相关论文: The Ghost in the Datacenter: Link Flapping, Topolo…

Recently, Bit-Flip Attack (BFA) has garnered widespread attention for its ability to compromise software system integrity remotely through hardware fault injection. With the widespread distillation and deployment of large language models…

Compute Express Link (CXL) 3.0 and beyond allows the compute nodes of a cluster to share data with hardware cache coherence and at the granularity of a cache line. This enables shared-memory semantics for distributed computing, but…

Subspace clustering is the problem of clustering data points into a union of low-dimensional linear/affine subspaces. It is the mathematical abstraction of many important problems in computer vision, image processing and machine learning. A…

All modern distributed systems list performance and scalability as their core strengths. Given that optimal performance requires carefully selecting configuration options, and typical cluster sizes can range anywhere from 2 to 300 nodes, it…

Too many defective compute chips are escaping existing manufacturing tests -- at least an order of magnitude more than industrial targets across all compute chip types in data centers. Silent data corruptions (SDCs) caused by test escapes,…

GPU systems are increasingly powering modern datacenters at scale. Despite being highly performant, GPU systems can exhibit performance variation at the node and cluster levels. Such performance variation can significantly impact both…

Large-scale cloud data centers have gained popularity due to their high availability, rapid elasticity, scalability, and low cost. However, current data centers continue to have high failure rates due to the lack of proper resource…

Silent Data Corruption (SDC) can have negative impact on large-scale infrastructure services. SDCs are not captured by error reporting mechanisms within a Central Processing Unit (CPU) and hence are not traceable at the hardware level.…

Fault tolerance overhead of high performance computing (HPC) applications is becoming critical to the efficient utilization of HPC systems at large scale. HPC applications typically tolerate fail-stop failures by checkpointing. Another…

Large-scale training systems typically use synchronous training, requiring all GPUs to be healthy simultaneously. In our experience training on O(100K) GPUs, synchronous training results in a low efficiency due to frequent failures and long…

Silent Data Errors (SDEs) from time-zero defects and aging degrade safety-critical systems. Functional testing detects SDE-related faults but is expensive to simulate. We present a unified spatio-temporal graph convolutional network…

Autoregressive inference in large transformer-based language models (LLMs) presents significant challenges for runtime efficiency, particularly during the decode phase where load imbalance across GPU shards can cause throughput degradation…

Hacks are one of the most damaging types of cryptocurrency related crime, accounting for billions of dollars in stolen funds since 2009. Professional investigators at Chainalysis have traced these stolen funds from the initial breach on an…

Graphics Processing Units (GPUs) have become a de facto solution for accelerating high-performance computing (HPC) applications. Understanding their memory error behavior is an essential step toward achieving efficient and reliable HPC…

The financial crisis made companies around the world search for cheaper and more efficient solutions to cover their needs in terms of computational power and storage. Their quest came to end with the birth of Cloud Computing…

Neural network applications have become popular in both enterprise and personal settings. Network solutions are tuned meticulously for each task, and designs that can robustly resolve queries end up in high demand. As the commercial value…

The growing use of third-party hardware accelerators (e.g., FPGAs, ASICs) for deep neural networks (DNNs) introduces new security vulnerabilities. Conventional model-level backdoor attacks, which only poison a model's weights to misclassify…

The network unreliability problem asks for the probability that a given undirected graph gets disconnected when every edge independently fails with a given probability $p$. Valiant (1979) showed that this problem is \#P-hard; therefore, the…

Supercomputing systems today often come in the form of large numbers of commodity systems linked together into a computing cluster. These systems, like any distributed system, can have large numbers of independent hardware components…

Access to frontier large language models (LLMs), such as GPT-5 and Gemini-2.5, is often hindered by high pricing, payment barriers, and regional restrictions. These limitations drive the proliferation of $\textit{shadow APIs}$, third-party…