Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313484751> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4313484751 abstract "In the last decade, enormous and renewed attention to Artificial Intelligence has emerged thanks to Deep Neural Networks (DNNs), which can achieve high performance in performing specific tasks at the cost of a high computational complexity. GPUs are commonly used to accelerate DNNs, but generally determine a very high power consumption and poor time predictability. For this reason, GPUs are becoming less attractive for resource-constrained, real-time systems, while there is a growing demand for specialized hardware accelerators that can better fit the requirements of embedded systems. Following this trend, this paper focuses on hardware acceleration for the DNNs used by Baidu Apollo, an open-source autonomous driving framework. As an experience report of performing R&D with industrial technologies, we discuss challenges faced in shifting from GPU-based to FPGA-based DNN acceleration when per-formed using the DPU core by Xilinx deployed on an Ultrascale+ SoC FPG A platform. Furthermore, it shows pros and cons of today's hardware accelerating tools. Experimental evaluations were conducted to evaluate the performance of FPGA-accelerated DNNs in terms of accuracy, throughput, and power consumption, in comparison with those achieved on embedded GPUs." @default.
- W4313484751 created "2023-01-06" @default.
- W4313484751 creator A5000981593 @default.
- W4313484751 creator A5022569570 @default.
- W4313484751 creator A5024920325 @default.
- W4313484751 creator A5072482410 @default.
- W4313484751 date "2022-08-01" @default.
- W4313484751 modified "2023-09-30" @default.
- W4313484751 title "Hardware Acceleration of Deep Neural Networks for Autonomous Driving on FPGA-based SoC" @default.
- W4313484751 cites W1999085092 @default.
- W4313484751 cites W2604319603 @default.
- W4313484751 cites W2910890510 @default.
- W4313484751 cites W3034940165 @default.
- W4313484751 cites W3038988173 @default.
- W4313484751 cites W3092347650 @default.
- W4313484751 cites W3102169921 @default.
- W4313484751 cites W3136021864 @default.
- W4313484751 cites W3165727671 @default.
- W4313484751 cites W4200195825 @default.
- W4313484751 doi "https://doi.org/10.1109/dsd57027.2022.00061" @default.
- W4313484751 hasPublicationYear "2022" @default.
- W4313484751 type Work @default.
- W4313484751 citedByCount "3" @default.
- W4313484751 countsByYear W43134847512023 @default.
- W4313484751 crossrefType "proceedings-article" @default.
- W4313484751 hasAuthorship W4313484751A5000981593 @default.
- W4313484751 hasAuthorship W4313484751A5022569570 @default.
- W4313484751 hasAuthorship W4313484751A5024920325 @default.
- W4313484751 hasAuthorship W4313484751A5072482410 @default.
- W4313484751 hasConcept C111919701 @default.
- W4313484751 hasConcept C117896860 @default.
- W4313484751 hasConcept C118524514 @default.
- W4313484751 hasConcept C121332964 @default.
- W4313484751 hasConcept C13164978 @default.
- W4313484751 hasConcept C149635348 @default.
- W4313484751 hasConcept C154945302 @default.
- W4313484751 hasConcept C157764524 @default.
- W4313484751 hasConcept C163258240 @default.
- W4313484751 hasConcept C197640229 @default.
- W4313484751 hasConcept C2984118289 @default.
- W4313484751 hasConcept C2984842247 @default.
- W4313484751 hasConcept C41008148 @default.
- W4313484751 hasConcept C42935608 @default.
- W4313484751 hasConcept C50644808 @default.
- W4313484751 hasConcept C555944384 @default.
- W4313484751 hasConcept C62520636 @default.
- W4313484751 hasConcept C74650414 @default.
- W4313484751 hasConceptScore W4313484751C111919701 @default.
- W4313484751 hasConceptScore W4313484751C117896860 @default.
- W4313484751 hasConceptScore W4313484751C118524514 @default.
- W4313484751 hasConceptScore W4313484751C121332964 @default.
- W4313484751 hasConceptScore W4313484751C13164978 @default.
- W4313484751 hasConceptScore W4313484751C149635348 @default.
- W4313484751 hasConceptScore W4313484751C154945302 @default.
- W4313484751 hasConceptScore W4313484751C157764524 @default.
- W4313484751 hasConceptScore W4313484751C163258240 @default.
- W4313484751 hasConceptScore W4313484751C197640229 @default.
- W4313484751 hasConceptScore W4313484751C2984118289 @default.
- W4313484751 hasConceptScore W4313484751C2984842247 @default.
- W4313484751 hasConceptScore W4313484751C41008148 @default.
- W4313484751 hasConceptScore W4313484751C42935608 @default.
- W4313484751 hasConceptScore W4313484751C50644808 @default.
- W4313484751 hasConceptScore W4313484751C555944384 @default.
- W4313484751 hasConceptScore W4313484751C62520636 @default.
- W4313484751 hasConceptScore W4313484751C74650414 @default.
- W4313484751 hasLocation W43134847511 @default.
- W4313484751 hasOpenAccess W4313484751 @default.
- W4313484751 hasPrimaryLocation W43134847511 @default.
- W4313484751 hasRelatedWork W1732210391 @default.
- W4313484751 hasRelatedWork W2100470915 @default.
- W4313484751 hasRelatedWork W2160069347 @default.
- W4313484751 hasRelatedWork W2351404747 @default.
- W4313484751 hasRelatedWork W2521029662 @default.
- W4313484751 hasRelatedWork W2756009169 @default.
- W4313484751 hasRelatedWork W3088312824 @default.
- W4313484751 hasRelatedWork W3147787617 @default.
- W4313484751 hasRelatedWork W4295855328 @default.
- W4313484751 hasRelatedWork W4363649491 @default.
- W4313484751 isParatext "false" @default.
- W4313484751 isRetracted "false" @default.
- W4313484751 workType "article" @default.