HAOTuner: A Hardware Adaptive Operator Auto-Tuner for Dynamic Shape Tensor Compilers-Reference-Cited by-同舟云学术

HAOTuner: A Hardware Adaptive Operator Auto-Tuner for Dynamic Shape Tensor Compilers

Published:2023-11 Issue:11 Volume:72 Page:3178-3190
ISSN:0018-9340
Container-title:IEEE Transactions on Computers
language:
Short-container-title:IEEE Trans. Comput.

Author:

Mu Pengyu¹^ORCID,Liu Yi²^ORCID,Wang Rui¹^ORCID,Liu Guoxiang²^ORCID,Sun Zhonghao²,Yang Hailong²^ORCID,Luan Zhongzhi²,Qian Depei²^ORCID

Affiliation:

1. Hangzhou Innovation Institute, Beihang University, Hangzhou, China

2. School of Computer Science and Engineering, Beihang University, Beijing, China

Funder

National Key R&D Program of China

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/ielx7/12/10274758/10160123.pdf?arnumber=10160123

Reference32 articles.

1. Packing: Towards 2x NLP BERT acceleration;kosec,2021

2. BERT: Pre-training of deep bidirectional transformers for language understanding;devlin;Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol,2019

3. OpenBLAS: An optimized BLAS library,2021

4. DietCode: Automatic optimization for dynamic tensor programs;zheng;Proc Mach Learn Syst,2022

5. Chameleon: Adaptive code optimization for expedited deep neural network compilation;ahn;Proc 8th Int Conf Learn Representations,2020

Cited by 1 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. Cross-Feature Transfer Learning for Efficient Tensor Program Generation;Applied Sciences;2024-01-06