分布式、并行与集群计算

Metadata hotspots remain one of the key obstacles to scalable Input/Output (I/O) in both High-Performance Computing (HPC) and cloud-scale storage environments. Situations such as job start-ups, checkpoint storms, or heavily skewed namespace…

For distributed control systems, modern latency-critical applications are increasingly demanding real-time guarantees and robustness. Response-time analysis (RTA) is useful for this purpose, as it helps analyze and guarantee timing bounds.…

Designing high-performance kernels requires expert-level tuning and a deep understanding of hardware characteristics. Recent advances in large language models (LLMs) have enabled automated kernel generation, yet most existing systems rely…

Recommendation is crucial for both user experience and company revenue in Meituan as a leading lifestyle company, and generative recommendation models (GRMs) are shown to produce quality recommendations recently. However, existing systems…

Model serving systems have become popular for deploying deep learning models for various latency-sensitive inference tasks. While traditional replication-based methods have been used for failure-resilient model serving in the cloud, such…

The proliferation of latency-critical and compute-intensive edge applications is driving increases in computing demand and carbon emissions at the edge. To better understand carbon emissions at the edge, we analyze granular carbon intensity…

We introduce Mysticeti-C, the first DAG-based Byzantine consensus protocol to achieve the lower bounds of latency of 3 message rounds. Since Mysticeti-C is built over DAGs it also achieves high resource efficiency and censorship resistance.…

Detecting and resolving performance anomalies in Cloud services is crucial for maintaining desired performance objectives. Scaling actions triggered by an anomaly detector help achieve target latency at the cost of extra resource…

The Job Shop Scheduling Problem (JSP) is a pivotal challenge in operations research and is essential for evaluating the effectiveness and performance of scheduling algorithms. Scheduling problems are a crucial domain in combinatorial…

We study the problem of computing a Maximal Independent Set (MIS) in distributed networks where each node is a rational agent whose payoff depends on whether it joins the MIS. Classical distributed algorithms assume that nodes follow the…

Federated Learning (FL) offers a promising solution for training machine learning models across distributed data sources while preserving data privacy. However, FL faces critical challenges related to communication overhead and local…

Efficient data access in High-Performance Computing (HPC) systems is essential to the performance of intensive computing tasks. Traditional optimizations of the I/O stack aim to improve peak performance but are often workload specific and…

General matrix multiplication (GEMM) is the computational backbone of modern AI workloads, and its efficiency is critically dependent on effective tiling strategies. Conventional approaches employ symmetric tile buffering, where the…

Large-scale genomic workflows used in precision medicine can process datasets spanning tens to hundreds of gigabytes per sample, leading to high memory spikes, intensive disk I/O, and task failures due to out-of-memory errors. Simple static…

Byzantine agreement protocols in asynchronous networks have received renewed interest because they do not rely on network behavior to achieve termination. Conventional asynchronous Byzantine agreement protocols require every party to…

A vertically integrated, end-to-end, research prototype system combines 288 NorthPole neural inference accelerator cards, offline training algorithms, a high-performance runtime stack, and a containerized inference pipeline to deliver a…

The exponential growth in LLM scales, with parameters soaring from billions to trillions, has necessitated distributed pretraining across large clusters comprising thousands to tens of thousands of devices. While hybrid parallelization…

Distributed cloud environments hosting data-intensive applications often experience slowdowns due to network congestion, asymmetric bandwidth, and inter-node data shuffling. These factors are typically not captured by traditional host-level…

Very recently, Khoury and Schild [FOCS 2025] showed that any randomized LOCAL algorithm that solves maximal matching requires $\Omega(\min\{\log \Delta, \log_\Delta n\})$ rounds, where $n$ is the number of nodes in the graph and $\Delta$ is…

The convergence of Artificial Intelligence (AI) and the Internet of Things has accelerated the development of distributed, network-sensitive applications, necessitating ultra-low latency, high throughput, and real-time processing…