分布式、并行与集群计算

Sketching is widely used in randomized linear algebra for low-rank matrix approximation, column subset selection, and many other problems, and it has gained significant traction in machine learning applications. However, sketching large…

Effectively leveraging the vast computational resources of modern cloud environments requires expertise spanning multiple technical domains: configuring scientific software with correct parameters and dependencies, navigating thousands of…

We study verification (decision) problems for graph properties in distributed networks under the locally checkable labeling framework, where nodes use labels (proofs) and local neighborhoods to decide acceptance or rejection. Our focus is…

Compound AI is a distributed intelligence approach that represents a unified system orchestrating specialized AI/ML models with engineered software components into AI workflows. Compound AI production deployments must satisfy accuracy,…

Graph Neural Network (GNN) on streaming graphs has gained increasing popularity. However, its practical deployment remains challenging, as the inference process relies on Runtime Embedding Computation (RTEC) to capture recent graph changes.…

Cloud and big data workloads are increasingly distributing data across multiple cloud providers and regions for rapid decision-making and analytics. Traditional transfer tools are typically specialized for a single paradigm, either stream…

Dynamic GNN inference has exhibited effectiveness in High Energy Physics (HEP) experiments at High Luminosity Large Hadron Collider (HL-LHC) due to strong capability to model complex particle interactions in collision events. Future HEP…

This paper presents a detailed case study of the T2_BR_SPRACE storage frontend architecture and its observed performance in high-intensity data transfers. The architecture is composed of a heterogeneous cluster of XRootD [1] Virtual…

Large language model (LLM) serving infrastructures are undergoing a shift toward heterogeneity and disaggregation. Modern deployments increasingly integrate diverse accelerators and near-memory processing technologies, introducing…

We define \emph{engineered simultaneity}: the construction of a system that requires temporal comparison of events at spacelike-separated locations, implements this comparison via an implicit simultaneity convention, and represents the…

Accurate performance prediction is essential for optimizing scientific applications on modern high-performance computing (HPC) architectures. Widely used performance models primarily focus on cache and memory bandwidth, which is suitable…

In recent years, the landscape of federated learning has witnessed significant advancements, particularly in decentralized methodologies. This research paper presents a comprehensive comparison of Centralized Hierarchical Federated Learning…

Serverless computing is renowned for its computation elasticity, yet its full potential is often constrained by the requirement for functions to operate within local and dedicated background environments, resulting in limited memory…

Cloud computing enables the dynamic provisioning of server resources. To exploit this opportunity, a policy is needed for dynamically allocating (and deallocating) servers in response to the current load conditions. In this paper we…

Large multimodal models (LMMs) have demonstrated excellent capabilities in both understanding and generation tasks with various modalities. While these models can accept flexible combinations of input data, their training efficiency suffers…

Distributed scientific workflows increasingly span heterogeneous compute clusters, edge resources, and geo-distributed data repositories. In these environments, a centralized orchestrator is an architectural bottleneck -- introducing a…

In July 1976, Metcalfe and Boggs published their foundational paper on Ethernet in Communications of the ACM. Their efficiency model -- E = (P/C)/(P/C + W*T) -- measures the fraction of Ether time carrying good forward packets under…

The need to reduce datacenter carbon footprint is urgent. While many sustainability techniques have been proposed, they are often evaluated in isolation, using limited setups or analytical models that overlook real-world dynamics and…

Civilization maintains an elaborate infrastructure devoted to the maintenance of synchronized time. Governments mandate daylight saving time. Standards bodies insert leap seconds into Coordinated Universal Time. Engineers debate leap…

By 2025, there are zettabytes of data generated every year. The size and complexity of modern large-scale computing infrastructures like High-Performance Computing (HPC) systems continue to evolve and become complex, leaving us wondering…