dtourolleandClaude Opus 5
6da8ac2bdb
The CPU path was a scalar triple loop. It is the correctness oracle for the GPU backends, but it is also what CI runs — there is no GPU on the N100 host — and since AR-003 removed the per-frame face cap, a crowded frame now scores many faces against a library-scale gallery. Scoring one face against 5000 embeddings is 2.6 MFLOP; in scalar that does not hold up (AR-027). S(g,f) viewed as row-major [n_faces x n_gallery] is exactly query * gallery^T, so the loop nest collapses into a single cblas_sgemm. OpenBLAS is optional in the build: found via pkg-config, and the scalar path remains when it is absent so no hard dependency is added and the two can be diffed when a similarity looks wrong. The configure step warns rather than failing, since a developer without it should still get a working tree. The test target links it too. Without that the suite compiles the scalar fallback while the builder image ships CBLAS, so CI would be verifying a kernel that is not the one running in production — the same class of mistake as testing a path the gate never executes. Recorded as required (not optional) in the DP-007 image, for the same reason. Suite: 92 cases, 6136 assertions, with CBLAS compiled in. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> TRACES: AR-026, AR-027, DP-007 | SR-001
70 lines
2.9 KiB
CMake
70 lines
2.9 KiB
CMake
# ── Unit tests ────────────────────────────────────────────────────────────────
|
|
# Pure, GPU-free, model-free tests. The similarity tests compile the GEMM backend
|
|
# directly with SAE_GEMM_CPU so the suite builds and runs on a machine without a
|
|
# GPU regardless of the main build's SAE_GEMM_BACKEND selection.
|
|
|
|
find_package(Catch2 3 QUIET)
|
|
if(NOT Catch2_FOUND)
|
|
include(FetchContent)
|
|
FetchContent_Declare(
|
|
Catch2
|
|
GIT_REPOSITORY https://github.com/catchorg/Catch2.git
|
|
GIT_TAG v3.5.3
|
|
)
|
|
FetchContent_MakeAvailable(Catch2)
|
|
endif()
|
|
|
|
add_executable(sae_tests
|
|
test_similarity.cpp
|
|
test_calibration.cpp
|
|
test_gallery_store.cpp
|
|
test_face_utils.cpp
|
|
test_track_gallery.cpp
|
|
test_face_tracker.cpp
|
|
test_track_registry.cpp
|
|
test_replay_fixtures.cpp
|
|
test_audio_signature.cpp
|
|
${CMAKE_SOURCE_DIR}/src/backends/gemm_backend.cpp
|
|
${CMAKE_SOURCE_DIR}/src/gallery/gallery_store.cpp
|
|
${CMAKE_SOURCE_DIR}/src/audio_signature.cpp
|
|
${CMAKE_SOURCE_DIR}/src/gallery/embedder_stamp.cpp
|
|
)
|
|
target_include_directories(sae_tests PRIVATE ${CMAKE_SOURCE_DIR}/src)
|
|
# SAE_GEMM_CPU: build the CPU reference GEMM regardless of the main backend.
|
|
# SAE_MODELS_DIR: config.hpp (pulled in by track_gallery.hpp) bakes model paths.
|
|
# SAE_TEST_FIXTURES_DIR: the audio golden vector is read from the source tree,
|
|
# not copied, so the file the plugin repo shares is the file under test.
|
|
# AR-026/AR-027: exercise the same kernel CI actually runs. Without this the
|
|
# suite compiles the scalar fallback while the CPU builder image links OpenBLAS,
|
|
# so the tested path and the shipped path would differ.
|
|
find_package(PkgConfig QUIET)
|
|
if(PkgConfig_FOUND)
|
|
pkg_check_modules(OPENBLAS_T QUIET openblas)
|
|
endif()
|
|
if(OPENBLAS_T_FOUND)
|
|
target_include_directories(sae_tests PRIVATE ${OPENBLAS_T_INCLUDE_DIRS})
|
|
target_link_libraries(sae_tests PRIVATE ${OPENBLAS_T_LINK_LIBRARIES})
|
|
endif()
|
|
|
|
target_compile_definitions(sae_tests PRIVATE
|
|
$<$<BOOL:${OPENBLAS_T_FOUND}>:SAE_GEMM_CBLAS>
|
|
SAE_GEMM_CPU
|
|
SAE_MODELS_DIR="${SAE_MODELS_DIR}"
|
|
SAE_TEST_FIXTURES_DIR="${CMAKE_CURRENT_SOURCE_DIR}/fixtures")
|
|
# gallery_store.cpp + gallery_calibration.hpp use nlohmann/json and HDF5
|
|
# (galleries are HDF5-native, see src/gallery/gallery_store.cpp); face_utils.hpp
|
|
# and the calibration GEMM pull in OpenCV (calib3d/imgproc/core) via types.hpp.
|
|
# ffmpeg_libs: audio_signature.cpp decodes the golden fixture (avformat/avcodec/
|
|
# avutil/swresample). Still GPU-free — the audio path is pure CPU.
|
|
target_link_libraries(sae_tests PRIVATE
|
|
Catch2::Catch2WithMain
|
|
nlohmann_json::nlohmann_json
|
|
ffmpeg_libs
|
|
${OpenCV_LIBS}
|
|
${HDF5_CXX_LIBRARIES})
|
|
target_include_directories(sae_tests PRIVATE ${HDF5_INCLUDE_DIRS})
|
|
|
|
include(CTest)
|
|
include(Catch)
|
|
catch_discover_tests(sae_tests)
|