咨询与建议

限定检索结果

文献类型

  • 4 篇 会议

馆藏范围

  • 4 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 4 篇 工学
    • 4 篇 计算机科学与技术...
    • 3 篇 电气工程
    • 1 篇 信息与通信工程
    • 1 篇 控制科学与工程
    • 1 篇 软件工程
    • 1 篇 网络空间安全
  • 1 篇 理学
    • 1 篇 数学
  • 1 篇 管理学
    • 1 篇 图书情报与档案管...

主题

  • 4 篇 multi-gpu progra...
  • 2 篇 numa
  • 1 篇 memory access pa...
  • 1 篇 amd mi250x gpu
  • 1 篇 amd mi250x memor...

机构

  • 2 篇 univ politecn ca...
  • 2 篇 nvidia corp sant...
  • 2 篇 barcelona superc...
  • 1 篇 kth royal instit...
  • 1 篇 jülich supercomp...
  • 1 篇 univ illinois il...
  • 1 篇 univ illinois ur...
  • 1 篇 hebrew univ jeru...

作者

  • 2 篇 navarro nacho
  • 2 篇 cabezas javier
  • 2 篇 vilanova lluis
  • 2 篇 jablin thomas b.
  • 2 篇 gelado isaac
  • 1 篇 herten andreas
  • 1 篇 hwu wen-mei w.
  • 1 篇 ben-nun tal
  • 1 篇 hwu wen-mei
  • 1 篇 faj jennifer
  • 1 篇 markidis stefano
  • 1 篇 peng ivy
  • 1 篇 rubin eri
  • 1 篇 shi ruimin
  • 1 篇 levy ely
  • 1 篇 schieffer gabin
  • 1 篇 barak amnon

语言

  • 3 篇 英文
  • 1 篇 其他
检索条件"主题词=Multi-GPU programming"
4 条 记 录,以下是1-10 订阅
排序:
Understanding Data Movement in AMD multi-gpu Systems with Infinity Fabric
Understanding Data Movement in AMD Multi-GPU Systems with In...
收藏 引用
2024 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, SC Workshops 2024
作者: Schieffer, Gabin Shi, Ruimin Markidis, Stefano Herten, Andreas Faj, Jennifer Peng, Ivy KTH Royal Institute of Technology Stockholm Sweden Jülich Supercomputing Centre Jülich Germany
Modern gpu systems are constantly evolving to meet the needs of computing-intensive applications in scientific and machine learning domains. However, there is typically a gap between the hardware capacity and the achi... 详细信息
来源: 评论
Memory Access Patterns: The Missing Piece of the multi-gpu Puzzle  15
Memory Access Patterns: The Missing Piece of the Multi-GPU P...
收藏 引用
International Conference for High Performance Computing, Networking, Storage and Analysis (SC)
作者: Ben-Nun, Tal Levy, Ely Barak, Amnon Rubin, Eri Hebrew Univ Jerusalem Dept Comp Sci IL-91905 Jerusalem Israel
With the increased popularity of multi-gpu nodes in modern HPC clusters, it is imperative to develop matching programming paradigms for their efficient utilization. In order to take advantage of the local gpus and the... 详细信息
来源: 评论
Automatic Parallelization of Kernels in Shared-Memory multi-gpu Nodes  15
Automatic Parallelization of Kernels in Shared-Memory Multi-...
收藏 引用
29th ACM International Conference on Supercomputing (ICS)
作者: Cabezas, Javier Vilanova, Lluis Gelado, Isaac Jablin, Thomas B. Navarro, Nacho Hwu, Wen-mei W. Barcelona Supercomp Ctr Barcelona Spain NVIDIA Corp Santa Clara CA USA Univ Illinois Urbana IL USA Univ Politecn Cataluna Barcelona Spain
In this paper we present AMGE, a programming framework and runtime system that transparently decomposes gpu kernels and executes them on multiple gpus in parallel. AMGE exploits the remote memory access capability in ... 详细信息
来源: 评论
Automatic Execution of Single-gpu Computations across multiple gpus  14
Automatic Execution of Single-GPU Computations across Multip...
收藏 引用
23rd International Conference on Parallel Architectures and Compilation Techniques (PACT)
作者: Cabezas, Javier Vilanova, Lluis Gelado, Isaac Jablin, Thomas B. Navarro, Nacho Hwu, Wen-mei Barcelona Supercomp Ctr Barcelona Spain NVIDIA Corp Santa Clara CA USA Univ Illinois Chicago IL 60680 USA Univ Politecn Cataluna Barcelona Spain
We present AMGE, a programming framework and runtime system to decompose data and gpu kernels and execute them on multiple gpus concurrently. AMGE exploits the remote memory access capability of recent gpus to guarant... 详细信息
来源: 评论