English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The performance of lattice-Boltzmann solver implementations usually dependsmainly on memory access patterns. Achieving high performance requires thencomplex code which handles careful data placement and ordering of memorytransactions. In this work, we analyse the performance of an implementationbased on a new approach called the data-oriented language, which allows thecombining of complex memory access patterns with simple source code. As a usecase, we present and provide the source code of a solver for D2Q9 lattice andshow its performance on GTX Titan Xp GPU for dense and sparse geometries up to4096 2 nodes. The obtained results are promising, around 1000 lines of codeallowed us to achieve performance in the range of 0.6 to 0.7 of maximumtheoretical memory bandwidth (over 2.5 and 5.0 GLUPS for double and singleprecision, respectively) for meshes of size above 1024 2 nodes, which is closeto the current state-of-the-art. However, we also observed relatively high andsometimes difficult to predict overheads, especially for sparse datastructures. The additional issue was also a rather long compilation, whichextended the time of short simulations, and a lack of access to low-leveloptimisation mechanisms.

Data-Oriented Language Implementation of Lattice-Boltzmann Method for Dense and Sparse Geometries