NVIDIA / NVIDIA/AMGX

GPU memory usage estimation

Open
#33 1 comment 0 reactions 0 assignees View on GitHub

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

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.