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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

High-throughput structure-based screening of drug-like molecules has become acommon tool in biomedical research. Recently, acceleration with graphicsprocessing units (GPUs) has provided a large performance boost for moleculardocking programs. Both cloud and high-performance computing (HPC) resourceshave been used for large screens with molecular docking programs; while NVIDIAGPUs have dominated cloud and HPC resources, new vendors such as AMD and Intelare now entering the field, creating the problem of software portability acrossdifferent GPUs. Ideally, software productivity could be maximized with portableprogramming models that are able to maintain high performance acrossarchitectures. While in many cases compiler directives have been used as aneasy way to offload parallel regions of a CPU-based program to a GPUaccelerator, they may also be an attractive programming model for providingportability across different GPU vendors, in which case the porting process mayproceed in the reverse direction: from low-level, architecture-specific code tohigher-level directive-based abstractions. MiniMDock is a new mini-application(miniapp) designed to capture the essential computational kernels found inmolecular docking calculations, such as are used in pharmaceutical drugdiscovery efforts, in order to test different solutions for porting across GPUarchitectures. Here we extend MiniMDock to GPU offloading with OpenMPdirectives, and compare to performance of kernels using CUDA, and HIP on bothNVIDIA and AMD GPUs, as well as across different compilers, exploringperformance bottlenecks. We document this reverse-porting process, from highlyoptimized device code to a higher-level version using directives, compare codestructure, and describe barriers that were overcome in this effort.

Portability for GPU-accelerated molecular docking applications for cloud  and HPC: can portable compiler directives provide performance across all  platforms?