Login / Signup
GPNPU: Enabling Efficient Hardware-Based Direct Convolution with Multi-Precision Support in GPU Tensor Cores.
Zhuoran Song
Jianfei Wang
Tianjian Li
Li Jiang
Jing Ke
Xiaoyao Liang
Naifeng Jing
Published in:
DAC (2020)
Keyphrases
</>
parallel architectures
graphics processors
real time
parallel computation
graphics hardware
low cost
image processing
computer systems
parallel processing
graphics cards
high precision
computing power
hardware architecture
multi core processors
gpu implementation