CSR: Small: First-Class Operating System Management of Computational Accelerators

CSR：小型：计算加速器的一流操作系统管理

• 批准号: 1319417
• 负责人: Michael Scott
• 金额: $ 45.53万
• 依托单位: University of Rochester
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2013
• 资助国家: 美国
• 起止时间: 2013-10-01 至 2018-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1319417&HistoricalAwards=false
• 关键词: CSR; Small; First; Class; Operating

This project investigates operating system mechanisms to manage hardware accelerator resources in a safe, fair, and protected manner while maintaining high performance. Programmable vector processors including general-purpose graphical processing units (GP-GPUs) and other accelerators for encryption, compression, media transcoding, pattern matching, parsing, etc. are increasingly ubiquitous in computer systems. For the sake of safety and fairness, such accelerators must be managed by the operating system, but for the sake of performance, they must be accessible directly from user-level applications, without OS intervention. The conflict between these goals is exacerbated by the opacity of proprietary library/driver/hardware interfaces. This project seeks a balanced solution to these conflicting goals through: (1) an operating system resource management architecture that allows direct user-level access in the common case, but intercedes in the existing accelerator access path when necessary to delay and re-order requests; (2) a tool chain that uncovers hidden interface semantics required for resource management, together with a characterization of the information needed from vendors in the future; and (3) an integrated management and scheduling strategy across the full set of computational resources in a given system.By focusing on safe, fair, and efficient access to computational accelerators, the project aims to increase performance and power efficiency over a broad range of applications critical to today's digital economy and society. Broad dissemination is promoted through implementation in the Linux kernel, and open-source software release. Technology transfer is pursued through regular communication and collaboration with GPU industry vendors. Project research is integrated with education through curricular development and graduate student instruction.

本项目研究操作系统机制，以安全、公平和受保护的方式管理硬件加速器资源，同时保持高性能。包括通用图形处理单元（GP-GPU）和用于加密、压缩、媒体转码、模式匹配、解析等的其他加速器的可编程向量处理器在计算机系统中越来越普遍。为了安全和公平起见，这些加速器必须由操作系统管理，但为了性能，它们必须可以直接从用户级应用程序访问，而无需操作系统干预。专有库/驱动程序/硬件接口的不透明性加剧了这些目标之间的冲突。本项目通过以下方式寻求这些冲突目标的平衡解决方案：（1）一个操作系统资源管理架构，在普通情况下允许直接的用户级访问，但在必要时在现有的加速器访问路径中插入以延迟和重新排序请求;（2）揭示资源管理所需的隐藏接口语义的工具链，同时说明今后需要供应商提供的信息的特点;以及（3）在给定系统中的整个计算资源集合上的集成管理和调度策略。通过关注对计算加速器的安全、公平和有效访问，该项目旨在提高对当今数字经济和社会至关重要的广泛应用的性能和功率效率。通过在Linux内核中实施和发布开放源码软件，促进了广泛传播。通过与GPU行业供应商的定期沟通和合作进行技术转让。项目研究通过课程开发和研究生教学与教育相结合。

项目成果

Interval-based memory reclamation

基于间隔的内存回收

• DOI: 10.1145/3178487.3178488
• 发表时间: 2018
• 期刊: Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming
• 作者: Wen, Haosen;Izraelevitz, Joseph;Cai, Wentao;Beadle, H. Alan;Scott, Michael L.
• 通讯作者: Scott, Michael L.

iDO: Compiler-Directed Failure Atomicity for Nonvolatile Memory

• DOI: 10.1109/micro.2018.00029
• 发表时间: 2018-10
• 期刊: 2018 51st Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)
• 作者: Qingrui Liu;Joseph Izraelevitz;Se Kwon Lee;M. Scott;S. Noh;Changhee Jung

Hodor: intra-process isolation for high-throughput data plane libraries

Hodor：高吞吐量数据平面库的进程内隔离

• 发表时间: 2019
• 期刊: Proceedings of the 2019 Usenix Annual Technical Conference
• 作者: Mohammad Hedayati, Spyridoula Gravani

Multi-queue fair queueing

多队列公平排队

• 发表时间: 2019
• 期刊: Proceedings of the 2019 Usenix Annual Technical Conference
• 作者: Mohammad Hedayati, Kai Shen