Matches in SemOpenAlex for { <https://semopenalex.org/work/W4210348541> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4210348541 abstract "Machine learning, and in particular deep learning (DL), has seen strong success in a wide variety of applications, e.g. object detection, image classification and self-driving. However, due to the limitations on hardware resources and power consumption, there are many challenges to deploy deep learning algorithms on resource-constrained mobile and embedded systems, especially for systems running multiple DL algorithms for a variety of tasks. In this paper, an adaptive hardware resource management system, implemented on field-programmable gate arrays (FPGAs), is proposed to dynamically manage the on-chip hardware resources (e.g. LUTs, BRAMs and DSPs) to adapt to a variety of tasks. Using dynamic function exchange (DFX) technology, the system can dynamically allocate hardware resources to deploy deep learning units (DPUs) so as to balance the requirements, performance and power consumption of the deep learning applications. The prototype is implemented on the Xilinx Zynq UltraScale+ series chips. The experiment results indicate that the proposed scheme significantly improves the computing efficiency of the resource-constrained systems under various experimental scenarios. Compared to the baseline, the proposed strategy consumes 38% and 82% of power in low working load cases and high working load cases, respectively. Typically, the proposed system can save approximately 75.8% of energy." @default.
- W4210348541 created "2022-02-08" @default.
- W4210348541 creator A5013456828 @default.
- W4210348541 creator A5034444080 @default.
- W4210348541 creator A5042584242 @default.
- W4210348541 creator A5059549524 @default.
- W4210348541 creator A5085501322 @default.
- W4210348541 date "2021-12-01" @default.
- W4210348541 modified "2023-10-05" @default.
- W4210348541 title "FPGA based Adaptive Hardware Acceleration for Multiple Deep Learning Tasks" @default.
- W4210348541 cites W2125612798 @default.
- W4210348541 cites W2137235679 @default.
- W4210348541 cites W2160011949 @default.
- W4210348541 cites W2176737848 @default.
- W4210348541 cites W3007493000 @default.
- W4210348541 doi "https://doi.org/10.1109/mcsoc51149.2021.00038" @default.
- W4210348541 hasPublicationYear "2021" @default.
- W4210348541 type Work @default.
- W4210348541 citedByCount "4" @default.
- W4210348541 countsByYear W42103485412022 @default.
- W4210348541 countsByYear W42103485412023 @default.
- W4210348541 crossrefType "proceedings-article" @default.
- W4210348541 hasAuthorship W4210348541A5013456828 @default.
- W4210348541 hasAuthorship W4210348541A5034444080 @default.
- W4210348541 hasAuthorship W4210348541A5042584242 @default.
- W4210348541 hasAuthorship W4210348541A5059549524 @default.
- W4210348541 hasAuthorship W4210348541A5085501322 @default.
- W4210348541 hasConcept C108583219 @default.
- W4210348541 hasConcept C118524514 @default.
- W4210348541 hasConcept C119599485 @default.
- W4210348541 hasConcept C127413603 @default.
- W4210348541 hasConcept C13164978 @default.
- W4210348541 hasConcept C136197465 @default.
- W4210348541 hasConcept C149635348 @default.
- W4210348541 hasConcept C153180895 @default.
- W4210348541 hasConcept C154945302 @default.
- W4210348541 hasConcept C2776151529 @default.
- W4210348541 hasConcept C2780165032 @default.
- W4210348541 hasConcept C41008148 @default.
- W4210348541 hasConcept C42935608 @default.
- W4210348541 hasConcept C9390403 @default.
- W4210348541 hasConceptScore W4210348541C108583219 @default.
- W4210348541 hasConceptScore W4210348541C118524514 @default.
- W4210348541 hasConceptScore W4210348541C119599485 @default.
- W4210348541 hasConceptScore W4210348541C127413603 @default.
- W4210348541 hasConceptScore W4210348541C13164978 @default.
- W4210348541 hasConceptScore W4210348541C136197465 @default.
- W4210348541 hasConceptScore W4210348541C149635348 @default.
- W4210348541 hasConceptScore W4210348541C153180895 @default.
- W4210348541 hasConceptScore W4210348541C154945302 @default.
- W4210348541 hasConceptScore W4210348541C2776151529 @default.
- W4210348541 hasConceptScore W4210348541C2780165032 @default.
- W4210348541 hasConceptScore W4210348541C41008148 @default.
- W4210348541 hasConceptScore W4210348541C42935608 @default.
- W4210348541 hasConceptScore W4210348541C9390403 @default.
- W4210348541 hasFunder F4320334627 @default.
- W4210348541 hasLocation W42103485411 @default.
- W4210348541 hasOpenAccess W4210348541 @default.
- W4210348541 hasPrimaryLocation W42103485411 @default.
- W4210348541 hasRelatedWork W1732210391 @default.
- W4210348541 hasRelatedWork W2369375926 @default.
- W4210348541 hasRelatedWork W2907463061 @default.
- W4210348541 hasRelatedWork W2970686063 @default.
- W4210348541 hasRelatedWork W3097193516 @default.
- W4210348541 hasRelatedWork W3124648670 @default.
- W4210348541 hasRelatedWork W3147787617 @default.
- W4210348541 hasRelatedWork W3201484345 @default.
- W4210348541 hasRelatedWork W4281707861 @default.
- W4210348541 hasRelatedWork W4295855328 @default.
- W4210348541 isParatext "false" @default.
- W4210348541 isRetracted "false" @default.
- W4210348541 workType "article" @default.