Collaborative Research: SHF: Medium: Co-Optimizing Computation and Data Transformations for Sparse Tensors
协作研究:SHF:中:稀疏张量的协同优化计算和数据转换
基本信息
- 批准号:2107556
- 负责人:
- 金额:$ 43万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-01-01 至 2025-12-31
- 项目状态:未结题
- 来源:
- 关键词:
项目摘要
Sparse tensor computations are central to important applications including computer-assisted drug design, fraud detection, and national security. Timely execution of these applications improves user productivity and reduces the energy consumption associated with each execution. Sparse computations are characterized as having inputs where many or most values are zero. To avoid the inefficiency of storing and computing on zero-valued data, applications only store the nonzeros, with auxiliary data structures to recover their locations. As a result, sparse tensor computations exhibit unpredictable memory-access patterns that include indirection through the auxiliary data structures. Consequently, on today’s computer architectures, performance of sparse tensor computations is completely dominated by the movement of data, through the memory system and across nodes. Data movement is expensive both in terms of execution time and energy expenditure. Optimizing data movement of sparse tensor computations as high-performance architectures have become increasingly diverse — conventional parallel architectures, graphics processors used as parallel accelerators and complex memory systems — creates a performance and productivity challenge for software developers who end up writing low-level architecture-specific code for each platform. The proposed approach simultaneously optimizes how data is organized in memory, how the computation is structured to access the data in a way that reduces data movement, and how the computation and data movement make best use of features of the hardware architectures. Since the nonzero structure of the data is unknown until program execution, the approach also examines runtime information in its decisions. The resulting co-optimization strategy enables a cohesive approach for iteratively making scheduling and data representation transformation decisions for a wide range of sparse computations and incorporating runtime adaptations.This project is developing a programming framework that permits high-level specification of a sparse computation and optimizes it to reduce data movement. It composes data representations, data layouts and storage mappings, and parallel schedules for sparse computations. It employs data dependencies, runtime information, and architecture features to fully bind the final generated code. This approach is intended to enable handling sparse tensor computations with dependences such as sparse triangular solve and many other solvers for systems of linear equations, applying reorderings such as Morton ordering on sparse tensors, and late binding of sparse tensor data representations. The novel and most significant aspects of the research include: (1) composable schedule and data transformations, including data layout transformations and storage mapping; (2) inspector synthesis for runtime data transformations between data representations, layouts, and storage mappings, which are composed with external functions; (3) support for data-dependent tensor computations; and, (4) framework abstractions deployed in the MLIR/LLVM compiler.The researchers are strongly committed to broadening participation in computing and have comprehensive plans to engage the underrepresented groups.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.
稀疏张量计算是重要应用的核心,包括计算机辅助药物设计,欺诈检测和国家安全。及时执行这些应用程序可以提高用户的工作效率,并减少与每次执行相关的能耗。稀疏计算的特征在于具有许多或大多数值为零的输入。 为了避免在零值数据上存储和计算的低效率,应用程序只存储非零值数据,并使用辅助数据结构来恢复它们的位置。 因此,稀疏张量计算表现出不可预测的内存访问模式,包括通过辅助数据结构的间接访问。 因此,在当今的计算机架构上,稀疏张量计算的性能完全由数据通过存储器系统和跨节点的移动所支配。数据移动在执行时间和能量消耗方面都是昂贵的。随着高性能架构变得越来越多样化(传统的并行架构、用作并行加速器的图形处理器和复杂的内存系统),优化稀疏张量计算的数据移动对最终为每个平台编写低级别架构特定代码的软件开发人员带来了性能和生产力挑战。所提出的方法同时优化了如何在内存中组织数据,如何构造计算以减少数据移动的方式访问数据,以及计算和数据移动如何最好地利用硬件架构的功能。由于数据的非零结构在程序执行之前是未知的,因此该方法还在其决策中检查运行时信息。 由此产生的协同优化策略,使一个有凝聚力的方法,迭代地作出调度和数据表示的转换决策,为广泛的稀疏计算,并纳入运行时adaptations.This项目正在开发一个编程框架,允许高层次的规范稀疏计算和优化,以减少数据移动。 它包括数据表示、数据布局和存储映射,以及用于稀疏计算的并行调度。 它使用数据依赖关系、运行时信息和架构特性来完全绑定最终生成的代码。这种方法旨在能够处理具有依赖关系的稀疏张量计算,例如稀疏三角求解和线性方程组的许多其他求解器,对稀疏张量应用重新排序,例如Morton排序,以及稀疏张量数据表示的后期绑定。 该研究的新颖和最重要的方面包括:(1)可组合的调度和数据转换,包括数据布局转换和存储映射;(2)用于数据表示、布局和存储映射之间的运行时数据转换的检查器合成,这些转换与外部函数组合在一起;(3)支持依赖于数据的张量计算;并且,在本发明中,(4)MLIR中部署的框架抽象; LLVM编译器。研究人员坚定地致力于扩大对计算的参与,并制定了全面的计划来吸引代表性不足的群体。该奖项反映了NSF的法定使命,并通过使用基金会的智力价值和更广泛的影响审查标准。
项目成果
期刊论文数量(3)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Code Synthesis for Sparse Tensor Format Conversion and Optimization
稀疏张量格式转换和优化的代码综合
- DOI:
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Popoola, Tobi;Zhao, Tuowen;St. George, Aaron;Bhetwal, Kalyan;Strout, Michelle;Hall, Mary;Olschanowsky, Catherine
- 通讯作者:Olschanowsky, Catherine
Polyhedral Specification and Code Generation of Sparse Tensor Contraction with Co-iteration
- DOI:10.1145/3566054
- 发表时间:2022-08
- 期刊:
- 影响因子:1.6
- 作者:Tuowen Zhao;Tobi Popoola;Mary W. Hall;C. Olschanowsky;M. Strout
- 通讯作者:Tuowen Zhao;Tobi Popoola;Mary W. Hall;C. Olschanowsky;M. Strout
Runtime Composition of Iterations for Fusing Loop-carried Sparse Dependence
用于融合循环携带稀疏依赖的迭代的运行时组合
- DOI:10.1145/3581784.3607097
- 发表时间:2023
- 期刊:
- 影响因子:0
- 作者:Cheshmi, Kazem;Strout, Michelle;Mehri Dehnavi, Maryam
- 通讯作者:Mehri Dehnavi, Maryam
{{
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 }}
Mary Hall其他文献
Extreme Heterogeneity 2018 - Productive Computational Science in the Era of Extreme Heterogeneity: Report for DOE ASCR Workshop on Extreme Heterogeneity
极端异质性 2018 - 极端异质性时代的高效计算科学:DOE ASCR 极端异质性研讨会报告
- DOI:
10.2172/1473756 - 发表时间:
2018 - 期刊:
- 影响因子:64.8
- 作者:
J. Vetter;R. Brightwell;M. Gokhale;P. McCormick;Robert Ross;J. Shalf;K. Antypas;D. Donofrio;T. Humble;Catherine C. Schuman;B. V. Van Essen;Shinjae Yoo;A. Aiken;D. Bernholdt;S. Byna;K. Cameron;Frank Cappello;Barbara M. Chapman;A. Chien;Mary Hall;R. Hartman;Z. Lan;M. Lang;John D. Leidel;Sherry Li;R. Lucas;J. Mellor;Paul Peltz Jr.;T. Peterka;M. Strout;Jeremiah J. Wilke - 通讯作者:
Jeremiah J. Wilke
A TISSUE SYSTEMS PATHOLOGY TEST ENABLES RISK-ALIGNED MANAGEMENT OF PATIENTS WITH NON-DYSPLASTIC BARRETT’S ESOPHAGUS: A CASE SERIES AT AN EXPERT FOREGUT SURGERY CENTER
组织系统病理学检测能够对非发育不良巴雷特食管患者进行风险调整管理:专家前肠外科中心的病例系列
- DOI:
10.1016/j.gie.2023.04.1542 - 发表时间:
2023-06-01 - 期刊:
- 影响因子:7.500
- 作者:
Paul Wisniowski;Luke Putnam;Mary Hall;Christian Smolko;Rebecca Critchley-Thorne;John Lipham - 通讯作者:
John Lipham
Mortality in Ireland and Northern Ireland 2000–2021 and the joint modelling of Irish and Northern Irish life tables
- DOI:
10.1007/s13385-025-00420-z - 发表时间:
2025-06-02 - 期刊:
- 影响因子:1.600
- 作者:
Linda Daly;Mary Hall - 通讯作者:
Mary Hall
$\nu$SpaceSim: A Comprehensive Neutrino Simulation Package for Space-based & Suborbital Experiments
$
u$SpaceSim:用于天基的综合中微子模拟软件包
- DOI:
10.22323/1.358.0936 - 发表时间:
2019 - 期刊:
- 影响因子:0
- 作者:
J. Krizmanic;J. Krizmanic;Y. Akaike;Y. Akaike;D. Bergman;J. Eser;Sameer Patel;A. Romero;Mary Hall;F. Sarazin;T. Venters;L. Anchordoqui;Š. Mackovjak;A. Olinto;L. Wiencke;S. Wissel;A. Reustle - 通讯作者:
A. Reustle
Integrating ytopt and libEnsemble to Autotune OpenMC
将 ytopt 和 libEnsemble 集成到 Autotune OpenMC
- DOI:
10.48550/arxiv.2402.09222 - 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Xingfu Wu;John R. Tramm;Jeffrey Larson;John;Prasanna Balaprakash;B. Videau;Michael Kruse;P. Hovland;Valerie Taylor;Mary Hall - 通讯作者:
Mary Hall
Mary Hall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('Mary Hall', 18)}}的其他基金
Collaborative Research: PPoSS: Planning: Performance Scalability, Trust, and Reproducibility: A Community Roadmap to Robust Science in High-throughput Applications
协作研究:PPoSS:规划:性能可扩展性、信任和可重复性:高通量应用中稳健科学的社区路线图
- 批准号:
2028955 - 财政年份:2020
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
EAGER: BPCnet: A Broadening Participation Resource Portal
EAGER:BPCnet:扩大参与资源门户
- 批准号:
1830364 - 财政年份:2018
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
SHF: Medium: Collaborative Research: An Inspector/Executor Compilation Framework for Irregular Applications
SHF:Medium:协作研究:针对不规则应用的检查器/执行器编译框架
- 批准号:
1564074 - 财政年份:2016
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Student Travel Support for the 2011 ACM SIGPLAN PLDI Conference
2011 年 ACM SIGPLAN PLDI 会议的学生旅行支持
- 批准号:
1135751 - 财政年份:2011
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
SHF Small: A Compiler-Based Auto-Tuning Framework for Many-Core Code Generation
SHF Small:用于多核代码生成的基于编译器的自动调优框架
- 批准号:
1018881 - 财政年份:2010
- 资助金额:
$ 43万 - 项目类别:
Continuing Grant
Collaborative Research: DDDAS-SMRP: Optimizing Signal and Image Processing in a Dynamic, Data-Driven Application System
合作研究:DDDAS-SMRP:在动态、数据驱动的应用系统中优化信号和图像处理
- 批准号:
0911750 - 财政年份:2008
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
CRI: CRD: Raising the Standard of Scientific Publishing Through an Experiment Archive
CRI:CRD:通过实验档案提高科学出版标准
- 批准号:
0709430 - 财政年份:2007
- 资助金额:
$ 43万 - 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:
0615412 - 财政年份:2006
- 资助金额:
$ 43万 - 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:
0509517 - 财政年份:2005
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: DDDAS-SMRP: Optimizing Signal and Image Processing in a Dynamic, Data-Driven Application System
合作研究:DDDAS-SMRP:在动态、数据驱动的应用系统中优化信号和图像处理
- 批准号:
0540407 - 财政年份:2005
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
相似国自然基金
Research on Quantum Field Theory without a Lagrangian Description
- 批准号:24ZR1403900
- 批准年份:2024
- 资助金额:0.0 万元
- 项目类别:省市级项目
Cell Research
- 批准号:31224802
- 批准年份:2012
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research
- 批准号:31024804
- 批准年份:2010
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Cell Research (细胞研究)
- 批准号:30824808
- 批准年份:2008
- 资助金额:24.0 万元
- 项目类别:专项基金项目
Research on the Rapid Growth Mechanism of KDP Crystal
- 批准号:10774081
- 批准年份:2007
- 资助金额:45.0 万元
- 项目类别:面上项目
相似海外基金
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331302 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: LEGAS: Learning Evolving Graphs At Scale
协作研究:SHF:小型:LEGAS:大规模学习演化图
- 批准号:
2331301 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Differentiable Hardware Synthesis
合作研究:SHF:媒介:可微分硬件合成
- 批准号:
2403134 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Small: Efficient and Scalable Privacy-Preserving Neural Network Inference based on Ciphertext-Ciphertext Fully Homomorphic Encryption
合作研究:SHF:小型:基于密文-密文全同态加密的高效、可扩展的隐私保护神经网络推理
- 批准号:
2412357 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Enabling Graphics Processing Unit Performance Simulation for Large-Scale Workloads with Lightweight Simulation Methods
合作研究:SHF:中:通过轻量级仿真方法实现大规模工作负载的图形处理单元性能仿真
- 批准号:
2402804 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Tiny Chiplets for Big AI: A Reconfigurable-On-Package System
合作研究:SHF:中:用于大人工智能的微型芯片:可重新配置的封装系统
- 批准号:
2403408 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Toward Understandability and Interpretability for Neural Language Models of Source Code
合作研究:SHF:媒介:实现源代码神经语言模型的可理解性和可解释性
- 批准号:
2423813 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Enabling GPU Performance Simulation for Large-Scale Workloads with Lightweight Simulation Methods
合作研究:SHF:中:通过轻量级仿真方法实现大规模工作负载的 GPU 性能仿真
- 批准号:
2402806 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Differentiable Hardware Synthesis
合作研究:SHF:媒介:可微分硬件合成
- 批准号:
2403135 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant
Collaborative Research: SHF: Medium: Tiny Chiplets for Big AI: A Reconfigurable-On-Package System
合作研究:SHF:中:用于大人工智能的微型芯片:可重新配置的封装系统
- 批准号:
2403409 - 财政年份:2024
- 资助金额:
$ 43万 - 项目类别:
Standard Grant