marfrit/daedalus-fourier
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

h264: V3D shaders for all 15 avg_ qpel positions — qpel QPU complete

Browse Source 
Generates 15 avg_ shader variants by templating from the existing
put_ shaders.  Each avg_ shader is identical to its put_ sibling
except the final write does an L2 average with the existing dst:

  put_:  dst[r,c] = result
  avg_:  dst[r,c] = (dst[r,c] + result + 1) >> 1

Per H.264 §8.4.2.3.1 (B-slice biprediction): caller pre-loads dst
with the list0 prediction; the avg_ call folds in list1.

Generated via python (avg-shader-gen.py): reads each
v3d_h264_qpel_mcXY.comp, transforms the docstring header + final
write hunk, writes v3d_h264_qpel_avg_mcXY.comp.  ~88 lines each;
15 new shader files.

Dispatch reuses the existing dispatch_h264_qpel_diag_qpu helper for
all 15 — same src envelope (10*stride+11 covers any (r±1, c±1)
shift), the L2 step only touches dst.  Slightly over-allocates for
the simpler positions (avg_mc20/02/10/30/01/03) but negligible
cost.  Eliminates 15 wrappers + 15 src_max bound calculations that
would otherwise duplicate.

CMake foreach loops compile + install 15 new SPV files.  ctx grows
15 pipeline pairs.  Recipe table flips DAEDALUS_KERNEL_H264_QPEL_AVG_*
from CPU to QPU.  Public dispatchers re-defined via the existing
DEFINE_QPEL_DIAG_PUBLIC macro (replaces the CPU-only
DEFINE_QPEL_DISPATCH instantiations).

Verified on hertz:

  $ ./build/test_api_h264 | grep "qpel avg" | wc -l
  15
  $ ./build/test_api_h264 | grep "qpel avg" | grep -c "100.0000%"
  15

All 15 PASS 2048/2048 bytes bit-exact via QPU.

QPU coverage for the H.264 8-bit 4:2:0 hot-path pixel kernels:

  Layer                Coverage
  ─────────────────────────────────────────────────────────────
  IDCT 4x4 luma        ✓ cycle 6 (one QPU shader, also handles chroma)
  IDCT 8x8 luma        ✓ cycle 7
  Chroma DC Hadamard   CPU only (4 adds + 4 subs; not worth)
  Deblock luma_v       ✓ cycle 8
  Deblock luma_h       ✓ PR #28
  Deblock chroma_v/h   ✓ PR #29
  Deblock *_intra      CPU only (less common, structurally different)
  qpel put_ 15 pos     ✓ cycle 9 (mc20) + PRs #30-#33
  qpel avg_ 15 pos     ✓ THIS PR

The H.264 non-intra-deblock hot path is now FULLY on QPU for any
consumer that initialises daedalus with a QPU-capable context.
This commit is contained in:
Claude (noether)
2026-05-25 20:22:33 +02:00
parent 55d3618408
commit 2079fe39c6
17 changed files with 1360 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CMakeLists.txt
+33 -1
View File
@@ -389,7 +389,24 @@ if (DAEDALUS_BUILD_VULKAN)
set(H264_QPEL_${_mc}_SPV ${_spv})
endforeach()
add_custom_target(daedalus_shaders ALL DEPENDS ${NOOP_SPV} ${IDCT8_SPV} ${LPF_SPV} ${MC_SPV} ${LPF8_SPV} ${CDEF_SPV} ${H264DEBLOCK_SPV} ${H264DEBLOCK_H_SPV} ${H264DEBLOCK_CHROMA_V_SPV} ${H264DEBLOCK_CHROMA_H_SPV} ${H264_IDCT4_SPV} ${H264_IDCT8_SPV} ${H264_QPEL_MC20_SPV} ${H264_QPEL_MC02_SPV} ${H264_QPEL_MC22_SPV} ${H264_QPEL_mc10_SPV} ${H264_QPEL_mc30_SPV} ${H264_QPEL_mc01_SPV} ${H264_QPEL_mc03_SPV} ${H264_QPEL_mc11_SPV} ${H264_QPEL_mc12_SPV} ${H264_QPEL_mc13_SPV} ${H264_QPEL_mc21_SPV} ${H264_QPEL_mc23_SPV} ${H264_QPEL_mc31_SPV} ${H264_QPEL_mc32_SPV} ${H264_QPEL_mc33_SPV})
# avg_ biprediction variants — same shader as put_ + extra L2 with
# existing dst. All 15 useful positions.
foreach(_mc mc20 mc02 mc22 mc10 mc30 mc01 mc03
mc11 mc12 mc13 mc21 mc23 mc31 mc32 mc33)
set(_spv ${CMAKE_BINARY_DIR}/v3d_h264_qpel_avg_${_mc}.spv)
add_custom_command(
OUTPUT ${_spv}
COMMAND ${GLSLANG_VALIDATOR} -V --target-env vulkan1.3
-o ${_spv}
${CMAKE_SOURCE_DIR}/src/v3d_h264_qpel_avg_${_mc}.comp
DEPENDS ${CMAKE_SOURCE_DIR}/src/v3d_h264_qpel_avg_${_mc}.comp
COMMENT "glslang: v3d_h264_qpel_avg_${_mc}.comp -> .spv"
VERBATIM
)
set(H264_QPEL_avg_${_mc}_SPV ${_spv})
endforeach()
add_custom_target(daedalus_shaders ALL DEPENDS ${NOOP_SPV} ${IDCT8_SPV} ${LPF_SPV} ${MC_SPV} ${LPF8_SPV} ${CDEF_SPV} ${H264DEBLOCK_SPV} ${H264DEBLOCK_H_SPV} ${H264DEBLOCK_CHROMA_V_SPV} ${H264DEBLOCK_CHROMA_H_SPV} ${H264_IDCT4_SPV} ${H264_IDCT8_SPV} ${H264_QPEL_MC20_SPV} ${H264_QPEL_MC02_SPV} ${H264_QPEL_MC22_SPV} ${H264_QPEL_mc10_SPV} ${H264_QPEL_mc30_SPV} ${H264_QPEL_mc01_SPV} ${H264_QPEL_mc03_SPV} ${H264_QPEL_mc11_SPV} ${H264_QPEL_mc12_SPV} ${H264_QPEL_mc13_SPV} ${H264_QPEL_mc21_SPV} ${H264_QPEL_mc23_SPV} ${H264_QPEL_mc31_SPV} ${H264_QPEL_mc32_SPV} ${H264_QPEL_mc33_SPV} ${H264_QPEL_avg_mc20_SPV} ${H264_QPEL_avg_mc02_SPV} ${H264_QPEL_avg_mc22_SPV} ${H264_QPEL_avg_mc10_SPV} ${H264_QPEL_avg_mc30_SPV} ${H264_QPEL_avg_mc01_SPV} ${H264_QPEL_avg_mc03_SPV} ${H264_QPEL_avg_mc11_SPV} ${H264_QPEL_avg_mc12_SPV} ${H264_QPEL_avg_mc13_SPV} ${H264_QPEL_avg_mc21_SPV} ${H264_QPEL_avg_mc23_SPV} ${H264_QPEL_avg_mc31_SPV} ${H264_QPEL_avg_mc32_SPV} ${H264_QPEL_avg_mc33_SPV})
# v3d_runner — reusable Vulkan plumbing.
add_library(v3d_runner STATIC src/v3d_runner.c)
@@ -542,6 +559,21 @@ if (DAEDALUS_BUILD_VULKAN)
${H264_QPEL_mc31_SPV}
${H264_QPEL_mc32_SPV}
${H264_QPEL_mc33_SPV}
${H264_QPEL_avg_mc20_SPV}
${H264_QPEL_avg_mc02_SPV}
${H264_QPEL_avg_mc22_SPV}
${H264_QPEL_avg_mc10_SPV}
${H264_QPEL_avg_mc30_SPV}
${H264_QPEL_avg_mc01_SPV}
${H264_QPEL_avg_mc03_SPV}
${H264_QPEL_avg_mc11_SPV}
${H264_QPEL_avg_mc12_SPV}
${H264_QPEL_avg_mc13_SPV}
${H264_QPEL_avg_mc21_SPV}
${H264_QPEL_avg_mc23_SPV}
${H264_QPEL_avg_mc31_SPV}
${H264_QPEL_avg_mc32_SPV}
${H264_QPEL_avg_mc33_SPV}
DESTINATION ${CMAKE_INSTALL_DATADIR}/daedalus-fourier/shaders
)
endif()