Skip to content

Comments

[DFT] Add rocFFT backend for DFT interface#330

Merged
FMarno merged 10 commits intouxlfoundation:developfrom
FMarno:rocfft_backend
Jun 22, 2023
Merged

[DFT] Add rocFFT backend for DFT interface#330
FMarno merged 10 commits intouxlfoundation:developfrom
FMarno:rocfft_backend

Conversation

@FMarno
Copy link
Contributor

@FMarno FMarno commented Jun 6, 2023

Description

Add rocFFT as a backend for the DFT interface, allowing use of the DFT interface with AMD GPUs.

There is a bit of a issue with rocfft_setup/rocfft_cleanup. These both affect the global state, so if the user was also using rocfft (unlikely), they could potentially cause a "double" setup/cleanup.

Fixes #27

Checklist

All Submissions

  • Do all unit tests pass locally? Attach a log.
  • Have you formatted the code using clang-format?

@FMarno
Copy link
Contributor Author

FMarno commented Jun 6, 2023

Things to do:

  • Update main README
  • Update runtime README
  • enable runtime example
  • review rocfft_singleton
  • fix potential plan description leak

@FMarno FMarno marked this pull request as ready for review June 7, 2023 15:15
@FMarno
Copy link
Contributor Author

FMarno commented Jun 8, 2023

Test run log - rocfft_run.log

Copy link
Contributor

@hjabird hjabird left a comment

Choose a reason for hiding this comment

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

Looks good on the whole!

@FMarno FMarno requested a review from anantsrivastava30 June 19, 2023 09:58
});
// Heuristic for the average-case error margins
abs_error_margin =
std::abs(max_norm_ref) * std::log2(static_cast<double>(forward_elements));
Copy link
Contributor

Choose a reason for hiding this comment

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

can you explain this change ?

Copy link
Contributor Author

Choose a reason for hiding this comment

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

The tests were failing and this was a way I found to make them pass. I can't really do much about increasing the accuracy of the rocfft results.

Copy link
Contributor

@anantsrivastava30 anantsrivastava30 left a comment

Choose a reason for hiding this comment

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

The implimentation looks good to me in regards to plan creating syncronization and execution interleaved and planner, all tests are passing and has good spec coverage. approved

@FMarno FMarno merged commit 8e0636f into uxlfoundation:develop Jun 22, 2023
@FMarno FMarno deleted the rocfft_backend branch June 22, 2023 16:37
normallytangent pushed a commit to normallytangent/oneMKL that referenced this pull request Aug 6, 2024
* Add rocfft backend

* avoid creating plans with invalid strides

* update example

* Update readme to show rocfft support

* Update product and version information

* increase tolerances

* update README

* formatting changes

* fix unique_ptr creation

* Apply rule of three to rocfft commit class
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Add DFT support

4 participants