Im2col-Winograd: An Efficient and Flexible Fused-Winograd Convolution for NHWC Format on GPUs-Reference-Cited by-同舟云学术

登录注册会员服务联系我们

Im2col-Winograd: An Efficient and Flexible Fused-Winograd Convolution for NHWC Format on GPUs

Published:2024-08-12 Issue: Volume: Page:1072-1081
ISSN:
Container-title:Proceedings of the 53rd International Conference on Parallel Processing
language:
Short-container-title:

Author:

Zhang Zhiyi¹^ORCID,Zhang Pengfei²^ORCID,Xu Zhuopin²^ORCID,Yan Bingjie³^ORCID,Wang Qi²^ORCID

Affiliation:

1. University of Science and Technology of China, China and Hefei Institutes of Physical Science, Chinese Academy of Sciences, China

2. Hefei Institutes of Physical Science, Chinese Academy of Sciences, China

3. Institute of Computing Technology, Chinese Academy of Sciences, China

Funder

Natural Science Foundation of China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3673038.3673039

Reference34 articles.

1. OpenCNN: A Winograd Minimal Filtering Algorithm Implementation in CUDA

2. Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, and Evan Shelhamer. 2014. cuDNN: Efficient Primitives for Deep Learning. CoRR abs/1410.0759, 2014 (2014).

3. SA Cook. 1966. On the minimum computation time for multiplication. Harvard University.

4. ImageNet: A large-scale hierarchical image database

5. Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep Learning. MIT Press, USA. http://www.deeplearningbook.org

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线，采集、加工和组织学术论文而形成的新型学术文献查询和分析系统，可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容，当前同舟云学术共收录了国内外主流学术期刊6万余种，收集的期刊论文及会议论文总量共计约1.5亿篇，并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询！咨询电话：010-8811{复制后删除}0370

www.globalauthorid.com

TOP