{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T15:12:48Z","timestamp":1785510768813,"version":"3.56.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universidad Carlos III"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cluster Comput"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Nowadays, high-performance networks in supercomputers have become indispensable for applications such as artificial intelligence, data analysis, and simulation, among others, all of which require high network speeds and minimal latencies. The standard of choice for developing these applications is MPI, as most implementations support such networks. However, some implementations of MPI exhibit notable limitations in error handling and with a rigid initialization model that proves problematic for certain applications. In addition, applications that use POSIX sockets or traditional RPC cannot benefit from these network interfaces. In response to these deficiencies, the Lightweight Fabric Interface (LFI) library has been developed as an alternative for communications, providing a very simplified user interface, error notification based on \u201cis alive\u201d requests, a more flexible initialization model, and is designed for efficient use in multi-threaded applications. LFI offers an interception library that enables applications using POSIX sockets or traditional RPC to benefit from high-performance networks without any modifications. Evaluations demonstrate that LFI delivers superior performance and efficiency compared to established communication libraries across both Omni-Path and InfiniBand architectures. When compared to MPICH, one of the most widely adopted MPI implementations, LFI improves bandwidth performance by up to 36% in real-world applications while substantially reducing resource overhead in multi-threaded environments by up to 97%. Furthermore, LFI consistently outperforms MPICH, OpenMPI, Mercury, and POSIX sockets (IPoIB) in terms of both raw throughput and operational efficiency, establishing it as a highly scalable solution for high-performance interconnects.<\/jats:p>","DOI":"10.1007\/s10586-026-06274-8","type":"journal-article","created":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T12:04:34Z","timestamp":1782993874000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LFI: a communication library for high-performance networks"],"prefix":"10.1007","volume":"29","author":[{"given":"Dario","family":"Mu\u00f1oz-Mu\u00f1oz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Garcia-Carballeira","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Diego","family":"Camarmas-Alonso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alejandro","family":"Calderon-Mateos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"6274_CR1","unstructured":"Message Passing Interface Forum: MPI: A Message-Passing Interface Standard Version 4.1. [Online]. Available: https:\/\/www.mpi-forum.org\/docs\/mpi-4.1\/mpi41-report.pdf (accessed July 17, 2025) (2023)"},{"key":"6274_CR2","doi-asserted-by":"publisher","unstructured":"Temu\u00e7in, Y.H., Schonbein, W., Levy, S., Sojoodi, A., Grant, R.E., Afsahi, A.: Design and implementation of mpi-native gpu-initiated mpi partitioned communication. In: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 436\u2013447 (2024). https:\/\/doi.org\/10.1109\/SCW63240.2024.00065","DOI":"10.1109\/SCW63240.2024.00065"},{"key":"6274_CR3","doi-asserted-by":"publisher","unstructured":"Shanley, T.: InfiniBand Network Architecture. Addison-Wesley Longman Publishing Co., Inc., USA (2002). [Online]. Available: https:\/\/doi.org\/10.5555\/579371 (accessed July 17, 2025)","DOI":"10.5555\/579371"},{"key":"6274_CR4","doi-asserted-by":"publisher","unstructured":"Birrittella, M.S., : Intel\u00ae omni-path architecture: Enabling scalable, high performance fabrics. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 1\u20139 (2015). https:\/\/doi.org\/10.1109\/HOTI.2015.22","DOI":"10.1109\/HOTI.2015.22"},{"key":"6274_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2025.108305","volume":"178","author":"S Iserte","year":"2026","unstructured":"Iserte, S., Madon, M., Da Costa, G., Pierson, J.-M., Pe\u00f1a, A.J.: Mpi malleability validation under replayed real-world hpc conditions. Futur. Gener. Comput. Syst. 178, 108305 (2026). https:\/\/doi.org\/10.1016\/j.future.2025.108305","journal-title":"Futur. Gener. Comput. Syst."},{"key":"6274_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2025.107949","volume":"174","author":"S Iserte","year":"2026","unstructured":"Iserte, S., Mart\u00edn-\u00e1lvarez, I., Rojek, K., Aliaga, J.I., Castillo, M., Folwarska, W., Pe\u00f1a, A.J.: Resource optimization with mpi process malleability for dynamic workloads in hpc clusters. Futur. Gener. Comput. Syst. 174, 107949 (2026). https:\/\/doi.org\/10.1016\/j.future.2025.107949","journal-title":"Futur. Gener. Comput. Syst."},{"key":"6274_CR7","unstructured":"MPICH: MPICH | High-Performance Portable MPI. [Online]. Available: https:\/\/www.mpich.org\/ (accessed July 17, 2025)"},{"key":"6274_CR8","unstructured":"ael-code: PSM2 error on local client reconnection. [Online]. Available: https:\/\/github.com\/cornelisnetworks\/opa-psm2\/issues\/34 (accessed July 17, 2025) (2025)"},{"key":"6274_CR9","doi-asserted-by":"publisher","unstructured":"Hjelm, N., Pritchard, H., Guti\u00e9rrez, S.K., Holmes, D.J., Castain, R., Skjellum, A.: Mpi sessions: Evaluation of an implementation in open mpi. In: 2019 IEEE International Conference on Cluster Computing (CLUSTER), pp. 1\u201311 (2019). https:\/\/doi.org\/10.1109\/CLUSTER.2019.8891002","DOI":"10.1109\/CLUSTER.2019.8891002"},{"key":"6274_CR10","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.future.2020.01.026","volume":"106","author":"N Losada","year":"2020","unstructured":"Losada, N., Gonz\u00e1lez, P., Mart\u00edn, M.J., Bosilca, G., Bouteiller, A., Teranishi, K.: Fault tolerance of mpi applications in exascale systems: The ulfm solution. Futur. Gener. Comput. Syst. 106, 467\u2013481 (2020). https:\/\/doi.org\/10.1016\/j.future.2020.01.026","journal-title":"Futur. Gener. Comput. Syst."},{"key":"6274_CR11","doi-asserted-by":"publisher","unstructured":"Grun, P.: A brief introduction to the openfabrics interfaces - a new network api for maximizing high performance application efficiency. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 34\u201339 (2015). https:\/\/doi.org\/10.1109\/HOTI.2015.19","DOI":"10.1109\/HOTI.2015.19"},{"key":"6274_CR12","unstructured":"OpenFabrics Alliance: Libfabric Programmer\u2019s Manual. [Online]. Available: https:\/\/ofiwg.github.io\/libfabric\/ (accessed July 17, 2025)"},{"key":"6274_CR13","unstructured":"OpenFabrics Alliance: OpenFabrics Alliance \u2013 Innovation in High Speed Fabrics. [Online]. Available: https:\/\/www.openfabrics.org\/ (accessed July 17, 2025)"},{"key":"6274_CR14","doi-asserted-by":"publisher","unstructured":"Chapman, B., Curtis, T., Pophale, S., Poole, S., Kuehn, J., Koelbel, C., Smith, L.: Introducing openshmem: Shmem for the pgas community. In: Proceedings of the Fourth Conference on Partitioned Global Address Space Programming Model. PGAS \u201910. Association for Computing Machinery, New York, NY, USA (2010). https:\/\/doi.org\/10.1145\/2020373.2020375","DOI":"10.1145\/2020373.2020375"},{"key":"6274_CR15","doi-asserted-by":"publisher","unstructured":"Almasi, G.: In: Padua, D. (ed.) PGAS (Partitioned Global Address Space) Languages, pp. 1539\u20131545. Springer, Boston, MA (2011). https:\/\/doi.org\/10.1007\/978-0-387-09766-4_210","DOI":"10.1007\/978-0-387-09766-4_210"},{"key":"6274_CR16","unstructured":"OpenFabrics Alliance: Libfabric Interface Providers. [Online]. Available: https:\/\/ofiwg.github.io\/libfabric\/v2.0.0\/man\/fi_provider.7.html (accessed July 17, 2025)"},{"key":"6274_CR17","unstructured":"HPE: HPE Slingshot | HPE Store US. [Online]. Available: https:\/\/buy.hpe.com\/us\/en\/options\/enterprise-networking-products\/switches\/slingshot\/hpe-slingshot\/p\/1012904596 (accessed July 17, 2025)"},{"key":"6274_CR18","unstructured":"Services, A.W.: Elastic Fabric Adapter \u2014 Amazon Web Services. [Online]. Available: https:\/\/aws.amazon.com\/es\/hpc\/efa\/ (accessed July 17, 2025)"},{"key":"6274_CR19","doi-asserted-by":"publisher","unstructured":"Shamis, P., : Ucx: An open source framework for hpc network apis and beyond. In: 2015 IEEE 23rd Annual Symposium on High-Performance Interconnects, pp. 40\u201343 (2015). https:\/\/doi.org\/10.1109\/HOTI.2015.13","DOI":"10.1109\/HOTI.2015.13"},{"key":"6274_CR20","doi-asserted-by":"publisher","unstructured":"Gabriel, E., : Open MPI: Goals, concept, and design of a next generation MPI implementation. In: Proceedings, 11th European PVM\/MPI Users\u2019 Group Meeting, Budapest, Hungary, pp. 97\u2013104 (2004). https:\/\/doi.org\/10.1007\/978-3-540-30218-6_19","DOI":"10.1007\/978-3-540-30218-6_19"},{"key":"6274_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.jocs.2020.101208","volume":"52","author":"DK Panda","year":"2021","unstructured":"Panda, D.K., Subramoni, H., Chu, C.-H., Bayatpour, M.: The mvapich project: Transforming research into high-performance mpi library for hpc community. J. Comput. Sci. 52, 101208 (2021). https:\/\/doi.org\/10.1016\/j.jocs.2020.101208","journal-title":"J. Comput. Sci."},{"key":"6274_CR22","unstructured":"Intel: Intel\u00ae MPI Library. [Online]. Available: https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/mpi-library.html (accessed July 17, 2025) (2025)"},{"issue":"04","key":"6274_CR23","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1142\/S0129626400000342","volume":"10","author":"S Louca","year":"2000","unstructured":"Louca, S., Neophytou, N., Lachanas, A., Evripidou, P.: Mpi-ft: Portable fault tolerance scheme for mpi. Parallel Processing Letters 10(04), 371\u2013382 (2000). https:\/\/doi.org\/10.1142\/S0129626400000342","journal-title":"Parallel Processing Letters"},{"key":"6274_CR24","doi-asserted-by":"publisher","unstructured":"Aulwes, R.T., Daniel, D.J., Desai, N.N., Graham, R.L., Risinger, L.D., Taylor, M.A., Woodall, T.S., Sukalski, M.W.: Architecture of la-mpi, a network-fault-tolerant mpi. In: 18th International Parallel and Distributed Processing Symposium, 2004. Proceedings., p. 15 (2004). https:\/\/doi.org\/10.1109\/IPDPS.2004.1302920","DOI":"10.1109\/IPDPS.2004.1302920"},{"key":"6274_CR25","doi-asserted-by":"publisher","unstructured":"Bosilca, G., Bouteiller, A., Cappello, F., Djilali, S., Fedak, G., Germain, C., Herault, T., Lemarinier, P., Lodygensky, O., Magniette, F., Neri, V., Selikhov, A.: Mpich-v: Toward a scalable fault tolerant mpi for volatile nodes. In: SC \u201902: Proceedings of the 2002 ACM\/IEEE Conference on Supercomputing, pp. 29\u201329 (2002). https:\/\/doi.org\/10.1109\/SC.2002.10048","DOI":"10.1109\/SC.2002.10048"},{"key":"6274_CR26","doi-asserted-by":"publisher","unstructured":"Soumagne, J., : Mercury: Enabling remote procedure call for high-performance computing. In: 2013 IEEE International Conference on Cluster Computing (CLUSTER), pp. 1\u20138 (2013). https:\/\/doi.org\/10.1109\/CLUSTER.2013.6702617","DOI":"10.1109\/CLUSTER.2013.6702617"},{"key":"6274_CR27","unstructured":"Mercury-HPC: Mercury Github. [Online]. Available: https:\/\/github.com\/mercury-hpc\/mercury (accessed July 17, 2025)"},{"key":"6274_CR28","unstructured":"OpenFabrics Alliance: Libfabric Interface Endpoint Types. [Online]. Available: https:\/\/ofiwg.github.io\/libfabric\/v2.0.0\/man\/fi_endpoint.3.html#type---endpoint-type (accessed July 17, 2025)"},{"key":"6274_CR29","unstructured":"OpenFabrics Alliance: Libfabric Interface Endpoint Capabilities. [Online]. Available: https:\/\/ofiwg.github.io\/libfabric\/v2.0.0\/man\/fi_getinfo.3.html#capabilities (accessed July 17, 2025)"},{"key":"6274_CR30","unstructured":"OpenFabrics Alliance: Libfabric Interface Connectionless Communications. [Online]. Available: https:\/\/ofiwg.github.io\/libfabric\/v2.0.0\/man\/fi_arch.7.html#connectionless-communications (accessed July 17, 2025)"},{"key":"6274_CR31","unstructured":"OpenFabrics Alliance: Libfabric Interface Progress Models. [Online]. Available: https:\/\/ofiwg.github.io\/libfabric\/v2.0.0\/man\/fi_domain.3.html#progress-models-progress (accessed July 17, 2025)"},{"key":"6274_CR32","unstructured":"OpenFabrics Alliance: Libfabric Interface SHM Provider. [Online]. Available: https:\/\/ofiwg.github.io\/libfabric\/v2.0.0\/man\/fi_shm.7.html (accessed July 17, 2025)"},{"key":"6274_CR33","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.future.2014.12.015","volume":"53","author":"R Ammendola","year":"2015","unstructured":"Ammendola, R., Biagioni, A., Frezza, O., Lo Cicero, F., Lonardo, A., Paolucci, P.S., Rossetti, D., Simula, F., Tosoratto, L., Vicini, P.: A hierarchical watchdog mechanism for systemic fault awareness on distributed systems. Futur. Gener. Comput. Syst. 53, 90\u201399 (2015). https:\/\/doi.org\/10.1016\/j.future.2014.12.015","journal-title":"Futur. Gener. Comput. Syst."},{"key":"6274_CR34","doi-asserted-by":"publisher","unstructured":"Ibrahim, K.Z., Hargrove, P.H., Iancu, C., Yelick, K.: An evaluation of one-sided and two-sided communication paradigms on relaxed-ordering interconnect. In: 2014 IEEE 28th International Parallel and Distributed Processing Symposium, pp. 1115\u20131125 (2014). https:\/\/doi.org\/10.1109\/IPDPS.2014.116","DOI":"10.1109\/IPDPS.2014.116"},{"key":"6274_CR35","unstructured":"Guerraoui, R., Murat, A., Xygkis, A.: Velos: One-sided paxos for RDMA applications. CoRR , (2021). arXiv:2106.08676"},{"key":"6274_CR36","unstructured":"Java: Java Serversocket. [Online]. Available: https:\/\/docs.oracle.com\/javase\/8\/docs\/api\/java\/net\/ServerSocket.html (accessed July 17, 2025) (2025)"},{"key":"6274_CR37","unstructured":"Java: Java Socket. [Online]. Available: https:\/\/docs.oracle.com\/javase\/8\/docs\/api\/java\/net\/Socket.html (accessed July 17, 2025) (2025)"},{"key":"6274_CR38","unstructured":"dariomnz: LFI Github. [Online]. Available: https:\/\/github.com\/dariomnz\/lfi (accessed July 17, 2025)"},{"key":"6274_CR39","unstructured":"HPC4AI: HPC4AI Laboratory specification. [Online]. Available: https:\/\/hpc4ai.unito.it\/ (accessed July 17, 2025) (2024)"},{"key":"6274_CR40","doi-asserted-by":"crossref","unstructured":"uc3m: C3 supercomputer web. Accessed January. 9, 2026. [Online] (2026). https:\/\/c3-uc3m.github.io\/c3-web\/","DOI":"10.1109\/MPOT.2026.3709372"},{"key":"6274_CR41","unstructured":"The Ohio State University: OSU Micro-Benchmarks. [Online]. Available: https:\/\/mvapich.cse.ohio-state.edu\/benchmarks\/ (accessed July 17, 2025) (2025)"},{"key":"6274_CR42","unstructured":"Google: Web gRPC. [Online]. Available: https:\/\/grpc.io\/ (accessed July 17, 2025)"},{"key":"6274_CR43","unstructured":"Google: gRPC Github. [Online]. Available: https:\/\/github.com\/grpc\/grpc (accessed July 17, 2025)"},{"key":"6274_CR44","doi-asserted-by":"publisher","unstructured":"Garcia-Carballeira, F., Camarmas-Alonso, D., Caderon-Mateos, A., Carretero, J.: A new ad-hoc parallel file system for hpc environments based on the expand parallel file system. In: 2023 22nd International Symposium on Parallel and Distributed Computing (ISPDC), pp. 69\u201376 (2023). https:\/\/doi.org\/10.1109\/ISPDC59212.2023.00015","DOI":"10.1109\/ISPDC59212.2023.00015"},{"key":"6274_CR45","doi-asserted-by":"publisher","unstructured":"Mu\u00f1oz-Mu\u00f1oz, D., Garcia-Carballeira, F., Camarmas-Alonso, D., Calderon-Mateos, A., Carretero, J.: Fault tolerant in the expand ad-hoc parallel file system. In: Euro-Par 2024: Parallel Processing, pp. 62\u201376. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-69766-1_55","DOI":"10.1007\/978-3-031-69766-1_55"},{"key":"6274_CR46","doi-asserted-by":"publisher","unstructured":"Mu\u00f1oz-Mu\u00f1oz, D., Garcia-Carballeira, F., Camarmas-Alonso, D., Calderon-Mateos, A., Carretero, J.: Malleability in the expand ad-hoc parallel file system. In: Euro-Par 2024: Parallel Processing Workshops, pp. 322\u2013333. Springer, Cham (2025).https:\/\/doi.org\/10.1007\/978-3-031-90200-0_26","DOI":"10.1007\/978-3-031-90200-0_26"},{"key":"6274_CR47","unstructured":"HPC: ior GitHub. [Online]. Available: https:\/\/github.com\/hpc\/ior (accessed July 17, 2025)"}],"container-title":["Cluster Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-026-06274-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10586-026-06274-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10586-026-06274-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T14:45:51Z","timestamp":1785509151000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10586-026-06274-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":47,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["6274"],"URL":"https:\/\/doi.org\/10.1007\/s10586-026-06274-8","relation":{},"ISSN":["1386-7857","1573-7543"],"issn-type":[{"value":"1386-7857","type":"print"},{"value":"1573-7543","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"22 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 June 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 July 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"454"}}