性能

Efficient routing is critical for payment channel networks (PCNs) such as the Lightning Network (LN), where most clients currently rely on Dijkstra-based algorithms for payment pathfinding. While Dijkstra's algorithm has long been regarded…

System-level resource monitoring with both precision and efficiency is a continuous challenge. We introduce eHashPipe, a lightweight, real-time resource observability system utilizing eBPF and the HashPipe sketching algorithm. eHashPipe…

Large Language Models (LLMs) with Mixture-of-Expert (MoE) architectures achieve superior model performance with reduced computation costs, but at the cost of high memory capacity and bandwidth requirements. Near-Memory Processing (NMP)…

Bottleneck evaluation plays a crucial part in performance tuning of HPC applications, as it directly influences the search for optimizations and the selection of the best hardware for a given code. In this paper, we introduce a new…

The choice between containers and unikernels is a critical trade-off for edge applications, balancing the container's ecosystem maturity against unikernel's specialized efficiency. However, until now, how this trade-off behaves under the…

The widespread adoption of microservices architecture in modern software systems has emphasized the need for efficient management of distributed services. While stateless microservices enable straightforward migration, stateful…

Modern software architectures are characterized by their cloud-native, modular, and microservice-based designs. While these systems are known for their efficiency, they also face complex challenges in service optimization, especially in…

Cloud application services are distributed in nature and have components across the stack working together to deliver the experience to end users. The wide adoption of microservice architecture exacerbates failure management due to…

Data compression is widely adopted for modern solid-state drives (SSDs) to mitigate both storage capacity and SSD lifetime issues. Researchers have proposed compression schemes at different system layers, including device-side solutions…

Uncrewed Aerial Vehicle (UAV) computing and networking are becoming a fundamental computation infrastructure for diverse cyber-physical application systems. UAVs can be empowered by AI on edge devices and can communicate with other UAVs and…

Matrix multiplication is the foundation from much of the success from high performance technologies like deep learning, scientific simulations, and video graphics. High level programming languages like Python and R rely on highly optimized…

Selected inversion is essential for applications such as Bayesian inference, electronic structure calculations, and inverse covariance estimation, where computing only specific elements of large sparse matrix inverses significantly reduces…

Elastic block storage (EBS) with the storage-compute disaggregated architecture stands as a pivotal piece in today's cloud. EBS furnishes users with storage capabilities through the elastic solid-state drive (ESSD). Nevertheless, despite…

Persistent Stochastic Non-Interference (PSNI) was introduced to capture a quantitative security property in stochastic process algebras, ensuring that a high-level process does not influence the observable behaviour of a low-level…

Approximate nearest neighbor search (ANNS) is essential for applications like recommendation systems and retrieval-augmented generation (RAG) but is highly I/O-intensive and memory-demanding. CPUs face I/O bottlenecks, while GPUs are…

This book, by Molero, Juiz, and Rodeno, titled Performance Evaluation and Modeling of Computer Systems, presents a comprehensive summary of simple quantitative techniques that help answer the above questions. Its approach is not one of…

Large language models (LLMs) have demonstrated remarkable capabilities across diverse domains, but their heavy resource demands make quantization-reducing precision to lower-bit formats-critical for efficient serving. While many…

With the maturity of deep learning, its use is emerging in every field. Also, as different types of GPUs are becoming more available in the markets, it creates a difficult decision for users. How can users select GPUs to achieve optimal…

Large Language Models (LLMs) are becoming the backbone of modern cloud services, yet their inference costs are dominated by GPU energy. Unlike traditional GPU workloads, LLM inference has two stages with different characteristics: the…

Collaborative edge computing addresses the resource constraints of individual edge nodes by enabling resource sharing and task co-processing across multiple nodes. To fully leverage the advantages of collaborative edge computing, joint…