Angara interconnect makes GPU-based Desmos supercomputer an efficient tool for molecular dynamics calculations

V Stegailov, E Dlinnova, T Ismagilov… - … Journal of High …, 2019 - journals.sagepub.com
In this article, we describe the Desmos supercomputer that consists of 32 hybrid nodes
connected by a low-latency high-bandwidth Angara interconnect with torus topology. This …

Vc-migration: Live migration of virtual clusters in the cloud

K Ye, X Jiang, R Ma, F Yan - 2012 ACM/IEEE 13th International …, 2012 - ieeexplore.ieee.org
Live migration of virtual machines (VM) has recently become a key ingredient behind the
management activities of cloud computing system to achieve the goals of load balancing …

a scalable space-time domain decomposition approach for solving large scale nonlinear regularized inverse ill posed problems in 4D variational data assimilation

L D'Amore, E Constantinescu… - Journal of Scientific …, 2022 - Springer
We address the development of innovative algorithms designed to solve the strong-
constraint Four Dimensional Variational Data Assimilation (4DVar DA) problems in large …

A decomposition of the tikhonov regularization functional oriented to exploit hybrid multilevel parallelism

R Arcucci, L D'Amore, L Carracciuolo, G Scotti… - International Journal of …, 2017 - Springer
We introduce a decomposition of the Tikhonov Regularization (TR) functional which split this
operator into several TR functionals, suitably modified in order to enforce the matching of …

Towards a parallel component in a GPU–CUDA environment: a case study with the L-BFGS Harwell routine

L D'Amore, G Laccetti, D Romano… - International Journal of …, 2015 - Taylor & Francis
Modern graphics processing units (GPUs) have been at the leading edge of increasing
parallelism over the last 10 years. This fact has encouraged the use of GPUs in a broader …

The high performance internet of things: using GVirtuS to share high-end GPUs with ARM based cluster computing nodes

G Laccetti, R Montella, C Palmieri… - … Conference on Parallel …, 2013 - Springer
The availability of computing resources and the need for high quality services are rapidly
evolving the vision about the acceleration of knowledge development, improvement and …

Optimization of checkpointing/recovery strategy in cloud computing with adaptive storage management

B Meroufel, G Belalem - Concurrency and Computation …, 2018 - Wiley Online Library
Cloud Computing is a type of distributed system that is usually based on the services offered
to the user based on SLA contract. In this case, the implementation of a fault‐tolerant system …

An effective physics simulation methodology based on a data-driven learning algorithm

L Jiang, M Veresko, Y Liu, MC Cheng - Proceedings of the Platform for …, 2022 - dl.acm.org
A methodology of multi-dimensional physics simulations is investigated based on a data-
driven learning algorithm derived from proper orthogonal decomposition (POD). The …

Scalability analysis of a two level domain decomposition approach in space and time solving data assimilation models

R Cacciapuoti, L D'Amore - Concurrency and Computation …, 2024 - Wiley Online Library
We are concerned with the mapping on high performance hybrid architectures of a parallel
software implementing a two level overlapping domain decomposition, that is, along space …

A PETSc parallel‐in‐time solver based on MGRIT algorithm

V Mele, EM Constantinescu… - Concurrency and …, 2018 - Wiley Online Library
We address the development of a modular implementation of the MGRIT (MultiGrid‐In‐Time)
algorithm to solve linear and nonlinear systems that arise from the discretization of …