GPU memory usage estimation
Nobody has claimed this yet.
- Dominant language
- Cuda
- Stars
- 692
- Forks
- 197
- PR merge metrics
- No merged PRs in 30d
Description
AMGX is currently able to provide an estimation of the GPU memory usage. Currently, this is achieved by computing the memory used by all processes, thanks to cudaMemGetInfo function.
It would be more interesting to only provide the memory used by the AMGX process.
To get the amount of memory used by the AMGX process, you may store at launch the current memory used estimation and subtract it to each "allocated = total - free" in the updateMaxMemoryUsage function.
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
Start by locating the launch-time memory state and the updateMaxMemoryUsage function described in the issue, along with its use of cudaMemGetInfo. Verify that the reported value reflects memory used by the AMGX process rather than all processes, and check any existing memory-usage tests or examples for the expected result.
Written by the indexing model from the issue text.
Assessment
- Domain
- hpc, performance
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100