分布式、并行与集群计算

The rapid development in scientific research provides a need for more compute power, which is partly being solved by GPUs. This paper presents a microarchitectural analysis of the modern NVIDIA Blackwell architecture by studying GPU…

Ethereum smart contracts operate in a concurrent environment where multiple transactions can be submitted simultaneously. However, the Ethereum Virtual Machine (EVM) enforces sequential execution of transactions within each block to prevent…

Organizations around the world schedule jobs (programs) regularly to perform various tasks dictated by their end users. With the major movement towards using a cloud computing infrastructure, our organization follows a hybrid approach with…

Serverless is an attractive computing model that offers seamless scalability and elasticity; it takes the infrastructure management burden away from users and enables a pay-as-you-use billing model. As a result, serverless is becoming…

Raft is a leader-based consensus algorithm that implements State Machine Replication (SMR), which replicates the service state across multiple servers to enhance fault tolerance. In Raft, the servers play one of three roles: leader,…

Collaboration among multiple large language model (LLM) agents is a promising approach to overcome inherent limitations of single-agent systems, such as hallucinations and single points of failure. As LLM agents are increasingly deployed on…

Pre-trained Transformer-based large models have revolutionized personal virtual assistants, but their deployment in cloud environments faces challenges related to data privacy and response latency. Deploying large models closer to the data…

We study the Distance-$k$-Dispersion (D-$k$-D) problem for synchronous mobile agents in a 1-interval-connected ring network having $n$ nodes and with $l$ agents where $3 \le l \le \lfloor \frac{n}{k}\rfloor$, without the assumption of…

Processing data at high speeds is becoming increasingly critical as digital economies generate enormous data. The current paradigms for timely data processing are edge computing and data stream processing (DSP). Edge computing places…

Large Language Models (LLMs) built on transformer architectures have transformed natural language processing, achieving remarkable performance across diverse applications. While distributed inference frameworks enable practical deployment…

High Performance Computing (HPC) centers provide resources to users who require greater scale to "get science done". They deploy infrastructure with singular hardware architectures, cutting-edge software environments, and stricter security…

Various numerical methods used for solving partial differential equations (PDE) result in tridiagonal systems. Solving tridiagonal systems on distributed-memory environments is not straightforward, and often requires significant amount of…

Ensuring liveness in a decentralized system, such as PBFT, is critical, because there may not be any single administrator that can restart the system if it encounters a liveness bug. At the same time, liveness is challenging to achieve…

The convergence of artificial intelligence and edge computing has spurred growing interest in enabling intelligent services directly on resource-constrained devices. While traditional deep learning models require significant computational…

NVIDIA MIG (Multi-Instance GPU) allows partitioning a physical GPU into multiple logical instances with fully-isolated resources, which can be dynamically reconfigured. This work highlights the untapped potential of MIG through moldable…

This paper presents Checkmate, a system that enables per-iteration checkpointing in DNN training without any training slowdown. The traditional approach to checkpointing requires a pause in training to copy model states to a separate…

Gossip algorithms and their accelerated versions have been studied exclusively in discrete time on graphs. In this work, we take a different approach, and consider the scaling limit of gossip algorithms in both large graphs and large number…

This paper proposes a reinforcement learning-based method for microservice resource scheduling and optimization, aiming to address issues such as uneven resource allocation, high latency, and insufficient throughput in traditional…

Distributed systems, such as state machine replication, are critical infrastructures for modern applications. Practical distributed protocols make minimum assumptions about the underlying network: They typically assume a partially…

Serverless platforms such as Kubernetes are increasingly adopted in high-performance computing, yet autoscaling remains challenging under highly dynamic and heterogeneous workloads. Existing approaches often rely on uniform reactive…