/* SPDX-License-Identifier: BSD-2-Clause */
/* CLOCK_MONOTONIC under -std=c11 -CMAKE_C_EXTENSIONS=OFF. */
#define _POSIX_C_SOURCE 200809L
/*
 * bench_h264_primitives — latency baseline for the H.264 primitive
 * library landed across PRs #9–#35.
 *
 * Each kernel is exercised at a representative per-frame N for 1080p
 * (8160 MBs); the per-kernel total + ns/op + ms/frame are reported,
 * once per substrate (CPU NEON, QPU V3D7 compute).  The QPU column
 * appears only when the host has a usable Vulkan device.  When both
 * columns exist a CPU/QPU ratio is printed; that's the per-kernel
 * data the QPU-substrate decree (2026-05-23) deliberately overrides
 * but which is still useful to track over time as dispatch overhead
 * shrinks (buffer pool, persistent cmdbuf, dmabuf import — tasks 160-162).
 *
 * NOT a ctest — produces wall-time numbers, doesn't pass/fail.
 *
 * Invoke:   ./build/bench_h264_primitives [iters [warmup]]
 *           (default iters = 50, warmup = 5)
 */

#include "daedalus.h"

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <time.h>

static uint64_t xs64_state = 0xfeedface5a5a5a5aULL;
static uint64_t xs64(void) {
    uint64_t x = xs64_state;
    x ^= x << 13; x ^= x >> 7; x ^= x << 17;
    return xs64_state = x;
}

static double now_ms(void) {
    struct timespec ts;
    clock_gettime(CLOCK_MONOTONIC, &ts);
    return ts.tv_sec * 1000.0 + ts.tv_nsec / 1.0e6;
}

/* Per-1080p-frame counts (8160 MBs at 1920x1088). */
#define MBS_1080P  8160

/* Standard benchmark loop.  fn() is called n times per iteration.
 *
 * fn() now returns the dispatch's int rc.  A single preflight call is
 * made before the hot loop; if rc != 0 (which on the QPU substrate
 * almost always means "SPV not found via any search path"), bench_ns
 * returns -1 and the caller must NOT report the kernel as measured.
 *
 * Without this, a missing SPV makes every dispatch fail fast at the
 * cost of one fprintf+open call (~1-5 µs), and the loop times that
 * cost as if it were real QPU work — producing absurdly-small ns/op
 * numbers that look like a QPU speedup.  This is exactly what made
 * PR #36's bench numbers a measurement artifact. */
typedef int (*bench_fn)(void);

static double bench_ns(const char *name, int iters, int warmup,
                        int ops_per_iter, bench_fn fn)
{
    int rc = fn();
    if (rc != 0) {
        printf("  %-32s    DISPATCH FAILED rc=%d — kernel skipped\n", name, rc);
        return -1;
    }
    for (int i = 0; i < warmup; i++) fn();
    double t0 = now_ms();
    for (int i = 0; i < iters; i++) fn();
    double t1 = now_ms();
    double total_ms = (t1 - t0);
    double ns_per_op = (total_ms * 1e6) / ((double) iters * ops_per_iter);
    printf("  %-32s %10.2f ns/op  (%d iters x %d ops)\n",
           name, ns_per_op, iters, ops_per_iter);
    return ns_per_op;
}

/* ---- Per-kernel scaffolding.  Each section sets up the buffers +
 * meta, then defines a static fn() that calls the corresponding
 * dispatch with a representative N.  The substrate is read from the
 * global g_sub so the same fn() can be re-driven with CPU then QPU. */

static daedalus_ctx          *ctx;
static daedalus_substrate     g_sub = DAEDALUS_SUBSTRATE_CPU;

/* --- IDCT 4x4 luma: N = 16 blocks per MB.  Bench with 1024 blocks
 *     per call (64 MBs worth).  Per-MB the dispatch overhead is the
 *     same regardless of N — we want ns per block. */
static int16_t              idct4_coeffs[1024 * 16];
static daedalus_h264_block_meta idct4_meta[1024];
static uint8_t              idct_dst[64 * 4 * 16 * 16];   /* 64 MB-rows × ... */

static int bench_idct4(void) {
    return daedalus_dispatch_h264_idct4(ctx, g_sub,
                                  idct_dst, 64*16, idct4_coeffs, 1024, idct4_meta);
}

/* --- IDCT 8x8 luma: 256 8x8 blocks per call. */
static int16_t              idct8_coeffs[256 * 64];
static daedalus_h264_block_meta idct8_meta[256];

static int bench_idct8(void) {
    return daedalus_dispatch_h264_idct8(ctx, g_sub,
                                  idct_dst, 64*16, idct8_coeffs, 256, idct8_meta);
}

/* --- Deblock luma_v (cycle 8 baseline; M3 path). */
static daedalus_h264_deblock_meta deblock_meta[256];
static uint8_t deblock_dst[256 * 16 * 16];

static int bench_deblock_v(void) {
    return daedalus_dispatch_h264_deblock_luma_v(ctx, g_sub,
                                           deblock_dst, 16, 256, deblock_meta);
}

static int bench_deblock_h(void) {
    return daedalus_dispatch_h264_deblock_luma_h(ctx, g_sub,
                                           deblock_dst, 16, 256, deblock_meta);
}

/* --- qpel mc20 + mc02 + mc22 (the H/V/HV anchors). */
static uint8_t qpel_src[256 * 16 * 16];
static uint8_t qpel_dst[256 * 16 * 16];
static daedalus_h264_qpel_meta qpel_meta[256];

static int bench_qpel_mc20(void) {
    return daedalus_dispatch_h264_qpel_mc20(ctx, g_sub,
                                      qpel_dst, qpel_src, 16, 256, qpel_meta);
}
static int bench_qpel_mc02(void) {
    return daedalus_dispatch_h264_qpel_mc02(ctx, g_sub,
                                      qpel_dst, qpel_src, 16, 256, qpel_meta);
}
static int bench_qpel_mc22(void) {
    return daedalus_dispatch_h264_qpel_mc22(ctx, g_sub,
                                      qpel_dst, qpel_src, 16, 256, qpel_meta);
}

/* ---- One row of bench output:
 *   - kernel name + N
 *   - CPU ns/op
 *   - QPU ns/op (or "n/a" if Vulkan absent)
 *   - CPU/QPU ratio (>1 means QPU wins; <1 means CPU wins) */
struct row {
    const char *name;
    int         n_per_call;
    bench_fn    fn;
    double      cpu_ns;
    double      qpu_ns;   /* -1 if not measured */
    int         frame_n;  /* count per 1080p frame */
};

static struct row rows[] = {
    {"IDCT 4x4 luma",       1024, bench_idct4,     0, -1, MBS_1080P * 16},
    {"IDCT 8x8 luma",        256, bench_idct8,     0, -1, MBS_1080P *  4},
    {"Deblock luma_v",       256, bench_deblock_v, 0, -1, MBS_1080P *  4},
    {"Deblock luma_h",       256, bench_deblock_h, 0, -1, MBS_1080P *  4},
    {"qpel mc20 (8x8)",      256, bench_qpel_mc20, 0, -1, MBS_1080P *  4},
    {"qpel mc02 (8x8)",      256, bench_qpel_mc02, 0, -1, MBS_1080P *  4},
    {"qpel mc22 (8x8)",      256, bench_qpel_mc22, 0, -1, MBS_1080P *  4},
};
#define N_ROWS ((int)(sizeof(rows)/sizeof(rows[0])))

int main(int argc, char **argv)
{
    int iters  = argc > 1 ? atoi(argv[1]) : 50;
    int warmup = argc > 2 ? atoi(argv[2]) : 5;

    ctx = daedalus_ctx_create();
    if (!ctx) {
        fprintf(stderr, "ctx create failed (Vulkan?)\n");
        return 1;
    }
    int has_qpu = daedalus_ctx_has_qpu(ctx);

    /* Pre-fill all input buffers with random data so the NEON inner
     * loops see realistic memory access patterns. */
    for (size_t i = 0; i < sizeof(idct4_coeffs)/2; i++)
        idct4_coeffs[i] = (int16_t)((int)(xs64() % 1024) - 512);
    for (size_t i = 0; i < sizeof(idct8_coeffs)/2; i++)
        idct8_coeffs[i] = (int16_t)((int)(xs64() % 1024) - 512);
    for (size_t i = 0; i < sizeof(qpel_src); i++) qpel_src[i] = (uint8_t)(xs64() & 0xff);

    /* IDCT meta. */
    for (size_t i = 0; i < 1024; i++)
        idct4_meta[i].dst_off = (uint32_t)((i / 16) * 64 + (i % 16) * 4);
    for (size_t i = 0; i < 256; i++)
        idct8_meta[i].dst_off = (uint32_t)((i / 8) * 64 + (i % 8) * 8);

    /* Deblock meta: edge offsets within 256 16x16 tiles. */
    for (size_t i = 0; i < 256; i++) {
        deblock_meta[i].dst_off = (uint32_t)(i * 256 + 4 * 16);
        deblock_meta[i].alpha = 30;
        deblock_meta[i].beta  = 10;
        for (int s = 0; s < 4; s++) deblock_meta[i].tc0[s] = (int8_t)(s + 1);
    }

    /* qpel meta. */
    for (size_t i = 0; i < 256; i++) {
        qpel_meta[i].src_off = (uint32_t)(i * 256 + 3 * 16 + 3);
        qpel_meta[i].dst_off = (uint32_t)(i * 256 + 3 * 16 + 3);
    }

    printf("bench_h264_primitives: %d iters (%d warmup)\n", iters, warmup);
    printf("  ctx has_qpu=%d  (CPU pass always runs; QPU pass skipped without Vulkan)\n\n", has_qpu);

    /* Pass 1: CPU NEON. */
    g_sub = DAEDALUS_SUBSTRATE_CPU;
    printf("== CPU NEON ==\n");
    for (int i = 0; i < N_ROWS; i++)
        rows[i].cpu_ns = bench_ns(rows[i].name, iters, warmup, rows[i].n_per_call, rows[i].fn);

    /* Pass 2: QPU compute (if available). */
    int qpu_failures = 0;
    if (has_qpu) {
        g_sub = DAEDALUS_SUBSTRATE_QPU;
        printf("\n== QPU V3D7 compute ==\n");
        for (int i = 0; i < N_ROWS; i++) {
            rows[i].qpu_ns = bench_ns(rows[i].name, iters, warmup, rows[i].n_per_call, rows[i].fn);
            if (rows[i].qpu_ns < 0) qpu_failures++;
        }
        if (qpu_failures) {
            fprintf(stderr,
                "\nbench_h264_primitives: %d of %d QPU dispatches failed.\n"
                "  Almost always means SPV files were not found via any of:\n"
                "    cwd  /  $DAEDALUS_SHADER_DIR  /  binary-dir  /\n"
                "    /opt/fourier/share/daedalus-fourier  /  /usr/share/daedalus-fourier\n"
                "  Set DAEDALUS_SHADER_DIR=<path> or run from a dir where the\n"
                "  .spv files exist (e.g. the cmake build dir).\n",
                qpu_failures, N_ROWS);
            return 2;
        }
    }

    /* Summary table — both substrates side by side. */
    printf("\n== Per-kernel comparison ==\n");
    printf("  %-24s %12s %12s %8s   %7s\n",
           "kernel", "CPU ns/op", "QPU ns/op", "winner", "ms/frame");
    for (int i = 0; i < N_ROWS; i++) {
        double cpu_ms = rows[i].cpu_ns * rows[i].frame_n / 1e6;
        double qpu_ms = rows[i].qpu_ns > 0 ? rows[i].qpu_ns * rows[i].frame_n / 1e6 : -1;
        const char *winner;
        char ratio[16];
        if (rows[i].qpu_ns <= 0) {
            winner = "CPU";  /* QPU n/a */
            snprintf(ratio, sizeof(ratio), "n/a");
        } else if (rows[i].cpu_ns < rows[i].qpu_ns) {
            winner = "CPU";
            snprintf(ratio, sizeof(ratio), "%.2fx", rows[i].qpu_ns / rows[i].cpu_ns);
        } else {
            winner = "QPU";
            snprintf(ratio, sizeof(ratio), "%.2fx", rows[i].cpu_ns / rows[i].qpu_ns);
        }
        char qpu_field[16];
        if (rows[i].qpu_ns > 0) snprintf(qpu_field, sizeof(qpu_field), "%.2f", rows[i].qpu_ns);
        else                    snprintf(qpu_field, sizeof(qpu_field), "n/a");
        char ms_field[24];
        if (qpu_ms > 0)
            snprintf(ms_field, sizeof(ms_field), "%.2f/%.2f", cpu_ms, qpu_ms);
        else
            snprintf(ms_field, sizeof(ms_field), "%.2f/n/a", cpu_ms);
        printf("  %-24s %12.2f %12s   %3s %s   %s\n",
               rows[i].name, rows[i].cpu_ns, qpu_field, winner, ratio, ms_field);
    }

    /* Per-frame budget summary at 1080p (8160 MBs). */
    double cpu_idct4 = rows[0].cpu_ns * MBS_1080P * 16 / 1e6;
    double cpu_debl  = (rows[2].cpu_ns + rows[3].cpu_ns) * MBS_1080P * 4 / 1e6;
    double cpu_mc    = rows[6].cpu_ns * MBS_1080P * 4 / 1e6;   /* mc22 worst-case */
    double cpu_sum   = cpu_idct4 + cpu_debl + cpu_mc;

    printf("\n== Projected 1080p worst-case (CPU NEON only) ==\n");
    printf("  IDCT 4x4 + deblock luma + qpel mc22:  %.2f ms (30fps deadline 33.33)\n", cpu_sum);
    printf("  Margin:                               %+.2f ms\n", 33.33 - cpu_sum);

    if (has_qpu) {
        double qpu_idct4 = rows[0].qpu_ns * MBS_1080P * 16 / 1e6;
        double qpu_debl  = (rows[2].qpu_ns + rows[3].qpu_ns) * MBS_1080P * 4 / 1e6;
        double qpu_mc    = rows[6].qpu_ns * MBS_1080P * 4 / 1e6;
        double qpu_sum   = qpu_idct4 + qpu_debl + qpu_mc;
        printf("\n== Projected 1080p worst-case (QPU V3D7 compute only) ==\n");
        printf("  IDCT 4x4 + deblock luma + qpel mc22:  %.2f ms (30fps deadline 33.33)\n", qpu_sum);
        printf("  Margin:                               %+.2f ms\n", 33.33 - qpu_sum);
        printf("\n  CPU vs QPU sum ratio: %.2fx  (>1 means QPU wins)\n",
               qpu_sum > 0 ? cpu_sum / qpu_sum : 0.0);
    }

    printf("\n(NOT included: chroma deblock, chroma IDCT, intra prediction,\n");
    printf(" CABAC/CAVLC entropy.  These bench numbers are a budget LOWER\n");
    printf(" bound; the real decode stack adds 20-40%% on top.\n");
    printf(" Per-kernel substrate decisions belong in daedalus_core.c recipe\n");
    printf(" table; the QPU substrate decree (2026-05-23) keeps everything\n");
    printf(" on QPU regardless of these numbers as a policy choice.)\n");

    daedalus_ctx_destroy(ctx);
    return 0;
}