咨询与建议

限定检索结果

文献类型

  • 2 篇 期刊文献

馆藏范围

  • 2 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 工学
    • 2 篇 电气工程
    • 2 篇 计算机科学与技术...

主题

  • 2 篇 graph neural net...
  • 2 篇 distributed and ...
  • 1 篇 graphs
  • 1 篇 massively parall...
  • 1 篇 hardware acceler...
  • 1 篇 sparse and unstr...
  • 1 篇 sparse matrices
  • 1 篇 single instructi...
  • 1 篇 load modeling
  • 1 篇 vectors
  • 1 篇 prefetching
  • 1 篇 social networkin...
  • 1 篇 multithreading
  • 1 篇 dynamic graphs
  • 1 篇 graphics process...
  • 1 篇 training

机构

  • 1 篇 univ connecticut...
  • 1 篇 univ connecticut...
  • 1 篇 univ connecticut...

作者

  • 2 篇 khan omer
  • 1 篇 ding caiwen
  • 1 篇 gurevin deniz

语言

  • 2 篇 英文
检索条件"主题词=Distributed and scalable parallelism"
2 条 记 录,以下是1-10 订阅
排序:
A Data Prefetcher-Based 1000-Core RISC-V Processor for Efficient Processing of Graph Neural Networks
IEEE COMPUTER ARCHITECTURE LETTERS
收藏 引用
IEEE COMPUTER ARCHITECTURE LETTERS 2025年 第1期24卷 73-76页
作者: Khan, Omer Univ Connecticut Elect & Comp Engn Storrs CT 06269 USA
Graphs-based neural networks have seen tremendous adoption to perform complex predictive analytics on massive real-world graphs. The trend in hardware acceleration has identified significant challenges with harnessing... 详细信息
来源: 评论
Exploiting Intrinsic Redundancies in Dynamic Graph Neural Networks for Processing Efficiency
IEEE COMPUTER ARCHITECTURE LETTERS
收藏 引用
IEEE COMPUTER ARCHITECTURE LETTERS 2024年 第2期23卷 170-174页
作者: Gurevin, Deniz Ding, Caiwen Khan, Omer Univ Connecticut Dept Elect & Comp Engn Storrs CT 06269 USA Univ Connecticut Dept Comp Sci & Engn Storrs CT 06269 USA
Modern dynamical systems are rapidly incorporating artificial intelligence to improve the efficiency and quality of complex predictive analytics. To efficiently operate on increasingly large datasets and intrinsically... 详细信息
来源: 评论