armv8.4 bf16 convolution im2col-gemm optimization

[nihui]

No description provided.

[nihui]

@codex review

[tencent-adm]

Thank you for your submission, we really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 93.80%. Comparing base (ef9eb9d) to head (f6fc658).
⚠️ Report is 3 commits behind head on master.

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #6715      +/-   ##
==========================================
- Coverage   93.86%   93.80%   -0.07%     
==========================================
  Files         932      931       -1     
  Lines      307558   309894    +2336     
==========================================
+ Hits       288694   290697    +2003     
- Misses      18864    19197     +333     

☔ 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.

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. What shall we delve into next?

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[Copilot]

Pull request overview

This PR refactors ARM im2col+GEMM convolution support to better integrate armv8.4 BF16 runtime-optimized code paths while consolidating shared packing/im2col helpers into the FP16 implementation header.

Changes:

• Moved/renamed the FP16 pack-A and im2col input-tile helpers into convolution_im2col_gemm_fp16s.h and updated call sites to use the new *_fp16 names.
• Deleted the now-redundant convolution_im2col_gemm_bf16s_fp16s.h header and removed its includes.
• Added convolution_arm_bf16.cpp to provide BF16 arch-opt wrapper symbols used by BF16 im2col+GEMM runtime dispatch.

Reviewed changes

Copilot reviewed 5 out of 6 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
src/layer/arm/convolution_im2col_gemm_fp16s.h	Adds FP16 pack/im2col tile helpers and updates internal call sites to the new helper names.
src/layer/arm/convolution_im2col_gemm_bf16s_fp16s.h	Removes the redundant header after consolidation.
src/layer/arm/convolution_arm.cpp	Drops the removed header include.
src/layer/arm/convolution_arm_asimdhp.cpp	Drops the removed header include (FP16 path now self-contained via convolution_im2col_gemm_fp16s.h).
src/layer/arm/convolution_arm_bf16.cpp	Adds armv8.4 BF16 arch-opt wrappers to satisfy BF16 runtime-dispatch symbols.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[nihui]

@codex review

[Copilot]

Pull request overview

Copilot reviewed 6 out of 7 changed files in this pull request and generated no new comments.

[chatgpt-codex-connector]

Codex Review: Didn't find any major issues. More of your lovely PRs please.

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".