Collaborative Research: PPoSS: LARGE: Cross-layer Coordination and Optimization for Scalable and Sparse Tensor Networks (CROSS)

合作研究:PPoSS:LARGE:可扩展和稀疏张量网络的跨层协调和优化(CROSS)

基本信息

  • 批准号:
    2316203
  • 负责人:
  • 金额:
    $ 99.7万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2023
  • 资助国家:
    美国
  • 起止时间:
    2023-09-15 至 2028-08-31
  • 项目状态:
    未结题

项目摘要

High-dimensional data computation and analytics are gaining importance in various domains, such as quantum chemistry/physics, quantum circuit simulation, social networks, healthcare, and machine/deep learning. Tensors, a representation of high-dimensional data, have become increasingly crucial. While extensive research has focused on tensor methods like decompositions and factorizations for low-dimensional data, there is a notable lack of development in tensor networks that cater to high-dimensional data (over ten dimensions) and can extract physically meaningful latent variables. The challenges arise from their complicated mathematical nature, extremely high computational complexity, and domain-specific difficulties. This project aims to bridge this critical gap by devising efficient tensor networks, especially for sparse data, which are prevalent in many real-world applications. The impacts of the project encompass four aspects: 1) Improving data compression, computation, memory usage, and interpretability of tensor networks; 2) fostering enduring and collaborative partnerships among academia, national research labs, and industry with a shared focus on the aforementioned applications; and 3) broadening education avenues by designing relevant new courses, training undergraduate and graduate students, organizing workshops, and enhancing K-12 outreach. This project delves into Cross-layer cooRdination and Optimization for Scalable and Sparse Tensor Networks (CROSS) designed for heterogeneous systems equipped with diverse accelerators like Graphics Processing Units (GPUs), Tensor Processing Units (TPUs) and Field Programmable Gate Arrays (FPGAs), and various memories such as dynamic and non-volatile random-access memories. This research aims to study sparsity within widely used tensor networks by incorporating constraints, regularization, dictionary, and domain knowledge. In addition to sparsity challenges, sparse tensor networks also face problems such as dimensionality, exacerbated data randomness and irregular program and memory access behaviors. This research tackles these challenges from four dimensions: (1) memory heterogeneity-aware representations and data (re-)arrangement, (2) balanced sparse tensor contraction algorithms with smart page arrangement, (3) memoization and intelligent allocation to reduce computational cost, and (4) specialized accelerator architectures for sparse tensor networks. The optimized sparse tensor networks represent a synergistic effort combining expertise from high-performance computing, algorithms, compilers, computer architecture and performance modeling. The proposed solutions are evaluated under diverse application scenarios and across a wide range of hardware environments to demonstrate their effectiveness and applicability in real-world settings.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
高维数据计算和分析在各种领域都变得重要,例如量子化学/物理,量子电路模拟,社交网络,医疗保健以及机器/深度学习。张量是高维数据的表示,越来越重要。尽管广泛的研究集中在张量方法上,例如分解和低维数据的因素化,但在张量网络中显着缺乏迎合高维数据(超过十个维度)的发展,并且可以提取物理意义的潜在变量。挑战是由于它们复杂的数学性质,极高的计算复杂性和特定领域的困难。该项目旨在通过设计有效的张量网络来弥合这一关键差距,尤其是对于稀疏数据,这些数据在许多现实世界中都普遍存在。项目的影响包括四个方面:1)改善张量网络的数据压缩,计算,内存使用和可解释性; 2)在学术界,国家研究实验室和行业之间建立持久和协作伙伴关系,共同关注上述应用程序; 3)通过设计相关的新课程,培训本科生和研究生,组织研讨会并增强K-12外展活动来扩大教育途径。该项目深入研究了跨层协调和优化,用于可扩展和稀疏的张量网络(Cross),专为配备有多种加速器的异质系统设计,例如图形处理单元(GPU)(GPU),张量处理单元(TPU)(TPU)和现场可编程的门阵列和可动态的录音,以及各种记忆,以及各种记忆。这项研究旨在通过结合约束,正则化,字典和域知识来研究广泛使用的张量网络中的稀疏性。除了稀疏挑战外,稀疏张量网络还面临诸如维度,加剧数据随机性以及不规则的程序和内存访问行为等问题。这项研究从四个方面解决了这些挑战:(1)内存异质性意识到的表示和数据(重新)安排,(2)具有智能页面布置的均衡稀疏稀疏张量收缩算法,(3)记忆和智能分配,以减少计算成本,以及(4)专用Accelerator Archator Archator ArchiteTures For Sparse Tensor网络网络的特殊Accelator ArchiteTures。优化的稀疏张量网络代表了一项协同努力,结合了高性能计算,算法,编译器,计算机体系结构和性能建模的专业知识。在各种应用程序方面和广泛的硬件环境中对所提出的解决方案进行了评估,以证明其在现实环境中的有效性和适用性。该奖项反映了NSF的法定任务,并被认为是通过基金会的知识分子优点和更广泛的审查标准通过评估来评估的。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Lizhong Chen其他文献

Combined liver and kidney transplantation in Guangzhou, China.
中国广州进行肝肾联合移植。
Kidney transplantation from living related donors aged more than 60 years: a single center experience
60 岁以上活体亲属捐献者的肾移植:单中心经验
  • DOI:
  • 发表时间:
    2013
  • 期刊:
  • 影响因子:
    3
  • 作者:
    Yifu Li;Jun Li;Q. Fu;Lizhong Chen;J. Fei;S. Deng;J. Qiu;Guodong Chen;Gang Huang;Changxi Wang
  • 通讯作者:
    Changxi Wang
Maximizing the performance of NoC-based MPSoCs under total power and power density constraints
在总功率和功率密度限制下最大限度地提高基于 NoC 的 MPSoC 的性能
On Trade-off Between Static and Dynamic Power Consumption in NoC Power Gating
NoC功率门控中静态与动态功耗的权衡
Clinical and Pathologic Feature of Patients With Early Versus Late Active Antibody-Mediated Rejection After Kidney Transplantation: A Single-Center Experience
肾移植后早期与晚期活性抗体介导的排斥反应患者的临床和病理特征:单中心经验
  • DOI:
  • 发表时间:
    2021
  • 期刊:
  • 影响因子:
    0.9
  • 作者:
    Zixuan Wu;Longhui Qiu;Chang Wang;Xiaomian Liu;Qihao Li;Shuangjin Yu;Yuan Yue;Jie Li;Wutao Chen;Jiajian Lai;Lizhong Chen;Changxi Wang;Guodong Chen
  • 通讯作者:
    Guodong Chen

Lizhong Chen的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Lizhong Chen', 18)}}的其他基金

Collaborative Research: PPoSS: Planning: Cross-layer Coordination and Optimization for Scalable and Sparse Tensor Networks (CROSS)
合作研究:PPoSS:规划:可扩展和稀疏张量网络的跨层协调和优化(CROSS)
  • 批准号:
    2217028
  • 财政年份:
    2022
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Standard Grant
Collaborative Research: SHF: Small: Architecture Innovations for Enabling Simultaneous Translation at the Edge
合作研究:SHF:小型:支持边缘同步翻译的架构创新
  • 批准号:
    2223483
  • 财政年份:
    2022
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Standard Grant
CAREER: Advancing On-chip Network Architecture for GPUs
职业:推进 GPU 片上网络架构
  • 批准号:
    1750047
  • 财政年份:
    2018
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Continuing Grant
SHF: Small: Collaborative Research: Design of Many-core NoCs for the Dark Silicon Era
SHF:小型:协作研究:暗硅时代的多核 NoC 设计
  • 批准号:
    1619456
  • 财政年份:
    2016
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Standard Grant
CRII: SHF: Investigation of Effective On-chip Network Designs for GPUs
CRII:SHF:有效的 GPU 片上网络设计研究
  • 批准号:
    1566637
  • 财政年份:
    2016
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Standard Grant

相似国自然基金

钛基骨植入物表面电沉积镁氢涂层及其促成骨性能研究
  • 批准号:
    52371195
  • 批准年份:
    2023
  • 资助金额:
    50 万元
  • 项目类别:
    面上项目
CLMP介导Connexin45-β-catenin复合体对先天性短肠综合征的致病机制研究
  • 批准号:
    82370525
  • 批准年份:
    2023
  • 资助金额:
    49 万元
  • 项目类别:
    面上项目
人工局域表面等离激元高灵敏传感及其系统小型化的关键技术研究
  • 批准号:
    62371132
  • 批准年份:
    2023
  • 资助金额:
    49 万元
  • 项目类别:
    面上项目
优先流对中俄原油管道沿线多年冻土水热稳定性的影响机制研究
  • 批准号:
    42301138
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目
用于稳定锌负极的界面层/电解液双向调控研究
  • 批准号:
    52302289
  • 批准年份:
    2023
  • 资助金额:
    30 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

Collaborative Research: PPoSS: Large: A Full-stack Approach to Declarative Analytics at Scale
协作研究:PPoSS:大型:大规模声明性分析的全栈方法
  • 批准号:
    2316161
  • 财政年份:
    2023
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: LARGE: Research into the Use and iNtegration of Data Movement Accelerators (RUN-DMX)
协作研究:PPoSS:大型:数据移动加速器 (RUN-DMX) 的使用和集成研究
  • 批准号:
    2316176
  • 财政年份:
    2023
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: Large: A Full-stack Approach to Declarative Analytics at Scale
协作研究:PPoSS:大型:大规模声明性分析的全栈方法
  • 批准号:
    2316158
  • 财政年份:
    2023
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Continuing Grant
Collaborative Research: PPoSS: LARGE: Cross-layer Coordination and Optimization for Scalable and Sparse Tensor Networks (CROSS)
合作研究:PPoSS:LARGE:可扩展和稀疏张量网络的跨层协调和优化(CROSS)
  • 批准号:
    2316201
  • 财政年份:
    2023
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Standard Grant
Collaborative Research: PPoSS: LARGE: Research into the Use and iNtegration of Data Movement Accelerators (RUN-DMX)
协作研究:PPoSS:大型:数据移动加速器 (RUN-DMX) 的使用和集成研究
  • 批准号:
    2316177
  • 财政年份:
    2023
  • 资助金额:
    $ 99.7万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了