On-the-Fly Lowering Engine: Offloading Data Layout Conversion for Convolutional Neural Networks
Many deep learning frameworks utilize GEneral Matrix Multiplication (GEMM)-based convolution to accelerate CNN execution. GEMM-based convolution provides faster convolution yet requires a data conversion process called lowering (i.e., im2col), which incurs significant memory overhead and diminishes...
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Artigo |
| Lingua: | Inglês |
| Pubblicazione: |
IEEE
2022-01-01
|
| Serie: | IEEE Access |
| Soggetti: | |
| Accesso online: | https://ieeexplore.ieee.org/document/9833499/ |
| Tags: |
Nessun Tag, puoi essere il primo ad aggiungerne!!
|