Matches in SemOpenAlex for { <https://semopenalex.org/work/W4385585510> ?p ?o ?g. }
Showing items 1 to 85 of
85
with 100 items per page.
- W4385585510 abstract "Recent research widely deployed Neural Networks (NNs) in various scenarios, such as IoT systems, wearable devices, or smart sensors. However, the complex application scenarios cause the rapid extension of network model size and the requirement for higher-performance hardware platforms. Related works apply Heterogeneous Streaming Dataflow (HSD) and Processing Element Matrix (PEM) architectures as the most popular schemes for FPGA-based implementation of NN accelerator: 1) HSD architecture implements a complete network for given trained models on FPGA with simplified control but more hardware consumption; 2) PEM architecture implements reusable neuron structures controlled by runtime environments/drivers providing the generic acceleration supports for different network models. Our work explores a new hybrid architecture based on HSD and PEM to implement a reusable partial network structure on FPGA and achieve generic acceleration supports for different network models with simplffied runtime control. This architecture supports scalable, mixable, quantized precision, and selectable activation functions, including ReLU, Sigmoid, Tanh, Sign, and Multi-Thresholds. Data stream transmission can reset the accelerator configuration in runtime without hardware implementation changes for different networks. Our design fully supports the generic inference acceleration for different Multi-Layer Perceptron (MLP) models." @default.
- W4385585510 created "2023-08-05" @default.
- W4385585510 creator A5028792027 @default.
- W4385585510 creator A5030691366 @default.
- W4385585510 creator A5075349265 @default.
- W4385585510 creator A5076463582 @default.
- W4385585510 date "2023-05-01" @default.
- W4385585510 modified "2023-10-16" @default.
- W4385585510 title "NetPU-M: a Generic Reconfigurable Neural Network Accelerator Architecture for MLPs" @default.
- W4385585510 cites W1973695593 @default.
- W4385585510 cites W1998379075 @default.
- W4385585510 cites W2112796928 @default.
- W4385585510 cites W2396572963 @default.
- W4385585510 cites W2586654419 @default.
- W4385585510 cites W2616014673 @default.
- W4385585510 cites W2795578121 @default.
- W4385585510 cites W2827334269 @default.
- W4385585510 cites W2883929540 @default.
- W4385585510 cites W2891946740 @default.
- W4385585510 cites W2936278485 @default.
- W4385585510 cites W2963122961 @default.
- W4385585510 cites W2964133305 @default.
- W4385585510 cites W2999803881 @default.
- W4385585510 cites W3008905965 @default.
- W4385585510 cites W3035262495 @default.
- W4385585510 cites W3093982621 @default.
- W4385585510 cites W3102169921 @default.
- W4385585510 cites W3185437734 @default.
- W4385585510 cites W3200780112 @default.
- W4385585510 cites W3205657855 @default.
- W4385585510 cites W3206719067 @default.
- W4385585510 cites W3206749822 @default.
- W4385585510 cites W4242577057 @default.
- W4385585510 cites W4311839450 @default.
- W4385585510 doi "https://doi.org/10.1109/ipdpsw59300.2023.00026" @default.
- W4385585510 hasPublicationYear "2023" @default.
- W4385585510 type Work @default.
- W4385585510 citedByCount "0" @default.
- W4385585510 crossrefType "proceedings-article" @default.
- W4385585510 hasAuthorship W4385585510A5028792027 @default.
- W4385585510 hasAuthorship W4385585510A5030691366 @default.
- W4385585510 hasAuthorship W4385585510A5075349265 @default.
- W4385585510 hasAuthorship W4385585510A5076463582 @default.
- W4385585510 hasConcept C118524514 @default.
- W4385585510 hasConcept C120314980 @default.
- W4385585510 hasConcept C13164978 @default.
- W4385585510 hasConcept C149635348 @default.
- W4385585510 hasConcept C154945302 @default.
- W4385585510 hasConcept C193415008 @default.
- W4385585510 hasConcept C31258907 @default.
- W4385585510 hasConcept C41008148 @default.
- W4385585510 hasConcept C42935608 @default.
- W4385585510 hasConcept C48044578 @default.
- W4385585510 hasConcept C50644808 @default.
- W4385585510 hasConcept C77088390 @default.
- W4385585510 hasConcept C9390403 @default.
- W4385585510 hasConceptScore W4385585510C118524514 @default.
- W4385585510 hasConceptScore W4385585510C120314980 @default.
- W4385585510 hasConceptScore W4385585510C13164978 @default.
- W4385585510 hasConceptScore W4385585510C149635348 @default.
- W4385585510 hasConceptScore W4385585510C154945302 @default.
- W4385585510 hasConceptScore W4385585510C193415008 @default.
- W4385585510 hasConceptScore W4385585510C31258907 @default.
- W4385585510 hasConceptScore W4385585510C41008148 @default.
- W4385585510 hasConceptScore W4385585510C42935608 @default.
- W4385585510 hasConceptScore W4385585510C48044578 @default.
- W4385585510 hasConceptScore W4385585510C50644808 @default.
- W4385585510 hasConceptScore W4385585510C77088390 @default.
- W4385585510 hasConceptScore W4385585510C9390403 @default.
- W4385585510 hasLocation W43855855101 @default.
- W4385585510 hasOpenAccess W4385585510 @default.
- W4385585510 hasPrimaryLocation W43855855101 @default.
- W4385585510 hasRelatedWork W1732210391 @default.
- W4385585510 hasRelatedWork W1975010174 @default.
- W4385585510 hasRelatedWork W1992741870 @default.
- W4385585510 hasRelatedWork W2027487876 @default.
- W4385585510 hasRelatedWork W2364921833 @default.
- W4385585510 hasRelatedWork W2380023786 @default.
- W4385585510 hasRelatedWork W2385146268 @default.
- W4385585510 hasRelatedWork W2546696010 @default.
- W4385585510 hasRelatedWork W3147787617 @default.
- W4385585510 hasRelatedWork W4295855328 @default.
- W4385585510 isParatext "false" @default.
- W4385585510 isRetracted "false" @default.
- W4385585510 workType "article" @default.