Razavi, Kamran ; Karlos, George ; Nigade, Vinod ; Mühlhäuser, Max ; Wang, Lin (2022)
Distributed DNN Serving in the Network Data Plane.
5th International Workshop on P4 in Europe. Rome, Italy (09.12.2022)
doi: 10.1145/3565475.3569079
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Programmable networks have received tremendous attention recently. Apart from exciting network innovations, in-network computing has been explored as a means to accelerate a variety of distributed systems concerns, by leveraging programmable network devices. In this paper, we extend in-network computing to an important class of applications called deep neural network (DNN) serving. In particular, we propose to run DNN inferences in the network data plane in a distributed fashion and make our programmable network a powerful accelerator for DNN serving. We demonstrate the feasibility of this idea through a case study with a real-world DNN on a typical data center network architecture.
Typ des Eintrags: | Konferenzveröffentlichung |
---|---|
Erschienen: | 2022 |
Autor(en): | Razavi, Kamran ; Karlos, George ; Nigade, Vinod ; Mühlhäuser, Max ; Wang, Lin |
Art des Eintrags: | Bibliographie |
Titel: | Distributed DNN Serving in the Network Data Plane |
Sprache: | Englisch |
Publikationsjahr: | 6 Dezember 2022 |
Verlag: | ACM |
Buchtitel: | EuroP4 '22: Proceedings of the 5th International Workshop on P4 in Europe |
Veranstaltungstitel: | 5th International Workshop on P4 in Europe |
Veranstaltungsort: | Rome, Italy |
Veranstaltungsdatum: | 09.12.2022 |
DOI: | 10.1145/3565475.3569079 |
Kurzbeschreibung (Abstract): | Programmable networks have received tremendous attention recently. Apart from exciting network innovations, in-network computing has been explored as a means to accelerate a variety of distributed systems concerns, by leveraging programmable network devices. In this paper, we extend in-network computing to an important class of applications called deep neural network (DNN) serving. In particular, we propose to run DNN inferences in the network data plane in a distributed fashion and make our programmable network a powerful accelerator for DNN serving. We demonstrate the feasibility of this idea through a case study with a real-world DNN on a typical data center network architecture. |
Freie Schlagworte: | programmable networks, in-network computing, DNN serving |
Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Telekooperation |
TU-Projekte: | DFG|SFB1053|SFB1053 TPA01 Mühlhä DFG|SFB1053|SFB1053 TPB02 Mühlhä |
Hinterlegungsdatum: | 02 Aug 2023 14:10 |
Letzte Änderung: | 04 Aug 2023 07:55 |
PPN: | 510354807 |
Export: | |
Suche nach Titel in: | TUfind oder in Google |
Frage zum Eintrag |
Optionen (nur für Redakteure)
Redaktionelle Details anzeigen |