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

[cuBLAS] Add an option to disable reduced precision reductions for BF16 GEMM #89172

Closed
wants to merge 3 commits into from
Closed

[cuBLAS] Add an option to disable reduced precision reductions for BF16 GEMM #89172

wants to merge 3 commits into from
+95 −4

Conversation

eqy
Copy link
Collaborator

@eqy eqy commented Nov 17, 2022

Essentially the same change as #67946, except that the default is to disallow reduced precision reductions in BFloat16 GEMMs (for now). If performance is severely regressed, we can change the default, but this option appears to be necessary to pass some addmm BFloat16 tests on H100.

CC @ptrblck @ngimel

@pytorch-bot
Copy link

pytorch-bot bot commented Nov 17, 2022 •
edited

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/89172

Note: Links to docs will display an error until the docs builds have been completed.

⏳ No Failures, 1 Pending

As of commit 909a989:
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@eqy eqy added the ciflow/trunk Trigger trunk jobs on your pull request label Nov 17, 2022
@soulitzer soulitzer added the triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module label Nov 18, 2022
@eqy eqy changed the title [cuBLAS] Add an option to disable reduced precision reductions for FP16 GEMM [cuBLAS] Add an option to disable reduced precision reductions for 16 GEMM Nov 19, 2022
@eqy eqy changed the title [cuBLAS] Add an option to disable reduced precision reductions for 16 GEMM [cuBLAS] Add an option to disable reduced precision reductions for BF16 GEMM Nov 19, 2022
@eqy
Copy link
Collaborator Author

eqy commented Nov 22, 2022

@pytorchmergebot rebase

@pytorchmergebot
Copy link
Collaborator

@pytorchbot successfully started a rebase job. Check the current status here

@pytorchmergebot
Copy link
Collaborator

Successfully rebased cublas_reduced_precision_bf16 onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via git checkout cublas_reduced_precision_bf16 && git pull --rebase)

@eqy
Copy link
Collaborator Author

eqy commented Dec 13, 2022

@pytorchmergebot rebase

@pytorchmergebot
Copy link
Collaborator

@pytorchbot successfully started a rebase job. Check the current status here

@pytorchmergebot
Copy link
Collaborator

Successfully rebased cublas_reduced_precision_bf16 onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via git checkout cublas_reduced_precision_bf16 && git pull --rebase)

ngimel
ngimel approved these changes Dec 13, 2022
View reviewed changes
Copy link
Collaborator

@ngimel ngimel left a comment

Choose a reason for hiding this comment

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

Approving, but I'd defer to @ptrblck for what the default value should be, just making tests pass may not be reason enough to flip the default, as long as real workloads still converge.

@eqy
Copy link
Collaborator Author

eqy commented Dec 20, 2022

@pytorchmergebot rebase

@pytorchmergebot
Copy link
Collaborator

@pytorchbot successfully started a rebase job. Check the current status here

@pytorchmergebot
Copy link
Collaborator

Successfully rebased cublas_reduced_precision_bf16 onto refs/remotes/origin/viable/strict, please pull locally before adding more changes (for example, via git checkout cublas_reduced_precision_bf16 && git pull --rebase)

@eqy
Copy link
Collaborator Author

eqy commented Dec 21, 2022

@pytorchmergebot merge

@pytorchmergebot
Copy link
Collaborator

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging
Check the merge workflow status
here

ShisuiUzumaki pushed a commit to ShisuiUzumaki/pytorch that referenced this pull request Dec 23, 2022
@eqy @ShisuiUzumaki
[cuBLAS] Add an option to disable reduced precision reductions for BF…
ffe6e21 
…16 GEMM (pytorch#89172)

Essentially the same change as pytorch#67946, except that the default is to disallow reduced precision reductions in `BFloat16` GEMMs (for now). If performance is severely regressed, we can change the default, but this option appears to be necessary to pass some `addmm` `BFloat16` tests on H100.

CC @ptrblck @ngimel
Pull Request resolved: pytorch#89172
Approved by: https://github.com/ngimel
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ngimel ngimel ngimel approved these changes

Assignees
No one assigned
Labels
ciflow/trunk Trigger trunk jobs on your pull request Merged open source triaged This issue has been looked at a team member, and triaged and prioritized into an appropriate module
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

None yet
5 participants
@eqy @pytorchmergebot @ngimel @soulitzer @pytorchbot