Skip to content

Conversation

badenh
Copy link
Contributor

@badenh badenh commented Feb 22, 2020

Various typographic, grammatical and formatting edits and tidy ups.

Various typographic, grammatical and formatting edits and tidy ups.
@repo-lockdown
Copy link

repo-lockdown bot commented Feb 22, 2020

This repository does not accept pull requests. Please follow http://llvm.org/docs/Contributing.html#how-to-submit-a-patch for contribution to LLVM.

@repo-lockdown repo-lockdown bot closed this Feb 22, 2020
@repo-lockdown repo-lockdown bot locked and limited conversation to collaborators Feb 22, 2020
@serge-sans-paille
Copy link
Collaborator

Applied as of d192a4a

jpinot pushed a commit to jpinot/llvm-project that referenced this pull request Apr 9, 2025
Notes:
- Ndrange grainsize chuncksize do not neet to capture anything. This is because they are parameters used in task creation but not in task execution
- dev_func is language dependent to link properly with CUDA (mangling if C++ or plain name if extern C or C source
  dev_func is in task_impl_info since its a constant value in every task instance.
  Also only set this value in task device pure to allow the runtime check that a kernel with that name exists.
- Do not emit function call in task outline device pure (with ndrange).
  Also make task pures to create a task if(0) in final mode
- Support for cuda, fpgas, opencl

Closes llvm#144 llvm#153 llvm#6
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants