Orchestration of Perception Systems for Reliable Performance in Heterogeneous Platforms
Anirban Ghosea, Srijeeta Maityb, Arijit Karc and Soumyajit Deyd
Indian Institute of Technology, Kharagpur
aanirban.ghose@cse.iitkgp.ac.in
bsrijeeta.maity@iitkgp.ac.in
carijit.kar14@iitkgp.ac.in
dsoumya@cse.iitkgp.ac.in
ABSTRACT
Delivering driving comfort in this age of connected mobility is one of the primary goals of semi-autonomous perception systems increasingly being used in modern automotives. The performance of such perception systems is a function of execution rate which demands on-board platform-level support. With the advent of GPGPU compute support in automobiles, there exists an opportunity to adaptively enable higher execution rates for such Advanced Driver Assistant System tasks (ADAS tasks) subject to different vehicular driving contexts. This can be achieved through a combination of program level locality optimizations such as kernel fusion, thread coarsening and corelevel DVFS techniques while keeping in mind their effects on tasklevel deadline requirements and platform-level thermal reliability. In this communication, we present a future-proof, learning-based adaptive scheduling framework that strives to deliver reliable and predictable performance of ADAS tasks while accommodating for increased task-level throughput requirements.
Keywords: ADAS, OpenCL, Machine Learning, Control Theory, Heterogeneous Multicore, Real Time Scheduling.
