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/

Zendy Plus

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

Zendy Tools

Zendy Open

For computational fluid dynamics (CFD) applications with a large number ofgrid points/cells, parallel computing is a common efficient strategy to reducethe computational time. How to achieve the best performance in the modernsupercomputer system, especially with heterogeneous computing resources such ashybrid CPU+GPU, or a CPU + Intel Xeon Phi (MIC) co-processors, is still a greatchallenge.  An in-house parallel CFD code capable of simulating three dimensionalstructured grid applications is developed and tested in this study. Severalmethods of parallelization, performance optimization and code tuning both inthe CPU-only homogeneous system and in the heterogeneous system are proposedbased on identifying potential parallelism of applications, balancing the workload among all kinds of computing devices, tuning the multi-thread code towardbetter performance in intra-machine node with hundreds of CPU/MIC cores, andoptimizing the communication among inter-nodes, inter-cores, and between CPUsand MICs.  Some benchmark cases from model and/or industrial CFD applications are testedon the Tianhe-1A and Tianhe-2 supercomputer to evaluate the performance. Amongthese CFD cases, the maximum number of grid cells reached 780 billion. Thetuned solver successfully scales up to half of the entire Tianhe-2supercomputer system with over 1.376 million of heterogeneous cores. The testresults and performance analysis are discussed in detail.

Performance optimizations for scalable CFD applications on hybrid CPU+MIC heterogeneous computing system with millions of cores