffrey","year":"2004","unstructured":"Jeffrey Dean and Sanjay Ghemawat . 2004 . MapReduce: Simplified Data Processing on Large Clusters. In OSDI'04: Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation. USENIX Association , Berkeley, CA, USA, 137--150. Jeffrey Dean and Sanjay Ghemawat. 2004. MapReduce: Simplified Data Processing on Large Clusters. In OSDI'04: Proceedings of the 6th conference on Symposium on Opearting Systems Design & Implementation. USENIX Association, Berkeley, CA, USA, 137--150."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1851476.1851593"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid.2015.122"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2737909.2737912"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.23035"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.232073"},{"key":"e_1_3_2_1_13_1","volume-title":"Omer Rana, and Yogesh Simmhan.","author":"Jha Shantenu","year":"2017","unstructured":"Shantenu Jha , Daniel S. Katz , Andre Luckow , Neil Chue Hong , Omer Rana, and Yogesh Simmhan. 2017 . Introducing distributed dynamic data-intensive (D3) science: Understanding applications and infrastructure. Concurrency and Computation: Practice and Experience ( 2017), e4032-n\/a. e4032 cpe.4032. Shantenu Jha, Daniel S. Katz, Andre Luckow, Neil Chue Hong, Omer Rana, and Yogesh Simmhan. 2017. Introducing distributed dynamic data-intensive (D3) science: Understanding applications and infrastructure. Concurrency and Computation: Practice and Experience (2017), e4032-n\/a. e4032 cpe.4032."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.Congress.2014.137"},{"key":"e_1_3_2_1_15_1","unstructured":"Eric Jones Travis Oliphant Pearu Peterson etal 2001-. SciPy: Open source scientific tools for Python.  Eric Jones Travis Oliphant Pearu Peterson et al. 2001-. SciPy: Open source scientific tools for Python."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Supun Kamburugamuve Geoffrey Fox Pulasthi Wickramasinghe Govindarajan Kannan and Vibhatha Abeykoon. 2018. Twister:Net - Communication Library for Big Data Processing in HPC and Cloud Environments.  Supun Kamburugamuve Geoffrey Fox Pulasthi Wickramasinghe Govindarajan Kannan and Vibhatha Abeykoon. 2018. Twister:Net - Communication Library for Big Data Processing in HPC and Cloud Environments.","DOI":"10.1109\/CLOUD.2018.00055"},{"key":"e_1_3_2_1_17_1","volume-title":"Fox","author":"Kamburugamuve Supun","year":"2017","unstructured":"Supun Kamburugamuve , Pulasthi Wickramasinghe , Saliya Ekanayake †, and Geoffrey C . Fox . 2017 . Anatomy of machine learning algorithm implementations in MPI, Spark, and Flink. In Technical Report. Indiana University , Bloomington. Supun Kamburugamuve, Pulasthi Wickramasinghe, Saliya Ekanayake†, and Geoffrey C. Fox. 2017. Anatomy of machine learning algorithm implementations in MPI, Spark, and Flink. In Technical Report. Indiana University, Bloomington."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"X. Lu D. Shankar S. Gugnani and D. K. Panda. 2016. High-Performance Design of Apache Spark with RDMA and Its Benefits on Various Workloads.  X. Lu D. Shankar S. Gugnani and D. K. Panda. 2016. High-Performance Design of Apache Spark with RDMA and Its Benefits on Various Workloads.","DOI":"10.1109\/BigData.2016.7840611"},{"key":"e_1_3_2_1_19_1","volume-title":"Hadoop on HPC: Integrating Hadoop and Pilot-Based Dynamic Resource Management. 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","author":"Luckow Andre","year":"2016","unstructured":"Andre Luckow , Ioannis Paraskevakos , George Chantzialexiou , and Shantenu Jha . 2016 . Hadoop on HPC: Integrating Hadoop and Pilot-Based Dynamic Resource Management. 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (2016), 1607--1616. Andre Luckow, Ioannis Paraskevakos, George Chantzialexiou, and Shantenu Jha. 2016. Hadoop on HPC: Integrating Hadoop and Pilot-Based Dynamic Resource Management. 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) (2016), 1607--1616."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/eScience.2012.6404423"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2287016.2287020"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpj.2015.08.015"},{"key":"e_1_3_2_1_23_1","first-page":"1","article-title":"MLlib: Machine Learning in Apache Spark","volume":"17","author":"Meng Xiangrui","year":"2016","unstructured":"Xiangrui Meng , Joseph Bradley , Burak Yavuz , Evan Sparks , Shivaram Venkataraman , Davies Liu , Jeremy Freeman , DB Tsai , Manish Amde , Sean Owen , Doris Xin , Reynold Xin , Michael J. Franklin , Reza Zadeh , Matei Zaharia , and Ameet Talwalkar . 2016 . MLlib: Machine Learning in Apache Spark . Journal of Machine Learning Research 17 , 34 (2016), 1 -- 7 . Xiangrui Meng, Joseph Bradley, Burak Yavuz, Evan Sparks, Shivaram Venkataraman, Davies Liu, Jeremy Freeman, DB Tsai, Manish Amde, Sean Owen, Doris Xin, Reynold Xin, Michael J. Franklin, Reza Zadeh, Matei Zaharia, and Ameet Talwalkar. 2016. MLlib: Machine Learning in Apache Spark. Journal of Machine Learning Research 17, 34 (2016), 1--7.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_24_1","volume-title":"Design and Performance Characterization of RADICAL-Pilot on Titan. in preparation","author":"Merzky Andre","year":"2018","unstructured":"Andre Merzky , Matteo Turilli , Manuel Maldonado , and Shantenu Jha . 2018. Design and Performance Characterization of RADICAL-Pilot on Titan. in preparation ( 2018 ). https:\/\/arxiv.org\/abs\/1801.01843. Andre Merzky, Matteo Turilli, Manuel Maldonado, and Shantenu Jha. 2018. Design and Performance Characterization of RADICAL-Pilot on Titan. in preparation (2018). https:\/\/arxiv.org\/abs\/1801.01843."},{"key":"e_1_3_2_1_25_1","unstructured":"Andre Merzky Matteo Turilli Manuel Maldonado Mark Santcroos and Shantenu Jha. 2018. Using Pilot Systems to Execute Many Task Workloads on Supercomputers. (2018). http:\/\/arxiv.org\/abs\/1512.08194.  Andre Merzky Matteo Turilli Manuel Maldonado Mark Santcroos and Shantenu Jha. 2018. Using Pilot Systems to Execute Many Task Workloads on Supercomputers. (2018). http:\/\/arxiv.org\/abs\/1512.08194."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.21787"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1080\/08927022.2014.935372"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-629e541a-00e"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-7b98e3ed-013"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1021\/ct400341p"},{"key":"e_1_3_2_1_32_1","volume-title":"Roe and III Thomas E. Cheatham","author":"Daniel","year":"2018","unstructured":"Daniel R. Roe and III Thomas E. Cheatham . 2018 . Parallelization of CPPTRAJ Enables Large Scale Analysis of Molecular Dynamics Trajectory Data. Journal of Computational Chemistry ( 2018). in press. Daniel R. Roe and III Thomas E. Cheatham. 2018. Parallelization of CPPTRAJ Enables Large Scale Analysis of Molecular Dynamics Trajectory Data. Journal of Computational Chemistry (2018). in press."},{"key":"e_1_3_2_1_33_1","volume-title":"Path Similarity Analysis: A Method for Quantifying Macromolecular Pathways. PLoS Comput Biol 11, 10 (10","author":"Seyler Sean L.","year":"2015","unstructured":"Sean L. Seyler , Avishek Kumar , M. F. Thorpe , and Oliver Beckstein . 2015. Path Similarity Analysis: A Method for Quantifying Macromolecular Pathways. PLoS Comput Biol 11, 10 (10 2015 ), 1--37. Sean L. Seyler, Avishek Kumar, M. F. Thorpe, and Oliver Beckstein. 2015. Path Similarity Analysis: A Method for Quantifying Macromolecular Pathways. PLoS Comput Biol 11, 10 (10 2015), 1--37."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2408351"},{"key":"e_1_3_2_1_35_1","volume-title":"RepEx: A Flexible Framework for Scalable Replica Exchange Molecular Dynamics Simulations. In 2016 45th International Conference on Parallel Processing (ICPP). 628--637","author":"Treikalis A.","unstructured":"A. Treikalis , A. Merzky , H. Chen , T. S. Lee , D. M. York , and S. Jha . 2016 . RepEx: A Flexible Framework for Scalable Replica Exchange Molecular Dynamics Simulations. In 2016 45th International Conference on Parallel Processing (ICPP). 628--637 . A. Treikalis, A. Merzky, H. Chen, T. S. Lee, D. M. York, and S. Jha. 2016. RepEx: A Flexible Framework for Scalable Replica Exchange Molecular Dynamics Simulations. In 2016 45th International Conference on Parallel Processing (ICPP). 628--637."},{"key":"e_1_3_2_1_36_1","volume-title":"2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis. 1--12","author":"Tu Tiankai","unstructured":"Tiankai Tu , C. A. Rendleman , D. W. Borhani , R. O. Dror , J. Gullingsrud , M. O. Jensen , J. L. Klepeis , P. Maragakis , P. Miller , K. A. Stafford , and D. E. Shaw . 2008. A scalable parallel framework for analyzing terascale molecular dynamics simulation trajectories . In 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis. 1--12 . Tiankai Tu, C. A. Rendleman, D. W. Borhani, R. O. Dror, J. Gullingsrud, M. O. Jensen, J. L. Klepeis, P. Maragakis, P. Miller, K. A. Stafford, and D. E. Shaw. 2008. A scalable parallel framework for analyzing terascale molecular dynamics simulation trajectories. In 2008 SC - International Conference for High Performance Computing, Networking, Storage and Analysis. 1--12."},{"key":"e_1_3_2_1_37_1","volume-title":"Evaluating Distributed Execution of Workloads. In 2017 IEEE 13th International Conference on e-Science (e-Science). 276--285","author":"Turilli M.","unstructured":"M. Turilli , Y. N. Babuji , A. Merzky , M. T. Ha , M. Wilde , D. S. Katz , and S. Jha . 2017 . Evaluating Distributed Execution of Workloads. In 2017 IEEE 13th International Conference on e-Science (e-Science). 276--285 . M. Turilli, Y. N. Babuji, A. Merzky, M. T. Ha, M. Wilde, D. S. Katz, and S. Jha. 2017. Evaluating Distributed Execution of Workloads. In 2017 IEEE 13th International Conference on e-Science (e-Science). 276--285."},{"key":"e_1_3_2_1_38_1","volume-title":"A Building Blocks Approach towards Domain Specific Workflow Systems? Short Paper","author":"Turilli Matteo","year":"2018","unstructured":"Matteo Turilli , Andre Merzky , Vivek Balasubramanian , and Shantenu Jha . 2018. A Building Blocks Approach towards Domain Specific Workflow Systems? Short Paper ( IEEE\/ACM CCGrid 2018 ) (2018). http:\/\/arxiv.org\/abs\/1609.03484. Matteo Turilli, Andre Merzky, Vivek Balasubramanian, and Shantenu Jha. 2018. A Building Blocks Approach towards Domain Specific Workflow Systems? Short Paper (IEEE\/ACM CCGrid 2018) (2018). http:\/\/arxiv.org\/abs\/1609.03484."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3177851"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2011.37"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcc.23943"},{"key":"e_1_3_2_1_42_1","volume-title":"Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI'12)","author":"Zaharia Matei","year":"2012","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Tathagata Das , Ankur Dave , Justin Ma , Murphy McCauley , Michael J. Franklin , Scott Shenker , and Ion Stoica . 2012 . Resilient Distributed Datasets: A Fault-tolerant Abstraction for In-memory Cluster Computing . In Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI'12) . USENIX Association, Berkeley, CA, USA, 2--2. Matei Zaharia, Mosharaf Chowdhury, Tathagata Das, Ankur Dave, Justin Ma, Murphy McCauley, Michael J. Franklin, Scott Shenker, and Ion Stoica. 2012. Resilient Distributed Datasets: A Fault-tolerant Abstraction for In-memory Cluster Computing. In Proceedings of the 9th USENIX Conference on Networked Systems Design and Implementation (NSDI'12). USENIX Association, Berkeley, CA, USA, 2--2."},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 2Nd USENIX Conference on Hot Topics in Cloud Computing (HotCloud'10)","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia , Mosharaf Chowdhury , Michael J. Franklin , Scott Shenker , and Ion Stoica . 2010 . Spark: Cluster Computing with Working Sets . In Proceedings of the 2Nd USENIX Conference on Hot Topics in Cloud Computing (HotCloud'10) . USENIX Association, Berkeley, CA, USA, 10--10. Matei Zaharia, Mosharaf Chowdhury, Michael J. Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster Computing with Working Sets. In Proceedings of the 2Nd USENIX Conference on Hot Topics in Cloud Computing (HotCloud'10). USENIX Association, Berkeley, CA, USA, 10--10."}],"event":{"name":"ICPP 2018: 47th International Conference on Parallel Processing","location":"Eugene OR USA","acronym":"ICPP 2018","sponsor":["University of Oregon University of Oregon"]},"container-title":["Proceedings of the 47th International Conference on Parallel Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3225058.3225128","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3225058.3225128","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3225058.3225128","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T01:39:50Z","timestamp":1750210790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3225058.3225128"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,8,13]]},"references-count":42,"alternative-id":["10.1145\/3225058.3225128","10.1145\/3225058"],"URL":"https:\/\/doi.org\/10.1145\/3225058.3225128","relation":{},"subject":[],"published":{"date-parts":[[2018,8,13]]},"assertion":[{"value":"2018-08-13","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}