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

Heterogeneous computing environments combining CPU and GPU resources providea great boost to large-scale scientific computing applications. Code generationutilities that partition the work into CPU and GPU tasks while considering datamovement costs allow researchers to more quickly and easily develophigh-performance solutions, and make these resources accessible to a largeruser base.  We present developments for a domain-specific language (DSL) and codegeneration framework for solving partial differential equations (PDEs). Theseenhancements facilitate GPU-accelerated solution of the Boltzmann transportequation (BTE) for phonons, which is the governing equation for simulatingthermal transport in semiconductor materials at sub-micron scales. The solutionof the BTE involves thousands of coupled PDEs as well as complicated boundaryconditions and nonlinear processing at each time step. These developmentsenable the DSL to generate configurable hybrid GPU/CPU code that couplesaccelerated kernels with user-defined code. We observed performanceimprovements of around 18X compared to a CPU-only version produced by this sameDSL with minimal additional programming effort.

Automating GPU Scalability for Complex Scientific Models: Phonon Boltzman Transport Equation