Optimizing DNNs With Partially Equivalent Transformations and Automated Corrections-Reference-Cited by-同舟云学术

Optimizing DNNs With Partially Equivalent Transformations and Automated Corrections

Published:2023-12 Issue:12 Volume:72 Page:3546-3560
ISSN:0018-9340
Container-title:IEEE Transactions on Computers
language:
Short-container-title:IEEE Trans. Comput.

Author:

Wang Haojie¹^ORCID,Zhai Jidong¹^ORCID,Gao Mingyu²^ORCID,Zhang Feng³^ORCID,Wang Tuowei¹^ORCID,Ma Zixuan¹^ORCID,Tang Shizhi¹^ORCID,Zheng Liyan¹^ORCID,Wang Wen⁴^ORCID,Rong Kaiyuan¹^ORCID,Chen Yuanyong¹^ORCID,Jia Zhihao⁵

Affiliation:

1. Department of Computer Science and Technology, Tsinghua University, Beijing, China

2. Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China

3. Key Laboratory of Data Engineering and Knowledge Engineering (MOE), School of Information, Renmin University of China, Beijing, China

4. Department of AI Computing, Peng Cheng Laboratory, Shenzhen, China

5. Department of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA

Funder

National Key R&D Program of China

NSFC for Distinguished Young Scholar

National Natural Science Foundation of China

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Computational Theory and Mathematics,Hardware and Architecture,Theoretical Computer Science,Software

Link

http://xplorestaging.ieee.org/ielx7/12/10311055/10233187.pdf?arnumber=10233187

Reference35 articles.

1. TensorFlow graph transform tool,0

2. An Efficient Parallel Secure Machine Learning Framework on GPUs

3. Ansor: Generating high-performance tensor programs for deep learning;zheng;Proc 14th USENIX Symp Oper Syst Des Implementation (OSDI),0

4. Optimizing Memory Efficiency for Deep Convolutional Neural Networks on GPUs

5. Learning to optimize tensor programs;chen;Proc Adv Neural Inf Process Syst 31,0