225 lines
9.4 KiB
CMake
225 lines
9.4 KiB
CMake
# SPDX-License-Identifier: BSD-2-Clause
|
|
#
|
|
# daedalus-decoder — frame-level GPU H.264 decoder for V3D7 (Pi 5).
|
|
# Phase 1 scaffold; see DESIGN.md for architecture.
|
|
#
|
|
# Build dependencies:
|
|
# - daedalus-fourier ≥ 0.1.0 (kernel pack, V3D primitives + recipe layer)
|
|
# resolved via pkg-config; install via the daedalus-fourier upstream
|
|
# `cmake --install` rule (PR #5 made the .pc relocatable, so any
|
|
# install prefix works as long as $PKG_CONFIG_PATH is set).
|
|
# - Vulkan headers + libvulkan (pulled in transitively via
|
|
# daedalus-fourier, listed here explicitly for the link order).
|
|
#
|
|
# Build:
|
|
# cmake -B build -G Ninja -DCMAKE_BUILD_TYPE=Release
|
|
# cmake --build build
|
|
# ctest --test-dir build
|
|
|
|
cmake_minimum_required(VERSION 3.20)
|
|
project(daedalus-decoder
|
|
VERSION 0.0.1
|
|
DESCRIPTION "Frame-level GPU H.264 decoder for Raspberry Pi 5 / V3D7"
|
|
LANGUAGES C)
|
|
|
|
set(CMAKE_C_STANDARD 11)
|
|
set(CMAKE_C_STANDARD_REQUIRED ON)
|
|
set(CMAKE_C_EXTENSIONS OFF)
|
|
|
|
if(NOT CMAKE_BUILD_TYPE)
|
|
set(CMAKE_BUILD_TYPE Release)
|
|
endif()
|
|
|
|
# Pi 5 is the only supported target. Other aarch64 SoCs (Pi 4 V3D4,
|
|
# RK3588 Mali, …) might work but would need explicit substrate +
|
|
# shader-pack validation per the daedalus-fourier architecture
|
|
# backlog. Don't pretend to support what we haven't validated.
|
|
if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64")
|
|
message(WARNING
|
|
"daedalus-decoder is designed for aarch64 (Pi 5 BCM2712 / V3D7). "
|
|
"Build will proceed but is unlikely to function.")
|
|
endif()
|
|
|
|
add_compile_options(-Wall -Wextra -Wno-unused-parameter)
|
|
|
|
# ---- Dependencies --------------------------------------------------
|
|
|
|
find_package(PkgConfig REQUIRED)
|
|
|
|
# daedalus-fourier — find_package via pkg-config per the Phase 1
|
|
# decision §9.6. Minimum version 0.1.0 (the cycle 6-9 shaders + pool
|
|
# + recipe-flip baseline). PKG_CONFIG_PATH should point at the
|
|
# directory holding daedalus-fourier.pc (e.g. /usr/local/lib/pkgconfig
|
|
# or a custom install prefix).
|
|
pkg_check_modules(DAEDALUS_FOURIER REQUIRED daedalus-fourier>=0.1.0)
|
|
|
|
# Vulkan — daedalus-fourier already depends on this; we add it
|
|
# explicitly so the link order stays correct (daedalus-fourier static
|
|
# archive contains undefined vk* symbols that the loader resolves).
|
|
find_package(Vulkan REQUIRED)
|
|
|
|
# ---- Version string baked into the library ------------------------
|
|
|
|
# git rev tagged onto the version string for traceability; degrades
|
|
# gracefully to bare semver if git isn't available.
|
|
execute_process(
|
|
COMMAND git -C ${CMAKE_CURRENT_SOURCE_DIR} rev-parse --short=7 HEAD
|
|
OUTPUT_VARIABLE DAEDALUS_DECODER_GITREV
|
|
OUTPUT_STRIP_TRAILING_WHITESPACE
|
|
ERROR_QUIET)
|
|
if(DAEDALUS_DECODER_GITREV)
|
|
set(DAEDALUS_DECODER_VERSION "${PROJECT_VERSION}+g${DAEDALUS_DECODER_GITREV}")
|
|
else()
|
|
set(DAEDALUS_DECODER_VERSION "${PROJECT_VERSION}")
|
|
endif()
|
|
message(STATUS "daedalus-decoder version: ${DAEDALUS_DECODER_VERSION}")
|
|
|
|
# ---- Library ------------------------------------------------------
|
|
|
|
add_library(daedalus_decoder STATIC
|
|
src/daedalus_decoder.c
|
|
)
|
|
target_include_directories(daedalus_decoder
|
|
PUBLIC
|
|
$<BUILD_INTERFACE:${CMAKE_CURRENT_SOURCE_DIR}/include>
|
|
$<INSTALL_INTERFACE:include>
|
|
PRIVATE
|
|
src
|
|
${DAEDALUS_FOURIER_INCLUDE_DIRS}
|
|
)
|
|
target_link_directories(daedalus_decoder
|
|
PUBLIC
|
|
${DAEDALUS_FOURIER_LIBRARY_DIRS}
|
|
)
|
|
target_link_libraries(daedalus_decoder
|
|
PUBLIC
|
|
# Order matters: daedalus-fourier static archive references
|
|
# vulkan symbols; the loader needs daedalus-fourier first then
|
|
# vulkan to resolve them.
|
|
${DAEDALUS_FOURIER_LIBRARIES}
|
|
Vulkan::Vulkan
|
|
)
|
|
target_compile_definitions(daedalus_decoder
|
|
PRIVATE
|
|
DAEDALUS_DECODER_VERSION="${DAEDALUS_DECODER_VERSION}"
|
|
)
|
|
target_compile_options(daedalus_decoder PRIVATE -O2)
|
|
|
|
# ---- Smoke test ---------------------------------------------------
|
|
|
|
enable_testing()
|
|
|
|
add_executable(test_smoke tests/test_smoke.c)
|
|
target_link_libraries(test_smoke PRIVATE daedalus_decoder)
|
|
target_compile_options(test_smoke PRIVATE -O2)
|
|
add_test(NAME smoke COMMAND test_smoke)
|
|
|
|
add_executable(test_idct_bitexact tests/test_idct_bitexact.c)
|
|
target_link_libraries(test_idct_bitexact PRIVATE daedalus_decoder)
|
|
target_compile_options(test_idct_bitexact PRIVATE -O2)
|
|
|
|
# 320x240 QVGA — fast inner-loop test (300 MBs, sub-second).
|
|
add_test(NAME idct_bitexact COMMAND test_idct_bitexact)
|
|
|
|
# Same QVGA test re-run on the CPU NEON path (forces fallback even on
|
|
# V3D7 hosts). Catches silent drift between the V3D shader and the
|
|
# NEON reference path — both must produce identical output for the
|
|
# same coefficient input. Also keeps the bit-exact gate alive on
|
|
# hosts without V3D7 (CI runners, x86 dev boxes).
|
|
add_test(NAME idct_bitexact_cpu COMMAND test_idct_bitexact 320 240
|
|
0xfeedface5a5a5a5a cpu)
|
|
|
|
# 1920x1088 1080p — deployment-scale test (8160 MBs, ~0.25 s on hertz).
|
|
# Validates the per-MB block index + pixel offset math at full coded
|
|
# height (1088, not 1080 — see daedalus_decoder.h on H.264 coded vs
|
|
# displayed dims). Cheap enough to run unconditionally; if it ever
|
|
# gets slow we'll split into a CTest LABEL for opt-in.
|
|
add_test(NAME idct_bitexact_1080p COMMAND test_idct_bitexact 1920 1088)
|
|
|
|
# ---- Stage 2 PR-b deblock smoke ------------------------------------
|
|
#
|
|
# Validates flush_frame's per-frame deblock dispatch (luma + chroma,
|
|
# V + H, bS<4 + bS=4 intra — up to 8 dispatches added after IDCT).
|
|
# Strategy: same input through substrate=CPU and substrate=QPU, assert
|
|
# byte-exact match (transitive bit-exact gate — daedalus-fourier's own
|
|
# test_api_h264 already validates each substrate against a C reference,
|
|
# so CPU-QPU equivalence here means both match the spec). Plus an
|
|
# anti-no-op check: run a third pass with edges removed and assert
|
|
# different output, proving deblock actually ran.
|
|
add_executable(test_deblock_smoke tests/test_deblock_smoke.c)
|
|
target_link_libraries(test_deblock_smoke PRIVATE daedalus_decoder)
|
|
target_compile_options(test_deblock_smoke PRIVATE -O2)
|
|
add_test(NAME deblock_smoke COMMAND test_deblock_smoke)
|
|
|
|
# ---- Benchmarks (not gated by ctest) ------------------------------
|
|
#
|
|
# Build-time only; user runs them by hand when checking perf. Adding
|
|
# them as ctest would make every CI run slow and the numbers would
|
|
# get drowned in pass/fail noise. See the header of each .c for what
|
|
# they measure.
|
|
|
|
add_executable(bench_flush_frame tests/bench_flush_frame.c)
|
|
target_link_libraries(bench_flush_frame PRIVATE daedalus_decoder)
|
|
target_compile_options(bench_flush_frame PRIVATE -O2)
|
|
|
|
# ---- Tools (not gated by ctest; opt-in via DAEDALUS_BUILD_TOOLS) ----
|
|
#
|
|
# daedalus_decode_h264 — option A standalone test harness that
|
|
# wraps libavcodec + daedalus-decoder and bit-exact-compares their
|
|
# outputs on real H.264 streams. Identity-passthrough mode in this
|
|
# first iteration (predicted = AVFrame pixels, coeffs = 0, no
|
|
# deblock edges); follow-up PRs use the per-MB inspection callback
|
|
# (marfrit-packages patch 0016) to feed REAL per-MB state.
|
|
#
|
|
# Requires libavcodec + libavformat headers + libs. Off by default
|
|
# so the standard ctest build doesn't pull in FFmpeg as a hard dep.
|
|
option(DAEDALUS_BUILD_TOOLS "Build daedalus-decoder CLI tools (requires libavcodec)" OFF)
|
|
if(DAEDALUS_BUILD_TOOLS)
|
|
# Optional path to a private FFmpeg install carrying the per-MB
|
|
# inspection callback (marfrit-packages patch 0016). When set,
|
|
# the CLI links against it instead of the system FFmpeg and the
|
|
# inspection-callback code path is compiled in.
|
|
set(DAEDALUS_FFMPEG_PREFIX "" CACHE PATH
|
|
"Path to a patched FFmpeg install (with 0016 mb-inspect-callback) for daedalus_decode_h264. Empty = use system pkg-config FFmpeg.")
|
|
|
|
if(DAEDALUS_FFMPEG_PREFIX)
|
|
message(STATUS "daedalus_decode_h264: patched FFmpeg at ${DAEDALUS_FFMPEG_PREFIX}")
|
|
set(FFMPEG_INCLUDE_DIRS ${DAEDALUS_FFMPEG_PREFIX}/include)
|
|
set(FFMPEG_LIBRARY_DIRS ${DAEDALUS_FFMPEG_PREFIX}/lib)
|
|
# Patched libavcodec is built static (no shared libs in the private prefix).
|
|
# System pull-ins are still needed for libav* dependencies.
|
|
set(FFMPEG_LIBRARIES
|
|
${DAEDALUS_FFMPEG_PREFIX}/lib/libavformat.a
|
|
${DAEDALUS_FFMPEG_PREFIX}/lib/libavcodec.a
|
|
${DAEDALUS_FFMPEG_PREFIX}/lib/libavutil.a
|
|
${DAEDALUS_FFMPEG_PREFIX}/lib/libswresample.a
|
|
m z pthread)
|
|
set(FFMPEG_CFLAGS_OTHER "-DDAEDALUS_HAVE_H264_MB_INSPECT_CB=1")
|
|
else()
|
|
pkg_check_modules(FFMPEG REQUIRED libavcodec libavformat libavutil)
|
|
message(STATUS "daedalus_decode_h264: system FFmpeg (no inspection callback)")
|
|
endif()
|
|
|
|
add_executable(daedalus_decode_h264 tools/daedalus_decode_h264.c)
|
|
target_link_libraries(daedalus_decode_h264
|
|
PRIVATE daedalus_decoder ${FFMPEG_LIBRARIES})
|
|
target_include_directories(daedalus_decode_h264
|
|
PRIVATE ${FFMPEG_INCLUDE_DIRS})
|
|
target_link_directories(daedalus_decode_h264
|
|
PRIVATE ${FFMPEG_LIBRARY_DIRS})
|
|
target_compile_options(daedalus_decode_h264
|
|
PRIVATE -O2 ${FFMPEG_CFLAGS_OTHER})
|
|
endif()
|
|
|
|
# ---- Install ------------------------------------------------------
|
|
#
|
|
# Library + public header. Stage 2/3 will add a pkg-config file and
|
|
# CMake config exports once the API stabilises; pre-0.1 the scaffold
|
|
# install just gives the static archive a home.
|
|
|
|
include(GNUInstallDirs)
|
|
install(TARGETS daedalus_decoder
|
|
ARCHIVE DESTINATION ${CMAKE_INSTALL_LIBDIR})
|
|
install(FILES include/daedalus_decoder.h
|
|
DESTINATION ${CMAKE_INSTALL_INCLUDEDIR})
|