CAREER: A Task-Parallel Platform for Interactive Applications

职业：交互式应用程序的任务并行平台

• 批准号: 1943456
• 负责人: I-Ting Lee
• 金额: $ 49.79万
• 依托单位: Washington University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-05-01 至 2025-04-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1943456&HistoricalAwards=false
• 关键词: CAREER; Task; Parallel; Platform; Interactive

Modern software tends to be service-oriented, long running, and interactive. The interaction can be external, such as waiting on a user input or a network package, or internal, where the components that make up the application interact with one another, often asynchronously. It is important that interactive applications run fast on commodity multicore hardware, because fast interactions lead to good user experiences, and multicore processors are the bargain components of today's hardware technology. Fast interactive parallel applications can be challenging to develop, however, as the programmer must deal with multiple non-trivial concerns simultaneously, including asynchrony, concurrency, and ensuring application responsiveness.This project focuses on developing software infrastructure to enable non-expert programmers to write parallel interactive applications that run fast on multicore hardware. The resulting platform provides: (1) a high-level language abstraction that decouple parallelism and concurrency specifications from scheduling and encapsulate nondeterminism; (2) a provably and practically efficient scheduler that achieve various desirable performance criteria; (3) a well-defined cost model to reason about the performance of the computation; and (4) a set of efficient tools to debug code written using the abstraction. The resulting platform enables programmer productivity in developing parallel interactive applications and efficient utilization of multicore hardware. The research results from this project is disseminated broadly though top parallel computing conferences.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.

现代软件趋向于面向服务、长期运行和交互式。 交互可以是外部的，例如等待用户输入或网络包，也可以是内部的，其中组成应用程序的组件通常以异步方式相互交互。交互式应用程序在商用多核硬件上快速运行非常重要，因为快速交互可以带来良好的用户体验，而多核处理器是当今硬件技术的廉价组件。 然而，快速交互式并行应用程序的开发可能具有挑战性，因为程序员必须同时处理多个重要问题，包括并发性，并发性和确保应用程序的响应性。该项目侧重于开发软件基础设施，使非专业程序员能够编写在多核硬件上快速运行的并行交互式应用程序。 由此产生的平台提供：（1）高级语言抽象，其将并行性和并发性规范与调度解耦并封装不确定性;（2）可证明且实际有效的调度器，其实现各种期望的性能标准;（3）良好定义的成本模型，其用于推理计算的性能;以及（4）一组高效的工具，其用于调试使用抽象编写的代码。由此产生的平台，使程序员的生产力在开发并行交互式应用程序和多核硬件的有效利用。 该项目的研究成果通过顶级并行计算会议广泛传播。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Efficient Access History for Race Detection

用于种族检测的高效访问历史记录

• DOI: 10.1145/3409964.3461825
• 发表时间: 2022
• 期刊: 022 Proceedings of the Symposium on Algorithm Engineering and Experiments (ALENEX
• 作者: Xu, Yifan;Zhou, Anchengcheng;Yin, Grace Q.;Agrawal, Kunal;Lee, I-Ting Angelina;Schardl, Tao B.
• 通讯作者: Schardl, Tao B.

An Efficient Scheduler for Task-Parallel Interactive Applications

• DOI: 10.1145/3558481.3591092
• 发表时间: 2023-06
• 期刊: Proceedings of the 35th ACM Symposium on Parallelism in Algorithms and Architectures
• 作者: Kyle Singer;Kunal Agrawal;I. Lee

PINT: Parallel INTerval-Based Race Detector

PINT：基于并行间隔的竞赛检测器

• DOI: 10.1109/ipdps53621.2022.00087
• 发表时间: 2022
• 期刊: 2022 IEEE International Parallel and Distributed Processing Symposium
• 作者: Xu, Yifan;Zhou, Anchengcheng;Agrawal, Kunal;Lee, I-Ting Angelina
• 通讯作者: Lee, I-Ting Angelina

A Hybrid Scheduling Scheme for Parallel Loops

并行循环的混合调度方案

• DOI: 10.1109/ipdps49936.2021.00067
• 发表时间: 2021
• 期刊: 2021 IEEE International Parallel and Distributed Processing Symposium
• 作者: Handleman, Aaron;Rattew, Arthur G.;Lee, I-Ting Angelina;Schardl, Tao B.
• 通讯作者: Schardl, Tao B.

OpenCilk: A Modular and Extensible Software Infrastructure for Fast Task-Parallel Code

OpenCilk：用于快速任务并行代码的模块化且可扩展的软件基础设施

• DOI: 10.1145/3572848.3577509
• 发表时间: 2023
• 期刊: Proceedings of the 28th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming
• 作者: Schardl, Tao B.;Lee, I-Ting Angelina
• 通讯作者: Lee, I-Ting Angelina