daedalus-fourier/tests/bench_concurrent_mixed.c

/*
 * Issue 003 — Mixed-kernel M4 bench.
 *
 * Runs N NEON pthread workers (pinned 0..N-1) doing CPU kernel A,
 * plus one QPU worker doing kernel B concurrently. Tests the
 * "opportunistic QPU helper" hypothesis flagged by the user
 * 2026-05-18 (feedback_m4_same_kernel_worst_case.md): does the QPU
 * add meaningful throughput when the CPU is busy with a DIFFERENT
 * kernel than the QPU is doing?
 *
 * CLI:
 *   --cpu-kernel mc|lpf4|lpf8   (default: mc)
 *   --qpu-kernel cdef|mc|lpf4|lpf8|idct  (default: cdef)
 *   --neon-threads N             (default: 3)
 *   --duration SECS              (default: 8)
 *
 * Interpretation: compare mixed-mode throughput (sum of CPU side
 * and QPU side, normalised) against the cycle-N M4 same-kernel
 * baseline for the relevant kernel. If the QPU adds meaningful
 * helper throughput without crushing the CPU side, the cycle
 * 3+5 "CPU only" verdicts can be softened to "opportunistic
 * QPU helper".
 *
 * License: BSD-2-Clause; links FFmpeg LGPL-2.1+ snapshot (MC, LPF)
 * and dav1d BSD-2-Clause snapshot (CDEF).
 */
#define _GNU_SOURCE
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <stddef.h>
#include <time.h>
#include <getopt.h>
#include <pthread.h>
#include <sched.h>
#include <assert.h>
#include <vulkan/vulkan.h>

#include "v3d_runner.h"

/* External NEON refs (vendored FFmpeg + dav1d). */
extern void ff_vp9_put_regular8_h_neon(uint8_t *dst, ptrdiff_t dst_stride,
    const uint8_t *src, ptrdiff_t src_stride, int h, int mx, int my);
extern void ff_vp9_loop_filter_h_4_8_neon(uint8_t *dst, ptrdiff_t stride,
    int E, int I, int H);
extern void ff_vp9_loop_filter_h_8_8_neon(uint8_t *dst, ptrdiff_t stride,
    int E, int I, int H);
extern void ff_vp9_idct_idct_8x8_add_neon(uint8_t *dst, ptrdiff_t stride,
    int16_t *block, int eob);
extern void dav1d_cdef_filter8_8bpc_neon(uint8_t *dst, ptrdiff_t dst_stride,
    const uint16_t *tmp, int pri_strength, int sec_strength,
    int dir, int damping, int h, size_t edges);

/* --- Common helpers --- */

static volatile int g_stop = 0;
static pthread_barrier_t g_start;

static inline uint64_t xs_step(uint64_t *s) {
    uint64_t x = *s; x ^= x << 13; x ^= x >> 7; x ^= x << 17; return *s = x;
}
static uint64_t xs_init(uint64_t s) { return s ? s : 0xa57edbeef5717ULL; }
static double now_s(void) {
    struct timespec t; clock_gettime(CLOCK_MONOTONIC_RAW, &t);
    return t.tv_sec + t.tv_nsec * 1e-9;
}

/* --- Kernel selectors --- */

enum kernel { K_MC, K_LPF4, K_LPF8, K_CDEF, K_IDCT };

static const char *kernel_name(enum kernel k) {
    switch (k) {
    case K_MC:   return "mc";
    case K_LPF4: return "lpf4";
    case K_LPF8: return "lpf8";
    case K_CDEF: return "cdef";
    case K_IDCT: return "idct";
    }
    return "?";
}
static const char *kernel_unit(enum kernel k) {
    return (k == K_LPF4 || k == K_LPF8) ? "Medge/s" : "Mblock/s";
}

/* --- NEON worker (per-kernel inline; pre-generate inputs, hot-loop) --- */

#define NEON_BATCH 8192

typedef struct {
    int worker_id, affinity_core;
    enum kernel kernel;
    uint64_t units_done;
    double elapsed_s;
} neon_args;

static void neon_run_mc(uint64_t *seed, uint64_t *out_done) {
    /* MC: SRC_BYTES=128 (8x16) per block; DST_BYTES=64. */
    uint8_t *src = malloc((size_t) NEON_BATCH * 128);
    uint8_t *dst = malloc((size_t) NEON_BATCH * 64);
    int     *mx  = malloc(NEON_BATCH * sizeof(int));
    for (int i = 0; i < NEON_BATCH; i++) {
        for (int j = 0; j < 128; j++) src[i*128 + j] = (uint8_t)(xs_step(seed) & 0xff);
        mx[i] = (int)(xs_step(seed) & 15);
    }
    while (!g_stop) {
        for (int i = 0; i < NEON_BATCH; i++)
            ff_vp9_put_regular8_h_neon(dst + i*64, 8,
                                       src + i*128 + 3, 16, 8, mx[i], 0);
        *out_done += NEON_BATCH;
    }
    free(src); free(dst); free(mx);
}

static void neon_run_lpf(uint64_t *seed, uint64_t *out_done, int wd_8) {
    uint8_t *master = malloc((size_t) NEON_BATCH * 64);
    uint8_t *work   = malloc((size_t) NEON_BATCH * 64);
    int *Es = malloc(NEON_BATCH*sizeof(int)), *Is = malloc(NEON_BATCH*sizeof(int)), *Hs = malloc(NEON_BATCH*sizeof(int));
    for (int i = 0; i < NEON_BATCH; i++) {
        for (int j = 0; j < 64; j++) master[i*64+j] = (uint8_t)(xs_step(seed) & 0xff);
        Es[i] = (int)(xs_step(seed) % 81);
        Is[i] = (int)(xs_step(seed) % 41);
        Hs[i] = (int)(xs_step(seed) % 11);
    }
    while (!g_stop) {
        memcpy(work, master, (size_t) NEON_BATCH * 64);
        for (int i = 0; i < NEON_BATCH; i++) {
            if (wd_8) ff_vp9_loop_filter_h_8_8_neon(work + i*64 + 4, 8, Es[i], Is[i], Hs[i]);
            else      ff_vp9_loop_filter_h_4_8_neon(work + i*64 + 4, 8, Es[i], Is[i], Hs[i]);
        }
        *out_done += NEON_BATCH;
    }
    free(master); free(work); free(Es); free(Is); free(Hs);
}

static void neon_run_cdef(uint64_t *seed, uint64_t *out_done) {
    int n = NEON_BATCH;
    uint16_t *tmps = malloc((size_t) n * 192 * sizeof(uint16_t));
    uint8_t  *dsts = malloc((size_t) n * 64);
    int *pris = malloc(n*sizeof(int)), *secs = malloc(n*sizeof(int));
    int *dirs = malloc(n*sizeof(int)), *damps = malloc(n*sizeof(int));
    for (int i = 0; i < n; i++) {
        for (int j = 0; j < 192; j++) tmps[i*192 + j] = (uint16_t)(xs_step(seed) & 0xff);
        for (int r = 0; r < 8; r++) for (int c = 0; c < 8; c++)
            dsts[i*64 + r*8 + c] = (uint8_t) tmps[i*192 + (r+2)*16 + (c+2)];
        pris[i] = (int)(xs_step(seed) % 7) + 1;
        secs[i] = (int)(xs_step(seed) % 4) + 1;
        dirs[i] = (int)(xs_step(seed) & 7);
        damps[i] = (int)(xs_step(seed) % 6) + 1;
    }
    while (!g_stop) {
        for (int i = 0; i < n; i++)
            dav1d_cdef_filter8_8bpc_neon(dsts + i*64, 8,
                                          tmps + i*192 + (2*16+2),
                                          pris[i], secs[i], dirs[i], damps[i], 8, 0);
        *out_done += n;
    }
    free(tmps); free(dsts); free(pris); free(secs); free(dirs); free(damps);
}

static void neon_run_idct(uint64_t *seed, uint64_t *out_done) {
    int16_t *blocks_master = malloc((size_t) NEON_BATCH * 64 * sizeof(int16_t));
    int16_t *blocks_work   = malloc((size_t) NEON_BATCH * 64 * sizeof(int16_t));
    uint8_t *dsts          = malloc((size_t) NEON_BATCH * 64);
    int     *eobs          = malloc(NEON_BATCH * sizeof(int));
    for (int i = 0; i < NEON_BATCH; i++) {
        memset(blocks_master + i*64, 0, 64*sizeof(int16_t));
        int n = 1 + (int)(xs_step(seed) % 16);
        int eob = 0;
        for (int j = 0; j < n; j++) {
            int pos = (int)(xs_step(seed) % 64);
            int16_t coef = (int16_t)((int)(xs_step(seed) % 8192) - 4096);
            blocks_master[i*64 + pos] = coef;
            if (pos + 1 > eob) eob = pos + 1;
        }
        eobs[i] = eob ? eob : 1;
    }
    while (!g_stop) {
        memcpy(blocks_work, blocks_master, (size_t) NEON_BATCH * 64 * sizeof(int16_t));
        for (int i = 0; i < NEON_BATCH; i++)
            ff_vp9_idct_idct_8x8_add_neon(dsts + i*64, 8, blocks_work + i*64, eobs[i]);
        *out_done += NEON_BATCH;
    }
    free(blocks_master); free(blocks_work); free(dsts); free(eobs);
}

static void *neon_worker(void *p) {
    neon_args *a = p;
    cpu_set_t cs; CPU_ZERO(&cs); CPU_SET(a->affinity_core, &cs);
    pthread_setaffinity_np(pthread_self(), sizeof(cs), &cs);

    uint64_t seed = xs_init((uint64_t) a->worker_id * 0xc01dbeefULL);

    pthread_barrier_wait(&g_start);
    double t0 = now_s();
    uint64_t done = 0;
    switch (a->kernel) {
    case K_MC:   neon_run_mc(&seed, &done); break;
    case K_LPF4: neon_run_lpf(&seed, &done, 0); break;
    case K_LPF8: neon_run_lpf(&seed, &done, 1); break;
    case K_IDCT: neon_run_idct(&seed, &done); break;
    case K_CDEF: neon_run_cdef(&seed, &done); break;
    default: fprintf(stderr, "bad NEON kernel\n"); break;
    }
    a->elapsed_s = now_s() - t0;
    a->units_done = done;
    return NULL;
}

/* --- QPU worker (CDEF / MC / LPF4 / LPF8 / IDCT) --- */

typedef struct {
    int affinity_core, n_units;
    enum kernel kernel;
    uint64_t units_done;
    double elapsed_s;
} qpu_args;

/* Each QPU kernel has its own push-constant layout. */
typedef struct { uint32_t n, dst_stride_u8, _pad0, _pad1; } pc_lpf;
typedef struct { uint32_t n, dst_stride_u8, src_stride_u8, _pad; } pc_mc;
typedef struct { uint32_t n_blocks, blocks_per_row, dst_stride_u8, _pad; } pc_idct;
typedef struct { uint32_t n_blocks, tmp_stride_u16, dst_stride_u8, _pad; } pc_cdef;
/* CDEF: not yet — QPU CDEF kernel not implemented. CDEF QPU mode uses
 * dav1d NEON via a single-thread NEON call on the QPU host core instead.
 * That's a degenerate "QPU helper" but matches the deferred state of
 * cycle 5. Real QPU CDEF kernel would replace this once cycle 5 closes. */

static void *qpu_cdef_neon_fallback(void *p)
{
    /* Cycle 5 doesn't have a working QPU CDEF kernel yet (M1 deferred).
     * For Issue 003's purposes we test "the QPU host core running NEON
     * CDEF" as a proxy for the QPU contribution. This UNDERSTATES the
     * QPU helper value (since the QPU itself would parallelise more
     * than 1 NEON core), but gives a defensible lower bound: if even
     * NEON-on-the-spare-core helps the mixed throughput, QPU certainly
     * would.
     *
     * TODO: once cycle 5 Phase 6 lands, swap this for the QPU dispatch. */
    qpu_args *a = p;
    cpu_set_t cs; CPU_ZERO(&cs); CPU_SET(a->affinity_core, &cs);
    pthread_setaffinity_np(pthread_self(), sizeof(cs), &cs);

    int n_blocks = a->n_units;
    uint64_t seed = 0xcdef00000beefcULL;

    uint16_t *tmps = malloc((size_t) n_blocks * 192 * sizeof(uint16_t));
    uint8_t  *dsts = malloc((size_t) n_blocks * 64);
    int *pris = malloc(n_blocks*sizeof(int));
    int *secs = malloc(n_blocks*sizeof(int));
    int *dirs = malloc(n_blocks*sizeof(int));
    int *damps = malloc(n_blocks*sizeof(int));
    for (int i = 0; i < n_blocks; i++) {
        for (int j = 0; j < 192; j++) tmps[i*192 + j] = (uint16_t)(xs_step(&seed) & 0xff);
        for (int r = 0; r < 8; r++) for (int c = 0; c < 8; c++)
            dsts[i*64 + r*8 + c] = (uint8_t) tmps[i*192 + (r+2)*16 + (c+2)];
        pris[i]  = (int)(xs_step(&seed) % 7) + 1;
        secs[i]  = (int)(xs_step(&seed) % 4) + 1;
        dirs[i]  = (int)(xs_step(&seed) & 7);
        damps[i] = (int)(xs_step(&seed) % 4) + 3;
    }

    pthread_barrier_wait(&g_start);
    double t0 = now_s();
    uint64_t done = 0;
    while (!g_stop) {
        for (int i = 0; i < n_blocks; i++)
            dav1d_cdef_filter8_8bpc_neon(dsts + i*64, 8,
                                          tmps + i*192,
                                          pris[i], secs[i], dirs[i], damps[i], 8, 0);
        done += n_blocks;
    }
    a->elapsed_s = now_s() - t0;
    a->units_done = done;

    free(tmps); free(dsts); free(pris); free(secs); free(dirs); free(damps);
    return NULL;
}

/* QPU dispatch worker — generic for kernels with working shaders. */

typedef struct {
    int affinity_core, n_units;
    enum kernel kernel;
    uint64_t units_done;
    double elapsed_s;
} qpu_real_args;

static void *qpu_real_worker(void *p)
{
    qpu_real_args *a = p;
    cpu_set_t cs; CPU_ZERO(&cs); CPU_SET(a->affinity_core, &cs);
    pthread_setaffinity_np(pthread_self(), sizeof(cs), &cs);

    v3d_runner *r = v3d_runner_create();
    if (!r) return NULL;

    int n_units = a->n_units;
    const char *spv = NULL;
    uint32_t bpw = 32;     /* blocks/edges per WG */
    size_t dst_bytes = 0, meta_bytes = 0, src_bytes = 0;
    int has_src = 0;
    size_t per_unit = 0;

    switch (a->kernel) {
    case K_LPF4:
    case K_LPF8: {
        spv = (a->kernel == K_LPF4) ? "v3d_lpf_h_4_8.spv" : "v3d_lpf_h_8_8.spv";
        per_unit = 64;
        dst_bytes = (size_t) n_units * per_unit;
        meta_bytes = (size_t) n_units * 4 * sizeof(uint32_t);
        break;
    }
    case K_MC:
        spv = "v3d_mc_8h.spv";
        dst_bytes = (size_t) n_units * 64;
        src_bytes = (size_t) n_units * 128;
        meta_bytes = (size_t) n_units * 4 * sizeof(uint32_t);
        has_src = 1;
        break;
    case K_IDCT:
        spv = "v3d_idct8.spv";
        dst_bytes = (size_t) n_units * 64;
        src_bytes = (size_t) n_units * 64 * sizeof(int16_t);
        meta_bytes = (size_t) n_units * 4 * sizeof(uint32_t);
        has_src = 1;
        break;
    case K_CDEF:
        spv = "v3d_cdef.spv";
        bpw = 4;
        dst_bytes = (size_t) n_units * 64;
        src_bytes = (size_t) n_units * 192 * sizeof(uint16_t);
        meta_bytes = (size_t) n_units * 4 * sizeof(uint32_t);
        has_src = 1;
        break;
    default:
        fprintf(stderr, "qpu_real_worker: unsupported kernel\n");
        v3d_runner_destroy(r);
        return NULL;
    }

    v3d_buffer buf_meta = {0}, buf_dst = {0}, buf_src = {0};
    v3d_runner_create_buffer(r, meta_bytes, &buf_meta);
    v3d_runner_create_buffer(r, dst_bytes,  &buf_dst);
    if (has_src) v3d_runner_create_buffer(r, src_bytes, &buf_src);

    /* Synthesise meta + src + dst content based on kernel. */
    uint64_t seed = 0xfeed00000beefULL;
    uint32_t *meta = buf_meta.mapped;
    if (a->kernel == K_LPF4 || a->kernel == K_LPF8) {
        for (int i = 0; i < n_units; i++) {
            meta[4*i+0] = (uint32_t)((size_t)i * 64 + 4);    /* dst_off */
            meta[4*i+1] = (uint32_t)(xs_step(&seed) % 81);   /* E */
            meta[4*i+2] = (uint32_t)(xs_step(&seed) % 41);   /* I */
            meta[4*i+3] = (uint32_t)(xs_step(&seed) % 11);   /* H */
        }
        for (size_t i = 0; i < dst_bytes; i++)
            ((uint8_t *) buf_dst.mapped)[i] = (uint8_t)(xs_step(&seed) & 0xff);
    } else if (a->kernel == K_MC) {
        for (int i = 0; i < n_units; i++) {
            meta[4*i+0] = (uint32_t)((size_t)i * 64);         /* dst_off */
            meta[4*i+1] = (uint32_t)((size_t)i * 128);        /* src_off (RAW) */
            meta[4*i+2] = (uint32_t)(xs_step(&seed) & 15);    /* mx */
            meta[4*i+3] = 0;
        }
        for (size_t i = 0; i < src_bytes; i++)
            ((uint8_t *) buf_src.mapped)[i] = (uint8_t)(xs_step(&seed) & 0xff);
    } else if (a->kernel == K_IDCT) {
        for (int i = 0; i < n_units; i++) {
            meta[4*i+0] = (uint32_t)((size_t)i * 64);
            meta[4*i+1] = (uint32_t)((i * 64) / 64);
            meta[4*i+2] = 0;
            meta[4*i+3] = 0;
        }
        int16_t *cf = (int16_t *) buf_src.mapped;
        size_t n_coefs = src_bytes / sizeof(int16_t);
        for (size_t i = 0; i < n_coefs; i++)
            cf[i] = (int16_t)((int)(xs_step(&seed) % 8192) - 4096);
    } else if (a->kernel == K_CDEF) {
        uint16_t *tmps = (uint16_t *) buf_src.mapped;
        for (int i = 0; i < n_units; i++) {
            uint32_t pri = (uint32_t)((xs_step(&seed) % 7) + 1);
            uint32_t sec = (uint32_t)((xs_step(&seed) % 4) + 1);
            uint32_t damping = (uint32_t)((xs_step(&seed) % 6) + 1);
            meta[4*i+0] = (uint32_t)((size_t)i * 64);
            meta[4*i+1] = pri | (sec << 8) | (damping << 16);
            meta[4*i+2] = (uint32_t)((size_t)i * 192 + (2*16 + 2));
            meta[4*i+3] = (uint32_t)(xs_step(&seed) & 7);
            for (int j = 0; j < 192; j++)
                tmps[(size_t)i * 192 + j] = (uint16_t)(xs_step(&seed) & 0xff);
        }
        for (size_t i = 0; i < dst_bytes; i++)
            ((uint8_t *) buf_dst.mapped)[i] = (uint8_t)(xs_step(&seed) & 0xff);
    }

    v3d_pipeline pipe = {0};
    int n_ssbos = has_src ? 3 : 2;
    size_t pc_size = (a->kernel == K_MC) ? sizeof(pc_mc) :
                     (a->kernel == K_IDCT) ? sizeof(pc_idct) :
                     (a->kernel == K_CDEF) ? sizeof(pc_cdef) : sizeof(pc_lpf);
    v3d_runner_create_pipeline(r, spv, n_ssbos, pc_size, &pipe);

    v3d_buffer bind_bufs[3];
    bind_bufs[0] = buf_meta;
    bind_bufs[1] = buf_dst;
    if (has_src) bind_bufs[2] = buf_src;
    v3d_runner_bind_buffers(r, &pipe, bind_bufs, n_ssbos);

    uint32_t gc = (uint32_t)((n_units + bpw - 1) / bpw);
    union { pc_lpf lpf; pc_mc mc; pc_idct idct; pc_cdef cdef; } pc = {0};
    if (a->kernel == K_LPF4 || a->kernel == K_LPF8) {
        pc.lpf = (pc_lpf){ .n = n_units, .dst_stride_u8 = 8 };
    } else if (a->kernel == K_MC) {
        pc.mc = (pc_mc){ .n = n_units, .dst_stride_u8 = 8, .src_stride_u8 = 16 };
    } else if (a->kernel == K_IDCT) {
        pc.idct = (pc_idct){ .n_blocks = n_units, .blocks_per_row = 16, .dst_stride_u8 = 128 };
    } else if (a->kernel == K_CDEF) {
        pc.cdef = (pc_cdef){ .n_blocks = n_units, .tmp_stride_u16 = 16, .dst_stride_u8 = 8 };
    }

    VkCommandBuffer cb = v3d_runner_alloc_cmdbuf(r);
    VkCommandBufferBeginInfo cbbi = { .sType = VK_STRUCTURE_TYPE_COMMAND_BUFFER_BEGIN_INFO };
    vkBeginCommandBuffer(cb, &cbbi);
    vkCmdBindPipeline(cb, VK_PIPELINE_BIND_POINT_COMPUTE, pipe.pipeline);
    vkCmdBindDescriptorSets(cb, VK_PIPELINE_BIND_POINT_COMPUTE,
                            pipe.layout, 0, 1, &pipe.desc_set, 0, NULL);
    vkCmdPushConstants(cb, pipe.layout, VK_SHADER_STAGE_COMPUTE_BIT,
                       0, pc_size, &pc);
    vkCmdDispatch(cb, gc, 1, 1);
    vkEndCommandBuffer(cb);

    for (int i = 0; i < 5; i++) v3d_runner_submit_wait(r, cb);

    pthread_barrier_wait(&g_start);
    double t0 = now_s();
    uint64_t done = 0;
    while (!g_stop) {
        v3d_runner_submit_wait(r, cb);
        done += n_units;
    }
    a->elapsed_s = now_s() - t0;
    a->units_done = done;

    v3d_runner_destroy_pipeline(r, &pipe);
    if (has_src) v3d_runner_destroy_buffer(r, &buf_src);
    v3d_runner_destroy_buffer(r, &buf_dst);
    v3d_runner_destroy_buffer(r, &buf_meta);
    v3d_runner_destroy(r);
    return NULL;
}

/* --- Timer --- */

typedef struct { double duration_s; } timer_args;
static void *timer_thread(void *p) {
    timer_args *a = p;
    pthread_barrier_wait(&g_start);
    double end = now_s() + a->duration_s;
    while (now_s() < end) {
        struct timespec ts = {0, 1000000}; nanosleep(&ts, NULL);
    }
    g_stop = 1;
    return NULL;
}

/* --- Main --- */

static enum kernel parse_kernel(const char *s) {
    if (!strcmp(s, "mc"))   return K_MC;
    if (!strcmp(s, "lpf4")) return K_LPF4;
    if (!strcmp(s, "lpf8")) return K_LPF8;
    if (!strcmp(s, "cdef")) return K_CDEF;
    if (!strcmp(s, "idct")) return K_IDCT;
    fprintf(stderr, "unknown kernel: %s\n", s); exit(2);
}

int main(int argc, char **argv)
{
    enum kernel cpu_k = K_MC, qpu_k = K_CDEF;
    int n_neon = 3, qpu_core = 3, qpu_n_units = 65536;
    double duration = 8.0;

    static struct option opts[] = {
        {"cpu-kernel",   required_argument, 0, 'c'},
        {"qpu-kernel",   required_argument, 0, 'q'},
        {"neon-threads", required_argument, 0, 'n'},
        {"qpu-core",     required_argument, 0, 'C'},
        {"qpu-units",    required_argument, 0, 'u'},
        {"duration",     required_argument, 0, 'd'},
        {0,0,0,0}
    };
    for (int c; (c = getopt_long(argc, argv, "c:q:n:C:u:d:", opts, 0)) != -1;) {
        switch (c) {
        case 'c': cpu_k = parse_kernel(optarg); break;
        case 'q': qpu_k = parse_kernel(optarg); break;
        case 'n': n_neon = atoi(optarg); break;
        case 'C': qpu_core = atoi(optarg); break;
        case 'u': qpu_n_units = atoi(optarg); break;
        case 'd': duration = atof(optarg); break;
        default: return 2;
        }
    }

    /* Cycle 5 Phase 6 landed — v3d_cdef.spv is M1-PASS. Use real
     * QPU dispatch for CDEF too. The NEON-fallback worker remains
     * compiled but is unselected. */
    int use_neon_fallback_for_cdef = 0;

    int barrier_count = n_neon + 1 /* QPU */ + 1 /* timer */ + 1 /* main */;
    printf("=== Issue 003 mixed-kernel M4 bench ===\n");
    printf("  cpu kernel: %s × %d threads (cores 0..%d)\n",
           kernel_name(cpu_k), n_neon, n_neon - 1);
    printf("  qpu kernel: %s on core %d (%s)\n",
           kernel_name(qpu_k), qpu_core,
           use_neon_fallback_for_cdef ?
             "dav1d NEON fallback — real QPU CDEF deferred to cycle 5 Phase 6" :
             "QPU dispatch");
    printf("  duration:   %.1fs\n\n", duration);

    pthread_barrier_init(&g_start, NULL, barrier_count);

    pthread_t timer_tid; timer_args ta = { .duration_s = duration };
    pthread_create(&timer_tid, NULL, timer_thread, &ta);

    pthread_t neon_tids[16] = {0};
    neon_args n_args[16] = {0};
    for (int i = 0; i < n_neon; i++) {
        n_args[i] = (neon_args){ .worker_id = i, .affinity_core = i, .kernel = cpu_k };
        pthread_create(&neon_tids[i], NULL, neon_worker, &n_args[i]);
    }

    pthread_t qpu_tid = 0;
    qpu_args q_args = {0};
    qpu_real_args qr_args = {0};
    if (use_neon_fallback_for_cdef) {
        q_args = (qpu_args){ .affinity_core = qpu_core, .n_units = qpu_n_units, .kernel = qpu_k };
        pthread_create(&qpu_tid, NULL, qpu_cdef_neon_fallback, &q_args);
    } else {
        qr_args = (qpu_real_args){ .affinity_core = qpu_core, .n_units = qpu_n_units, .kernel = qpu_k };
        pthread_create(&qpu_tid, NULL, qpu_real_worker, &qr_args);
    }

    pthread_barrier_wait(&g_start);

    pthread_join(timer_tid, NULL);
    for (int i = 0; i < n_neon; i++) pthread_join(neon_tids[i], NULL);
    pthread_join(qpu_tid, NULL);

    uint64_t cpu_total = 0; double cpu_max_e = 0;
    printf("NEON workers (%s):\n", kernel_name(cpu_k));
    for (int i = 0; i < n_neon; i++) {
        double r = n_args[i].units_done / n_args[i].elapsed_s / 1e6;
        printf("  core %d: %.3f %s\n", n_args[i].affinity_core, r, kernel_unit(cpu_k));
        cpu_total += n_args[i].units_done;
        if (n_args[i].elapsed_s > cpu_max_e) cpu_max_e = n_args[i].elapsed_s;
    }
    double cpu_rate = cpu_total / cpu_max_e / 1e6;
    printf("  CPU aggregate: %.3f %s\n\n", cpu_rate, kernel_unit(cpu_k));

    uint64_t qpu_done = use_neon_fallback_for_cdef ? q_args.units_done : qr_args.units_done;
    double qpu_elapsed = use_neon_fallback_for_cdef ? q_args.elapsed_s : qr_args.elapsed_s;
    double qpu_rate = qpu_done / qpu_elapsed / 1e6;
    printf("QPU worker (%s on core %d):\n", kernel_name(qpu_k), qpu_core);
    printf("  %.3f %s  (%llu units / %.3f s)\n",
           qpu_rate, kernel_unit(qpu_k),
           (unsigned long long) qpu_done, qpu_elapsed);

    pthread_barrier_destroy(&g_start);
    return 0;
}