USEFUSE fuses CNN convolution layers with online arithmetic and a uniform tile stride method, reporting 1.43 to 1.87x speedups and 42.6 to 48.5 percent energy savings over conventional bit-serial fused designs.
Non-uniform step size quantization for accurate post-training quantization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
USEFUSE: Uniform Stride for Enhanced Performance in Fused Layer Architecture of Deep Neural Networks
USEFUSE fuses CNN convolution layers with online arithmetic and a uniform tile stride method, reporting 1.43 to 1.87x speedups and 42.6 to 48.5 percent energy savings over conventional bit-serial fused designs.