Collaborative Research: SHF:SMALL: Compile-Parallelize-Schedule-Retarget-Repeat (EASER) Paradigm for Dealing with Extreme Heterogeneity
合作研究:SHF:SMALL:处理极端异构性的编译-并行化-调度-重定向-重复 (EASER) 范式
基本信息
- 批准号:2146852
- 负责人:
- 金额:$ 25万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Standard Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-06-15 至 2023-07-31
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Heterogeneity in computing refers to having a variety of devices present within one computing system or even within one node of a cluster. A number of technological trends are making a high degree of heterogeneity inevitable in High Performance Computing (HPC), leading to research along many directions. The traditional scheduling problem, which refers to taking a set of programs to be executed and mapping them to the available resources, becomes more complicated in the presence of such heterogeneity, as the schedulers need to interact with the compiler also. The goal of this project is to consider new paradigms for application execution in view of these developments and conduct research in developing predictions of execution times, compilation, parallelization, and scheduling. Traditionally, deciding (likely manually) how an application is to be parallelized, compilation, and cluster-level scheduling are done sequentially and independently. The investigators posit that their isolated treatment is not going to be acceptable when one tries to optimize for multi-tenant heterogeneous clusters. Instead, the investigators envision a requirement that can be referred to as EASER -- compilE-pArallelize-Schedule-rEtarget-Repeat. To elaborate on the vision, in the EASER paradigm the compiler first maps the core functions to a specific device, generating predictions of execution time that are input to the parallelization approach selection module, and together they produce a final executable. Subsequently, this binary is presented to the scheduler, which assesses the job queue and might suggest alternative configuration(s)/device(s). If so, a retargeting module is to be invoked, leading to a potential repetition of the above steps. This project develops, supports, and evaluates the EASER framework in the context of a cluster that executes emerging machine learning (ML) workloads. Research is proposed in the following areas: 1) Compiler-Driven Performance Prediction -- It includes a novel strategy that comprises a general model for predicting SIMD/VLIW performance and an operator classification based approach to developing a memory hierarchy performance model. 2) Integrated Job Scheduling and Parallelization Strategy Selection -- Building on the performance prediction models, these two (conventionally independent) modules are integrated, by including parameterized and incremental parallelization strategy selection methods and aggressively reducing the search space in scheduling methods. 3) Retargeting Compiler -- By classifying optimizations as either architecture-dependent or independent, a retargeting compiler for ML workloads will be developed. This project will also make several contributions to education and human resource development. Both investigators will be introducing course(s) (material) at the intersection of computer systems and machine learning, bringing attention to ML-related workloads in computer systems education. A majority of funds at each University will be used to support Ph.D. students in their research, who will be trained to work across traditional (sub-) areas. Both investigators are strongly committed to increasing diversity in computing fields and have a strong record of supervising members of underrepresented groups in their research programs. Building on their Universities' existing connections, they will be further working on improving diversity at all levels.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.
计算中的异质性是指在一个计算系统中甚至在集群的一个节点内具有各种设备。许多技术趋势在高性能计算(HPC)中不可避免地具有高度的异质性,从而沿着许多方向进行了研究。 传统的调度问题是指在存在此类异质性的情况下,要执行一组程序并将其映射到可用资源中,因为调度程序也需要与编译器进行交互。鉴于这些发展,该项目的目的是考虑用于应用程序执行的新范式,并在开发执行时间,汇编,并行化和调度的预测时进行研究。 传统上,(可能是手动)如何并行编译和集群级调度(可能是手动)进行的。研究人员认为,当人们试图优化多租户异质簇时,他们的孤立处理将无法接受。相反,调查人员设想了一个可以称为更宽松的要求 - 汇编 - 划分 - 安排retarget-repeat。为了详细说明视觉,在较为范式中,编译器首先将核心功能映射到特定的设备,从而生成对并行化方法选择模块输入的执行时间的预测,并共同产生最终的可执行文件。随后,将此二进制呈现给调度程序,该调度程序评估了作业队列,并可能建议替代配置(S)/设备。如果是这样,则将调用重新定位模块,从而导致上述步骤的潜在重复。 该项目在执行新兴计算机学习(ML)工作量的集群的上下文中开发,支持和评估较较高的框架。在以下领域提出了研究:1)编译器驱动的性能预测 - 它包括一种新型策略,该策略包括一个通用模型,用于预测SIMD/VLIW性能和基于操作员分类的方法,用于开发内存层次结构绩效模型。 2)集成的作业计划和并行化策略选择 - 基于绩效预测模型,通过包括参数化和增量并行化策略选择方法并积极地减少调度方法中的搜索空间,从而集成了这两个(常规独立的)模块。 3)重新定位编译器 - 通过将优化分类为体系结构依赖性或独立,将开发用于ML工作负载的重新定位编译器。 该项目还将为教育和人力资源开发做出一些贡献。两位研究人员都将在计算机系统和机器学习的交集中引入课程(S)(材料),从而引起对计算机系统教育中与ML相关的工作量的关注。每所大学的大多数资金将用于支持博士学位。他们的研究中的学生将接受培训,可以在传统(子)领域工作。两位研究人员都强烈致力于提高计算领域的多样性,并在其研究计划中拥有监督代表性不足的群体成员的记录。在大学的现有联系的基础上,他们将进一步努力改善各个级别的多样性。该奖项反映了NSF的法定任务,并被认为是值得通过基金会的知识分子优点和更广泛的影响审查标准来评估的。
项目成果
期刊论文数量(2)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
GPU Adaptive In-situ Parallel Analytics (GAP)
- DOI:10.1145/3559009.3569661
- 发表时间:2022-01-01
- 期刊:
- 影响因子:0
- 作者:Xing,Haoyuan;Agrawal,Gagan;Ramnath,Rajiv
- 通讯作者:Ramnath,Rajiv
End-to-End LU Factorization of Large Matrices on GPUs
- DOI:10.1145/3572848.3577486
- 发表时间:2023-02
- 期刊:
- 影响因子:0
- 作者:Yang Xia;Peng Jiang;G. Agrawal;R. Ramnath
- 通讯作者:Yang Xia;Peng Jiang;G. Agrawal;R. Ramnath
{{
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 }}
Gagan Agrawal其他文献
Organizing Records for Retrieval in Multi-Dimensional Range Searchable Encryption
多维范围可搜索加密中组织检索记录
- DOI:
- 发表时间:
2024 - 期刊:
- 影响因子:0
- 作者:
Mahdieh Heidaripour;Ladan Kian;Maryam Rezapour;Mark Holcomb;Benjamin Fuller;Gagan Agrawal;Hoda Maleki - 通讯作者:
Hoda Maleki
CML-062 Define the Vulnerable - Social Determinants of Health Impact on Hematological Malignancies Affecting Children, Adolescents, and Young Adults: Systematic Review and Meta-Analysis
- DOI:
10.1016/s2152-2650(23)01122-9 - 发表时间:
2023-09-01 - 期刊:
- 影响因子:
- 作者:
Muhannad Sharara;Kellen Cristine Tjioe;Marisol Miranda Galvis;Gagan Agrawal;Andrew Balas;Jorge Cortes - 通讯作者:
Jorge Cortes
MMIS-07, 08: Mining Multiple Information Sources Workshop Report
MMIS-07, 08:挖掘多信息源研讨会报告
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
朱兴全;Gagan Agrawal;Yuri Breitbart;Ruoming Jin - 通讯作者:
Ruoming Jin
<strong>POSTER:</strong> MDS-044 Cancer Disparities in Survival of Patients With Hematologic Malignancies in the Context of Social Determinants of Health: A Systematic Review
- DOI:
10.1016/s2152-2650(23)00577-3 - 发表时间:
2023-09-01 - 期刊:
- 影响因子:
- 作者:
Marisol Miranda-Galvis;Kellen Tjioe;Andrew Balas;Gagan Agrawal;Jorge Cortes - 通讯作者:
Jorge Cortes
Middleware for data mining applications on clusters and grids
- DOI:
10.1016/j.jpdc.2007.06.007 - 发表时间:
2008-01-01 - 期刊:
- 影响因子:
- 作者:
Leonid Glimcher;Ruoming Jin;Gagan Agrawal - 通讯作者:
Gagan Agrawal
Gagan Agrawal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('Gagan Agrawal', 18)}}的其他基金
Collaborative Research: CNS Core: Small: A Compilation System for Mapping Deep Learning Models to Tensorized Instructions (DELITE)
合作研究:CNS Core:Small:将深度学习模型映射到张量化指令的编译系统(DELITE)
- 批准号:
2230945 - 财政年份:2023
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
Collaborative Research: CNS Core: Small: A Compilation System for Mapping Deep Learning Models to Tensorized Instructions (DELITE)
合作研究:CNS Core:Small:将深度学习模型映射到张量化指令的编译系统(DELITE)
- 批准号:
2341378 - 财政年份:2023
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
OAC Core: SHF: SMALL: ICURE -- In-situ Analytics with Compressed or Summary Representations for Extreme-Scale Architectures
OAC 核心:SHF:SMALL:ICURE——针对超大规模架构的压缩或摘要表示的原位分析
- 批准号:
2333899 - 财政年份:2023
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
SHF: Small: K-Way Speculation for Mapping Applications with Dependencies on Modern HPC Systems
SHF:小型:依赖现代 HPC 系统的地图应用程序的 K-Way 推测
- 批准号:
2334273 - 财政年份:2023
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
Collaborative Research: SHF:SMALL: Compile-Parallelize-Schedule-Retarget-Repeat (EASER) Paradigm for Dealing with Extreme Heterogeneity
合作研究:SHF:SMALL:处理极端异构性的编译-并行化-调度-重定向-重复 (EASER) 范式
- 批准号:
2333895 - 财政年份:2023
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
OAC Core: SHF: SMALL: ICURE -- In-situ Analytics with Compressed or Summary Representations for Extreme-Scale Architectures
OAC 核心:SHF:SMALL:ICURE——针对超大规模架构的压缩或摘要表示的原位分析
- 批准号:
2007775 - 财政年份:2020
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
OAC Core: SHF: SMALL: ICURE -- In-situ Analytics with Compressed or Summary Representations for Extreme-Scale Architectures
OAC 核心:SHF:SMALL:ICURE——针对超大规模架构的压缩或摘要表示的原位分析
- 批准号:
2034850 - 财政年份:2020
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
SHF: Small: K-Way Speculation for Mapping Applications with Dependencies on Modern HPC Systems
SHF:小型:依赖于现代 HPC 系统的地图应用程序的 K-Way 推测
- 批准号:
2007793 - 财政年份:2020
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
II-New: Infrastructure for Energy-Aware High Performance Computing (HPC) and Data Analytics on Heterogeneous Systems
II-新:异构系统上的能源感知高性能计算 (HPC) 和数据分析基础设施
- 批准号:
1513120 - 财政年份:2015
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
SI2-SSE: Collaborative Research: Software Elements for Transfer and Analysis of Large-Scale Scientific Data
SI2-SSE:协作研究:用于大规模科学数据传输和分析的软件元素
- 批准号:
1339757 - 财政年份:2013
- 资助金额:
$ 25万 - 项目类别:
Standard Grant
相似国自然基金
支持二维毫米波波束扫描的微波/毫米波高集成度天线研究
- 批准号:62371263
- 批准年份:2023
- 资助金额:52 万元
- 项目类别:面上项目
腙的Heck/脱氮气重排串联反应研究
- 批准号:22301211
- 批准年份:2023
- 资助金额:30 万元
- 项目类别:青年科学基金项目
水系锌离子电池协同性能调控及枝晶抑制机理研究
- 批准号:52364038
- 批准年份:2023
- 资助金额:33 万元
- 项目类别:地区科学基金项目
基于人类血清素神经元报告系统研究TSPYL1突变对婴儿猝死综合征的致病作用及机制
- 批准号:82371176
- 批准年份:2023
- 资助金额:49 万元
- 项目类别:面上项目
FOXO3 m6A甲基化修饰诱导滋养细胞衰老效应在补肾法治疗自然流产中的机制研究
- 批准号:82305286
- 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: 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:
$ 25万 - 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:
$ 25万 - 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:
$ 25万 - 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:
$ 25万 - 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:
$ 25万 - 项目类别:
Standard Grant