Automated Methods for Runtime Performance Optimization for Sparse and Irregular Numeric Applications

稀疏和不规则数值应用程序运行时性能优化的自动化方法

基本信息

  • 批准号:
    8819374
  • 负责人:
  • 金额:
    $ 14.2万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    1989
  • 资助国家:
    美国
  • 起止时间:
    1989-08-01 至 1993-01-31
  • 项目状态:
    已结题

项目摘要

Scientific computational problems exhibit substantial data level parallelism. The PARTY run-time system is an attempt to obtain efficient parallel implementations for scientific computations, particularly those where the data dependencies are manifest only at run-time. This can preclude compiler based detection of certain types of parallelism. The automated system is structured as follows: A high level language interface is employed in which annotations are used to select an appropriate level of granularity. A directed acyclic graph representation of the program is generated on which various aggregation techniques may be employed in order to generate efficient schedules. These schedules are then mapped onto the target machine. Work clustering and scheduling heuristics are evaluated by 1) using sparse representation of regular problems with well studied multiprocessor mappings, 2) comparing scheduling and clustering methods using a varied and realistic workload of sparse matrix problems, 3) generation, analysis and modeling of synthetic workloads. The aggregation, mapping and parallel schedule execution methods and software modules developed in the context of the PARTY system are used to implement a system that schedules and executes preconditioned Kryolov space sparse iterative algorithms and explicit PDE solution methods for non uniform meshes on the Encore Multimax, the Intel iPSC and Thinking Machine's CM-II. Finally, a Fortran based interface to the PARTY system will use annotated Fortran to facilitate transparent programmer access to PARTY.
科学计算问题表现出大量的数据级并行性。PARTY运行时系统试图为科学计算获得有效的并行实现,特别是那些仅在运行时显示数据依赖关系的计算。这可以排除基于编译器对某些类型的并行性的检测。自动化系统的结构如下:采用高级语言接口,其中使用注释来选择适当的粒度级别。生成程序的有向无环图表示,在其上可以采用各种聚合技术以生成有效的调度。然后将这些计划映射到目标计算机上。对工作聚类和调度启发式算法进行了评价:1)使用正则问题的稀疏表示,充分研究了多处理器映射;2)比较调度和聚类方法,使用稀疏矩阵问题的各种实际工作负载;3)合成工作负载的生成、分析和建模。在PARTY系统背景下开发的聚合、映射和并行调度执行方法和软件模块用于实现一个系统,该系统在Encore Multimax、Intel iPSC和Thinking Machine的CM-II上调度和执行预处理Kryolov空间稀疏迭代算法和非均匀网格的显式PDE解决方法。最后,一个基于Fortran的PARTY系统接口将使用带注释的Fortran,以方便程序员透明地访问PARTY。

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 }}

Joel Saltz其他文献

Design of an Integrated Clinical Data Warehouse
  • DOI:
    10.1016/s1535-5535(04)00075-9
  • 发表时间:
    2000-06-01
  • 期刊:
  • 影响因子:
  • 作者:
    Merwyn Taylor;Joel Saltz;James H. Nichols
  • 通讯作者:
    James H. Nichols
Implementation of a parallel unstructured Euler solver on shared- and distributed-memory architectures
  • DOI:
    10.1007/bf01901613
  • 发表时间:
    1995-12-01
  • 期刊:
  • 影响因子:
    2.700
  • 作者:
    D. J. Mavriplis;Raja Das;Joel Saltz;R. E. Vermeland
  • 通讯作者:
    R. E. Vermeland
Prioritizing cases from a multi-institutional cohort for a dataset of pathologist annotations
  • DOI:
    10.1016/j.jpi.2024.100411
  • 发表时间:
    2025-01-01
  • 期刊:
  • 影响因子:
  • 作者:
    Victor Garcia;Emma Gardecki;Stephanie Jou;Xiaoxian Li;Kenneth R. Shroyer;Joel Saltz;Balazs Acs;Katherine Elfer;Jochen Lennerz;Roberto Salgado;Brandon D. Gallas
  • 通讯作者:
    Brandon D. Gallas
Desaturation events are frequent while often undocumented in electronic medical records
  • DOI:
    10.1016/j.jcrc.2012.10.057
  • 发表时间:
    2013-02-01
  • 期刊:
  • 影响因子:
  • 作者:
    Sharath Cholleti;Gabriel Najarro;Joel Saltz;Timothy Buchman
  • 通讯作者:
    Timothy Buchman
Publisher Correction to: Deep learning-based image analysis methods for brightfield-acquired multiplex immunohistochemistry images
  • DOI:
    10.1186/s13000-020-01021-y
  • 发表时间:
    2020-09-24
  • 期刊:
  • 影响因子:
    2.300
  • 作者:
    Danielle J. Fassler;Shahira Abousamra;Rajarsi Gupta;Chao Chen;Maozheng Zhao;David Paredes;Syeda Areeha Batool;Beatrice S. Knudsen;Luisa Escobar-Hoyos;Kenneth R. Shroyer;Dimitris Samaras;Tahsin Kurc;Joel Saltz
  • 通讯作者:
    Joel Saltz

Joel Saltz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('Joel Saltz', 18)}}的其他基金

CSR---AES: Collaborative Research: Intelligent Optimization of Parallel and Distributed Applications (WP2)
CSR---AES:协作研究:并行和分布式应用的智能优化(WP2)
  • 批准号:
    0917775
  • 财政年份:
    2008
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Continuing Grant
Tightly-coupled Heterogeneous Supercomputing
紧耦合异构超级计算
  • 批准号:
    0703139
  • 财政年份:
    2007
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Standard Grant
CSR---AES: Collaborative Research: Intelligent Optimization of Parallel and Distributed Applications (WP2)
CSR---AES:协作研究:并行和分布式应用的智能优化(WP2)
  • 批准号:
    0615155
  • 财政年份:
    2006
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Continuing Grant
CSR---AES: Collaborative Research: Intelligent Design and Optimization of Parallel and Distributed Applications
CSR---AES:协作研究:并行和分布式应用的智能设计和优化
  • 批准号:
    0509326
  • 财政年份:
    2005
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Standard Grant
ITR: Collaborative Research (ASE+EVS)-(dmc+sim): Data Driven Simulation of the Subsurface: Optimization and Uncertainty Estimation
ITR:协作研究 (ASE EVS)-(dmc sim):数据驱动的地下模拟:优化和不确定性估计
  • 批准号:
    0426241
  • 财政年份:
    2004
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Standard Grant
GridDB-Lite: Database Support for Data-Driven Scientific Applications in the Grid
GridDB-Lite:网格中数据驱动科学应用程序的数据库支持
  • 批准号:
    0330612
  • 财政年份:
    2003
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Standard Grant
International Workshop on Dynamic Data Driven Application Systems as a Mechanism to Foster International Collaboration, Melbourne, Australia
动态数据驱动应用系统作为促进国际合作机制的国际研讨会,澳大利亚墨尔本
  • 批准号:
    0332988
  • 财政年份:
    2003
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Standard Grant
Collaborative Research: ITR/AP&IM "A Data Intense Challenge: The Instrumented Oilfield of the Future"
合作研究:ITR/AP
  • 批准号:
    0121177
  • 财政年份:
    2001
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Continuing Grant

相似国自然基金

Computational Methods for Analyzing Toponome Data
  • 批准号:
    60601030
  • 批准年份:
    2006
  • 资助金额:
    17.0 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

Impact of Urban Environmental Factors on Momentary Subjective Wellbeing (SWB) using Smartphone-Based Experience Sampling Methods
使用基于智能手机的体验采样方法研究城市环境因素对瞬时主观幸福感 (SWB) 的影响
  • 批准号:
    2750689
  • 财政年份:
    2025
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Studentship
Developing behavioural methods to assess pain in horses
开发评估马疼痛的行为方法
  • 批准号:
    2686844
  • 财政年份:
    2025
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Studentship
CAREER: Nonlinear Dynamics of Exciton-Polarons in Two-Dimensional Metal Halides Probed by Quantum-Optical Methods
职业:通过量子光学方法探测二维金属卤化物中激子极化子的非线性动力学
  • 批准号:
    2338663
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Continuing Grant
REU Site: Computational Methods with applications in Materials Science
REU 网站:计算方法及其在材料科学中的应用
  • 批准号:
    2348712
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Standard Grant
CAREER: New methods in curve counting
职业:曲线计数的新方法
  • 批准号:
    2422291
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Continuing Grant
Conference: North American High Order Methods Con (NAHOMCon)
会议:北美高阶方法大会 (NAHOMCon)
  • 批准号:
    2333724
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Standard Grant
Population genomic methods for modelling bacterial pathogen evolution
用于模拟细菌病原体进化的群体基因组方法
  • 批准号:
    DE240100316
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Discovery Early Career Researcher Award
Spectral embedding methods and subsequent inference tasks on dynamic multiplex graphs
动态多路复用图上的谱嵌入方法和后续推理任务
  • 批准号:
    EP/Y002113/1
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Research Grant
Non invasive methods to accelerate the development of injectable therapeutic depots
非侵入性方法加速注射治疗储库的开发
  • 批准号:
    EP/Z532976/1
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Research Grant
Development and Translation Mass Spectrometry Methods to Determine BioMarkers for Parkinson's Disease and Comorbidities
确定帕金森病和合并症生物标志物的质谱方法的开发和转化
  • 批准号:
    2907463
  • 财政年份:
    2024
  • 资助金额:
    $ 14.2万
  • 项目类别:
    Studentship
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了