Lrn ref fix

[pfultz2]

Motivation

LRN ref version does produce correct values when size <= 4.

Technical Details

The scale was set to zero outside of the loop, which was incorrect.

Changelog Category

• • Added: New functionality.
• • Changed: Changes to existing functionality.
• • Removed: Functionality or support that has been removed. (Compared to a previous release)
• • Optimized: Component performance that has been optimized or improved.
• • Resolved Issues: Known issues from a previous version that have been resolved.
• • Not Applicable: This PR is not to be included in the changelog.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

Additional details and impacted files

@@           Coverage Diff            @@
##           develop    #4370   +/-   ##
========================================
  Coverage    92.26%   92.26%           
========================================
  Files          560      560           
  Lines        26358    26358           
========================================
  Hits         24319    24319           
  Misses        2039     2039           

Files with missing lines	Coverage Δ
src/targets/ref/lowering.cpp	94.66% <100.00%> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

[Copilot]

Pull Request Overview

This PR fixes a bug in the Local Response Normalization (LRN) reference implementation where incorrect values were produced when the LRN size was <= 4. The fix involves moving the scale variable initialization inside the channel loop and improving numerical precision.

• Moved scale variable initialization from outside to inside the channel loop to ensure correct per-channel computation
• Changed data types from float to double for better numerical precision
• Replaced std::pow(x, 2) with direct multiplication (x * x) for performance
• Added test cases for smaller LRN sizes (3 and 4) to prevent regression

Reviewed Changes

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

File	Description
src/targets/ref/lowering.cpp	Fixed LRN scale computation bug and improved numerical precision
test/verify/test_lrn.cpp	Added test coverage for smaller LRN sizes that were previously failing

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}