Matches in SemOpenAlex for { <https://semopenalex.org/work/W4281736000> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4281736000 endingPage "351" @default.
- W4281736000 startingPage "344" @default.
- W4281736000 abstract "To solve the problem of low computing efficiency of existing accelerators for convolutional neural network (CNNs), which caused by the inability to adapt to the characteristics of computing mode and caching for the mixed-precision quantized CNNs model, we propose a reconfigurable CNN processor in this paper, which consists of the reconfigurable adaptable computing unit, flexible on-chip cache unit and macro-instruction set. The multi-core CNN processor can be reconstructed according to the structure of CNN models and constraints of reconfigurable resources, to improve the utilization of computing resources. The elastic on-chip buffer and the data access approach by dynamically configuring an address to better utilization of on-chip memory. Then, the macroinstruction set architecture (mISA) can fully express the characteristics of the mixed-precision CNN models and reconfigurable processors, to reduce the complexity of mapping CNNs with different network structures and computing modes to reconfigurable the CNNs processors. For the well-known CNNs-VGG16 and ResNet-50, the proposed CNN processor has been implemented using Ultra96-V2 and ZCU102 FPGA, showing the throughput of 216.6 GOPS, and 214 GOPS, the computing efficiency of 0.63 GOPS/DSP and 0.64 GOPS/DSP on Ultra96-V2, respectively, achieving a better efficiency than the CNN accelerator based on fixed bit-width. Meanwhile, for ResNet-50, the throughput and the computing efficiency are up to 931.8 GOPS, 0.40 GOPS/DSP on ZCU102, respectively. In addition, these achieve up to 55.4% higher throughput than state-of-the-art CNN accelerators." @default.
- W4281736000 created "2022-06-13" @default.
- W4281736000 creator A5015491819 @default.
- W4281736000 creator A5056711524 @default.
- W4281736000 date "2022-04-01" @default.
- W4281736000 modified "2023-09-26" @default.
- W4281736000 title "A reconfigurable processor for mix-precision CNNs on FPGA" @default.
- W4281736000 cites W2616014673 @default.
- W4281736000 cites W2625954420 @default.
- W4281736000 cites W2794754997 @default.
- W4281736000 cites W2895531329 @default.
- W4281736000 cites W2902895686 @default.
- W4281736000 cites W2912949188 @default.
- W4281736000 cites W2933438941 @default.
- W4281736000 cites W2952857977 @default.
- W4281736000 cites W2963367920 @default.
- W4281736000 cites W2982479999 @default.
- W4281736000 cites W3119549454 @default.
- W4281736000 cites W4247198796 @default.
- W4281736000 doi "https://doi.org/10.1051/jnwpu/20224020344" @default.
- W4281736000 hasPublicationYear "2022" @default.
- W4281736000 type Work @default.
- W4281736000 citedByCount "0" @default.
- W4281736000 crossrefType "journal-article" @default.
- W4281736000 hasAuthorship W4281736000A5015491819 @default.
- W4281736000 hasAuthorship W4281736000A5056711524 @default.
- W4281736000 hasBestOaLocation W42817360001 @default.
- W4281736000 hasConcept C111919701 @default.
- W4281736000 hasConcept C118524514 @default.
- W4281736000 hasConcept C149635348 @default.
- W4281736000 hasConcept C154945302 @default.
- W4281736000 hasConcept C157764524 @default.
- W4281736000 hasConcept C173608175 @default.
- W4281736000 hasConcept C41008148 @default.
- W4281736000 hasConcept C42935608 @default.
- W4281736000 hasConcept C555944384 @default.
- W4281736000 hasConcept C81363708 @default.
- W4281736000 hasConcept C84462506 @default.
- W4281736000 hasConcept C9390403 @default.
- W4281736000 hasConceptScore W4281736000C111919701 @default.
- W4281736000 hasConceptScore W4281736000C118524514 @default.
- W4281736000 hasConceptScore W4281736000C149635348 @default.
- W4281736000 hasConceptScore W4281736000C154945302 @default.
- W4281736000 hasConceptScore W4281736000C157764524 @default.
- W4281736000 hasConceptScore W4281736000C173608175 @default.
- W4281736000 hasConceptScore W4281736000C41008148 @default.
- W4281736000 hasConceptScore W4281736000C42935608 @default.
- W4281736000 hasConceptScore W4281736000C555944384 @default.
- W4281736000 hasConceptScore W4281736000C81363708 @default.
- W4281736000 hasConceptScore W4281736000C84462506 @default.
- W4281736000 hasConceptScore W4281736000C9390403 @default.
- W4281736000 hasIssue "2" @default.
- W4281736000 hasLocation W42817360001 @default.
- W4281736000 hasLocation W42817360002 @default.
- W4281736000 hasOpenAccess W4281736000 @default.
- W4281736000 hasPrimaryLocation W42817360001 @default.
- W4281736000 hasRelatedWork W2129894819 @default.
- W4281736000 hasRelatedWork W2339728242 @default.
- W4281736000 hasRelatedWork W2350861609 @default.
- W4281736000 hasRelatedWork W2352017551 @default.
- W4281736000 hasRelatedWork W2363310833 @default.
- W4281736000 hasRelatedWork W2466675884 @default.
- W4281736000 hasRelatedWork W2524802307 @default.
- W4281736000 hasRelatedWork W2951390974 @default.
- W4281736000 hasRelatedWork W2997828269 @default.
- W4281736000 hasRelatedWork W4308216800 @default.
- W4281736000 hasVolume "40" @default.
- W4281736000 isParatext "false" @default.
- W4281736000 isRetracted "false" @default.
- W4281736000 workType "article" @default.