Skip to content

Add SVE2 Haar detection optimization#470

Merged
ermig1979 merged 1 commit into
devfrom
cursor/sve2-haar-detect-7746
Jun 18, 2026
Merged

Add SVE2 Haar detection optimization#470
ermig1979 merged 1 commit into
devfrom
cursor/sve2-haar-detect-7746

Conversation

@ermig1979

@ermig1979 ermig1979 commented Jun 18, 2026

Copy link
Copy Markdown
Owner

Summary

  • Add SVE2 implementation of SimdDetectionHaarDetect32fp.
  • Dispatch the public Haar 32fp detector to SVE2 on capable ARM/ARM64 builds.
  • Add SVE2 coverage to DetectionHaarDetect32fpAutoTest and update Visual Studio SVE2 project files.
  • Document the new optimization in release 7.2.163 notes.

Verification

  • aarch64-linux-gnu-g++ -march=armv9-a+sve2 -msve-vector-bits=scalable -std=c++11 -I./src -fsyntax-only src/Simd/SimdSve2Detection.cpp
  • aarch64-linux-gnu-g++ -march=armv9-a+sve2 -msve-vector-bits=scalable -std=c++11 -I./src -fsyntax-only src/Simd/SimdLib.cpp
  • cmake ./prj/cmake -B build -DCMAKE_BUILD_TYPE=Release -DCMAKE_CXX_COMPILER=g++ -DCMAKE_C_COMPILER=gcc -DSIMD_TOOLCHAIN="g++" -DSIMD_TARGET="" -DSIMD_AVX512VNNI=ON -DSIMD_AMXBF16=ON -DSIMD_TEST_FLAGS="-march=native" -DSIMD_SHARED=ON
  • cmake --build build --parallel$(nproc)
  • export LD_LIBRARY_PATH="$(pwd):$LD_LIBRARY_PATH" && ./Test "-r=.." -fi=DetectionHaarDetect32fp -tt=1 -ts=1
Open in Web Open in Cursor 

Co-authored-by: Ihar Yermalayeu <ermig1979@gmail.com>
@ermig1979 ermig1979 marked this pull request as ready for review June 18, 2026 09:38
@ermig1979 ermig1979 merged commit c5de7c9 into dev Jun 18, 2026
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants