咨询与建议

限定检索结果

文献类型

  • 1 篇 会议

馆藏范围

  • 1 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 1 篇 工学
    • 1 篇 计算机科学与技术...

主题

  • 1 篇 scalability
  • 1 篇 libraries
  • 1 篇 protocol control...
  • 1 篇 accelerators
  • 1 篇 high-performance
  • 1 篇 hpl linpack dgem...
  • 1 篇 flexible
  • 1 篇 high performance...
  • 1 篇 task performance
  • 1 篇 basic linear alg...
  • 1 篇 matrix multiplic...

机构

  • 1 篇 frankfurt inst a...

作者

  • 1 篇 rohr david
  • 1 篇 lindenstruth vol...

语言

  • 1 篇 英文
检索条件"主题词=HPL Linpack DGEMM OpenCL CUDA BLAS GPU multi-GPU DMA"
1 条 记 录,以下是1-10 订阅
排序:
A flexible and portable large-scale dgemm library for linpack on next-generation multi-gpu systems  23
A flexible and portable large-scale DGEMM library for Linpac...
收藏 引用
23rd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing (PDP)
作者: Rohr, David Lindenstruth, Volker Frankfurt Inst Adv Studies Ruth Moufang Str 1 Frankfurt Germany
In recent years, high performance computing has benefitted greatly from special accelerator cards such as gpus. Matrix multiplication performed by the blas function dgemm is one of the prime examples where such accele... 详细信息
来源: 评论