{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T07:49:01Z","timestamp":1768031341834,"version":"3.49.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031396977","type":"print"},{"value":"9783031396984","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-39698-4_22","type":"book-chapter","created":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:02:40Z","timestamp":1692770560000},"page":"323-338","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Optimizing Data Movement for\u00a0GPU-Based In-Situ Workflow Using GPUDirect RDMA"],"prefix":"10.1007","author":[{"given":"Bo","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip E.","family":"Davis","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Morales","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keita","family":"Teranishi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Manish","family":"Parashar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,8,24]]},"reference":[{"key":"22_CR1","unstructured":"ADIOS 2 Documentation (2022). https:\/\/adios2.readthedocs.io\/en\/latest\/advanced\/gpu_aware.html"},{"key":"22_CR2","unstructured":"AMD ROCm Information Portal - v4.5 (2022). https:\/\/rocmdocs.amd.com\/en\/latest\/Remote_Device_Programming\/Remote-Device-Programming.html"},{"key":"22_CR3","unstructured":"NVIDIA GPUDirect RDMA Documentation (2022). https:\/\/docs.nvidia.com\/cuda\/gpudirect-rdma\/index.html"},{"key":"22_CR4","doi-asserted-by":"publisher","unstructured":"Zhang, B., Davis, P.E., Morales, N., Zhang, Z., Teranishi, K., Parashar, M. Artifact and instructions to generate experimental results for Euro-Par 2023 paper: SymED: Adaptive and Online Symbolic Representation of Data on the Edge, 2023. https:\/\/doi.org\/10.6084\/m9.figshare.23535855","DOI":"10.6084\/m9.figshare.23535855"},{"issue":"2","key":"22_CR5","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1109\/MCG.2015.35","volume":"35","author":"J Ahrens","year":"2015","unstructured":"Ahrens, J., Rhyne, T.M.: Increasing scientific data insights about exascale class simulations under power and storage constraints. IEEE Comput. Graph. Appl. 35(2), 8\u201311 (2015)","journal-title":"IEEE Comput. Graph. Appl."},{"issue":"4","key":"22_CR6","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1177\/1094342018778123","volume":"32","author":"M Asch","year":"2018","unstructured":"Asch, M., et al.: Big data and extreme-scale computing: pathways to convergence-toward a shaping strategy for a future software and data ecosystem for scientific inquiry. Int. J. High Perform. Comput. Appl. 32(4), 435\u2013479 (2018)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Beckingsale, D.A., et al.: RAJA: portable performance for large-scale scientific applications. In: 2019 IEEE\/ACM International Workshop on Performance, Portability and Productivity in HPC (P3HPC), pp. 71\u201381. IEEE (2019)","DOI":"10.1109\/P3HPC49587.2019.00012"},{"key":"22_CR8","unstructured":"Bethel, E., et al.: In Situ Methods, Infrastructures, and Applications on High Performance Computing Platforms, a State-of-the-art (STAR) Report (2021)"},{"key":"22_CR9","unstructured":"Brown, W.M.: GPU acceleration in LAMMPS. In: LAMMPS User\u2019s Workshop and Symposium (2011)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Docan, C., Parashar, M., Klasky, S.: Dataspaces: an interaction and coordination framework for coupled simulation workflows. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing, pp. 25\u201336 (2010)","DOI":"10.1145\/1851476.1851481"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Godoy, W.F., et al.: Adios 2: the adaptable input output system. a framework for high-performance data management. SoftwareX 12, 100561 (2020)","DOI":"10.1016\/j.softx.2020.100561"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Goswami, A., et al.: Landrush: rethinking in-situ analysis for GPGPU workflows. In: 2016 16th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 32\u201341. IEEE (2016)","DOI":"10.1109\/CCGrid.2016.58"},{"key":"22_CR13","unstructured":"Jeaugey, S.: Nccl 2.0. In: GPU Technology Conference (GTC), vol. 2 (2017)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Karlin, I., Keasler, J., Neely, R.: Lulesh 2.0 updates and changes. Technical report LLNL-TR-641973, August 2013","DOI":"10.2172\/1090032"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Kress, J., Klasky, S., Podhorszki, N., Choi, J., Childs, H., Pugmire, D.: Loosely coupled in situ visualization: a perspective on why it\u2019s here to stay. In: Proceedings of the First Workshop on In Situ Infrastructures for Enabling Extreme-Scale Analysis and Visualization, pp. 1\u20136 (2015)","DOI":"10.1145\/2828612.2828623"},{"issue":"12","key":"22_CR16","doi-asserted-by":"publisher","first-page":"2674","DOI":"10.1109\/TVCG.2014.2346458","volume":"20","author":"P Lindstrom","year":"2014","unstructured":"Lindstrom, P.: Fixed-rate compressed floating-point arrays. IEEE Trans. Vis. Comput. Graph. 20(12), 2674\u20132683 (2014)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"issue":"2","key":"22_CR17","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/MCG.2016.35","volume":"36","author":"K Moreland","year":"2016","unstructured":"Moreland, K.: The tensions of in situ visualization. IEEE Comput. Graph. Appl. 36(2), 5\u20139 (2016)","journal-title":"IEEE Comput. Graph. Appl."},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"Potluri, S., Hamidouche, K., Venkatesh, A., Bureddy, D., Panda, D.K.: Efficient inter-node MPI communication using GPUDirect RDMA for InfiniBand clusters with NVIDIA GPUs. In: 2013 42nd International Conference on Parallel Processing, pp. 80\u201389. IEEE (2013)","DOI":"10.1109\/ICPP.2013.17"},{"key":"22_CR19","unstructured":"Pulatov, D., Zhang, B., Suresh, S., Miller, C.: Porting IDL programs into Python for GPU-Accelerated In-situ Analysis (2021)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Reyes, R., Brown, G., Burns, R., Wong, M.: SYCL 2020: more than meets the eye. In: Proceedings of the International Workshop on OpenCL, p. 1 (2020)","DOI":"10.1145\/3388333.3388649"},{"issue":"1","key":"22_CR21","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/s11390-020-9802-0","volume":"35","author":"RB Ross","year":"2020","unstructured":"Ross, R.B., et al.: Mochi: composing data services for high-performance computing environments. J. Comput. Sci. Technol. 35(1), 121\u2013144 (2020)","journal-title":"J. Comput. Sci. Technol."},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Shi, R., et al.: Designing efficient small message transfer mechanism for inter-node MPI communication on InfiniBand GPU clusters. In: 2014 21st International Conference on High Performance Computing (HiPC), pp. 1\u201310. IEEE (2014)","DOI":"10.1109\/HiPC.2014.7116873"},{"key":"22_CR23","unstructured":"Strohmaier, E., Dongarra, J., Simon, H., Meuer, M.: TOP500 List, November 2022. https:\/\/www.top500.org\/lists\/top500\/2022\/11\/"},{"issue":"4","key":"22_CR24","doi-asserted-by":"publisher","first-page":"805","DOI":"10.1109\/TPDS.2021.3097283","volume":"33","author":"CR Trott","year":"2021","unstructured":"Trott, C.R., et al.: Kokkos 3: programming model extensions for the exascale era. IEEE Trans. Parallel Distrib. Syst. 33(4), 805\u2013817 (2021)","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"22_CR25","unstructured":"Wang, D., Foran, D.J., Qi, X., Parashar, M.: Enabling asynchronous coupled data intensive analysis workflows on GPU-accelerated platforms via data staging"},{"issue":"3","key":"22_CR26","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s00450-011-0171-3","volume":"26","author":"H Wang","year":"2011","unstructured":"Wang, H., Potluri, S., Luo, M., Singh, A.K., Sur, S., Panda, D.K.: MVAPICH2-GPU: optimized GPU to GPU communication for InfiniBand clusters. Comput. Sci.-Res. Dev. 26(3), 257\u2013266 (2011)","journal-title":"Comput. Sci.-Res. Dev."},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Zhang, B., Subedi, P., Davis, P.E., Rizzi, F., Teranishi, K., Parashar, M.: Assembling portable in-situ workflow from heterogeneous components using data reorganization. In: 2022 22nd IEEE International Symposium on Cluster, Cloud and Internet Computing (CCGrid), pp. 41\u201350. IEEE (2022)","DOI":"10.1109\/CCGrid54584.2022.00013"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2023: Parallel Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-39698-4_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,23]],"date-time":"2023-08-23T06:06:25Z","timestamp":1692770785000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-39698-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031396977","9783031396984"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-39698-4_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"24 August 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Euro-Par","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Parallel Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Limassol","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Cyprus","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":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2023.euro-par.org\/","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":"164","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":"49","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":"30% - 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":"3.98","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":"4","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}