dtourolleandClaude Opus 5
c1155cb607
The per-film annex was folded in after the gallery multiply by a host-side
cosine loop over a vector of {embedding, actor} structs, justified in-comment
by "tens of embeddings". AR-018/AR-019 retired that assumption: every owned
track promotes, so the annex grows with cast size and film length.
TrackGallery now holds it as a contiguous row-major matrix with a parallel
actor index — the flat_emb_/flat_actor_ shape the baked gallery already uses —
and hands newly promoted rows to the matcher once per frame. The matcher pushes
them into the similarity engine's resident matrix through a new
ISimilarityEngine::append_rows, so one SGEMM covers baked and promoted
references alike and best-of-N is a single pass over one similarity column.
Capacity doubles on overflow, and the GPU backends grow device-to-device, so a
promotion never re-uploads the gallery across the bus.
Absorbing promotions runs once per frame, after every face has been scored.
Appending mid-frame would invalidate the similarity pointer the chunk loop is
still reading, and it also removes an incidental dependence on face order
within a frame — a promotion helps subsequent frames, never the one that
produced it, which is the semantics the expansion store already documented.
OpenBLAS becomes a requirement of the CPU GEMM backend rather than an
opportunistic upgrade. That path is what CI and the cpu builder image run, so
falling back to the scalar loop in silence meant AR-027 could be measured — or
believed — on a kernel no release uses. The loop survives as the correctness
oracle the BLAS backends are diffed against, behind SAE_ALLOW_SCALAR_GEMM.
Call site 3, the deferred TBI pass, is untouched: it does not exist until
AR-020, so AR-026 stays In Progress.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
TRACES: AR-026 | UT-004, UT-005 | SR-001
80 lines
3.4 KiB
CMake
80 lines
3.4 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_face_detector_node.cpp
|
|
test_scene_detector_node.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})
|
|
elseif(NOT SAE_ALLOW_SCALAR_GEMM)
|
|
# Same rule as the CPU backend itself: testing the scalar loop while the
|
|
# shipped CPU path is OpenBLAS means the suite is not evidence about the
|
|
# kernel that runs.
|
|
message(FATAL_ERROR
|
|
"OpenBLAS not found, and the unit tests compile the CPU GEMM kernel "
|
|
"(AR-026). Install openblas-devel, or pass -DSAE_ALLOW_SCALAR_GEMM=ON "
|
|
"to test the scalar fallback deliberately.")
|
|
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)
|