perf: change order of element-wise op in edge angle update calculations #4677

caic99 · 2025-03-28T04:20:18Z

This PR changes the order of element-wise multiply when calculating weighted_edge_angle_update. The largest matrix should be calculated last to avoid saving large intermediate results and unnecessary broadcast.

I've tested this PR on OMat with 9 DPA-3 layers and batch size=auto:512.

Metric	Before	After	Improvement
Peak Memory	25.0G	21.4G	-15%
Speed (per 100 steps)	31.27s	28.9s	+7.7%

Since this is an element-wise multiply, changing the order of arguments should not affect the result. The correctness is verified by torch.allclose.

Summary by CodeRabbit

Refactor
- Improved internal calculation order for weighted updates to enhance code clarity and maintainability, while ensuring the functionality remains consistent.

Copilot

Pull Request Overview

This PR optimizes memory usage and speed by changing the order of element-wise multiplications in the calculation of weighted edge angle updates.

Reorders multiplication operations so that the larger matrix is multiplied last.
Applies the change in both PyTorch and NumPy code paths in separate files.

Reviewed Changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.

File	Description
deepmd/pt/model/descriptor/repflow_layer.py	Reorders multiplication order to optimize memory usage in PyTorch code.
deepmd/dpmodel/descriptor/repflows.py	Reorders multiplication order to optimize memory usage in NumPy code.

coderabbitai · 2025-03-28T04:22:52Z

📝 Walkthrough

Walkthrough

The modifications reorder the multiplication factors in the computation of weighted_edge_angle_update within two classes. In both the DescrptBlockRepflows and RepFlowLayer methods, the order of multiplying edge_angle_update and the switch function factors (a_sw) has been rearranged. Although the order of operations has changed, the resulting mathematical expression remains equivalent due to the commutative property of multiplication. No changes were made to the public API.

Changes

File	Change Summary
`deepmd/.../repflows.py` and `deepmd/.../repflow_layer.py`	Reordered the multiplication factors in the computation of `weighted_edge_angle_update`. The reordering does not affect the overall mathematical result.

Suggested labels

Python

Suggested reviewers

njzjz

📜 Recent review details

Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 2e4da81 and 7620a35.

📒 Files selected for processing (2)

deepmd/dpmodel/descriptor/repflows.py (1 hunks)
deepmd/pt/model/descriptor/repflow_layer.py (1 hunks)

⏰ Context from checks skipped due to timeout of 90000ms (7)

GitHub Check: Build wheels for cp310-manylinux_aarch64
GitHub Check: Build wheels for cp311-win_amd64
GitHub Check: Build C library (2.14, >=2.5.0rc0,<2.15, libdeepmd_c_cu11.tar.gz)
GitHub Check: Test C++ (false)
GitHub Check: Test C++ (true)
GitHub Check: Build C library (2.18, libdeepmd_c.tar.gz)
GitHub Check: Build C++ (cpu, cpu)

🔇 Additional comments (2)

deepmd/dpmodel/descriptor/repflows.py (1)

1120-1123: Excellent performance optimization!

This change reorders the element-wise multiplication to compute the product of the two smaller a_sw tensors first, before multiplying by the larger edge_angle_update tensor. Because multiplication is commutative, the mathematical result is identical, but this approach reduces memory usage by avoiding large intermediate tensors.

The optimization aligns perfectly with the PR objective of reducing peak memory usage (15% reduction) and improving computation speed (7.7% faster).

deepmd/pt/model/descriptor/repflow_layer.py (1)

700-704: Great consistency with the previous optimization!

This change in the PyTorch implementation mirrors the same optimization applied in the numpy-compatible version, ensuring consistency across both implementations. By multiplying the smaller a_sw tensors first before the larger edge_angle_update, memory usage is reduced while preserving mathematical correctness.

This change contributes to the overall performance improvements reported in the PR (15% memory reduction and 7.7% speed improvement).

✨ Finishing Touches

📝 Generate Docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

🪧 Tips

Chat

There are 3 ways to chat with CodeRabbit:

Review comments: Directly reply to a review comment made by CodeRabbit. Example:
- I pushed a fix in commit <commit_id>, please review it.
- Generate unit testing code for this file.
- Open a follow-up GitHub issue for this discussion.
Files and specific lines of code (under the "Files changed" tab): Tag @coderabbitai in a new review comment at the desired location with your query. Examples:
- @coderabbitai generate unit testing code for this file.
- @coderabbitai modularize this function.
PR comments: Tag @coderabbitai in a new PR comment to ask questions about the PR branch. For the best results, please provide a very specific query, as very limited context is provided in this mode. Examples:
- @coderabbitai gather interesting stats about this repository and render them as a table. Additionally, render a pie chart showing the language distribution in the codebase.
- @coderabbitai read src/utils.ts and generate unit testing code.
- @coderabbitai read the files in the src/scheduler package and generate a class diagram using mermaid and a README in the markdown format.
- @coderabbitai help me debug CodeRabbit configuration file.

Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments.

CodeRabbit Commands (Invoked using PR comments)

@coderabbitai pause to pause the reviews on a PR.
@coderabbitai resume to resume the paused reviews.
@coderabbitai review to trigger an incremental review. This is useful when automatic reviews are disabled for the repository.
@coderabbitai full review to do a full review from scratch and review all the files again.
@coderabbitai summary to regenerate the summary of the PR.
@coderabbitai generate docstrings to generate docstrings for this PR.
@coderabbitai resolve resolve all the CodeRabbit review comments.
@coderabbitai plan to trigger planning for file edits and PR creation.
@coderabbitai configuration to show the current CodeRabbit configuration for the repository.
@coderabbitai help to get help.

Other keywords and placeholders

Add @coderabbitai ignore anywhere in the PR description to prevent this PR from being reviewed.
Add @coderabbitai summary to generate the high-level summary at a specific location in the PR description.
Add @coderabbitai anywhere in the PR title to generate the title automatically.

CodeRabbit Configuration File (`.coderabbit.yaml`)

You can programmatically configure CodeRabbit by adding a .coderabbit.yaml file to the root of your repository.
Please see the configuration documentation for more information.
If your editor has YAML language server enabled, you can add the path at the top of this file to enable auto-completion and validation: # yaml-language-server: $schema=https://coderabbit.ai/integrations/schema.v2.json

Documentation and Community

Visit our Documentation for detailed information on how to use CodeRabbit.
Join our Discord Community to get help, request features, and share feedback.
Follow us on X/Twitter for updates and announcements.

codecov · 2025-03-28T05:14:19Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 84.80%. Comparing base (2e4da81) to head (7620a35).
Report is 80 commits behind head on devel.

Additional details and impacted files

@@           Coverage Diff           @@
##            devel    #4677   +/-   ##
=======================================
  Coverage   84.80%   84.80%           
=======================================
  Files         692      692           
  Lines       66396    66396           
  Branches     3539     3538    -1     
=======================================
  Hits        56306    56306           
  Misses       8949     8949           
  Partials     1141     1141

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

Similar changes of #4677 Brings +5% speed up compared with #4687  ## Summary by CodeRabbit - **Refactor** - Adjusted the order of operations in update calculations to enhance clarity while maintaining the same functional outcomes.

perf: change order of element-wise op in edge angle update calculations

7620a35

caic99 requested review from Copilot and iProzd March 28, 2025 04:20

github-actions bot added the Python label Mar 28, 2025

Copilot AI reviewed Mar 28, 2025

View reviewed changes

iProzd approved these changes Mar 28, 2025

View reviewed changes

njzjz added this pull request to the merge queue Mar 29, 2025

Merged via the queue into deepmodeling:devel with commit 78b8f01 Mar 29, 2025
60 checks passed

caic99 deleted the perf-weight-angle branch March 30, 2025 05:27

coderabbitai bot mentioned this pull request Mar 31, 2025

perf: use torch.split in replace of slicing ops in repflow #4687

Merged

caic99 mentioned this pull request Mar 31, 2025

perf: reschedule plus op #4688

Merged

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

perf: change order of element-wise op in edge angle update calculations #4677

perf: change order of element-wise op in edge angle update calculations #4677

Uh oh!

caic99 commented Mar 28, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

coderabbitai bot commented Mar 28, 2025

Walkthrough

Changes

Suggested labels

Suggested reviewers

Chat

CodeRabbit Commands (Invoked using PR comments)

Other keywords and placeholders

CodeRabbit Configuration File (`.coderabbit.yaml`)

Documentation and Community

Uh oh!

codecov bot commented Mar 28, 2025 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

perf: change order of element-wise op in edge angle update calculations #4677

perf: change order of element-wise op in edge angle update calculations #4677

Uh oh!

Conversation

caic99 commented Mar 28, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull Request Overview

Reviewed Changes

Uh oh!

coderabbitai bot commented Mar 28, 2025

Walkthrough

Changes

Suggested labels

Suggested reviewers

Chat

CodeRabbit Commands (Invoked using PR comments)

Other keywords and placeholders

CodeRabbit Configuration File (.coderabbit.yaml)

Documentation and Community

Uh oh!

codecov bot commented Mar 28, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

caic99 commented Mar 28, 2025 •

edited by coderabbitai bot

Loading

CodeRabbit Configuration File (`.coderabbit.yaml`)

codecov bot commented Mar 28, 2025 •

edited

Loading