[Optimization]: Use dynamic HIP kernel block sizes

[zacharyvincze]

PR Description

• Adds a helper function to determine block sizes (and wavefront sizes) dynamically based on the kernel being launched. Avoids hard-coded block sizes to ensure optimal performance across different GPU architectures.
• Refactors existing operators to use the new helper function, if applicable to that operator.

Notes

• For 2D block sizes, the x dimension is always set to the queried wavefront size of the device. The y-dimension is determined based on the wavefront size (x dimension) and the maximum occupancy block size reported by the HIP runtime.

[Copilot]

Pull request overview

This PR introduces dynamic HIP kernel block size determination to optimize performance across different GPU architectures. It adds helper functions GetMaximumPotentialBlockSize2D and GetGridSize2D to replace hardcoded block sizes throughout the codebase.

Changes:

• Added GetMaximumPotentialBlockSize2D and GetGridSize2D helper functions in include/core/detail/hip_utils.hpp
• Refactored 14 operator files to use dynamic block sizes instead of hardcoded values
• Cleaned up unused includes and reorganized some headers

Reviewed changes

Copilot reviewed 20 out of 20 changed files in this pull request and generated 3 comments.

Show a summary per file

File	Description
include/core/detail/hip_utils.hpp	Adds helper functions for dynamic 2D block size calculation using HIP occupancy API
include/kernels/host/bnd_box_host.hpp	Adds missing math_vector.hpp include
include/kernels/device/bnd_box_device.hpp	Adds missing math_vector.hpp include
src/op_warp_perspective.cpp	Replaces hardcoded (64,16) block size with dynamic calculation
src/op_thresholding.cpp	Replaces hardcoded (64,16) block size with dynamic calculation per threshold type
src/op_rotate.cpp	Replaces hardcoded (32,16) block size with dynamic calculation
src/op_resize.cpp	Replaces hardcoded (64,16) block size with dynamic calculation; reformats function map
src/op_remap.cpp	Replaces hardcoded (64,16) block size with dynamic calculation
src/op_normalize.cpp	Replaces hardcoded (32,8) block size with dynamic calculation; reformats line breaks
src/op_non_max_suppression.cpp	Removes unused include (no block size changes as this uses 1D blocks)
src/op_histogram.cpp	Removes unused includes (no block size changes)
src/op_gamma_contrast.cpp	Replaces hardcoded (64,16) block size with dynamic calculation
src/op_flip.cpp	Replaces hardcoded (64,16) block size with dynamic calculation
src/op_cvt_color.cpp	Replaces hardcoded (32,16) block size with dynamic calculation per color conversion type
src/op_custom_crop.cpp	Replaces hardcoded (64,16) block size with dynamic calculation
src/op_copy_make_border.cpp	Replaces hardcoded (64,16) block size with dynamic calculation
src/op_convert_to.cpp	Replaces hardcoded (64,16) block size with dynamic calculation; reformats function signatures
src/op_composite.cpp	Replaces hardcoded (64,16) block size with dynamic calculation
src/op_bnd_box.cpp	Replaces hardcoded (32,32) block size with dynamic calculation
src/op_bilateral_filter.cpp	Replaces hardcoded (8,8) block size with dynamic calculation

---

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

[codecov-commenter]

Codecov Report

❌ Patch coverage is 91.45299% with 10 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
src/op_thresholding.cpp	75.00%	5 Missing ⚠️
include/core/detail/hip_utils.hpp	81.82%	0 Missing and 2 partials ⚠️
src/op_cvt_color.cpp	94.87%	2 Missing ⚠️
src/op_normalize.cpp	75.00%	0 Missing and 1 partial ⚠️

Additional details and impacted files

@@             Coverage Diff             @@
##           develop     #122      +/-   ##
===========================================
+ Coverage    73.51%   73.56%   +0.05%     
===========================================
  Files           77       77              
  Lines         2956     2996      +40     
  Branches       640      642       +2     
===========================================
+ Hits          2173     2204      +31     
- Misses         338      345       +7     
- Partials       445      447       +2     

Files with missing lines	Coverage Δ
include/kernels/host/bnd_box_host.hpp	94.44% <ø> (ø)
src/op_bilateral_filter.cpp	71.15% <100.00%> (ø)
src/op_bnd_box.cpp	78.62% <100.00%> (ø)
src/op_composite.cpp	54.02% <100.00%> (ø)
src/op_convert_to.cpp	77.22% <100.00%> (ø)
src/op_copy_make_border.cpp	70.31% <100.00%> (-0.46%)	⬇️
src/op_custom_crop.cpp	75.47% <100.00%> (ø)
src/op_flip.cpp	81.82% <100.00%> (ø)
src/op_gamma_contrast.cpp	64.29% <100.00%> (ø)
src/op_histogram.cpp	70.79% <ø> (ø)
... and 9 more

🚀 New features to boost your workflow:

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

[jeffqjiangNew]

Update (c) year to 2026 here and other places.

[simonCatBot]

Review: [Optimization] Dynamic HIP kernel block sizes

Performance optimization for GPU kernel launches:

What's changed:

• Dynamic block size determination based on device capabilities
• Wavefront size queries for optimal occupancy
• Refactored 20 operators to use new helper

Assessment: APPROVED - Performance improvement with no API changes.

Already approved, this is a solid optimization. Removing hard-coded block sizes improves portability across different GPU architectures (MI series, RDNA, etc.). The approach of querying wavefront size at runtime is the right way to handle this.

Nice cleanup of magic numbers throughout the codebase.