The Wayback Machine - https://web.archive.org/web/20211117200255/https://github.com/topics/high-performance-computing
Skip to content
#

high-performance-computing

Here are 525 public repositories matching this topic...

hipSYCL
illuhad
illuhad commented Sep 6, 2021

Bug summary
There is evidence that sub_group::get_group_id() does not return the same value as threadIdx.x / warpSize (assuming 1D kernel), as expected on CUDA. We should check the implementation of this function. Our implementation of this function performs bit manipulation magic, presumably the optimization went to far...

To Reproduce
Compare sub_group{}.get_group_id() or `sub

precice
fsimonis
fsimonis commented May 12, 2021

Please describe the problem you are trying to solve.
The current implementation of the barycentric coordinates are overly complicated and explicitly require the normals of triangles or edges. There are simpler ways to implement this.

Describe the solution you propose.

  • Simplify math/barycenter.[ch]pp
  • Remove Edge::computeNormal() as it is unnecessary.

**Describe alternativ

Improve this page

Add a description, image, and links to the high-performance-computing topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the high-performance-computing topic, visit your repo's landing page and select "manage topics."

Learn more