Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316252407> ?p ?o ?g. }
Showing items 1 to 91 of
91
with 100 items per page.
- W4316252407 abstract "Convolutional neural networks (CNNs) have been widely used in different areas. The success of CNNs comes with a huge amount of parameters and computations, and nowaday CNNs still keep moving toward larger structures. Although larger structures often bring about better inference accuracy, the increasing size also slows the inference speed down. Recently, various parameter sparsity methods have been proposed to accelerate CNNs by reducing the number of parameters and computations. Existing sparsity methods could be classified into two categories: unstructured and structured. Unstructured sparsity methods easily cause irregularity and thus have a suboptimal speedup. On the other hand, the structured sparsity methods could keep regularity by pruning the parameters following a certain pattern but result in low sparsity. In this paper, we propose a software/hardware co-design approach to bring local irregular sparsity into CNNs. Benefiting from the local irregularity, we design a row-wise computing engine, RConv Engine, to achieve workload balance and remarkable speedup. The experimental results show that our software/hardware co-design method can achieve a 10.9x speedup than the state-of-the-art methods with a negligible accuracy loss." @default.
- W4316252407 created "2023-01-15" @default.
- W4316252407 creator A5007368731 @default.
- W4316252407 creator A5016038041 @default.
- W4316252407 creator A5047305591 @default.
- W4316252407 creator A5058394999 @default.
- W4316252407 creator A5060378664 @default.
- W4316252407 creator A5084915949 @default.
- W4316252407 date "2022-08-29" @default.
- W4316252407 modified "2023-10-17" @default.
- W4316252407 title "A Software/Hardware Co-design Local Irregular Sparsity Method for Accelerating CNNs on FPGA" @default.
- W4316252407 cites W2108598243 @default.
- W4316252407 cites W2112796928 @default.
- W4316252407 cites W2533598788 @default.
- W4316252407 cites W2616014673 @default.
- W4316252407 cites W2625457103 @default.
- W4316252407 cites W2792503273 @default.
- W4316252407 cites W2904902077 @default.
- W4316252407 cites W2949619037 @default.
- W4316252407 cites W2963037989 @default.
- W4316252407 cites W2963363373 @default.
- W4316252407 cites W2964233199 @default.
- W4316252407 cites W3005712428 @default.
- W4316252407 cites W3009383973 @default.
- W4316252407 cites W3085447111 @default.
- W4316252407 cites W3093982621 @default.
- W4316252407 cites W3104393472 @default.
- W4316252407 doi "https://doi.org/10.1145/3547276.3548521" @default.
- W4316252407 hasPublicationYear "2022" @default.
- W4316252407 type Work @default.
- W4316252407 citedByCount "0" @default.
- W4316252407 crossrefType "proceedings-article" @default.
- W4316252407 hasAuthorship W4316252407A5007368731 @default.
- W4316252407 hasAuthorship W4316252407A5016038041 @default.
- W4316252407 hasAuthorship W4316252407A5047305591 @default.
- W4316252407 hasAuthorship W4316252407A5058394999 @default.
- W4316252407 hasAuthorship W4316252407A5060378664 @default.
- W4316252407 hasAuthorship W4316252407A5084915949 @default.
- W4316252407 hasConcept C108010975 @default.
- W4316252407 hasConcept C111919701 @default.
- W4316252407 hasConcept C113775141 @default.
- W4316252407 hasConcept C11413529 @default.
- W4316252407 hasConcept C154945302 @default.
- W4316252407 hasConcept C173608175 @default.
- W4316252407 hasConcept C199360897 @default.
- W4316252407 hasConcept C2776214188 @default.
- W4316252407 hasConcept C2777904410 @default.
- W4316252407 hasConcept C2778476105 @default.
- W4316252407 hasConcept C41008148 @default.
- W4316252407 hasConcept C42935608 @default.
- W4316252407 hasConcept C45374587 @default.
- W4316252407 hasConcept C6557445 @default.
- W4316252407 hasConcept C68339613 @default.
- W4316252407 hasConcept C81363708 @default.
- W4316252407 hasConcept C86803240 @default.
- W4316252407 hasConcept C9390403 @default.
- W4316252407 hasConceptScore W4316252407C108010975 @default.
- W4316252407 hasConceptScore W4316252407C111919701 @default.
- W4316252407 hasConceptScore W4316252407C113775141 @default.
- W4316252407 hasConceptScore W4316252407C11413529 @default.
- W4316252407 hasConceptScore W4316252407C154945302 @default.
- W4316252407 hasConceptScore W4316252407C173608175 @default.
- W4316252407 hasConceptScore W4316252407C199360897 @default.
- W4316252407 hasConceptScore W4316252407C2776214188 @default.
- W4316252407 hasConceptScore W4316252407C2777904410 @default.
- W4316252407 hasConceptScore W4316252407C2778476105 @default.
- W4316252407 hasConceptScore W4316252407C41008148 @default.
- W4316252407 hasConceptScore W4316252407C42935608 @default.
- W4316252407 hasConceptScore W4316252407C45374587 @default.
- W4316252407 hasConceptScore W4316252407C6557445 @default.
- W4316252407 hasConceptScore W4316252407C68339613 @default.
- W4316252407 hasConceptScore W4316252407C81363708 @default.
- W4316252407 hasConceptScore W4316252407C86803240 @default.
- W4316252407 hasConceptScore W4316252407C9390403 @default.
- W4316252407 hasFunder F4320321001 @default.
- W4316252407 hasLocation W43162524071 @default.
- W4316252407 hasOpenAccess W4316252407 @default.
- W4316252407 hasPrimaryLocation W43162524071 @default.
- W4316252407 hasRelatedWork W1509211761 @default.
- W4316252407 hasRelatedWork W156843270 @default.
- W4316252407 hasRelatedWork W1905659066 @default.
- W4316252407 hasRelatedWork W2007449167 @default.
- W4316252407 hasRelatedWork W2036853476 @default.
- W4316252407 hasRelatedWork W2154055002 @default.
- W4316252407 hasRelatedWork W2391299576 @default.
- W4316252407 hasRelatedWork W2904876938 @default.
- W4316252407 hasRelatedWork W3128179121 @default.
- W4316252407 hasRelatedWork W2185731423 @default.
- W4316252407 isParatext "false" @default.
- W4316252407 isRetracted "false" @default.
- W4316252407 workType "article" @default.