EAGER: Towards Automated Characterization of the Data-Movement Complexity of Large Scale Analytics Applications

EAGER:实现大规模分析应用程序数据移动复杂性的自动表征

基本信息

  • 批准号:
    1645599
  • 负责人:
  • 金额:
    $ 30万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Standard Grant
  • 财政年份:
    2016
  • 资助国家:
    美国
  • 起止时间:
    2016-08-15 至 2019-07-31
  • 项目状态:
    已结题

项目摘要

We have entered a new era where power/energy limitations have become fundamental drivers of technological trends. The cost in both time and energy for moving data from off-chip main memory to the processor is significantly higher than the cost of a double-precision floating-point computation. With future technologies, this ratio will only get worse. Therefore the characterization of the inherent data movement costs of algorithms is very important, and is particularly critical for large scale data-analytic applications. However, unlike the well-understood computational complexity of algorithms, the data movement complexity is known only for a small number of algorithms.Prior techniques for characterizing the data movement complexity of algorithms has either been restricted to subclasses of computations, or has required ad hoc manual reasoning. This project develops a scalable automated tool for analyzing the data movement complexity of arbitrary unstructured computations, expressed as computational directed acyclic graphs (CDAGs). The researchers explore several directions including out-of-core strategies, decomposition/recomposition of graphs, directional component analysis, and empirical function fitting, to address scalability challenges.
我们已经进入了一个新时代,电力/能源限制已成为技术趋势的基本驱动力。 将数据从片外主存储器移动到处理器的时间和能量成本明显高于双精度浮点计算的成本。 随着未来技术的发展,这一比例只会变得更糟。 因此,算法的固有数据移动成本的表征是非常重要的,并且对于大规模数据分析应用是特别关键的。 然而,与众所周知的算法的计算复杂性不同,数据移动复杂性仅对于少数算法是已知的。用于表征算法的数据移动复杂性的现有技术要么被限制于计算的子类,要么需要专门的人工推理。该项目开发了一个可扩展的自动化工具,用于分析任意非结构化计算的数据移动复杂性,表示为计算有向无环图(CDAG)。研究人员探索了几个方向,包括核心外策略,图的分解/重组,方向分量分析和经验函数拟合,以解决可扩展性挑战。

项目成果

期刊论文数量(9)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Automated derivation of parametric data movement lower bounds for affine programs
自动推导仿射程序的参数数据移动下限
Characterization of Data Movement Requirements for Sparse Matrix Computations on GPUs
GPU 上稀疏矩阵计算的数据移动要求的表征
ColdRoute: effective routing of cold questions in stack exchange sites
  • DOI:
    10.1007/s10618-018-0577-7
  • 发表时间:
    2018-06
  • 期刊:
  • 影响因子:
    4.8
  • 作者:
    Jiankai Sun-;Abhinav Vishnu;Aniket Chakrabarti;Charles Siegel;S. Parthasarathy
  • 通讯作者:
    Jiankai Sun-;Abhinav Vishnu;Aniket Chakrabarti;Charles Siegel;S. Parthasarathy
ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation
  • DOI:
    10.1609/aaai.v33i01.3301265
  • 发表时间:
    2018-11
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Jiankai Sun-;Bortik Bandyopadhyay;Armin Bashizade;Jiongqian Liang;P. Sadayappan;S. Parthasarathy
  • 通讯作者:
    Jiankai Sun-;Bortik Bandyopadhyay;Armin Bashizade;Jiongqian Liang;P. Sadayappan;S. Parthasarathy
Symmetrization for Embedding Directed Graphs
嵌入有向图的对称化
{{ 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 }}

Ponnuswamy Sadayappan其他文献

Ponnuswamy Sadayappan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('Ponnuswamy Sadayappan', 18)}}的其他基金

Collaborative Research: PPoSS: Large: A Comprehensive Framework for Efficient, Scalable, and Performance-Portable Tensor Applications
合作研究:PPoSS:大型:高效、可扩展和性能可移植的张量应用的综合框架
  • 批准号:
    2217154
  • 财政年份:
    2022
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Collaborative Research: PPoSS: Planning: Model-Driven Compiler Optimization and Algorithm-Architecture Co-Design for Scalable Machine Learning
协作研究:PPoSS:规划:用于可扩展机器学习的模型驱动编译器优化和算法架构协同设计
  • 批准号:
    2119677
  • 财政年份:
    2021
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
OAC: Small: Data Locality Optimization for Sparse Matrix/Tensor Computations
OAC:小型:稀疏矩阵/张量计算的数据局部性优化
  • 批准号:
    2009007
  • 财政年份:
    2020
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Collaborative Research: PPoSS: Planning: A Cross-Layer Observable Approach to Extreme Scale Machine Learning and Analytics
协作研究:PPoSS:规划:超大规模机器学习和分析的跨层可观察方法
  • 批准号:
    2028942
  • 财政年份:
    2020
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
CDS&E: Compiler/Runtime Support for Developing Scalable Parallel Multi-Scale Multi-Physics
CDS
  • 批准号:
    1940789
  • 财政年份:
    2019
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
SHF: Small: Tools for Productive High-performance Computing with GPUs
SHF:小型:使用 GPU 进行高效高性能计算的工具
  • 批准号:
    2018016
  • 财政年份:
    2019
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
SPX: Collaborative Research: Parallel Algorithm by Blocks - A Data-centric Compiler/runtime System for Productive Programming of Scalable Parallel Systems
SPX:协作研究:块并行算法 - 用于可扩展并行系统的高效编程的以数据为中心的编译器/运行时系统
  • 批准号:
    1946752
  • 财政年份:
    2019
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
SPX: Collaborative Research: Parallel Algorithm by Blocks - A Data-centric Compiler/runtime System for Productive Programming of Scalable Parallel Systems
SPX:协作研究:块并行算法 - 用于可扩展并行系统的高效编程的以数据为中心的编译器/运行时系统
  • 批准号:
    1919211
  • 财政年份:
    2019
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
SHF: Small: Tools for Productive High-performance Computing with GPUs
SHF:小型:使用 GPU 进行高效高性能计算的工具
  • 批准号:
    1816793
  • 财政年份:
    2018
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
XPS: FULL: Collaborative Research: PARAGRAPH: Parallel, Scalable Graph Analytics
XPS:完整:协作研究:段落:并行、可扩展图形分析
  • 批准号:
    1629548
  • 财政年份:
    2016
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant

相似海外基金

ARTES - Automated Remanufacturing Towards Environmental Sustainability
ARTES - 实现环境可持续性的自动化再制造
  • 批准号:
    10038680
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Collaborative R&D
Towards Internet of Things Enabled Automated Mushroom Cultivation
迈向物联网实现蘑菇自动化种植
  • 批准号:
    IE230100119
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Early Career Industry Fellowships
Towards automated Australian Sign Language translation
迈向自动化澳大利亚手语翻译
  • 批准号:
    DE230100049
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Discovery Early Career Researcher Award
SBIR Phase I: The Automated Forensic Economist: Towards Affordability, Transparency, and Efficiency in Forensic Economics
SBIR 第一阶段:自动化法证经济学家:实现法证经济学的可负担性、透明度和效率
  • 批准号:
    2304596
  • 财政年份:
    2023
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Towards reliable automated fact-checking in Public Health
在公共卫生领域实现可靠的自动事实核查
  • 批准号:
    2719172
  • 财政年份:
    2022
  • 资助金额:
    $ 30万
  • 项目类别:
    Studentship
CISE-MSI: DP: IIS:III: Deep Learning Based Automated Concept and Caption Generation of Medical Images Towards Developing an Effective Decision Support System (DSS)
CISE-MSI:DP:IIS:III:基于深度学习的医学图像自动概念和标题生成,以开发有效的决策支持系统 (DSS)
  • 批准号:
    2131207
  • 财政年份:
    2022
  • 资助金额:
    $ 30万
  • 项目类别:
    Standard Grant
Automated Selective Broccoli Harvesting to increase grower productivity and resillience towards net zero
自动化选择性西兰花收割可提高种植者的生产力和实现净零排放的弹性
  • 批准号:
    10028115
  • 财政年份:
    2022
  • 资助金额:
    $ 30万
  • 项目类别:
    Collaborative R&D
Towards broad-spectrum antimicrobial vaccines: uniting automated and enzymatic glycan assembly for the synthesis and bioconjugation of bacterial exopo
迈向广谱抗菌疫苗:将自动化和酶促聚糖组装结合起来,用于细菌外泌体的合成和生物共轭
  • 批准号:
    2595945
  • 财政年份:
    2021
  • 资助金额:
    $ 30万
  • 项目类别:
    Studentship
CAREER: Guiding automated synthesis of hybrid perovskites towards stability via knowledge of nanoscale ionic mechanisms
职业:通过纳米级离子机制的知识指导杂化钙钛矿的自动化合成以实现稳定性
  • 批准号:
    2043205
  • 财政年份:
    2021
  • 资助金额:
    $ 30万
  • 项目类别:
    Continuing Grant
Towards an open-source, equipment-agnostic framework for automated welfare monitoring in the home cage
建立一个开源的、与设备无关的框架,用于家庭笼子中的自动化福利监测
  • 批准号:
    NC/T002050/1
  • 财政年份:
    2020
  • 资助金额:
    $ 30万
  • 项目类别:
    Training Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了