High-Performance 3D convolution on the Latest Generation Sunway Processor-Reference-Cited by-同舟云学术

High-Performance 3D convolution on the Latest Generation Sunway Processor

Published:2024-08-12 Issue: Volume: Page:241-251
ISSN:
Container-title:Proceedings of the 53rd International Conference on Parallel Processing
language:
Short-container-title:

Author:

Li Jialin¹^ORCID,Feng Zhichen¹^ORCID,Gao Yaqian¹^ORCID,Tian Shaobo¹^ORCID,Zhang Haoyuan²^ORCID,Ye Huang³^ORCID,Zhang Jian³^ORCID

Affiliation:

1. Computer Network Information Center, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, China

2. Computer Network Information Center, Chinese Academy of Sciences, China and University of Chinese Academy of Sciences, Beijing, China, China

3. Computer Network Information Center, Chinese Academy of Sciences, China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3673038.3673093

Reference32 articles.

1. Andrew Anderson, Aravind Vasudevan, Cormac Keane, and David Gregg. 2017. Low-memory gemm-based convolution algorithms for deep neural networks. arXiv preprint arXiv:1709.03395 (2017).

2. Increasing the Efficiency of Massively Parallel Sparse Matrix-Matrix Multiplication in First-Principles Calculation on the New-Generation Sunway Supercomputer

3. Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cudnn: Efficient primitives for deep learning. arXiv preprint arXiv:1410.0759 (2014).

4. A set of level 3 basic linear algebra subprograms

5. Jiarui Fang, Haohuan Fu, Wenlai Zhao, Bingwei Chen, Weijie Zheng, and Guangwen Yang. 2017. swdnn: A library for accelerating deep learning applications on sunway taihulight. In 2017 IEEE international parallel and distributed processing symposium (IPDPS). IEEE, 615–624.