分布式、并行与集群计算

Training large deep learning models at scale is very challenging. This paper proposes Chimera, a novel pipeline parallelism scheme which combines bidirectional pipelines for efficiently training large-scale models. Chimera is a synchronous…

Deep learning at scale is dominated by communication time. Distributing samples across nodes usually yields the best performance, but poses scaling challenges due to global information dissemination and load imbalance across uneven sample…

Load imbalance pervasively exists in distributed deep learning training systems, either caused by the inherent imbalance in learned tasks or by the system itself. Traditional synchronous Stochastic Gradient Descent (SGD) achieves good…

In recent years, cloud providers have introduced novel approaches for trading virtual machines. For example, Virtustream introduced so-called muVMs to charge cloud computing resources while other providers such as Google, Microsoft, or…

General Matrix Multiplication (GEMM) is a critical operation underpinning a wide range of applications in high-performance computing (HPC) and artificial intelligence (AI). The emergence of hardware optimized for low-precision arithmetic…

The rapid growth of Internet of Things (IoT) ecosystems has intensified the challenge of efficiently allocating heterogeneous resources in highly dynamic, distributed environments. Conventional centralized mechanisms and single-objective…

Payment channel networks (PCNs) are a promising technology that alleviates blockchain scalability by shifting the transaction load from the blockchain to the PCN. Nevertheless, the network topology has to be carefully designed to maximise…

Auditability allows to track operations performed on a shared object, recording who accessed which information. This gives data owners more control on their data. Initially studied in the context of single-writer registers, this work…

In a previous work, "pure data" is proposed as an axiomatic foundation for mathematics and computing, based on "finite sequence" as the foundational concept rather than based on logic or type. Within this framework, objects with…

In a connected graph with an autonomous robot swarm with limited visibility, it is natural to ask whether the robots can be deployed to certain vertices satisfying a given property using only local knowledge. This paper affirmatively…

Large Language Models (LLMs) and other foundation models are increasingly used as the core of AI agents. In agentic workflows, these agents plan tasks, interact with humans and peers, and influence scientific outcomes across federated and…

Function as a Service (FaaS) is poised to become the foundation of the next generation of cloud systems due to its inherent advantages in scalability, cost-efficiency, and ease of use. However, challenges such as the need for specialized…

The pace of RISC-V adoption continues to grow rapidly, yet for the successes enjoyed in areas such as embedded computing, RISC-V is yet to gain ubiquity in High Performance Computing (HPC). The Sophon SG2044 is SOPHGO's next generation…

This work presents a carbon footprint plugin designed to extend the capabilities of the Batsim simulator by allowing the calculation of CO$_2$ emissions during simulation runs. The goal is to comprehensively assess the environmental impact…

DDoS attacks are one of the most prevalent and harmful cybersecurity threats faced by organizations and individuals today. In recent years, the complexity and frequency of DDoS attacks have increased significantly, making it challenging to…

Many parallel applications rely on iterative stencil operations, whose performance are dominated by communication costs at large scales. Several MPI optimizations, such as persistent and partitioned communication, reduce overheads and…

Censor-Hillel, Cohen, Gelles, and Sela (PODC 2022 & Distributed Computing 2023) studied fully-defective asynchronous networks, where communication channels may suffer an extreme form of alteration errors, rendering messages completely…

A novel long-lived distributed problem, called Team Formation (TF), is introduced together with a message- and time-efficient randomized algorithm. The problem is defined over the asynchronous model with a complete communication graph,…

There are well established reductions between combinatorial sampling and counting problems (Jerrum, Valiant, Vazirani TCS 1986). Building off of a very recent parallel algorithm utilizing this connection (Liu, Yin, Zhang arxiv 2024), we…

Non-fungible tokens (NFTs) have become a significant digital asset class, each uniquely representing virtual entities such as artworks. These tokens are stored in collections within smart contracts and are actively traded across platforms…