Results 161 to 170 of about 88,406 (306)

Performance and Cost Evaluation of StarPU on AWS: Case Studies With Dense Linear Algebra Kernels and N‐Body Simulations

open access: yesConcurrency and Computation: Practice and Experience, Volume 38, Issue 3, February 2026.
ABSTRACT Task‐based programming interfaces introduce a paradigm in which computations are decomposed into fine‐grained units of work known as “tasks”. StarPU is a runtime system originally developed to support task‐based parallelism on on‐premise heterogeneous architectures by abstracting low‐level hardware details and efficiently managing resource ...
Vanderlei Munhoz   +5 more
wiley   +1 more source

Framework for Task Offloading in O‐RAN Architecture for Heterogeneous Computing Applications

open access: yesTransactions on Emerging Telecommunications Technologies, Volume 37, Issue 2, February 2026.
This work proposes a task offloading framework in ORAN architecture, optimizing computational assignment across user devices, edge cloud, and regional cloud. By efficiently selecting processing nodes and allocating computational and radio resources, it minimizes delay while accommodating diverse latency requirements for gold, silver, and bronze‐tier ...
Samira Taheri   +3 more
wiley   +1 more source

On Multilevel Energy‐Based Fragmentation Methods

open access: yesInternational Journal of Quantum Chemistry, Volume 126, Issue 3, January 30, 2026.
We investigate the working equations of energy‐based fragmentation methods and present ML‐SUPANOVA, a Möbius‐inversion‐based multilevel fragmentation scheme that enables adaptive, quasi‐optimal truncations to efficiently approximate Born‐Oppenheimer potentials across hierarchies of electronic‐structure methods and basis sets.
James Barker   +2 more
wiley   +1 more source

Clustering Analysis of Very Large Measurement and Model Data Sets on High‐Performance Computing Platforms

open access: yesJournal of Geophysical Research: Atmospheres, Volume 131, Issue 1, 16 January 2026.
Abstract Hierarchical agglomerative clustering is a useful analysis technique which allows for a level of stability, interpretability and flexibility not available in other similar techniques such as K‐means, density‐based clustering or positive matrix factorization.
Colin J. Lee   +2 more
wiley   +1 more source

CacheShuffle: An Oblivious Shuffle Algorithm Using Caches [PDF]

open access: green, 2017
Sarvar Patel   +2 more
openalex   +1 more source

A High‐Precision and Robust Geometric Relationships‐Inspired Neural Network for the Inverse Kinematic Modeling of the Tendon‐Actuated Continuum Manipulator

open access: yesAdvanced Intelligent Systems, Volume 8, Issue 1, January 2026.
An online learning control framework with a data cache pool based on a constant‐curvature model inspired neural network (CCMINN) model to obtain the inverse kinematics model of tendon‐actuated continuum manipulators is proposed. Combining the fast‐converging CCMINN with an online learning control framework enables high‐precision and highly robust ...
Jinyu Duan   +5 more
wiley   +1 more source

A Python/Fortran Implementation of the Lattice‐Boltzmann Kernel on Multiple GPU Using the OpenACC Framework

open access: yesConcurrency and Computation: Practice and Experience, Volume 38, Issue 1, January 2026.
ABSTRACT The increasing availability of GPU accelerated architectures for high‐performance computing presents new opportunities for scientific software but also challenges due to the complexity of porting legacy codes to accelerator platforms. Directive‐based programming models such as OpenACC offer a minimally intrusive pathway to exploit GPU ...
Carlos Junqueira‐Junior   +3 more
wiley   +1 more source

Home - About - Disclaimer - Privacy