咨询与建议

限定检索结果

文献类型

  • 4 篇 期刊文献
  • 2 篇 会议

馆藏范围

  • 6 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 6 篇 工学
    • 3 篇 计算机科学与技术...
    • 1 篇 电气工程
    • 1 篇 电子科学与技术(可...
    • 1 篇 控制科学与工程
    • 1 篇 土木工程
    • 1 篇 石油与天然气工程
    • 1 篇 农业工程
    • 1 篇 城乡规划学
    • 1 篇 软件工程
  • 1 篇 理学
    • 1 篇 物理学
  • 1 篇 管理学
    • 1 篇 管理科学与工程(可...

主题

  • 6 篇 gpu memory optim...
  • 2 篇 deep learning
  • 1 篇 graph neural net...
  • 1 篇 memory access pa...
  • 1 篇 fur rendering
  • 1 篇 cfd
  • 1 篇 gpgpu
  • 1 篇 cuda out of memo...
  • 1 篇 memory access pa...
  • 1 篇 subgraph partiti...
  • 1 篇 urban wind field
  • 1 篇 swap
  • 1 篇 natural language...
  • 1 篇 data layout opti...
  • 1 篇 cuda performance...
  • 1 篇 data tokenizatio...
  • 1 篇 machine learning
  • 1 篇 gpu computing
  • 1 篇 recomputation
  • 1 篇 dnn training

机构

  • 1 篇 north china elec...
  • 1 篇 tsinghua univ sc...
  • 1 篇 capital normal u...
  • 1 篇 childrens playgr...
  • 1 篇 univ mississippi...
  • 1 篇 china acad trans...
  • 1 篇 missouri univ sc...
  • 1 篇 minist educ engn...
  • 1 篇 mb univ fac busi...
  • 1 篇 north china elec...
  • 1 篇 acad appl tech &...
  • 1 篇 daegu univ dept ...
  • 1 篇 department of co...

作者

  • 1 篇 jang byunghyun
  • 1 篇 xia ning
  • 1 篇 dodic dejan
  • 1 篇 feng xuecong
  • 1 篇 shao xuqiang
  • 1 篇 wu zhaohui
  • 1 篇 liu zhijian
  • 1 篇 choi minsu
  • 1 篇 lin leilei
  • 1 篇 abdullah al-mamu...
  • 1 篇 lin li
  • 1 篇 wen lijie
  • 1 篇 kim kyung ki
  • 1 篇 zong zan
  • 1 篇 zhang siqi
  • 1 篇 neda seifi
  • 1 篇 yin xiaofei
  • 1 篇 regodic dusan

语言

  • 6 篇 英文
检索条件"主题词=GPU Memory Optimization"
6 条 记 录,以下是1-10 订阅
排序:
Tokenization and memory optimization for Reducing gpu Load in NLP Deep Learning Models
收藏 引用
TEHNICKI VJESNIK-TECHNICAL GAZETTE 2024年 第6期31卷 1995-2002页
作者: Dodic, Dejan Regodic, Dusan Acad Appl Tech & Presch Studies Dept Informat Commun Technol Beogradska 18 Nish Serbia MB Univ Fac Business & Law Dept Adv Informat Technol Teodora Drajzera 27 Belgrade Serbia
In the current landscape of advanced natural language processing (NLP), managing gpu memory effectively is crucial. This paper delves into new tokenization methods and data handling to enhance NLP model efficiency, fo... 详细信息
来源: 评论
Algorithmic GPgpu memory optimization
收藏 引用
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE 2014年 第4期14卷 391-406页
作者: Jang, Byunghyun Choi, Minsu Kim, Kyung Ki Univ Mississippi Dept Comp & Informat Sci University MS 38677 USA Missouri Univ Sci & Technol Dept Elect & Comp Engn Rolla MO USA Daegu Univ Dept Elect & Comp Engn Gyongsan South Korea
The performance of General-Purpose computation on Graphics Processing Units (GPgpu) is heavily dependent on the memory access behavior. This sensitivity is due to a combination of the underlying Massively Parallel Pro... 详细信息
来源: 评论
A Swap Dominated Tensor Re-Generation Strategy for Training Deep Learning Models  36
A Swap Dominated Tensor Re-Generation Strategy for Training ...
收藏 引用
36th IEEE International Parallel and Distributed Processing Symposium (IEEE IPDPS)
作者: Wen, Lijie Zong, Zan Lin, Li Lin, Leilei Tsinghua Univ Sch Software Beijing Peoples R China Capital Normal Univ Sch Management Beijing Peoples R China
With the growing of the depth of neural networks and the scale of data, the difficulty of network training also increases. When the gpu memory is insufficient, it is challenging to train deeper models. Recent research... 详细信息
来源: 评论
Empowering CG ProductionCost-Effective Techniques for Voluminous Fur Rendering with Unreal Engine  24
Empowering CG ProductionCost-Effective Techniques for Volumi...
收藏 引用
2024 SIGGRAPH Asia Conference-SIGGRAPH Asia
作者: Xia, Ning Yin, Xiaofei Feng, Xuecong Childrens Playground Entertainment Inc Tokyo Japan
This paper presents a novel approach to optimizing realistic fur rendering for CG animation using Unreal Engine (UE). We introduce a progressive method combining three key techniques to enhance rendering efficiency wh... 详细信息
来源: 评论
Accurate and efficient urban wind prediction at city-scale with memory-scalable graph neural network
收藏 引用
SUSTAINABLE CITIES AND SOCIETY 2023年 99卷
作者: Liu, Zhijian Zhang, Siqi Shao, Xuqiang Wu, Zhaohui North China Elect Power Univ Dept Power Engn Baoding 071003 Hebei Peoples R China North China Elect Power Univ Dept Comp Sci Baoding 071003 Hebei Peoples R China Minist Educ Engn Res Ctr Intelligent Comp Complex Energy Syst Baoding 071003 Hebei Peoples R China China Acad Transportat Sci Beijing 100029 Peoples R China
The interaction between buildings and wind significantly impacts the comfort and safety of pedestrians, thereby influencing the sustainability of cities. Computational fluid dynamics (CFD) simulation of wind velocity ... 详细信息
来源: 评论
Optimizing memory Access Efficiency in CUDA Kernel via Data Layout Technique
收藏 引用
Journal of Computer and Communications 2024年 第5期12卷 124-139页
作者: Neda Seifi Abdullah Al-Mamun Department of Computer & Cyber Sciences&#8212 SCCS Augusta University Augusta Georgia USA
Over the past decade, Graphics Processing Units (gpus) have revolutionized high-performance computing, playing pivotal roles in advancing fields like IoT, autonomous vehicles, and exascale computing. Despite these adv... 详细信息
来源: 评论