Matches in SemOpenAlex for { <https://semopenalex.org/work/W2910252103> ?p ?o ?g. }
Showing items 1 to 90 of
90
with 100 items per page.
- W2910252103 abstract "Convolutional Neural Networks (CNNs) are rapidly gaining popularity in varied fields. Due to their increasingly deep and computationally heavy structures, it is difficult to deploy them on energy constrained mobile applications. Hardware accelerators such as FPGAs have come up as an attractive alternative. However, with the limited on-chip memory and computation resources of FPGA, meeting the high memory throughput requirement and exploiting the parallelism of CNNs is a major challenge. We propose a high-performance FPGA based architecture - Depth Concatenation and Inter-Layer Fusion based ConvNet Accelerator - DeCoILFNet which exploits the intra-layer parallelism of CNNs by flattening across depth and combines it with a highly pipelined data flow across the layers enabling inter-layer fusion. This architecture significantly reduces off-chip memory accesses and maximizes the throughput. Compared to a 3.5GHz hexa-core Intel Xeon E7 caffe-implementation, our 120MHz FPGA accelerator is 30X faster. In addition, our design reduces external memory access by 11.5X along with a speedup of more than 2X in the number of clock cycles compared to state-of-the-art FPGA accelerators." @default.
- W2910252103 created "2019-01-25" @default.
- W2910252103 creator A5018760997 @default.
- W2910252103 creator A5051691675 @default.
- W2910252103 creator A5054562780 @default.
- W2910252103 creator A5075816776 @default.
- W2910252103 date "2018-12-01" @default.
- W2910252103 modified "2023-09-27" @default.
- W2910252103 title "DeCoILFNet: Depth Concatenation and Inter-Layer Fusion based ConvNet Accelerator" @default.
- W2910252103 cites W1667652561 @default.
- W2910252103 cites W1686810756 @default.
- W2910252103 cites W1980208272 @default.
- W2910252103 cites W2009832130 @default.
- W2910252103 cites W2048266589 @default.
- W2910252103 cites W2094756095 @default.
- W2910252103 cites W2122862680 @default.
- W2910252103 cites W2155893237 @default.
- W2910252103 cites W2194775991 @default.
- W2910252103 cites W2309086850 @default.
- W2910252103 cites W2395611524 @default.
- W2910252103 cites W2565305208 @default.
- W2910252103 cites W2963881378 @default.
- W2910252103 hasPublicationYear "2018" @default.
- W2910252103 type Work @default.
- W2910252103 sameAs 2910252103 @default.
- W2910252103 citedByCount "0" @default.
- W2910252103 crossrefType "posted-content" @default.
- W2910252103 hasAuthorship W2910252103A5018760997 @default.
- W2910252103 hasAuthorship W2910252103A5051691675 @default.
- W2910252103 hasAuthorship W2910252103A5054562780 @default.
- W2910252103 hasAuthorship W2910252103A5075816776 @default.
- W2910252103 hasConcept C108583219 @default.
- W2910252103 hasConcept C111919701 @default.
- W2910252103 hasConcept C114614502 @default.
- W2910252103 hasConcept C118524514 @default.
- W2910252103 hasConcept C145108525 @default.
- W2910252103 hasConcept C149635348 @default.
- W2910252103 hasConcept C154945302 @default.
- W2910252103 hasConcept C157764524 @default.
- W2910252103 hasConcept C173608175 @default.
- W2910252103 hasConcept C33923547 @default.
- W2910252103 hasConcept C41008148 @default.
- W2910252103 hasConcept C42935608 @default.
- W2910252103 hasConcept C555944384 @default.
- W2910252103 hasConcept C68339613 @default.
- W2910252103 hasConcept C81363708 @default.
- W2910252103 hasConcept C87619178 @default.
- W2910252103 hasConceptScore W2910252103C108583219 @default.
- W2910252103 hasConceptScore W2910252103C111919701 @default.
- W2910252103 hasConceptScore W2910252103C114614502 @default.
- W2910252103 hasConceptScore W2910252103C118524514 @default.
- W2910252103 hasConceptScore W2910252103C145108525 @default.
- W2910252103 hasConceptScore W2910252103C149635348 @default.
- W2910252103 hasConceptScore W2910252103C154945302 @default.
- W2910252103 hasConceptScore W2910252103C157764524 @default.
- W2910252103 hasConceptScore W2910252103C173608175 @default.
- W2910252103 hasConceptScore W2910252103C33923547 @default.
- W2910252103 hasConceptScore W2910252103C41008148 @default.
- W2910252103 hasConceptScore W2910252103C42935608 @default.
- W2910252103 hasConceptScore W2910252103C555944384 @default.
- W2910252103 hasConceptScore W2910252103C68339613 @default.
- W2910252103 hasConceptScore W2910252103C81363708 @default.
- W2910252103 hasConceptScore W2910252103C87619178 @default.
- W2910252103 hasLocation W29102521031 @default.
- W2910252103 hasOpenAccess W2910252103 @default.
- W2910252103 hasPrimaryLocation W29102521031 @default.
- W2910252103 hasRelatedWork W2404540148 @default.
- W2910252103 hasRelatedWork W2584616277 @default.
- W2910252103 hasRelatedWork W2585546120 @default.
- W2910252103 hasRelatedWork W2699539367 @default.
- W2910252103 hasRelatedWork W2786661381 @default.
- W2910252103 hasRelatedWork W2793009992 @default.
- W2910252103 hasRelatedWork W2805153572 @default.
- W2910252103 hasRelatedWork W2903731869 @default.
- W2910252103 hasRelatedWork W2907579173 @default.
- W2910252103 hasRelatedWork W2917450576 @default.
- W2910252103 hasRelatedWork W2943187097 @default.
- W2910252103 hasRelatedWork W2949619037 @default.
- W2910252103 hasRelatedWork W2951390974 @default.
- W2910252103 hasRelatedWork W2962953210 @default.
- W2910252103 hasRelatedWork W3010819965 @default.
- W2910252103 hasRelatedWork W3034653380 @default.
- W2910252103 hasRelatedWork W3113177379 @default.
- W2910252103 hasRelatedWork W3159322265 @default.
- W2910252103 hasRelatedWork W3169326189 @default.
- W2910252103 hasRelatedWork W3197490098 @default.
- W2910252103 isParatext "false" @default.
- W2910252103 isRetracted "false" @default.
- W2910252103 magId "2910252103" @default.
- W2910252103 workType "article" @default.