一种用于众核系统可靠性管理的两级热循环感知任务映射技术
A Two-Level Thermal Cycling-aware Task Mapping Technique for Reliability Management in Manycore Systems
AI总结：
针对众核系统热循环老化影响可靠性的问题，提出一种考虑核心相邻性与工艺偏差的两级热循环感知任务映射技术，可最高提升20%的热循环相关平均无故障时间。
摘要：
可靠性管理是众核系统设计中的核心问题之一。负偏置温度不稳定性（NBTI）、电迁移（EM）和热循环等不同老化机制会降低这类系统的可靠性。然而，现有研究主要聚焦于NBTI和EM，仅有少量工作考虑了热循环效应。热循环效应会显著缩短系统寿命。此外，核心因相邻而产生的热相互影响也可能影响系统的平均无故障时间（MTTF）。本文提出了一种管理众核系统可靠性的新技术。该技术考虑了热循环、核心相邻性以及工艺偏差导致的工作频率差异，通过两级任务映射提升系统寿命。第一级将温度接近的核心归入同一分组（bin），随后将到达的任务分配给温度相近的分组；第二级则根据性能需求和核心频率，将任务分配到第一级选定分组内的某个核心上。与传统的热循环感知技术相比，所提方法在更高层级（分组层级）执行，以降低分组内核心的温度波动，提升系统的热循环相关平均无故障时间（MTTFTC），是众核系统的一种理想解决方案。我们在16核、32核、64核和256核系统上，使用SPLASH2和PARSEC基准测试套件应用评估了所提技术的有效性。结果表明，与传统的热循环感知任务映射技术相比，该方法可将MTTFTC提升最高达20%。
英文摘要：
Reliability management is one of the primary concerns in manycore systems design. Different aging mechanisms such as Negative-Bias Temperature Instability (NBTI), Electromigration (EM), and thermal cycling can reduce the reliability of these systems. However, state-of-the-art works mainly focused on NBTI and EM, whereas a few works have considered the thermal cycling effect. The thermal cycling effect can significantly aggravate the systems lifetime. Moreover, the thermal effects of cores on each other due to their adjacency may also influence the systems Mean Time to Failure (MTTF). This paper introduces a new technique to manage the reliability of manycore systems. The technique considers thermal cycling, adjacency of cores, and process variation-induced diversity of operating frequencies. It uses two levels of task mapping to improve system lifetime. At the first level, cores with close temperatures are packed into the same bin, and then, an arrived task is assigned to a bin with a similar temperature. Afterward in the second level, the task is assigned to a core inside the selected bin in the first level, based on performance requirements and the core frequency. Compared to the conventional TC-aware techniques, the proposed method is performed at a higher level (bins level) to reduce the thermal variations of cores inside a bin, and improves the system MTTFTC, making it a promising solution for manycore systems. The efficacy of our proposed technique is evaluated on 16, 32, 64, and 256 core systems using SPLASH2 and PARSEC benchmark suite applications. The results show up to 20% MTTFTC increment compared to the conventional thermal cycling-aware task mapping techniques.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
