Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update timings for GPUs #31

Merged
merged 5 commits into from
Nov 13, 2023
Merged

Update timings for GPUs #31

merged 5 commits into from
Nov 13, 2023

Conversation

ElliottKasoar
Copy link
Contributor

@ElliottKasoar ElliottKasoar commented Nov 7, 2023 •
edited
Loading

Replaces #27 due to large number of merge conflicts. Changes are largely the same, including:

  • use_cuda flag to move all input tensors to GPU (output tensors should be kept on GPU)
  • Precision requirement slightly so assertions still pass
  • Update Python scripts to ensure each pt2ts.py can save models to be run on GPU correct
  • GPU-enabled TorchScript files, matching the GPU files, to enable benchmarking to be run without rerunning pt2ts.py
  • Benchmarking script, to enable benchmarking on GPU
  • Renamed benchmarker_utils.f90 -> benchmarker_utils_mod.f90 for consistency with other modules
  • Updated CMake for benchmarker_utils_mod.f90, and ensuring precision_mod.f90 is always linked.

@ElliottKasoar ElliottKasoar added the enhancement New feature or request label Nov 7, 2023
@ElliottKasoar ElliottKasoar requested a review from TomMelt November 7, 2023 11:51
@ElliottKasoar ElliottKasoar mentioned this pull request Nov 7, 2023
Open
TomMelt
TomMelt requested changes Nov 10, 2023
View reviewed changes
Copy link
Member

@TomMelt TomMelt left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks for the PR. Looks good and also it runs on my machine as well 👍

CMakeLists.txt Outdated Show resolved Hide resolved
@ElliottKasoar ElliottKasoar mentioned this pull request Nov 13, 2023
Closed
@TomMelt TomMelt merged commit 48fb769 into main Nov 13, 2023
@TomMelt TomMelt deleted the update-timings-gpu branch November 13, 2023 13:27
@jatkinson1000 jatkinson1000 mentioned this pull request Jan 15, 2024
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@TomMelt TomMelt TomMelt approved these changes

Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@ElliottKasoar @TomMelt