DVABatch: Diversity-aware Multi-Entry Multi-Exit Batching for Efficient Processing of DNN Services on GPUs


Weihao Cui, Han Zhao, Quan Chen, Hao Wei, and Zirui Li, Shanghai Jiao Tong University; Deze Zeng, China University of Geosciences; Chao Li and Minyi Guo, Shanghai Jiao Tong University


The DNN inferences are often batched for better utilizing the hardware in existing DNN serving systems. However, DNN serving exhibits diversity in many aspects, such as input, operator, and load. The unawareness of these diversities results in inefficient processing. Our investigation shows that the inefficiency roots in the feature of existing batching mechanism: one entry and one exit. Therefore, we propose DVABatch, a runtime batching system that enables the multi-entry multi-exit batching scheme for existing DNN serving system. We first abstract three meta operations for adjusting the ongoing batch of queries to achieve the multi-entry multi-exit scheme. The meta operations could be used to form different scheduling logics for different diversities. To deliver the meta operations to an ongoing batch, we slice the DNN models into multiple stages. Each stage corresponds to one executor, which is managed by a state transition diagram. Compared with state-of-the-art solutions, our experimental results show that DVABatch reduces 46.4% average latency and achieves up to 2.12× throughput improvement.

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

@inproceedings {280682,
author = {Weihao Cui and Han Zhao and Quan Chen and Hao Wei and Zirui Li and Deze Zeng and Chao Li and Minyi Guo},
title = {{DVABatch}: Diversity-aware {Multi-Entry} {Multi-Exit} Batching for Efficient Processing of {DNN} Services on {GPUs}},
booktitle = {2022 USENIX Annual Technical Conference (USENIX ATC 22)},
year = {2022},
isbn = {978-1-939133-29-10},
address = {Carlsbad, CA},
pages = {183--198},
url = {https://www.usenix.org/conference/atc22/presentation/cui},
publisher = {USENIX Association},
month = jul

Presentation Video