Phase 8b: opportunistic QPU paths through public API

Wires QPU dispatch for cycles 3 (VP9 MC), 5 (AV1 CDEF), 8 (H.264
deblock) through the public API. These three kernels have recipe
substrate = CPU, but per Issue 003 the mixed-kernel helper value
is real — the dispatch path must exist so override-mode callers
can request QPU on the side.

Pattern mirrors dispatch_idct8_qpu (lazy pipeline + per-call SSBO
alloc + memcpy + dispatch + readback). Each kernel has its own
push-constant struct (mc_pc 3-field, cdef_pc 3-field, deblock_pc
2-field shared with lpf).

Notable bug caught + fixed in test_api_opportunistic_qpu: the
initial dispatch_mc_8h_qpu sized src_max using CPU-side reach
(src_off + 3 + 8 + 7*stride), but the QPU shader reads src[
src_off + row*stride + 0..14] for row=0..7. Last block had 3
uninitialized bytes → 99.8% match → 100% after fix.

After this commit, the public API surface fully covers cycles 1-8:
  Cycle 1 (IDCT 8x8): CPU + QPU + AUTO bit-exact
  Cycle 2 (LPF wd=4): CPU + QPU + AUTO bit-exact
  Cycle 3 (MC 8h): CPU recipe; QPU override bit-exact
  Cycle 4 (LPF wd=8): CPU + QPU + AUTO bit-exact
  Cycle 5 (CDEF): CPU recipe; QPU override (untested in this
    test — bench_v3d_cdef is the authoritative 3-way M1)
  Cycle 6 (H.264 IDCT 4x4): CPU only (no QPU shader by recipe)
  Cycle 7 (H.264 IDCT 8x8): CPU only
  Cycle 8 (H.264 deblock luma-v): CPU recipe; QPU override bit-exact

Tests: test_api_opportunistic_qpu adds CPU-vs-QPU bit-exact
comparison for VP9 MC and H.264 deblock through the API.
test_api_idct, test_api_lpf, test_api_h264 still pass.

Per the locked Phase 8 architecture (project_phase8_architecture
memory): next session opens daedalus-v4l2 sibling repo with
Option B (kernel V4L2 shim + userspace daemon), Option γ (dlopen
FFmpeg parser).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-05-18 14:50:41 +00:00
parent fd55f5ebc1
commit 0a99b16489
3 changed files with 396 additions and 9 deletions
+4
View File
@@ -384,6 +384,10 @@ add_executable(test_api_h264
target_link_libraries(test_api_h264 PRIVATE daedalus_core) target_link_libraries(test_api_h264 PRIVATE daedalus_core)
target_compile_options(test_api_h264 PRIVATE -O2) target_compile_options(test_api_h264 PRIVATE -O2)
add_executable(test_api_opportunistic_qpu tests/test_api_opportunistic_qpu.c)
target_link_libraries(test_api_opportunistic_qpu PRIVATE daedalus_core)
target_compile_options(test_api_opportunistic_qpu PRIVATE -O2)
if (DAEDALUS_BUILD_VULKAN) if (DAEDALUS_BUILD_VULKAN)
# (re-open the conditional so the closing endif() below balances) # (re-open the conditional so the closing endif() below balances)
+271 -6
View File
@@ -34,6 +34,12 @@ struct daedalus_ctx {
v3d_pipeline lpf4_pipe; v3d_pipeline lpf4_pipe;
int lpf8_pipe_ready; int lpf8_pipe_ready;
v3d_pipeline lpf8_pipe; v3d_pipeline lpf8_pipe;
int mc8h_pipe_ready;
v3d_pipeline mc8h_pipe;
int cdef_pipe_ready;
v3d_pipeline cdef_pipe;
int h264deblock_pipe_ready;
v3d_pipeline h264deblock_pipe;
}; };
daedalus_ctx *daedalus_ctx_create(void) daedalus_ctx *daedalus_ctx_create(void)
@@ -66,6 +72,9 @@ void daedalus_ctx_destroy(daedalus_ctx *ctx)
if (ctx->idct8_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->idct8_pipe); if (ctx->idct8_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->idct8_pipe);
if (ctx->lpf4_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->lpf4_pipe); if (ctx->lpf4_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->lpf4_pipe);
if (ctx->lpf8_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->lpf8_pipe); if (ctx->lpf8_pipe_ready) v3d_runner_destroy_pipeline(ctx->runner, &ctx->lpf8_pipe);
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);
v3d_runner_destroy(ctx->runner); v3d_runner_destroy(ctx->runner);
} }
free(ctx); free(ctx);
@@ -449,6 +458,244 @@ fail:
return -1; return -1;
} }
/* -------------------- VP9 MC QPU dispatch (cycle 3) ------------- */
typedef struct {
uint32_t n_blocks;
uint32_t dst_stride_u8;
uint32_t src_stride_u8;
uint32_t _pad;
} mc_pc;
static int dispatch_mc_8h_qpu(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
const uint8_t *src, size_t src_stride,
size_t n_blocks, const daedalus_mc_meta *meta)
{
if (!ctx->mc8h_pipe_ready) {
if (v3d_runner_create_pipeline(ctx->runner, "v3d_mc_8h.spv",
3, sizeof(mc_pc), &ctx->mc8h_pipe) != 0)
return -1;
ctx->mc8h_pipe_ready = 1;
}
size_t meta_bytes = n_blocks * 4 * sizeof(uint32_t);
size_t dst_max = 0, src_max = 0;
for (size_t i = 0; i < n_blocks; i++) {
size_t de = meta[i].dst_off + (8 - 1) * dst_stride + 8;
if (de > dst_max) dst_max = de;
/* QPU shader reads src[src_off + row*stride + 0..14] for row=0..7. */
size_t se = meta[i].src_off + 7 * src_stride + 15;
if (se > src_max) src_max = se;
}
v3d_buffer bm = {0}, bd = {0}, bs = {0};
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_create_buffer(ctx->runner, src_max, &bs)) { v3d_runner_destroy_buffer(ctx->runner, &bd); v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
memcpy(bs.mapped, src, src_max);
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] = meta[i].src_off;
m[4*i+2] = (uint32_t) meta[i].mx;
m[4*i+3] = 0;
}
v3d_buffer binds[3] = { bm, bd, bs };
if (v3d_runner_bind_buffers(ctx->runner, &ctx->mc8h_pipe, binds, 3)) goto fail;
uint32_t wg_count = (uint32_t)((n_blocks + 31) / 32);
mc_pc pc = { .n_blocks = (uint32_t) n_blocks,
.dst_stride_u8 = (uint32_t) dst_stride,
.src_stride_u8 = (uint32_t) src_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->mc8h_pipe.pipeline);
vkCmdBindDescriptorSets(cb, VK_PIPELINE_BIND_POINT_COMPUTE,
ctx->mc8h_pipe.layout, 0, 1, &ctx->mc8h_pipe.desc_set, 0, NULL);
vkCmdPushConstants(cb, ctx->mc8h_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);
v3d_runner_destroy_buffer(ctx->runner, &bs);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &bs);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
return -1;
}
/* -------------------- CDEF QPU dispatch (cycle 5) --------------- */
typedef struct {
uint32_t n_blocks;
uint32_t tmp_stride_u16;
uint32_t dst_stride_u8;
uint32_t _pad;
} cdef_pc;
static int dispatch_cdef_qpu(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
const uint16_t *tmp,
size_t n_blocks, const daedalus_cdef_meta *meta)
{
if (!ctx->cdef_pipe_ready) {
if (v3d_runner_create_pipeline(ctx->runner, "v3d_cdef.spv",
3, sizeof(cdef_pc), &ctx->cdef_pipe) != 0)
return -1;
ctx->cdef_pipe_ready = 1;
}
size_t meta_bytes = n_blocks * 4 * sizeof(uint32_t);
size_t dst_max = 0, tmp_max_u16 = 0;
for (size_t i = 0; i < n_blocks; i++) {
size_t de = meta[i].dst_off + (8 - 1) * dst_stride + 8;
if (de > dst_max) dst_max = de;
size_t te = meta[i].tmp_off_u16 + (8 - 1) * 16 + 8; /* center 8x8 in stride-16 tmp */
if (te > tmp_max_u16) tmp_max_u16 = te;
}
size_t tmp_bytes = tmp_max_u16 * sizeof(uint16_t);
v3d_buffer bm = {0}, bd = {0}, bt = {0};
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
if (v3d_runner_create_buffer(ctx->runner, tmp_bytes, &bt)) { v3d_runner_destroy_buffer(ctx->runner, &bd); v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
/* tmp may need padding before block-origin offset (caller-allocated). Just
* copy from caller; we assume meta[i].tmp_off_u16 is consistent with how
* caller has the layout set up. */
memcpy(bt.mapped, tmp, tmp_bytes);
memcpy(bd.mapped, dst, dst_max);
uint32_t *m = bm.mapped;
for (size_t i = 0; i < n_blocks; i++) {
uint32_t pri = (uint32_t) meta[i].pri_strength;
uint32_t sec = (uint32_t) meta[i].sec_strength;
uint32_t damping = (uint32_t) meta[i].damping;
m[4*i+0] = meta[i].dst_off;
m[4*i+1] = pri | (sec << 8) | (damping << 16);
m[4*i+2] = meta[i].tmp_off_u16;
m[4*i+3] = (uint32_t) meta[i].dir;
}
v3d_buffer binds[3] = { bm, bd, bt };
if (v3d_runner_bind_buffers(ctx->runner, &ctx->cdef_pipe, binds, 3)) goto fail;
uint32_t wg_count = (uint32_t)((n_blocks + 3) / 4);
cdef_pc pc = { .n_blocks = (uint32_t) n_blocks,
.tmp_stride_u16 = 16,
.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->cdef_pipe.pipeline);
vkCmdBindDescriptorSets(cb, VK_PIPELINE_BIND_POINT_COMPUTE,
ctx->cdef_pipe.layout, 0, 1, &ctx->cdef_pipe.desc_set, 0, NULL);
vkCmdPushConstants(cb, ctx->cdef_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);
v3d_runner_destroy_buffer(ctx->runner, &bt);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &bt);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
return -1;
}
/* -------------------- H.264 deblock QPU dispatch (cycle 8) ------ */
typedef struct {
uint32_t n_edges;
uint32_t dst_stride_u8;
uint32_t _pad0;
uint32_t _pad1;
} h264deblock_pc;
static int dispatch_h264_deblock_qpu(daedalus_ctx *ctx,
uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta)
{
if (!ctx->h264deblock_pipe_ready) {
if (v3d_runner_create_pipeline(ctx->runner, "v3d_h264deblock.spv",
2, sizeof(h264deblock_pc), &ctx->h264deblock_pipe) != 0)
return -1;
ctx->h264deblock_pipe_ready = 1;
}
size_t meta_bytes = n_edges * 4 * sizeof(uint32_t);
size_t dst_max = 0;
for (size_t i = 0; i < n_edges; i++) {
/* Reads -4*stride to +3*stride+15 from dst_off; writes -2..+1 *stride. */
size_t e = meta[i].dst_off + 3 * dst_stride + 16;
if (e > dst_max) dst_max = e;
}
v3d_buffer bm = {0}, bd = {0};
if (v3d_runner_create_buffer(ctx->runner, meta_bytes, &bm)) return -1;
if (v3d_runner_create_buffer(ctx->runner, dst_max, &bd)) { v3d_runner_destroy_buffer(ctx->runner, &bm); return -1; }
memcpy(bd.mapped, dst, dst_max);
uint32_t *m = bm.mapped;
for (size_t i = 0; i < n_edges; i++) {
m[4*i+0] = meta[i].dst_off;
m[4*i+1] = ((uint32_t) meta[i].alpha) | (((uint32_t) meta[i].beta) << 8);
m[4*i+2] = ((uint32_t)(uint8_t) meta[i].tc0[0])
| (((uint32_t)(uint8_t) meta[i].tc0[1]) << 8)
| (((uint32_t)(uint8_t) meta[i].tc0[2]) << 16)
| (((uint32_t)(uint8_t) meta[i].tc0[3]) << 24);
m[4*i+3] = 0;
}
v3d_buffer binds[2] = { bm, bd };
if (v3d_runner_bind_buffers(ctx->runner, &ctx->h264deblock_pipe, binds, 2)) goto fail;
uint32_t wg_count = (uint32_t)((n_edges + 15) / 16);
h264deblock_pc pc = { .n_edges = (uint32_t) n_edges,
.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->h264deblock_pipe.pipeline);
vkCmdBindDescriptorSets(cb, VK_PIPELINE_BIND_POINT_COMPUTE,
ctx->h264deblock_pipe.layout, 0, 1, &ctx->h264deblock_pipe.desc_set, 0, NULL);
vkCmdPushConstants(cb, ctx->h264deblock_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);
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
return 0;
fail:
v3d_runner_destroy_buffer(ctx->runner, &bd);
v3d_runner_destroy_buffer(ctx->runner, &bm);
return -1;
}
/* -------------------- Public dispatch entry points -------------- */ /* -------------------- Public dispatch entry points -------------- */
#define ROUTE_CPU_ONLY(_kernel, _cpu_fn, ...) \ #define ROUTE_CPU_ONLY(_kernel, _cpu_fn, ...) \
@@ -507,8 +754,14 @@ int daedalus_dispatch_vp9_mc_8h(daedalus_ctx *ctx, daedalus_substrate sub,
const uint8_t *src, size_t src_stride, const uint8_t *src, size_t src_stride,
size_t n_blocks, const daedalus_mc_meta *meta) size_t n_blocks, const daedalus_mc_meta *meta)
{ {
ROUTE_CPU_ONLY(DAEDALUS_KERNEL_VP9_MC_8H, dispatch_mc_8h_cpu, daedalus_substrate eff = sub;
dst, dst_stride, src, src_stride, n_blocks, meta); if (eff == DAEDALUS_SUBSTRATE_AUTO)
eff = daedalus_recipe_substrate_for(DAEDALUS_KERNEL_VP9_MC_8H);
if (eff == DAEDALUS_SUBSTRATE_QPU && !daedalus_ctx_has_qpu(ctx))
eff = DAEDALUS_SUBSTRATE_CPU;
if (eff == DAEDALUS_SUBSTRATE_CPU)
return dispatch_mc_8h_cpu(ctx, dst, dst_stride, src, src_stride, n_blocks, meta);
return dispatch_mc_8h_qpu(ctx, dst, dst_stride, src, src_stride, n_blocks, meta);
} }
int daedalus_dispatch_cdef_8x8(daedalus_ctx *ctx, daedalus_substrate sub, int daedalus_dispatch_cdef_8x8(daedalus_ctx *ctx, daedalus_substrate sub,
@@ -516,8 +769,14 @@ int daedalus_dispatch_cdef_8x8(daedalus_ctx *ctx, daedalus_substrate sub,
const uint16_t *tmp, const uint16_t *tmp,
size_t n_blocks, const daedalus_cdef_meta *meta) size_t n_blocks, const daedalus_cdef_meta *meta)
{ {
ROUTE_CPU_ONLY(DAEDALUS_KERNEL_AV1_CDEF_8X8, dispatch_cdef_cpu, daedalus_substrate eff = sub;
dst, dst_stride, tmp, n_blocks, meta); if (eff == DAEDALUS_SUBSTRATE_AUTO)
eff = daedalus_recipe_substrate_for(DAEDALUS_KERNEL_AV1_CDEF_8X8);
if (eff == DAEDALUS_SUBSTRATE_QPU && !daedalus_ctx_has_qpu(ctx))
eff = DAEDALUS_SUBSTRATE_CPU;
if (eff == DAEDALUS_SUBSTRATE_CPU)
return dispatch_cdef_cpu(ctx, dst, dst_stride, tmp, n_blocks, meta);
return dispatch_cdef_qpu(ctx, dst, dst_stride, tmp, n_blocks, meta);
} }
int daedalus_dispatch_h264_idct4(daedalus_ctx *ctx, daedalus_substrate sub, int daedalus_dispatch_h264_idct4(daedalus_ctx *ctx, daedalus_substrate sub,
@@ -542,8 +801,14 @@ int daedalus_dispatch_h264_deblock_luma_v(daedalus_ctx *ctx, daedalus_substrate
uint8_t *dst, size_t dst_stride, uint8_t *dst, size_t dst_stride,
size_t n_edges, const daedalus_h264_deblock_meta *meta) size_t n_edges, const daedalus_h264_deblock_meta *meta)
{ {
ROUTE_CPU_ONLY(DAEDALUS_KERNEL_H264_DEBLOCK_LV, dispatch_h264_deblock_cpu, daedalus_substrate eff = sub;
dst, dst_stride, n_edges, meta); if (eff == DAEDALUS_SUBSTRATE_AUTO)
eff = daedalus_recipe_substrate_for(DAEDALUS_KERNEL_H264_DEBLOCK_LV);
if (eff == DAEDALUS_SUBSTRATE_QPU && !daedalus_ctx_has_qpu(ctx))
eff = DAEDALUS_SUBSTRATE_CPU;
if (eff == DAEDALUS_SUBSTRATE_CPU)
return dispatch_h264_deblock_cpu(ctx, dst, dst_stride, n_edges, meta);
return dispatch_h264_deblock_qpu(ctx, dst, dst_stride, n_edges, meta);
} }
/* -------------------- Recipe convenience wrappers --------------- */ /* -------------------- Recipe convenience wrappers --------------- */
+118
View File
@@ -0,0 +1,118 @@
/*
* Phase 8b — opportunistic-QPU dispatch paths through public API.
*
* Verifies that cycles 3 (VP9 MC), 5 (AV1 CDEF), 8 (H.264 deblock)
* can be force-routed to QPU via daedalus_dispatch_*(QPU, ...) and
* produce bit-exact output vs the CPU path (which is the C ref proxy
* for each kernel — see per-cycle Phase 7 docs).
*
* AUTO/recipe path stays on CPU for these kernels — that's the
* deployment shape. This test exercises the override-mode path
* the integration layer would use for runtime-aware scheduling.
*/
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <stddef.h>
#include <string.h>
#include "../include/daedalus.h"
static uint64_t xs_state = 0xab10b81cULL;
static inline uint64_t xs(void) {
uint64_t x = xs_state;
x ^= x << 13; x ^= x >> 7; x ^= x << 17;
return xs_state = x;
}
static int test_mc(void)
{
enum { N = 32, DST_STRIDE = 16, DST_ROWS = 8 * 4, DST_BYTES = DST_ROWS * DST_STRIDE,
SRC_STRIDE = 16, SRC_ROWS = 12, SRC_BYTES = SRC_ROWS * SRC_STRIDE * N };
daedalus_ctx *ctx = daedalus_ctx_create();
if (!ctx) return 1;
if (!daedalus_ctx_has_qpu(ctx)) {
printf(" VP9 MC: SKIP (no QPU)\n"); daedalus_ctx_destroy(ctx); return 0;
}
/* Allocate per-block src tiles (12 rows x 16 cols each). */
uint8_t *src = malloc(SRC_BYTES);
uint8_t *dst_cpu = calloc(1, DST_BYTES * N);
uint8_t *dst_qpu = calloc(1, DST_BYTES * N);
daedalus_mc_meta *meta = calloc(N, sizeof(*meta));
if (!src || !dst_cpu || !dst_qpu || !meta) return 1;
for (size_t i = 0; i < SRC_BYTES; i++) src[i] = (uint8_t)(xs() & 0xff);
for (int i = 0; i < N; i++) {
meta[i].dst_off = i * 64; /* 8 rows × 8 cols = 64 bytes per block */
meta[i].src_off = i * SRC_STRIDE * SRC_ROWS; /* RAW src offset; shader handles -3 */
meta[i].mx = (int)(xs() & 15);
}
daedalus_dispatch_vp9_mc_8h(ctx, DAEDALUS_SUBSTRATE_CPU, dst_cpu, 8, src, SRC_STRIDE, N, meta);
daedalus_dispatch_vp9_mc_8h(ctx, DAEDALUS_SUBSTRATE_QPU, dst_qpu, 8, src, SRC_STRIDE, N, meta);
int diff = 0;
for (int i = 0; i < N * 64; i++) if (dst_cpu[i] != dst_qpu[i]) diff++;
printf(" VP9 MC (CPU vs QPU): %d/%d bytes match (%.4f%%)\n",
N * 64 - diff, N * 64, 100.0 * (N * 64 - diff) / (N * 64));
free(src); free(dst_cpu); free(dst_qpu); free(meta);
daedalus_ctx_destroy(ctx);
return diff == 0 ? 0 : 1;
}
static int test_deblock(void)
{
enum { N = 8, TILE_STRIDE = 16, TILE_BYTES = 16 * TILE_STRIDE,
TOTAL = N * TILE_BYTES, EDGE_OFF = 4 * TILE_STRIDE };
daedalus_ctx *ctx = daedalus_ctx_create();
if (!ctx) return 1;
if (!daedalus_ctx_has_qpu(ctx)) {
printf(" H.264 deblock: SKIP (no QPU)\n"); daedalus_ctx_destroy(ctx); return 0;
}
uint8_t *master = malloc(TOTAL);
uint8_t *dst_cpu = malloc(TOTAL);
uint8_t *dst_qpu = malloc(TOTAL);
daedalus_h264_deblock_meta *meta = calloc(N, sizeof(*meta));
if (!master || !dst_cpu || !dst_qpu || !meta) return 1;
for (int i = 0; i < TOTAL; i++) master[i] = (uint8_t)(xs() & 0xff);
memcpy(dst_cpu, master, TOTAL);
memcpy(dst_qpu, master, TOTAL);
for (int i = 0; i < N; i++) {
meta[i].dst_off = i * TILE_BYTES + EDGE_OFF;
meta[i].alpha = (int)(xs() % 64) + 1;
meta[i].beta = (int)(xs() % 16) + 1;
for (int s = 0; s < 4; s++) {
int r = (int)(xs() % 8);
meta[i].tc0[s] = (int8_t)(r == 0 ? -1 : (r - 1));
}
}
daedalus_dispatch_h264_deblock_luma_v(ctx, DAEDALUS_SUBSTRATE_CPU, dst_cpu, TILE_STRIDE, N, meta);
daedalus_dispatch_h264_deblock_luma_v(ctx, DAEDALUS_SUBSTRATE_QPU, dst_qpu, TILE_STRIDE, N, meta);
int diff = 0;
for (int i = 0; i < TOTAL; i++) if (dst_cpu[i] != dst_qpu[i]) diff++;
printf(" H.264 deblock (CPU vs QPU): %d/%d bytes match (%.4f%%)\n",
TOTAL - diff, TOTAL, 100.0 * (TOTAL - diff) / TOTAL);
free(master); free(dst_cpu); free(dst_qpu); free(meta);
daedalus_ctx_destroy(ctx);
return diff == 0 ? 0 : 1;
}
int main(void)
{
printf("=== Phase 8b: opportunistic-QPU paths through API ===\n");
int fail = 0;
fail |= test_mc();
fail |= test_deblock();
/* CDEF skipped here — tmp construction in C ref differs subtly
* from dav1d NEON's; bench_v3d_cdef.c is the authoritative gate
* for the QPU CDEF path. */
return fail;
}