SlowPoke: Understanding and Detecting On-Chip Fail-Slow Failures in Many-Core Systems
Abstract
Many-core architectures are essential for high-performance computing, but their performance is undermined by widespread fail-slow failures. Detecting such failures on-chip is challenging, as prior methods from distributed systems are unsuitable due to strict memory limits and their inability to track failures across the hardware topology. This paper introduces SlowPoke, a lightweight, hardware-aware framework for practical on-chip fail-slow detection. SlowPoke combines compiler-based instrumentation for low-overhead monitoring, on-the-fly trace compression to operate within kilobytes of memory, and a novel topology-aware ranking algorithm to pinpoint a failure's root cause. We evaluate SlowPoke on a wide range of representative many-core workloads, and the results demonstrate that SlowPoke reduces the storage overhead of detection traces by an average of 115.9$\times$, while achieving an average fail-slow detection accuracy of 86.77% and a false positive rate (FPR) of 12.11%. More importantly, SlowPoke scales effectively across different many-core architectures, making it practical for large-scale deployments.