Optimus: towards optimal layer-fusion on deep learning processors

Author:

Cai Xuyi1ORCID,Wang Ying2,Zhang Lei2

Affiliation:

1. Institute of Computing Technology at Chinese Academy of Sciences, China / University of Chinese Academy of Sciences, China

2. Institute of Computing Technology at Chinese Academy of Sciences, China

Publisher

ACM

Cited by 8 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. Fusing Depthwise and Pointwise Convolutions for Efficient Inference on GPUs;The 53rd International Conference on Parallel Processing Workshops;2024-08-12

2. Discovering Efficient Fused Layer Configurations for Executing Multi-Workloads on Multi-Core NPUs;2024 Design, Automation & Test in Europe Conference & Exhibition (DATE);2024-03-25

3. Memory Bandwidth Efficient Design for Super-Resolution Accelerators With Structure Adaptive Fusion and Channel-Aware Addressing;IEEE Transactions on Very Large Scale Integration (VLSI) Systems;2023-06

4. Pin or Fuse? Exploiting Scratchpad Memory to Reduce Off-Chip Data Transfer in DNN Accelerators;Proceedings of the 21st ACM/IEEE International Symposium on Code Generation and Optimization;2023-02-17

5. Occam: Optimal Data Reuse for Convolutional Neural Networks;ACM Transactions on Architecture and Code Optimization;2022-12-16

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

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3