Conditions for privatizing the elements of arrays by computing threads

MaRDI QIDQ5107076zbMATH OpenFDO

Authors N. A. Likhoded, Maksim Aleksandrovich Poleshchuk

Publication date 22 April 2020

Full work available at URL https://journals.bsu.by/index.php/mathematics/article/view/1013

zbMATH Keywords

array privatizationGPUparallel computationsregisterstiling

Mathematics Subject Classification ID

Parallel algorithms in computer science (68W10)

Recommendations

• Conditions for the localization of data in sequential and parallel implementation of algorithms
• Sufficient conditions for the determination and use of data in the same granular parallel computation process
• Multi-dimensional parallelization considering conditions of data localization
• Lifespan distribution of SIMD groups on a GPU engaged in a class of probabilistic computation
• Resource efficient finite element computing on multicore architectures

Cited in

(1)

• Conditions for the existence of broadcast and spatial locality in computation threads

This page was built for publication: Conditions for privatizing the elements of arrays by computing threads

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5107076)