分布式、并行与集群计算

This work evaluates the impact of sparse matrix reordering on the performance of sparse matrix-vector multiplication across different multicore CPU platforms. Reordering can significantly enhance performance by optimizing the non-zero…

The rise of serverless computing introduced a new class of scalable, elastic and widely available parallel workers in the cloud. Many systems and applications benefit from offloading computations and parallel tasks to dynamically allocated…

The model of population protocols provides a universal platform to study distributed processes driven by pairwise interactions of anonymous agents. While population protocols present an elegant and robust model for randomized distributed…

The scaling law for large language models (LLMs) depicts that the path towards machine intelligence necessitates training at large scale. Thus, companies continuously build large-scale GPU clusters, and launch training jobs that span over…

Modern distributed ML suffers from a fundamental gap between the theoretical and realized performance of collective communication algorithms due to congestion and hop-count induced dilation in practical GPU clusters. We present PCCL, a…

The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…

Edge computing has become critical for enabling latency-sensitive applications, especially when paired with cloud resources to form cloud-assisted edge clusters. However, efficient resource management remains challenging due to edge nodes'…

Modern wireless networks face critical challenges when mobile users traverse heterogeneous network configurations with varying antenna layouts, carrier frequencies, and scattering statistics. Traditional predictors degrade under…

Wireless channels in motion-rich urban microcell (UMi) settings are non-stationary; mobility and scatterer dynamics shift the distribution over time, degrading classical and deep estimators. This work proposes conditional prior diffusion…

The field of distributed machine learning (ML) faces increasing demands for scalable and cost-effective training solutions, particularly in the context of large, complex models. Serverless computing has emerged as a promising paradigm to…

Centralized search engines control what we see, read, believe, and vote. Consequently, they raise concerns over information control, censorship, and bias. Decentralized search engines offer a remedy to this problem, but their adoption has…

We present the design, implementation, and comprehensive evaluation of a specialized course on GPU architecture, GPU programming, and how these are used for developing AI agents. This course is offered to undergraduate and graduate students…

To meet the increasing demand for cloud computing services, the scale and number of data centers keeps increasing worldwide. This growth comes at the cost of increased electricity consumption, which directly correlates to CO2 emissions, the…

There is an exponential growth of connected Internet of Things (IoT) devices. These have given rise to applications that rely on real time data to make critical decisions quickly. Enterprises today are adopting cloud at a rapid pace. There…

Version 3.0 of the Message-Passing Interface (MPI) standard, released in 2012, introduced a new set of language bindings for Fortran 2008. By making use of modern language features and the enhanced interoperability with C, there was finally…

Skiplists are widely used for in-memory indexing in many key-value stores, such as RocksDB and LevelDB, due to their ease of implementation and simple concurrency control mechanisms. However, traditional skiplists suffer from poor cache…

This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation,…

The widespread growth in LLM developments increasingly demands more computational power from clusters than what they can supply. Traditional LLM applications inherently require huge static resource allocations, which force users to either…

The celebrated asynchronous computability theorem (ACT) characterizes tasks solvable in the read-write shared-memory model using the unbounded full-information protocol, where in every round of computation, each process shares its complete…

Quorum systems are a common way to formalize failure assumptions in distributed systems. Traditionally, these assumptions are shared by all involved processes. More recently, systems have emerged which allow processes some freedom in…