Performance Efficient Layer-aware DNN Inference Task Scheduling in GPU Cluster.

Hongmin Geng Deze Zeng Yuepeng Li

Published in: GLOBECOM (2022)

Keyphrases

real time
data mining
computationally efficient
multi layer
computationally expensive
data clustering
graphics hardware
parallel computation
efficient learning
computing systems
belief networks
cluster analysis
cost effective
hidden markov models
expert systems
neural network
data sets