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

cycle 6: V3D shader for H.264 IDCT 4x4 (first cycle-6 QPU dispatch)

Browse Source 
Per the QPU-default substrate decree 2026-05-23, cycle 6 (H.264
IDCT 4x4 + add) was the highest-priority H.264 kernel to flip
from NEON-only to QPU-capable.  The same shape as VP9 IDCT 8x8
(cycle 1) — two-pass butterfly with shared-memory transpose —
but at 4x4 scale: 4 lanes per block, 16 blocks per WG.

What's added:

  - src/v3d_h264_idct4.comp: GLSL compute shader implementing
    the H.264 §8.5.12.1 1D butterfly twice (row pass then column
    pass), with (val + 32) >> 6 rounding and clip-to-u8 add to
    dst.  Block memory layout is column-major (matches FFmpeg
    `ff_h264_idct_add_neon` convention).

  - CMakeLists: glslang rule + install entry for v3d_h264_idct4.spv.

  - dispatch_h264_idct4_qpu() in daedalus_core.c: lazy pipeline
    init, 3 SSBOs (coeffs / dst / meta as uvec4), push-constant
    (n_blocks, dst_stride), 16 blocks per WG dispatch.  Matches
    the existing dispatch_*_qpu patterns; uses
    v3d_runner_create_buffer / destroy_buffer (will swap to
    pool API once PR #6 lands).

  - daedalus_dispatch_h264_idct4() replaces ROUTE_CPU_ONLY with
    the same CPU/QPU substrate switch the deblock dispatch uses.

  - daedalus_recipe_substrate_for(H264_IDCT4) returns QPU now
    that the shader exists.

Verification on hertz (Pi 5 + V3D 7.1):

  $ ./test_api_h264
  === Phase 8a API smoke: H.264 kernels via recipe dispatch ===
    H264_IDCT4 recipe substrate:      2 (1=CPU, 2=QPU)
    H264_IDCT8 recipe substrate:      1
    H264_DEBLOCK_LV recipe substrate: 2
    H264_QPEL_MC20 recipe substrate:  1
    H.264 IDCT 4x4: 2048/2048 bytes bit-exact (100.0000%)   ← QPU
    H.264 IDCT 8x8: 2048/2048 bytes bit-exact
    H.264 deblock luma v: 2048/2048 bytes bit-exact
    H.264 qpel mc20: 1024/1024 bytes bit-exact

The AUTO-substrate path now picks QPU for H.264 IDCT 4x4, and
the output is bit-exact against the C reference (which is
identical to the NEON .S code by construction — same FFmpeg
upstream).

Remaining cycle-6/7/9 work in task #165:
  - cycle 7: H.264 IDCT 8x8 (template same shape; 8 lanes per
    block, fewer blocks per WG)
  - cycle 9: H.264 luma qpel mc20 (different shape — 6-tap MC
    not a transform)

This commit lands the cycle-6 piece of task #165.
This commit is contained in:
Claude (noether)
2026-05-23 20:06:20 +02:00
parent 737e87980d
commit 65bd5c3fe3
3 changed files with 248 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
CMakeLists.txt
+13 -1
View File
@@ -284,7 +284,18 @@ if (DAEDALUS_BUILD_VULKAN)
VERBATIM
)
add_custom_target(daedalus_shaders ALL DEPENDS ${NOOP_SPV} ${IDCT8_SPV} ${LPF_SPV} ${MC_SPV} ${LPF8_SPV} ${CDEF_SPV} ${H264DEBLOCK_SPV})
set(H264_IDCT4_SPV ${CMAKE_BINARY_DIR}/v3d_h264_idct4.spv)
add_custom_command(
OUTPUT ${H264_IDCT4_SPV}
COMMAND ${GLSLANG_VALIDATOR} -V --target-env vulkan1.3
-o ${H264_IDCT4_SPV}
${CMAKE_SOURCE_DIR}/src/v3d_h264_idct4.comp
DEPENDS ${CMAKE_SOURCE_DIR}/src/v3d_h264_idct4.comp
COMMENT "glslang: v3d_h264_idct4.comp -> v3d_h264_idct4.spv"
VERBATIM
)
add_custom_target(daedalus_shaders ALL DEPENDS ${NOOP_SPV} ${IDCT8_SPV} ${LPF_SPV} ${MC_SPV} ${LPF8_SPV} ${CDEF_SPV} ${H264DEBLOCK_SPV} ${H264_IDCT4_SPV})
# v3d_runner — reusable Vulkan plumbing.
add_library(v3d_runner STATIC src/v3d_runner.c)
@@ -412,6 +423,7 @@ if (DAEDALUS_BUILD_VULKAN)
${LPF8_SPV}
${CDEF_SPV}
${H264DEBLOCK_SPV}
${H264_IDCT4_SPV}
DESTINATION ${CMAKE_INSTALL_DATADIR}/daedalus-fourier/shaders
)
endif()
src/daedalus_core.c
+106 -3
View File
@@ -40,6 +40,8 @@ struct daedalus_ctx {
v3d_pipeline cdef_pipe;
int h264deblock_pipe_ready;
v3d_pipeline h264deblock_pipe;
int h264_idct4_pipe_ready;
v3d_pipeline h264_idct4_pipe;
};
daedalus_ctx *daedalus_ctx_create(void)
@@ -94,6 +96,7 @@ void daedalus_ctx_destroy(daedalus_ctx *ctx)
if (ctx->mc8h_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->mc8h_pipe);
if (ctx->cdef_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->cdef_pipe);
if (ctx->h264deblock_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->h264deblock_pipe);
if (ctx->h264_idct4_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->h264_idct4_pipe);
v3d_runner_destroy(ctx->runner);
}
free(ctx);
@@ -118,7 +121,7 @@ daedalus_substrate daedalus_recipe_substrate_for(daedalus_kernel k)
case DAEDALUS_KERNEL_VP9_MC_8H: return DAEDALUS_SUBSTRATE_QPU; /* v3d_mc_8h.spv */
case DAEDALUS_KERNEL_VP9_LPF8_INNER: return DAEDALUS_SUBSTRATE_QPU;
case DAEDALUS_KERNEL_AV1_CDEF_8X8: return DAEDALUS_SUBSTRATE_QPU; /* v3d_cdef.spv */
case DAEDALUS_KERNEL_H264_IDCT4: return DAEDALUS_SUBSTRATE_CPU; /* TODO task #165 */
case DAEDALUS_KERNEL_H264_IDCT4: return DAEDALUS_SUBSTRATE_QPU; /* v3d_h264_idct4.spv */
case DAEDALUS_KERNEL_H264_IDCT8: return DAEDALUS_SUBSTRATE_CPU; /* TODO task #165 */
case DAEDALUS_KERNEL_H264_DEBLOCK_LV: return DAEDALUS_SUBSTRATE_QPU; /* v3d_h264deblock.spv */
case DAEDALUS_KERNEL_H264_QPEL_MC20: return DAEDALUS_SUBSTRATE_CPU; /* TODO task #165 */
@@ -743,6 +746,98 @@ fail:
return -1;
}
/* -------------------- H.264 IDCT 4x4 QPU dispatch (cycle 6) ----- */
typedef struct {
uint32_t n_blocks;
uint32_t dst_stride_u8;
uint32_t _pad0;
uint32_t _pad1;
} h264_idct4_pc;
static int dispatch_h264_idct4_qpu(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
int16_t *coeffs, size_t n_blocks,
const daedalus_h264_block_meta *meta)
{
if (!ctx->h264_idct4_pipe_ready) {
if (v3d_runner_create_pipeline(ctx->runner, "v3d_h264_idct4.spv",
3, sizeof(h264_idct4_pc),
&ctx->h264_idct4_pipe) != 0)
return -1;
ctx->h264_idct4_pipe_ready = 1;
}
size_t coeff_bytes = n_blocks * 16 * sizeof(int16_t);
size_t meta_bytes = n_blocks * 4 * sizeof(uint32_t); /* uvec4 per block */
size_t dst_max = 0;
for (size_t i = 0; i < n_blocks; i++) {
size_t e = meta[i].dst_off + (size_t) 3 * dst_stride + 4;
if (e > dst_max) dst_max = e;
}
v3d_buffer bc = {0}, bd = {0}, bm = {0};
if (v3d_runner_create_buffer(ctx->runner, coeff_bytes, &bc)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_max, &bd)) {
v3d_runner_destroy_buffer(ctx->runner, &bc); return -1;
}
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &bm)) {
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bc); return -1;
}
memcpy(bc.mapped, coeffs, coeff_bytes);
memcpy(bd.mapped, dst, dst_max);
uint32_t *m = bm.mapped;
for (size_t i = 0; i < n_blocks; i++) {
m[4*i+0] = meta[i].dst_off;
m[4*i+1] = 0;
m[4*i+2] = 0;
m[4*i+3] = 0;
}
v3d_buffer binds[3] = { bc, bd, bm };
if (v3d_runner_bind_buffers(ctx->runner, &ctx->h264_idct4_pipe, binds, 3))
goto fail;
uint32_t wg_count = (uint32_t)((n_blocks + 15) / 16); /* 16 blocks/WG */
h264_idct4_pc pc = {
.n_blocks = (uint32_t) n_blocks,
.dst_stride_u8 = (uint32_t) dst_stride,
};
VkCommandBuffer cb = v3d_runner_alloc_cmdbuf(ctx->runner);
if (cb == VK_NULL_HANDLE) goto fail;
VkCommandBufferBeginInfo cbbi = { .sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO };
vkBeginCommandBuffer(cb, &cbbi);
vkCmdBindPipeline(cb, VK_PIPELINE_BIND_POINT_COMPUTE,
ctx->h264_idct4_pipe.pipeline);
vkCmdBindDescriptorSets(cb, VK_PIPELINE_BIND_POINT_COMPUTE,
ctx->h264_idct4_pipe.layout, 0, 1,
&ctx->h264_idct4_pipe.desc_set, 0, NULL);
vkCmdPushConstants(cb, ctx->h264_idct4_pipe.layout,
VK_SHADER_STAGE_COMPUTE_BIT, 0, sizeof(pc), &pc);
vkCmdDispatch(cb, wg_count, 1, 1);
vkEndCommandBuffer(cb);
if (v3d_runner_submit_wait(ctx->runner, cb)) goto fail;
memcpy(dst, bd.mapped, dst_max);
/* H.264/FFmpeg convention: zero the coeffs block after the
* transform (matches the C ref + NEON .S behaviour). */
memset(coeffs, 0, coeff_bytes);
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bc);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &bm);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bc);
return -1;
}
/* -------------------- Public dispatch entry points -------------- */
#define ROUTE_CPU_ONLY(_kernel, _cpu_fn, ...) \
@@ -831,8 +926,16 @@ int daedalus_dispatch_h264_idct4(daedalus_ctx *ctx, daedalus_substrate sub,
int16_t *coeffs, size_t n_blocks,
const daedalus_h264_block_meta *meta)
{
ROUTE_CPU_ONLY(DAEDALUS_KERNEL_H264_IDCT4, dispatch_h264_idct4_cpu,
dst, dst_stride, coeffs, n_blocks, meta);
daedalus_substrate eff = sub;
if (eff == DAEDALUS_SUBSTRATE_AUTO)
eff = daedalus_recipe_substrate_for(DAEDALUS_KERNEL_H264_IDCT4);
if (eff == DAEDALUS_SUBSTRATE_QPU && !daedalus_ctx_has_qpu(ctx))
eff = DAEDALUS_SUBSTRATE_CPU;
if (eff == DAEDALUS_SUBSTRATE_CPU)
return dispatch_h264_idct4_cpu(ctx, dst, dst_stride,
coeffs, n_blocks, meta);
return dispatch_h264_idct4_qpu(ctx, dst, dst_stride,
coeffs, n_blocks, meta);
}
int daedalus_dispatch_h264_idct8(daedalus_ctx *ctx, daedalus_substrate sub,
src/v3d_h264_idct4.comp
+129
View File
@@ -0,0 +1,129 @@
// daedalus-fourier — H.264 4x4 inverse integer transform + add, V3D 7.1.
//
// H.264 spec §8.5.12.1. Pure integer arithmetic — no trig constants
// (unlike VP9 IDCT 8x8). Row pass first, column pass second; round
// (+32) >> 6, add to dst, clip to u8.
//
// Block memory layout: COLUMN-MAJOR. block[c*4 + r] = coefficient at
// (row r, column c). Matches FFmpeg `ff_h264_idct_add_neon`.
//
// Workgroup layout: 64 invocations = 4 lanes/block × 16 blocks/WG.
// - row pass: lane k (0..3) reads row k of the block (4 coefficients,
// one from each column), runs the butterfly, writes 4
// outputs to one row of tmp_shared.
// - column pass: lane k reads column k of tmp_shared (4 rows),
// runs the butterfly, writes 4 outputs to dst as
// column k at rows 0..3.
//
// shared = 16 × 16 × 4 B = 1 KiB. Well under V3D's 16 KiB limit.
//
// License: BSD-2-Clause.
#version 450
#extension GL_EXT_shader_8bit_storage : require
#extension GL_EXT_shader_16bit_storage : require
#extension GL_EXT_shader_explicit_arithmetic_types : require
layout(local_size_x = 64, local_size_y = 1, local_size_z = 1) in;
layout(binding = 0) readonly buffer Coeffs {
int16_t coeffs[]; // N × 16 column-major
} u_coeffs;
layout(binding = 1) buffer Dst {
uint8_t dst[]; // H × stride bytes (caller-provided base)
} u_dst;
layout(binding = 2) readonly buffer Meta {
uvec4 meta[]; // .x = dst_off (byte offset into u_dst.dst)
} u_meta;
layout(push_constant) uniform PC {
uint n_blocks;
uint dst_stride_u8;
uint _pad0, _pad1;
} pc;
// 16 blocks per WG × 16 ints per block = 256 ints = 1 KiB shared.
shared int tmp_shared[16 * 16];
// 1D butterfly per H.264 §8.5.12.1. d[0..3] in, o[0..3] out.
void idct4_1d(int d0, int d1, int d2, int d3,
out int o0, out int o1, out int o2, out int o3)
{
int e = d0 + d2;
int f = d0 - d2;
int g = (d1 >> 1) - d3;
int h = d1 + (d3 >> 1);
o0 = e + h;
o1 = f + g;
o2 = f - g;
o3 = e - h;
}
void main()
{
// Lane decomposition: local_size 64 = 16 blocks × 4 lanes/block.
uint gid = gl_GlobalInvocationID.x;
uint wg_id = gid / 64u;
uint lane_in_wg = gid & 63u;
uint block_local = lane_in_wg >> 2; // 0..15
uint k = lane_in_wg & 3u; // 0..3
uint block_idx = wg_id * 16u + block_local;
bool oob = (block_idx >= pc.n_blocks);
// ---- Row pass --------------------------------------------------
// lane k handles row r=k. Reads block[c*4 + k] for c=0..3 (one
// element from each column at fixed row).
if (!oob) {
uint base = block_idx * 16u;
int d0 = int(u_coeffs.coeffs[base + 0u * 4u + k]);
int d1 = int(u_coeffs.coeffs[base + 1u * 4u + k]);
int d2 = int(u_coeffs.coeffs[base + 2u * 4u + k]);
int d3 = int(u_coeffs.coeffs[base + 3u * 4u + k]);
int o0, o1, o2, o3;
idct4_1d(d0, d1, d2, d3, o0, o1, o2, o3);
// Write row k of tmp_shared[block_local].
uint tbase = block_local * 16u + k * 4u;
tmp_shared[tbase + 0u] = o0;
tmp_shared[tbase + 1u] = o1;
tmp_shared[tbase + 2u] = o2;
tmp_shared[tbase + 3u] = o3;
}
barrier();
// ---- Column pass ----------------------------------------------
// lane k handles column c=k. Reads tmp[r][k] for r=0..3.
if (!oob) {
uint tbase = block_local * 16u;
int s0 = tmp_shared[tbase + 0u * 4u + k];
int s1 = tmp_shared[tbase + 1u * 4u + k];
int s2 = tmp_shared[tbase + 2u * 4u + k];
int s3 = tmp_shared[tbase + 3u * 4u + k];
int o0, o1, o2, o3;
idct4_1d(s0, s1, s2, s3, o0, o1, o2, o3);
// Column k at rows 0..3 of dst, offset by meta.x (dst_off).
uint dst_off = u_meta.meta[block_idx].x;
uint stride = pc.dst_stride_u8;
uint a0 = dst_off + 0u * stride + k;
uint a1 = dst_off + 1u * stride + k;
uint a2 = dst_off + 2u * stride + k;
uint a3 = dst_off + 3u * stride + k;
int p0 = int(u_dst.dst[a0]);
int p1 = int(u_dst.dst[a1]);
int p2 = int(u_dst.dst[a2]);
int p3 = int(u_dst.dst[a3]);
u_dst.dst[a0] = uint8_t(clamp(p0 + ((o0 + 32) >> 6), 0, 255));
u_dst.dst[a1] = uint8_t(clamp(p1 + ((o1 + 32) >> 6), 0, 255));
u_dst.dst[a2] = uint8_t(clamp(p2 + ((o2 + 32) >> 6), 0, 255));
u_dst.dst[a3] = uint8_t(clamp(p3 + ((o3 + 32) >> 6), 0, 255));
}
}