Skip to content

[ROCm] Improvements to non-vectorized elementwise kernels#145635

Closed
jerrymannil wants to merge 1 commit intopytorch:mainfrom
jerrymannil:non_vec_elemwise_fixes
Closed

[ROCm] Improvements to non-vectorized elementwise kernels#145635
jerrymannil wants to merge 1 commit intopytorch:mainfrom
jerrymannil:non_vec_elemwise_fixes

Conversation

@jerrymannil
Copy link
Copy Markdown
Collaborator

@jerrymannil jerrymannil commented Jan 24, 2025

  • Unroll loops manually to hide memory access latency
  • Strided access for coalesced memory acesses

Cherry-pick of #145635

Co-authors: @akadutta @doru1004 @amd-hhashemi @carlobertolli

cc @jeffdaily @sunway513 @jithunnair-amd @pruthvistony @ROCmSupport @dllehr-amd @jataylo @hongxiayang @naromero77amd

@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Jan 24, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/145635

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

❌ 1 New Failure, 1 Unrelated Failure

As of commit 0410997 with merge base 354fe48 (image):

NEW FAILURE - The following job has failed:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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

@pytorch-bot pytorch-bot Bot added module: rocm AMD GPU support for Pytorch release notes: cuda release notes category labels Jan 24, 2025
@jerrymannil jerrymannil marked this pull request as draft January 24, 2025 18:34
@pruthvistony pruthvistony added ciflow/periodic Trigger jobs ran periodically on master (periodic.yml) on the PR ciflow/rocm ciflow/inductor-rocm Trigger "inductor" config CI on ROCm labels Jan 24, 2025
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Jan 24, 2025

To add the ciflow label ciflow/periodic please first approve the workflows that are awaiting approval (scroll to the bottom of this page).

This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows.

@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Jan 24, 2025

To add the ciflow label ciflow/rocm please first approve the workflows that are awaiting approval (scroll to the bottom of this page).

This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows.

@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Jan 24, 2025

To add the ciflow label ciflow/inductor-rocm please first approve the workflows that are awaiting approval (scroll to the bottom of this page).

This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows.

@pytorch-bot pytorch-bot Bot removed ciflow/periodic Trigger jobs ran periodically on master (periodic.yml) on the PR ciflow/rocm ciflow/inductor-rocm Trigger "inductor" config CI on ROCm labels Jan 24, 2025
@pruthvistony pruthvistony added ciflow/periodic Trigger jobs ran periodically on master (periodic.yml) on the PR rocm This tag is for PRs from ROCm team ciflow/rocm ciflow/inductor-rocm Trigger "inductor" config CI on ROCm labels Jan 24, 2025
@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Jan 24, 2025

To add the ciflow label ciflow/inductor-rocm please first approve the workflows that are awaiting approval (scroll to the bottom of this page).

This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows.

@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Jan 24, 2025

To add the ciflow label ciflow/rocm please first approve the workflows that are awaiting approval (scroll to the bottom of this page).

This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows.

@pytorch-bot
Copy link
Copy Markdown

pytorch-bot Bot commented Jan 24, 2025

To add the ciflow label ciflow/periodic please first approve the workflows that are awaiting approval (scroll to the bottom of this page).

This helps ensure we don't trigger CI on this PR until it is actually authorized to do so. Please ping one of the reviewers if you do not have access to approve and run workflows.

@pytorch-bot pytorch-bot Bot removed ciflow/rocm ciflow/inductor-rocm Trigger "inductor" config CI on ROCm ciflow/periodic Trigger jobs ran periodically on master (periodic.yml) on the PR labels Jan 24, 2025
@pruthvistony pruthvistony added topic: not user facing topic category ciflow/periodic Trigger jobs ran periodically on master (periodic.yml) on the PR ciflow/rocm and removed release notes: cuda release notes category labels Jan 24, 2025
@pruthvistony pruthvistony added the ciflow/inductor-rocm Trigger "inductor" config CI on ROCm label Jan 24, 2025
@jerrymannil
Copy link
Copy Markdown
Collaborator Author

@pytorchbot rebase

@pytorchmergebot
Copy link
Copy Markdown
Collaborator

@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here

@pytorchmergebot
Copy link
Copy Markdown
Collaborator

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

@jerrymannil
Copy link
Copy Markdown
Collaborator Author

Will make a new PR

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ciflow/inductor-rocm Trigger "inductor" config CI on ROCm ciflow/periodic Trigger jobs ran periodically on master (periodic.yml) on the PR module: rocm AMD GPU support for Pytorch open source rocm This tag is for PRs from ROCm team topic: not user facing topic category

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants