OpenNMT / OpenNMT/CTranslate2

[Profiling] Help needed with Profiling CT2 on both CUDA and CPU

Open
#1,734 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
4.7k
Forks
537
Avg merge
12h 12m
Merged PRs (30d)
4

Description

Hi All,

I'm trying to profile the ct2 model on both CPU and CUDA, but I'm unable to see any data output when using the '-DENABLE_PROFILING=ONflag inCMakeLists.txt`.

Specifically, I'm trying to profile the transformers module on both CUDA and CPU. I have attempted to wrap the init_profiling and dump_profiling functions around the model, but I still don't see any profiling outputs on the cout stream.

Could anyone provide guidance on this issue or point me to the relevant documentation or examples? Any help would be greatly appreciated.

Thanks in advance!

Contributor guide

Open the contributing guide

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 with CMakeLists.txt and the profiling entry points init_profiling and dump_profiling, then trace how the transformers module is profiled on CPU and CUDA. Reproduce the missing output with ENABLE_PROFILING=ON and check whether profiling data reaches the cout stream; done means a documented or reproducible profiling output path for both targets.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.