{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T10:10:57Z","timestamp":1748859057137,"version":"3.37.3"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2022,1,15]],"date-time":"2022-01-15T00:00:00Z","timestamp":1642204800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,15]],"date-time":"2022-01-15T00:00:00Z","timestamp":1642204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100006769","name":"Russian Science Foundation","doi-asserted-by":"publisher","award":["18-71-10075"],"award-info":[{"award-number":["18-71-10075"]}],"id":[{"id":"10.13039\/501100006769","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2022,8]]},"DOI":"10.1007\/s10586-021-03452-8","type":"journal-article","created":{"date-parts":[[2022,1,15]],"date-time":"2022-01-15T10:02:48Z","timestamp":1642240968000},"page":"2683-2697","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["IMB-ASYNC: a revised method and benchmark to estimate MPI-3 asynchronous progress efficiency"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9312-391X","authenticated-orcid":false,"given":"Alexey V.","family":"Medvedev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,1,15]]},"reference":[{"key":"3452_CR1","doi-asserted-by":"publisher","unstructured":"Amer, A., Lu, H., Wei, Y., Balaji, P., Matsuoka, S.: MPI+threads: runtime contention and remedies. In: Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. ACM (2015). 10.1145\/2688500.2688522. https:\/\/doi.org\/10.1145\/2688500.2688522","DOI":"10.1145\/2688500.2688522"},{"key":"3452_CR2","doi-asserted-by":"publisher","unstructured":"Awan, A.A., Hamidouche, K., Venkatesh, A., Perkins, J., Subramoni, H., Panda, D.K.: GPU-aware design, implementation, and evaluation of non-blocking collective benchmarks. In: Proceedings of the 22nd European MPI Users\u2019 Group Meeting. ACM (2015). 10.1145\/2802658.2802672. https:\/\/doi.org\/10.1145\/2802658.2802672","DOI":"10.1145\/2802658.2802672"},{"key":"3452_CR3","doi-asserted-by":"crossref","unstructured":"Bayatpour, M., Maqbool, J.H., Chakraborty, S., Suresh, K.K., Ghazimirsaeed, S.M., Ramesh, B., Subramoni, H., Panda, D.K.: Communication-aware hardware-assisted MPI overlap engine. In: Lecture Notes in Computer Science, pp. 517\u2013535. Springer, New York (2020)","DOI":"10.1007\/978-3-030-50743-5_26"},{"issue":"2","key":"3452_CR4","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1177\/1094342005054257","volume":"19","author":"R Brightwell","year":"2005","unstructured":"Brightwell, R., Riesen, R., Underwood, K.D.: Analyzing the impact of overlap, offload, and independent progress for message passing interface applications. Int. J. High Perform. Comput. Appl. 19(2), 103\u2013117 (2005)","journal-title":"Int. J. High Perform. Comput. Appl."},{"issue":"1","key":"3452_CR5","first-page":"33","volume":"18","author":"M Brinskiy","year":"2014","unstructured":"Brinskiy, M., Supalov, A., Chuvelev, M., Leksikov, E.: Mastering performance challenges with the new MPI-3 standard. Parallel Univ. 18(1), 33\u201340 (2014)","journal-title":"Parallel Univ."},{"key":"3452_CR6","unstructured":"Intel Corparation.: Intel MPI Library (2021). https:\/\/software.intel.com. Accessed 26 August 2021"},{"key":"3452_CR7","doi-asserted-by":"crossref","unstructured":"Daily, J., Vishnu, A., Palmer, B., van Dam, H., Kerbyson, D.: On the suitability of MPI as a PGAS runtime. In: 2014 21st International Conference on High Performance Computing (HiPC), pp. 1\u201310 (2014). 10.1109\/HiPC.2014.7116712","DOI":"10.1109\/HiPC.2014.7116712"},{"issue":"6","key":"3452_CR8","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1177\/1094342019860184","volume":"33","author":"A Denis","year":"2019","unstructured":"Denis, A., Jaeger, J., Jeannot, E., P\u00e9rache, M., Taboada, H.: Study on progress threads placement and dedicated cores for overlapping MPI nonblocking collectives on manycore processor. Int. J. High Perform. Comput. Appl. 33(6), 1240\u20131254 (2019)","journal-title":"Int. J. High Perform. Comput. Appl."},{"key":"3452_CR9","doi-asserted-by":"publisher","unstructured":"Denis, A., Trahay, F.: MPI overlap: Benchmark and analysis. In: 2016 45th International Conference on Parallel Processing (ICPP). IEEE (2016). 10.1109\/icpp.2016.37. https:\/\/doi.org\/10.1109\/icpp.2016.37","DOI":"10.1109\/icpp.2016.37"},{"key":"3452_CR10","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/11846802_46","volume-title":"Recent Advances in Parallel Virtual Machine and Message Passing Interface","author":"D Doerfler","year":"2006","unstructured":"Doerfler, D., Brightwell, R.: Measuring MPI send and receive overhead and application availability in high performance network interfaces. In: Mohr, B., Tr\u00e4ff, J.L., Worringen, J., Dongarra, J. (eds.) Recent Advances in Parallel Virtual Machine and Message Passing Interface, pp. 331\u2013338. Springer, Berlin (2006)"},{"key":"3452_CR11","unstructured":"Hager, G., Schubert, G., Schoenemeyer, T., Wellein, G.: Prospects for truly asynchronous communication with pure MPI and hybrid MPI\/OpenMP on current supercomputing platforms. In: Proceedings of The Cray User Group (2011)"},{"key":"3452_CR12","doi-asserted-by":"crossref","unstructured":"Hoefler, T., Kambadur, P., Graham, R.L., Shipman, G., Lumsdaine, A.: A case for standard non-blocking collective operations. In: Recent Advances in Parallel Virtual Machine and Message Passing Interface, pp. 125\u2013134. Springer, Berlin (2007)","DOI":"10.1007\/978-3-540-75416-9_22"},{"key":"3452_CR13","doi-asserted-by":"publisher","unstructured":"Hoefler, T., Lumsdaine, A.: Message progression in parallel computing - to thread or not to thread? In: 2008 IEEE International Conference on Cluster Computing. IEEE (2008). 10.1109\/clustr.2008.4663774. https:\/\/doi.org\/10.1109\/clustr.2008.4663774","DOI":"10.1109\/clustr.2008.4663774"},{"key":"3452_CR14","doi-asserted-by":"publisher","unstructured":"Hoefler, T., Lumsdaine, A., Rehm, W.: Implementation and performance analysis of non-blocking collective operations for MPI. In: Proceedings of the 2007 ACM\/IEEE Conference on Supercomputing-SC \u201907. ACM Press (2007). https:\/\/doi.org\/10.1145\/1362622.1362692","DOI":"10.1145\/1362622.1362692"},{"key":"3452_CR15","doi-asserted-by":"publisher","unstructured":"Kaiser, C., Hoefler, T., Bierbaum, B., Bemmerl, T.: Implementation and analysis of nonblocking collective operations on SCI networks. In: 2009 IEEE International Symposium on Parallel & Distributed Processing. IEEE (2009). https:\/\/doi.org\/10.1109\/ipdps.2009.5160892","DOI":"10.1109\/ipdps.2009.5160892"},{"key":"3452_CR16","unstructured":"Kandalla, K., Mendygral, P., Radcliffe, N., Cernohous, B., Namashivayam, N., McMahon, K., Sadlo, C., Pagel, M.: Current state of the cray mpt software stacks on the cray xc series supercomputers. In: Proceedings of The Cray User Group (2017)"},{"issue":"3\u20134","key":"3452_CR17","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1007\/s00450-011-0170-4","volume":"26","author":"K Kandalla","year":"2011","unstructured":"Kandalla, K., Subramoni, H., Tomko, K., Pekurovsky, D., Sur, S., Panda, D.K.: High-performance and scalable non-blocking all-to-all with collective offload on InfiniBand clusters: a study with parallel 3d FFT. Comput. Sci. Res. Dev. 26(3\u20134), 237\u2013246 (2011)","journal-title":"Comput. Sci. Res. Dev."},{"key":"3452_CR18","doi-asserted-by":"publisher","unstructured":"Koop, M., Sridhar, J., Panda, D.: TupleQ: Fully-asynchronous and zero-copy MPI over InfiniBand. In: 2009 IEEE International Symposium on Parallel & Distributed Processing. IEEE (2009). https:\/\/doi.org\/10.1109\/ipdps.2009.5161056","DOI":"10.1109\/ipdps.2009.5161056"},{"issue":"9","key":"3452_CR19","doi-asserted-by":"publisher","first-page":"2574","DOI":"10.1016\/j.camwa.2019.11.025","volume":"79","author":"B Krasnopolsky","year":"2020","unstructured":"Krasnopolsky, B.: Revisiting performance of BiCGStab methods for solving systems with multiple right-hand sides. Comput. Math. Appl. 79(9), 2574\u20132597 (2020). https:\/\/doi.org\/10.1016\/j.camwa.2019.11.025","journal-title":"Comput. Math. Appl."},{"key":"3452_CR20","unstructured":"Lawry, W., Wilson, C., Maccabe, A.B., Brightwell, R.: COMB: a portable benchmark suite for assessing MPI overlap. In: Proceedings. IEEE International Conference on Cluster Computing, pp. 472\u2013475 (2002). 10.1109\/CLUSTR.2002.1137785"},{"key":"3452_CR21","volume-title":"Patterns for Parallel Programming","author":"T Mattson","year":"2004","unstructured":"Mattson, T., Sanders, B., Massingill, B.: Patterns for Parallel Programming, 1st edn. Addison-Wesley Professional, Boston (2004)","edition":"1"},{"issue":"Parallel Comput","key":"3452_CR22","doi-asserted-by":"publisher","first-page":"419","DOI":"10.3233\/APC200067","volume":"36","author":"AV Medvedev","year":"2020","unstructured":"Medvedev, A.V.: Towards benchmarking the asynchronous progress of non-blocking MPI operations. Adv. Parallel Comput. 36(Parallel Computing: Technology Trends), 419\u2013428 (2020). https:\/\/doi.org\/10.3233\/APC200067","journal-title":"Adv. Parallel Comput."},{"key":"3452_CR23","doi-asserted-by":"publisher","unstructured":"Miwa, M., Nakashima, K.: Progression of MPI non-blocking collective operations using hyper-threading. In: 2015 23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing. IEEE (2015). https:\/\/doi.org\/10.1109\/pdp.2015.68","DOI":"10.1109\/pdp.2015.68"},{"key":"3452_CR24","unstructured":"Niethammer, C., Khabi, D., Zhou, H., Marjanovic, V., Gracica, J.: Impact of Late-Arrivals on MPI Collective Operations. In: INFOCOMP 2015: The Fifth International Conference on Advanced Communications and Computation, pp. 60\u201365. ThinkMind (2015)"},{"key":"3452_CR25","unstructured":"Pritchard, H., Roweth, D., Henseler, D., Cassella, P.: Leveraging the cray linux environment core specialization feature to realize mpi asynchronous progress on cray xe systems. In: Proceedings of The Cray User Group (2012)"},{"key":"3452_CR26","doi-asserted-by":"publisher","unstructured":"Ruhela, A., Subramoni, H., Chakraborty, S., Bayatpour, M., Kousha, P., Panda, D.K.: Efficient asynchronous communication progress for MPI without dedicated resources. In: Proceedings of the 25th European MPI Users\u2019 Group Meeting. ACM (2018). https:\/\/doi.org\/10.1145\/3236367.3236376","DOI":"10.1145\/3236367.3236376"},{"key":"3452_CR27","doi-asserted-by":"publisher","unstructured":"Si, M., Balaji, P.: Process-based asynchronous progress model for MPI point-to-point communication. In: 2017 IEEE 19th International Conference on High Performance Computing and Communications; IEEE 15th International Conference on Smart City; IEEE 3rd International Conference on Data Science and Systems (HPCC\/SmartCity\/DSS). IEEE (2017). https:\/\/doi.org\/10.1109\/hpcc-smartcity-dss.2017.27","DOI":"10.1109\/hpcc-smartcity-dss.2017.27"},{"key":"3452_CR28","doi-asserted-by":"publisher","unstructured":"Si, M., Pena, A.J., Hammond, J., Balaji, P., Ishikawa, Y.: Scaling NWChem with efficient and portable asynchronous communication in MPI RMA. In: 2015 15th IEEE\/ACM International Symposium on Cluster, Cloud and Grid Computing. IEEE (2015). https:\/\/doi.org\/10.1109\/ccgrid.2015.48","DOI":"10.1109\/ccgrid.2015.48"},{"key":"3452_CR29","doi-asserted-by":"publisher","unstructured":"Si, M., Pena, A.J., Hammond, J., Balaji, P., Takagi, M., Ishikawa, Y.: Casper: An asynchronous progress model for MPI RMA on many-core architectures. In: 2015 IEEE International Parallel and Distributed Processing Symposium. IEEE (2015). https:\/\/doi.org\/10.1109\/ipdps.2015.35","DOI":"10.1109\/ipdps.2015.35"},{"key":"3452_CR30","doi-asserted-by":"crossref","unstructured":"Song, S., Hollingsworth, J.: Designing and auto-tuning parallel 3-D FFT for computation-communication overlap. In: PPoPP \u201914: Proceedings of the 19th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming. Association for Computing Machinery (2014)","DOI":"10.1145\/2555243.2555249"},{"key":"3452_CR31","unstructured":"The Ohio State University: OSU Micro-Benchmarks (2021). http:\/\/mvapich.cse.ohio-state.edu\/benchmarks. Acccessed 26 August 2021"},{"key":"3452_CR32","doi-asserted-by":"crossref","unstructured":"Trahay, F., Denis, A.: A scalable and generic task scheduling system for communication libraries. In: 2009 IEEE International Conference on Cluster Computing and Workshops, pp. 1\u20138 (2009). 10.1109\/CLUSTR.2009.5289169","DOI":"10.1109\/CLUSTR.2009.5289169"},{"key":"3452_CR33","unstructured":"The Ohio\u00a0State University: MVAPICH: MPI over InfiniBand, 10GigE\/iWARP and RoCE (2021). http:\/\/mvapich.cse.ohio-state.edu. Accessed 26 August 2021"},{"key":"3452_CR34","doi-asserted-by":"publisher","unstructured":"Vaidyanathan, K., Kalamkar, D.D., Pamnany, K., Hammond, J.R., Balaji, P., Das, D., Park, J., Jo\u00f3, B.: Improving concurrency and asynchrony in multithreaded MPI applications using software offloading. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis. ACM (2015). https:\/\/doi.org\/10.1145\/2807591.2807602","DOI":"10.1145\/2807591.2807602"},{"key":"3452_CR35","unstructured":"Voevodin, V., Antonov, A., Nikitenko, D., Shvets, P., Sobolev, S., Sidorov, I., Stefanov, K., Voevodin, V., Zhumatiy, S.: Supercomputer Lomonosov-2: Large Scale, Deep Monitoring and Fine Analytics for the User Community. Supercomputing Frontiers and Innovations 6(2) (2019). https:\/\/superfri.org\/superfri\/article\/view\/278"},{"key":"3452_CR36","unstructured":"Wittmann, M., Hager, G., Zeiser, T., Wellein, G.: Asynchronous MPI for the Masses. (2013). ArXiv abs\/1302.4280"},{"key":"3452_CR37","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.parco.2019.05.004","volume":"86","author":"I Yamazaki","year":"2019","unstructured":"Yamazaki, I., Chow, E., Bouteiller, A., Dongarra, J.: Performance of asynchronous optimized Schwarz with one-sided communication. Parallel Comput. 86, 66\u201381 (2019)","journal-title":"Parallel Comput."},{"key":"3452_CR38","doi-asserted-by":"publisher","unstructured":"Zhou, H., Gracia, J.: Asynchronous progress design for a MPI-based PGAS one-sided communication system. In: 2016 IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS). IEEE (2016). https:\/\/doi.org\/10.1109\/icpads.2016.0133","DOI":"10.1109\/icpads.2016.0133"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03452-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-021-03452-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-021-03452-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T11:31:14Z","timestamp":1657798274000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-021-03452-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,15]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8]]}},"alternative-id":["3452"],"URL":"https:\/\/doi.org\/10.1007\/s10586-021-03452-8","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"type":"print","value":"1386-7857"},{"type":"electronic","value":"1573-7543"}],"subject":[],"published":{"date-parts":[[2022,1,15]]},"assertion":[{"value":"16 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 August 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}