Minimizing GPU Kernel Launch Overhead in Deep Learning Inference on Mobile GPUs.
Sumin KimSeunghwan OhYoungmin YiPublished in: HotMobile (2021)
Keyphrases
- deep learning
- graphics processing units
- graphics hardware
- gpu implementation
- unsupervised learning
- parallel programming
- unsupervised feature learning
- graphics processors
- parallel processing
- general purpose
- machine learning
- bayesian networks
- parallel computing
- mental models
- parallel implementation
- weakly supervised
- support vector
- deep architectures
- text classification
- multiscale