An Energy-Efficient GeMM-Based Convolution Accelerator With On-the-Fly im2col.
Jordi ForntPau Fontova-MustéMartí CaroJaume AbellaFrancesc MollJosep AltetChristoph StuderPublished in: IEEE Trans. Very Large Scale Integr. Syst. (2023)
Keyphrases
- energy efficient
- wireless sensor networks
- parallel implementation
- image processing
- sensor networks
- neural network
- energy consumption
- machine learning
- fast fourier transform
- discrete fourier transform
- energy efficiency
- diffusion equation
- gaussian kernel
- genetic algorithm
- compute intensive
- convolution kernel
- maximum lifetime