{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T04:03:20Z","timestamp":1749528200799,"version":"3.41.0"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031902024","type":"print"},{"value":"9783031902031","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-90203-1_3","type":"book-chapter","created":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T15:48:43Z","timestamp":1749484123000},"page":"26-35","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Offloading PyTorch Collective Operations to\u00a0Independent Programmable Logic at\u00a0the\u00a0Edge"],"prefix":"10.1007","author":[{"given":"Chanaka","family":"Hettige","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankush","family":"Pathak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luke","family":"D\u2019Alessandro","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Swany","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,10]]},"reference":[{"issue":"5","key":"3_CR1","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1109\/MM.2017.3711654","volume":"37","author":"O Arap","year":"2017","unstructured":"Arap, O., Brasilino, L.R.B., Kissel, E., Shroyer, A., Swany, M.: Offloading collective operations to programmable logic. IEEE Micro 37(5), 52\u201360 (2017)","journal-title":"IEEE Micro"},{"key":"3_CR2","doi-asserted-by":"crossref","unstructured":"Arap, O., Swany, M., Brown, G., Himebaugh, B.: Adaptive recursive doubling algorithm for collective communication. In: Proceedings - 2015 IEEE 29th International Parallel and Distributed Processing Symposium Workshops, IPDPSW 2015, pp. 121\u2013128 (2015)","DOI":"10.1109\/IPDPSW.2015.82"},{"key":"3_CR3","doi-asserted-by":"crossref","unstructured":"Chunduri, S., Parker, S., Balaji, P., Harms, K., Kumaran, K.: Characterization of MPI usage on a production supercomputer. In: Proceedings - International Conference for High Performance Computing, Networking, Storage, and Analysis, SC 2018, vol. 2018, pp. 386\u2013400 (2018)","DOI":"10.1109\/SC.2018.00033"},{"key":"3_CR4","unstructured":"Facebook. Collective communications library with various primitives for multi-machine training (gloo). https:\/\/github.com\/facebookincubator\/gloo. Accessed 19 Feb 2024"},{"key":"3_CR5","unstructured":"Open networking foundation. OpenFlow. https:\/\/opennetworking.org\/sdn-resources\/openflow-2\/. Accessed 20 Mar 2024"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Fujita, N., Kobayashi, R., Yamaguchi, Y., Ueno, T., Sano, K., Boku, T.: Performance evaluation of pipelined communication combined with computation in OpenCL programming on FPGA. In: 2020 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 450\u2013459. IEEE (2020)","DOI":"10.1109\/IPDPSW50202.2020.00083"},{"key":"3_CR7","unstructured":"Khronos group. OpenCL. https:\/\/www.khronos.org\/opencl\/. Accessed 22 Sep 2023"},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Haghi, P., et al.: FPGAs in the network and novel communicator support accelerate MPI collectives. In: 2020 IEEE High Performance Extreme Computing Conference, HPEC 2020. Institute of Electrical and Electronics Engineers Inc. (2020)","DOI":"10.1109\/HPEC43674.2020.9286200"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"He, Z., Parravicini, D., Petrica, L., Obrien, K., Alonso, G., Blott, M.: ACCL: FPGA-accelerated collectives over 100 GBPS TCP-IP. In: Proceedings of H2RC 2021: 7th International Workshop on Heterogeneous High-Performance Reconfigurable Computing Held in conjunction with SC 2021: The International Conference for High Performance Computing, Networking, Storage and Analysis, pp. 33\u201343. Institute of Electrical and Electronics Engineers Inc. (2021)","DOI":"10.1109\/H2RC54759.2021.00009"},{"key":"3_CR10","doi-asserted-by":"crossref","unstructured":"Kikuchi, K., Fujita, N., Kobayashi, R., Boku, T.: Implementation and performance evaluation of collective communications using circus on multiple FPGAS. In: Proceedings of the HPC Asia 2023 Workshops, HPC Asia 2023 Workshops, pp. 15\u201323. Association for Computing Machinery, New York (2023)","DOI":"10.1145\/3581576.3581602"},{"key":"3_CR11","doi-asserted-by":"crossref","unstructured":"Li, Y., Liu, I.J., Yuan, Y., Chen, D., Schwing, A., Huang, J.: Accelerating distributed reinforcement learning with in-switch computing. In: Proceedings - International Symposium on Computer Architecture, pp. 279\u2013291 (2019)","DOI":"10.1145\/3307650.3322259"},{"key":"3_CR12","unstructured":"MPICH. High-performance portable MPI (MPICH). https:\/\/www.mpich.org\/. Accessed 19 Mar 2024"},{"key":"3_CR13","doi-asserted-by":"crossref","unstructured":"Narayanan, D., et al.: PipeDream: generalized pipeline parallelism for DNN training. In: ACM Symposium on Operating Systems Principles (SOSP 2019) (2019)","DOI":"10.1145\/3341301.3359646"},{"key":"3_CR14","unstructured":"NVIDIA. Nvidia collective communication library (NCCL). https:\/\/developer.nvidia.com\/nccl. Accessed 18 Sept 2023"},{"key":"3_CR15","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32, pp. 8024\u20138035. Curran Associates, Inc. (2019)"},{"key":"3_CR16","unstructured":"Stern, J., Xiong, Q., Skjellum, A., Herbordt. M.: A novel approach to supporting communicators for in-switch processing of MPI collectives. In: Proceedings of the Workshop on Exascale MPI (2018)"},{"issue":"5","key":"3_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/MM.2014.61","volume":"34","author":"N Zilberman","year":"2014","unstructured":"Zilberman, N., Audzevich, Y., Covington, G.A., Moore, A.W.: NetFPGA SUME: toward 100 Gbps as research commodity. IEEE Micro 34(5), 32\u201341 (2014)","journal-title":"IEEE Micro"}],"container-title":["Lecture Notes in Computer Science","Euro-Par 2024: Parallel Processing Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-90203-1_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,9]],"date-time":"2025-06-09T15:48:48Z","timestamp":1749484128000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-90203-1_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031902024","9783031902031"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-90203-1_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"10 June 2025","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":"Madrid","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Spain","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"europar2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.euro-par.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}