Deep Learning Inference Parallelization on Heterogeneous Processors With TensorRT.
Eunjin JeongJangryul KimSamnieng TanJaeseong LeeSoonhoi HaPublished in: IEEE Embed. Syst. Lett. (2022)
Keyphrases
- deep learning
- parallel processing
- parallel execution
- shared memory
- unsupervised learning
- unsupervised feature learning
- distributed memory
- machine learning
- parallel algorithm
- mental models
- bayesian networks
- decision making
- restricted boltzmann machine
- deep architectures
- multiscale
- weakly supervised
- probabilistic model
- pattern recognition
- data mining
- data sets