Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312561214> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W4312561214 abstract "The increasing adoption of Field-Programmable Gate Arrays (FPGA) into cloud and data center systems opens the way to the unprecedented acceleration of Machine Learning applications. Convolutional Neural Networks (CNN) have largely been adopted as algorithms for image classification and object detection. As we head towards FPGA multi-tenancy in the cloud, it becomes necessary to investigate architectures and mechanisms for the efficient deployment of CNN into multitenant FPGAs cloud Infrastructure. In this work, we propose an FPGA architecture and a design flow that support efficient integration of CNN applications into a cloud infrastructure that exposes multi-tenancy to cloud developers. We prototype the proposed approach on randomly allocated virtual regions to tenants. We study how space-sharing of a single device between multiple cloud tenants influence the design flow, the allocation of resources, and the performance in term of resource utilization and overall latency compared to single-tenant deployments. Prototyping results show a latency at most 8% lower than that of single-tenant deployment while achieving higher resource utilization. We also record a maximum frequency of up to 12% higher in multi-tenant implementations." @default.
- W4312561214 created "2023-01-05" @default.
- W4312561214 creator A5032279242 @default.
- W4312561214 creator A5033410278 @default.
- W4312561214 creator A5039241745 @default.
- W4312561214 creator A5081869234 @default.
- W4312561214 date "2022-10-01" @default.
- W4312561214 modified "2023-09-28" @default.
- W4312561214 title "Accelerating Hybrid Quantized Neural Networks on Multi-tenant Cloud FPGA" @default.
- W4312561214 cites W1965513150 @default.
- W4312561214 cites W2046771798 @default.
- W4312561214 cites W2466675884 @default.
- W4312561214 cites W2761085955 @default.
- W4312561214 cites W2790167166 @default.
- W4312561214 cites W2888171537 @default.
- W4312561214 cites W2891839221 @default.
- W4312561214 cites W2891946740 @default.
- W4312561214 cites W2895540242 @default.
- W4312561214 cites W2915553904 @default.
- W4312561214 cites W2917087921 @default.
- W4312561214 cites W2945306514 @default.
- W4312561214 cites W2963427045 @default.
- W4312561214 cites W3025152414 @default.
- W4312561214 cites W3031858395 @default.
- W4312561214 cites W3102169921 @default.
- W4312561214 cites W3129643976 @default.
- W4312561214 cites W3159273459 @default.
- W4312561214 cites W3161542527 @default.
- W4312561214 doi "https://doi.org/10.1109/iccd56317.2022.00079" @default.
- W4312561214 hasPublicationYear "2022" @default.
- W4312561214 type Work @default.
- W4312561214 citedByCount "0" @default.
- W4312561214 crossrefType "proceedings-article" @default.
- W4312561214 hasAuthorship W4312561214A5032279242 @default.
- W4312561214 hasAuthorship W4312561214A5033410278 @default.
- W4312561214 hasAuthorship W4312561214A5039241745 @default.
- W4312561214 hasAuthorship W4312561214A5081869234 @default.
- W4312561214 hasConcept C105339364 @default.
- W4312561214 hasConcept C111919701 @default.
- W4312561214 hasConcept C120314980 @default.
- W4312561214 hasConcept C149635348 @default.
- W4312561214 hasConcept C154945302 @default.
- W4312561214 hasConcept C175133352 @default.
- W4312561214 hasConcept C2777904410 @default.
- W4312561214 hasConcept C41008148 @default.
- W4312561214 hasConcept C42935608 @default.
- W4312561214 hasConcept C529173508 @default.
- W4312561214 hasConcept C69016650 @default.
- W4312561214 hasConcept C76155785 @default.
- W4312561214 hasConcept C79974875 @default.
- W4312561214 hasConcept C81363708 @default.
- W4312561214 hasConcept C82876162 @default.
- W4312561214 hasConceptScore W4312561214C105339364 @default.
- W4312561214 hasConceptScore W4312561214C111919701 @default.
- W4312561214 hasConceptScore W4312561214C120314980 @default.
- W4312561214 hasConceptScore W4312561214C149635348 @default.
- W4312561214 hasConceptScore W4312561214C154945302 @default.
- W4312561214 hasConceptScore W4312561214C175133352 @default.
- W4312561214 hasConceptScore W4312561214C2777904410 @default.
- W4312561214 hasConceptScore W4312561214C41008148 @default.
- W4312561214 hasConceptScore W4312561214C42935608 @default.
- W4312561214 hasConceptScore W4312561214C529173508 @default.
- W4312561214 hasConceptScore W4312561214C69016650 @default.
- W4312561214 hasConceptScore W4312561214C76155785 @default.
- W4312561214 hasConceptScore W4312561214C79974875 @default.
- W4312561214 hasConceptScore W4312561214C81363708 @default.
- W4312561214 hasConceptScore W4312561214C82876162 @default.
- W4312561214 hasFunder F4320306076 @default.
- W4312561214 hasLocation W43125612141 @default.
- W4312561214 hasOpenAccess W4312561214 @default.
- W4312561214 hasPrimaryLocation W43125612141 @default.
- W4312561214 hasRelatedWork W2015855483 @default.
- W4312561214 hasRelatedWork W2201161321 @default.
- W4312561214 hasRelatedWork W2957766342 @default.
- W4312561214 hasRelatedWork W3009341939 @default.
- W4312561214 hasRelatedWork W3152278044 @default.
- W4312561214 hasRelatedWork W3159710779 @default.
- W4312561214 hasRelatedWork W3170853132 @default.
- W4312561214 hasRelatedWork W3179465017 @default.
- W4312561214 hasRelatedWork W4214756537 @default.
- W4312561214 hasRelatedWork W4376134025 @default.
- W4312561214 isParatext "false" @default.
- W4312561214 isRetracted "false" @default.
- W4312561214 workType "article" @default.