Skip to content

Optimize OpenMP routines

Nicolas Tancogne-Dejean requested to merge optim_openmp into main

Description

Rewrite the norm2 routine to avoid false sharing and scale on OpenMP. Tune some OpenMP loops to improve memory access (by reducing NUMA) and using OpenMP simd more often.

News snippet

Improve performances using OpenMP.

Checklist

  • I have checked that my code follows the Octopus coding standards
  • I have added tests for all the new features added in this request.
Edited by Nicolas Tancogne-Dejean

Merge request reports