Avoid referencing the current device in `LaunchConfig`
Open
Nobody has claimed this yet.
cuda.core
enhancement
P1
- Dominant language
- Cython
- Stars
- 3.4k
- Forks
- 329
- Avg merge
- 1d 23h
- Merged PRs (30d)
- 116
Description
This is strictly speaking not 100% safe:
https://github.com/NVIDIA/cuda-python/blob/bf590e4301c36879410c3f84dad265c641362926/cuda_core/cuda/core/experimental/_launch_config.py#L68-L86
because we could be changing the device after creating a launch config and before we use it to launch a kernel (on another device).
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start with cuda_core/cuda/core/experimental/_launch_config.py at lines 68-86, then trace how LaunchConfig is used to launch a kernel. Check the behavior when the device changes between creating the launch configuration and launching the kernel. Done means LaunchConfig does not incorrectly depend on the current device in that interval.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- hpc
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100