Traverse-Research / Traverse-Research/gpu-allocator
Multithreading strategies
Nobody has claimed this yet.
- Dominant language
- Rust
- Stars
- 497
- Forks
- 82
- Avg merge
- 18d 17h
- Merged PRs (30d)
- 1
Description
What's the best way to allow threads to independently allocate/deallocate resources?
Sticking Allocator in an Arc<Mutex<Allocator>> means that only one thread can allocate/deallocate a resource at a time.
Does it make sense to use a separate Allocator per thread in a thread-local? How are the underlying descriptor pools managed?
Contributor guide
No contributing guide indexed for this repository
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
No file, test, or entry point is identified; begin by tracing the Allocator and descriptor-pool ownership paths across the Vulkan, DirectX 12, and Metal backends. Compare the Arc<Mutex> approach with thread-local allocators, and treat the work as complete only once a multithreading strategy and its resource-management implications are agreed.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- rust
- Domain
- computer-graphics
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100