Microsecond-scale Preemption for Concurrent GPU-accelerated DNN Inferences

TitleMicrosecond-scale Preemption for Concurrent GPU-accelerated DNN Inferences
Publication TypeConference Paper
Year of Publication2022
AuthorsHan M, Zhang H, Chen R, Chen H
Conference Name16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22)
Date Published07/2022
PublisherUSENIX Association
Conference LocationCarlsbad, CA
ISBN Number978-1-939133-28-1
URLhttps://www.usenix.org/conference/osdi22/presentation/han