[论文笔记]Neurosurgeon: Collaborative Intelligence Between the Cloud and Mobile Edge

keypoints

1. How feasible it is to execute large-scale intelligent workloads on today’s mobile platforms?
2. At what point is the cost of transferring speech and image data over the wireless network too high to justify cloud processing?
3. What role should the mobile edge play in provid- ing processing support for intelligent applications requiring heavy computation?

contributions

1. In-depth examination of the status quo
   the latency and energy consumption of executing state- of-the-art DNNs in the cloud and on the mobile device

2. DNN compute and data size characteristics study
   DNN layers have significantly different compute and data size characteristics depending on their type and configurations

3. DNN computation partitioning across the cloud and mobile edge

4. Neurosurgeon runtime system and layer performance prediction models
   a set of models to pre- dict the latency and power consumption of a DNN layer based on its type and configuration
   a system to intelligently partition DNN com- putation between the mobile and cloud

Model

Algorithm

Experimental setup

mobile devices

server:

framework:
caffe

model:
AlexNet

other:

1. TestMyNet(measure the bandwidth)

2. Watts Up(measure energy consumption)Watts Up?
   Power Meter. https://www.wattsupmeters. com/. Accessed: 2015-05.

3. Thrift
   an open source flexible RPC inter- face for inter-process communication

4. MAUI
   a general offloading framework（可用做实验比较）
   Eduardo Cuervo, Aruna Balasubramanian, Dae-ki Cho, Alec Wolman, Stefan Saroiu, Ranveer Chandra, and Paramvir Bahl. Maui: making smartphones last longer with code offload. In Proceedings of the 8th international conference on Mobile systems, applications, and services, pages 49–62. ACM, 2010.

5. BigHouse（Data Center throughput）
   David Meisner, Junjie Wu, and Thomas F. Wenisch. Big- House: A Simulation Infrastructure for Data Center Systems. ISPASS ’12: International Symposium on Performance Anal- ysis of Systems and Software, April 2012.