Neurosurgeon: Collaborative intelligence between the cloud and mobile edge
#graph_partitioning #cloud-edge_collaboration #prediction_model #computation_offloading
Last updated
#graph_partitioning #cloud-edge_collaboration #prediction_model #computation_offloading
Last updated
Presented in ASPLOS 2017.
Authors: Yiping Kang, Johann Hauswald, Cao Gao, Austin Rovinski, Trevor Mudge, Jason Mars, Lingjia Tang (UMich).
This paper presents Neurosurgeon, a lightweight scheduler to automatically partition DNN computation between mobile devices and data centers at the granularity of neural network layers.
It doesn't require per-application profiling.
Analysis of the target DNN (use the prediction models to estimate)
Partition point selection (for best end-to-end latency or best mobile energy consumption)
Previous research efforts focus on offloading computation from the mobile to the cloud.