Microsecond-scale Preemption for Concurrent GPU-accelerated DNN Inferences
Submitted by jasmine@usenix.org on May 11, 2022 - 7:12 pm
| Title | Microsecond-scale Preemption for Concurrent GPU-accelerated DNN Inferences |
| Publication Type | Conference Paper |
| Year of Publication | 2022 |
| Authors | Han M, Zhang H, Chen R, Chen H |
| Conference Name | 16th USENIX Symposium on Operating Systems Design and Implementation (OSDI 22) |
| Date Published | 07/2022 |
| Publisher | USENIX Association |
| Conference Location | Carlsbad, CA |
| ISBN Number | 978-1-939133-28-1 |
| URL | https://www.usenix.org/conference/osdi22/presentation/han |
- DBLP
- Log in or Register to post comments
- Google Scholar
- BibTeX