TY - GEN
T1 - On Removing Algorithmic Priority Inversion from Mission-critical Machine Inference Pipelines
AU - Liu, Shengzhong
AU - Yao, Shuochao
AU - Fu, Xinzhe
AU - Tabish, Rohan
AU - Yu, Simon
AU - Bansal, Ayoosh
AU - Yun, Heechul
AU - Sha, Lui
AU - Abdelzaher, Tarek
N1 - Publisher Copyright:
© 2020 IEEE.
PY - 2020/12
Y1 - 2020/12
N2 - The paper discusses algorithmic priority inversion in mission-critical machine inference pipelines used in modern neural-network-based cyber-physical applications, and develops a scheduling solution to mitigate its effect. In general, priority inversion occurs in real-time systems when computations that are of lower priority are performed together with or ahead of those that are of higher priority.1 In current machine intelligence software, significant priority inversion occurs on the path from perception to decision-making, where the execution of underlying neural network algorithms does not differentiate between critical and less critical data. We describe a scheduling framework to resolve this problem, and demonstrate that it improves the system's ability to react to critical inputs, while at the same time reducing platform cost.
AB - The paper discusses algorithmic priority inversion in mission-critical machine inference pipelines used in modern neural-network-based cyber-physical applications, and develops a scheduling solution to mitigate its effect. In general, priority inversion occurs in real-time systems when computations that are of lower priority are performed together with or ahead of those that are of higher priority.1 In current machine intelligence software, significant priority inversion occurs on the path from perception to decision-making, where the execution of underlying neural network algorithms does not differentiate between critical and less critical data. We describe a scheduling framework to resolve this problem, and demonstrate that it improves the system's ability to react to critical inputs, while at the same time reducing platform cost.
KW - Algorithmic Priority Inversion
KW - Cyber-Physical Systems (CPS)
KW - Machine Inference
UR - http://www.scopus.com/inward/record.url?scp=85101990148&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85101990148&partnerID=8YFLogxK
U2 - 10.1109/RTSS49844.2020.00037
DO - 10.1109/RTSS49844.2020.00037
M3 - Conference contribution
AN - SCOPUS:85101990148
T3 - Proceedings - Real-Time Systems Symposium
SP - 319
EP - 332
BT - Proceedings - 2020 IEEE 41st Real-Time Systems Symposium, RTSS 2020
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 41st IEEE Real-Time Systems Symposium, RTSS 2020
Y2 - 1 December 2020 through 4 December 2020
ER -