Automated Runtime-Aware Scheduling for Multi-Tenant DNN Inference on GPU

Thumbnail Image

Files

2111.14255.pdf (1.27 MB)

Links to Files

https://arxiv.org/abs/2111.14255

Permanent Link

http://hdl.handle.net/11603/23954

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection

Author/Creator

Author/Creator ORCID

https://orcid.org/0000-0001-7749-0640

Date

2021-11-28

Type of Work

conference papers and proceedings
preprints
Text

Department

Program

Citation of Original Publication

Rights

This item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Attribution 4.0 International (CC BY 4.0)

Subjects

Abstract

With the fast development of deep neural networks (DNNs), many real-world applications are adopting multiple models to conduct compound tasks, such as co-running classification, detection, and segmentation models on autonomous vehicles. Such multi-tenant DNN inference cases greatly exacerbate the computational complexity and call for comprehensive collaboration for graph-level operator scheduling, runtime-level resource awareness, as well as hardware scheduler support. However, the current scheduling support for such multi-tenant inference is still relatively backward. In this work, we propose a resource-aware scheduling framework for efficient multi-tenant DNN inference on GPU, which automatically coordinates DNN computing in different execution levels. Leveraging the unified scheduling intermediate representation and the automated MLbased searching algorithm, optimal schedules could be generated to wisely adjust model concurrency and interleave DNN model operators, maintaining a continuously balanced resource utilization across the entire inference process, and eventually improving the runtime efficiency. Experiments show that we could consistently achieve 1.3×1.7× speed-up, comparing to regular DNN runtime libraries (e.g., CuDNN, TVM) and particular concurrent scheduling methods (e.g., NVIDIA Multi-Stream).