English
Related papers

Related papers: The Communication-Hiding Conjugate Gradient Method…

200 papers

Gradient-based distributed learning in Parameter Server (PS) computing architectures is subject to random delays due to straggling worker nodes, as well as to possible communication bottlenecks between PS and workers. Solutions have been…

Information Theory · Computer Science 2020-04-09 Jingjing Zhang , Osvaldo Simeone

Analyzing massive spatial datasets using Gaussian process model poses computational challenges. This is a problem prevailing heavily in applications such as environmental modeling, ecology, forestry and environmental heath. We present a…

Methodology · Statistics 2021-12-07 Suman Majumder , Yawen Guan , Brian J. Reich , Arvind K. Saibaba

Distributed synchronous stochastic gradient descent has been widely used to train deep neural networks (DNNs) on computer clusters. With the increase of computational power, network communications generally limit the system scalability.…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-01-19 Shaohuai Shi , Xiaowen Chu , Bo Li

We consider the problem of how to reduce the cost of communication that is required for the parallel training of a neural network. The state-of-the-art method, Bulk Synchronous Parallel Stochastic Gradient Descent (BSP-SGD), requires many…

Distributed, Parallel, and Cluster Computing · Computer Science 2017-04-18 Linnan Wang , Wei Wu , George Bosilca , Richard Vuduc , Zenglin Xu

We study the use of Krylov subspace recycling for the solution of a sequence of slowly-changing families of linear systems, where each family consists of shifted linear systems that differ in the coefficient matrix only by multiples of the…

Numerical Analysis · Mathematics 2014-10-01 Kirk M. Soodhalter , Daniel B. Szyld , Fei Xue

Low-precision computing is essential for efficiently utilizing memory bandwidth and computing cores. While many mixed-precision algorithms have been developed for iterative sparse linear solvers, effectively leveraging half-precision (fp16)…

Numerical Analysis · Mathematics 2025-05-28 Kengo Suzuki , Takeshi Iwashita

We deal with accelerating the solution of a sequence of large linear systems solved by preconditioned conjugate gradient method (PCG). The sequence originates from time-stepping within a simulation of an unsteady incompressible flow. We…

Numerical Analysis · Mathematics 2026-02-04 Martin Hanek , Jan Papež , Jakub Šístek

This paper presents an optimized and scalable semi-Lagrangian solver for the Vlasov-Poisson system in six-dimensional phase space. Grid-based solvers of the Vlasov equation are known to give accurate results. At the same time, these solvers…

Computational Physics · Physics 2019-03-29 Katharina Kormann , Klaus Reuter , Markus Rampp

Federated Learning is a powerful machine learning paradigm to cooperatively train a global model with highly distributed data. A major bottleneck on the performance of distributed Stochastic Gradient Descent (SGD) algorithm for large-scale…

Machine Learning · Computer Science 2020-01-24 Haozhao Wang , Zhihao Qu , Song Guo , Xin Gao , Ruixuan Li , Baoliu Ye

Augmented Krylov subspace methods aid in accelerating the convergence of a standard Krylov subspace method by including additional vectors in the search space. A residual projection framework based on residual (Petrov-) Galerkin constraints…

Numerical Analysis · Mathematics 2023-05-19 Liam Burke , Kirk M. Soodhalter

An efficient algorithm for computing the terms appearing in the Generalised Kolmogorov Equation (GKE) written for the indefinite plane channel flow is presented. The algorithm, which features three distinct strategies for parallel…

Communication compression techniques are of growing interests for solving the decentralized optimization problem under limited communication, where the global objective is to minimize the average of local cost functions over a multi-agent…

Optimization and Control · Mathematics 2022-05-26 Yiwei Liao , Zhuorui Li , Kun Huang , Shi Pu

Currently, training large-scale deep learning models is typically achieved through parallel training across multiple GPUs. However, due to the inherent communication overhead and synchronization delays in traditional model parallelism…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Xiuyuan Guo , Chengqi Xu , Guinan Guo , Feiyu Zhu , Changpeng Cai , Peizhe Wang , Xiaoming Wei , Junhao Su , Jialin Gao

We consider the iterative solution of regularized saddle-point systems. When the leading block is symmetric and positive semi-definite on an appropriate subspace, Dollar, Gould, Schilders, and Wathen (2006) describe how to apply the…

Numerical Analysis · Mathematics 2021-01-06 Daniela di Serafino , Dominique Orban

Robust and efficient solvers for coupled-adjoint linear systems are crucial to successful aerostructural optimization. Monolithic and partitioned strategies can be applied. The monolithic approach is expected to offer better robustness and…

Numerical Analysis · Mathematics 2023-09-25 Christophe Blondeau , Mehdi Jadoui

Compute nodes on modern heterogeneous supercomputing systems comprise CPUs, GPUs, and high-speed network interconnects (NICs). Parallelization is identified as a technique for effectively utilizing these systems to execute scalable…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-04-01 Naveen Namashivayam

Large language models have led to state-of-the-art accuracies across a range of tasks. However, training these models efficiently is challenging for two reasons: a) GPU memory capacity is limited, making it impossible to fit large models on…

Recent advancements and widespread adoption of Large Language Models (LLMs) in both industry and academia have catalyzed significant demand for LLM serving. However, traditional cloud services incur high costs, while on-device inference…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-30 Yida Zhang , Zhiyong Gao , Shuaibing Yue , Jie Li , Rui Wang

Distributed training is an effective way to accelerate the training process of large-scale deep learning models. However, the parameter exchange and synchronization of distributed stochastic gradient descent introduce a large amount of…

Distributed, Parallel, and Cluster Computing · Computer Science 2021-08-16 LingFei Dai , Boyu Diao , Chao Li , Yongjun Xu

Gaussian process (GP) models are widely used to analyze spatially referenced data and to predict values at locations without observations. In contrast to many algorithmic procedures, GP models are based on a statistical framework, which…

Computation · Statistics 2020-01-01 Florian Gerber , Douglas W. Nychka