相关论文: The Ghost in the Datacenter: Link Flapping, Topolo…
Large-scale AI training is now fundamentally a distributed systems problem, and hardware failures have become routine operating conditions rather than rare exceptions. Public operational evidence from production training clusters, however,…
Silent data corruption (SDC) threatens the reliability of large-scale GPU clusters used for training large language models, yet its rarity and lack of explicit error signals make accurate high-level modeling challenging. To address this…
Inferring the root cause of failures among thousands of components in a data center network is challenging, especially for "gray" failures that are not reported directly by switches. Faults can be localized through end-to-end measurements,…
Abrupt learning is a common phenomenon in recurrent neural networks (RNNs) trained on working memory tasks. In such cases, the networks develop transient slow regions in state space that extend the effective timescales of computation.…
Attention mechanisms are at the core of modern neural architectures, powering systems ranging from ChatGPT to autonomous vehicles and driving a major economic impact. However, high-profile failures, such as ChatGPT's nonsensical outputs or…
With relentless CMOS technology downsizing Networks-on-Chips (NoCs) are inescapably experiencing escalating susceptibility to wearout and reduced reliability. While faults in processors and memories may be masked via redundancy, or…
Network failures continue to plague datacenter operators as their symptoms may not have direct correlation with where or why they occur. We introduce 007, a lightweight, always-on diagnosis application that can find problematic links and…
In recent years, cyberattacks - along with physical faults - have become an increasing factor causing system failures, especially in DER (Distributed Energy Resources) systems. In addition, according to the literature, a number of faults…
Fail-slows, or stragglers, are common but largely unheeded problems in large-scale hybrid-parallel training that spans thousands of GPU servers and runs for weeks to months. Yet, these problems are not well studied, nor can they be quickly…
The adoption of Large Language Models (LLMs) in scientific writing promises efficiency but risks introducing informational entropy. While "hallucinated papers" are a known artifact, the systematic degradation of valid citation chains…
GPU clouds have become a popular computing platform because of the cost of owning and maintaining high-performance computing clusters. Many cloud architectures have also been proposed to ensure a secure execution environment for guest…
GPU nodes are central to modern HPC and AI workloads, yet many failures do not manifest as immediate hard faults. While some instabilities emerge gradually as weak thermal or efficiency drift, a significant class occurs abruptly with little…
The datacenter industry is converging on SmartNIC-based resource management. Wave (Humphries et al., ASPLOS '25) demonstrates the practical feasibility of offloading kernel thread scheduling, memory management, and RPC stacks to the ARM…
Recent years have seen a surge in the number of data leaks despite aggressive information-containment measures deployed by cloud providers. When attackers acquire sensitive data in a secure cloud environment, covert communication channels…
Over the past decade, the Bitcoin P2P network protocol has become a reference model for all modern cryptocurrencies. While nodes in this network are known, the connections among them are kept hidden, as it is commonly believed that this…
To design fast neural networks, many works have been focusing on reducing the number of floating-point operations (FLOPs). We observe that such reduction in FLOPs, however, does not necessarily lead to a similar level of reduction in…
In the past few years, deep learning has transformed artificial intelligence research and led to impressive performance in various difficult tasks. However, it is still unclear how the brain can perform credit assignment across many areas…
The Network-on-Chip (NoC) paradigm has been proposed as a favorable solution to handle the strict communication requirements between the increasingly large number of cores on a single chip. However, NoC systems are exposed to the aggressive…
Denial-of-Service (DoS) conditions in enterprise networks are commonly attributed to malicious actors. However, availability can also be compromised by benign non-malicious insider behavior. This paper presents an empirical study of a…
We consider gossip networks consisting of a source that maintains the current version of a file, $n$ nodes that use asynchronous gossip mechanisms to disseminate fresh information in the network, and an oblivious adversary who infects the…