Coordinated Batching and DVFS for DNN Inference on GPU Accelerators-Reference-Cited by-同舟云学术

Coordinated Batching and DVFS for DNN Inference on GPU Accelerators

Author:

Nabavinejad Seyed Morteza¹^ORCID,Reda Sherief²^ORCID,Ebrahimi Masoumeh³^ORCID

Affiliation:

1. School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran

2. School of Engineering, Brown University, Providence, RI, USA

3. KTH Royal Institute of Technology, Stockholm, Sweden

Funder

National Science Foundation

DoD ARO

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computational Theory and Mathematics,Hardware and Architecture,Signal Processing

Link

Reference58 articles.

3. Inception-v4, inception-ResNet and the impact of residual connections on learning;szegedy;Proc AAAI Conf Artif Intell,2017

4. Batch normalization: Accelerating deep network training by reducing internal covariate shift;ioffe,2015

5. Tensorflow-slim image classification model library;silberman,2016

Cited by 21 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

4. MOC: Multi-Objective Mobile CPU-GPU Co-Optimization for Power-Efficient DNN Inference;2023 IEEE/ACM International Conference on Computer Aided Design (ICCAD);2023-10-28

5. Challenges Towards VR Technology: VR Architecture Optimization;2023 13th International Conference on Dependable Systems, Services and Technologies (DESSERT);2023-10-13