Enable simultaneous DNN services based on deterministic operator overlap and precise latency prediction-Reference-Cited by-同舟云学术

Enable simultaneous DNN services based on deterministic operator overlap and precise latency prediction

Published:2021-11-13 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis
language:
Short-container-title:

Author:

Cui Weihao¹,Zhao Han¹,Chen Quan¹,Zheng Ningxin²,Leng Jingwen¹,Zhao Jieru¹,Song Zhuo³,Ma Tao³,Yang Yong³,Li Chao¹,Guo Minyi¹

Affiliation:

1. Shanghai Jiao Tong University

2. Microsoft Research Asia

3. Alibaba Cloud

Funder

National Natural Science Foundation of China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3458817.3476143

Reference60 articles.

1. 2021. cgroups. https://www.kernel.org/doc/Documentation/cgroup-v2.txt. 2021. cgroups. https://www.kernel.org/doc/Documentation/cgroup-v2.txt.

2. 2021. memcached. https://memcached.org. 2021. memcached. https://memcached.org.

3. Zhihao Bai Zhen Zhang Yibo Zhu and Xin Jin. 2020. PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications. In OSDI. 499--514. Zhihao Bai Zhen Zhang Yibo Zhu and Xin Jin. 2020. PipeSwitch: Fast Pipelined Context Switching for Deep Learning Applications. In OSDI. 499--514.

4. LIBSVM

Cited by 38 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. InSS: An Intelligent Scheduling Orchestrator for Multi-GPU Inference With Spatio-Temporal Sharing;IEEE Transactions on Parallel and Distributed Systems;2024-10

2. ESEN: Efficient GPU sharing of Ensemble Neural Networks;Neurocomputing;2024-09

3. BCEdge: SLO-Aware DNN Inference Services With Adaptive Batch-Concurrent Scheduling on Edge Devices;IEEE Transactions on Network and Service Management;2024-08

4. Accelerated Neural Enhancement for Video Analytics With Video Quality Adaptation;IEEE/ACM Transactions on Networking;2024-08

5. ElasticRoom: Multi-Tenant DNN Inference Engine via Co-design with Resource-constrained Compilation and Strong Priority Scheduling;Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing;2024-06-03