/*
 * Cycle 8 Phase 6+7 — QPU bench for H.264 luma deblock.
 *
 * Reports:
 *   M1: 3-way bit-exact (QPU vs NEON vs C ref) per Phase 5 YELLOW-1.
 *   M2: QPU sustained Medge/s.
 *
 * Bench contract enforcement (Phase 5 RED-2): m.x is positioned so
 * that m.x >= 4 * stride for every edge.
 *
 * License: BSD-2-Clause.
 */
#define _POSIX_C_SOURCE 200809L
#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <stddef.h>
#include <string.h>
#include <assert.h>
#include <time.h>
#include <getopt.h>
#include <vulkan/vulkan.h>

#include "v3d_runner.h"

extern void daedalus_h264_v_loop_filter_luma_ref(
    uint8_t *pix, ptrdiff_t stride,
    int alpha, int beta, int8_t tc0[4]);

extern void ff_h264_v_loop_filter_luma_neon(
    uint8_t *pix, ptrdiff_t stride,
    int alpha, int beta, int8_t *tc0);

#define TILE_STRIDE 16
#define TILE_ROWS    16
#define TILE_BYTES  (TILE_ROWS * TILE_STRIDE)
#define EDGE_ROW    4
#define EDGE_OFF    (EDGE_ROW * TILE_STRIDE)   /* byte offset into a tile to row 0 of bottom block */

static uint64_t xs_state;
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 void gen_tile(uint8_t *tile)
{
    int a = (int)(xs() % 200) + 20;
    int b = (int)(xs() % 200) + 20;
    int noise = (int)(xs() % 30) + 1;
    for (int r = 0; r < TILE_ROWS; r++) {
        for (int c = 0; c < TILE_STRIDE; c++) {
            int v;
            if (r >= EDGE_ROW - 4 && r < EDGE_ROW + 4) {
                int base = (r < EDGE_ROW) ? a : b;
                int n = ((int)(xs() % (2*noise + 1))) - noise;
                v = base + n;
            } else {
                v = (int)(xs() & 0xff);
            }
            tile[r * TILE_STRIDE + c] = (uint8_t)(v < 0 ? 0 : v > 255 ? 255 : v);
        }
    }
}

static void gen_thresholds(int *alpha, int *beta, int8_t tc0[4])
{
    *alpha = (int)(xs() % 64) + 1;
    *beta  = (int)(xs() % 16) + 1;
    for (int s = 0; s < 4; s++) {
        int r = (int)(xs() % 8);
        tc0[s] = (int8_t)(r == 0 ? -1 : (r - 1));
    }
}

static double now_seconds(void) {
    struct timespec ts;
    clock_gettime(CLOCK_MONOTONIC_RAW, &ts);
    return ts.tv_sec + ts.tv_nsec * 1e-9;
}

typedef struct {
    uint32_t n_edges;
    uint32_t dst_stride_u8;
    uint32_t _pad0;
    uint32_t _pad1;
} push_consts;

int main(int argc, char **argv)
{
    int n_edges = 16384;
    int iters = 200;
    int verify_only = 0;
    uint64_t seed = 0;
    const char *spv_path = "v3d_h264deblock.spv";

    static struct option opts[] = {
        {"edges",       required_argument, 0, 'e'},
        {"iters",       required_argument, 0, 'i'},
        {"seed",        required_argument, 0, 's'},
        {"spv",         required_argument, 0, 'S'},
        {"verify-only", no_argument,       0, 'V'},
        {0,0,0,0}
    };
    for (int c; (c = getopt_long(argc, argv, "e:i:s:S:V", opts, 0)) != -1;) {
        switch (c) {
        case 'e': n_edges = atoi(optarg); break;
        case 'i': iters = atoi(optarg); break;
        case 's': seed = strtoull(optarg, 0, 0); break;
        case 'S': spv_path = optarg; break;
        case 'V': verify_only = 1; break;
        default: return 2;
        }
    }

    xs_state = seed ? seed : 0xdeb1ec500dULL;

    v3d_runner *r = v3d_runner_create();
    if (!r) { fprintf(stderr, "v3d_runner_create failed\n"); return 1; }
    printf("=== v3d H.264 deblock bench ===\n");
    printf("  device:  %s\n", v3d_runner_device_name(r));
    printf("  n_edges: %d  iters: %d  seed: 0x%016llx\n",
           n_edges, iters, (unsigned long long) (seed ? seed : 0xdeb1ec500dULL));

    size_t meta_bytes = (size_t) n_edges * 4 * sizeof(uint32_t);
    size_t dst_bytes  = (size_t) n_edges * TILE_BYTES;

    v3d_buffer buf_meta = {0}, buf_dst = {0};
    if (v3d_runner_create_buffer(r, meta_bytes, &buf_meta)) return 1;
    if (v3d_runner_create_buffer(r, dst_bytes,  &buf_dst))  return 1;

    uint8_t *master = malloc(dst_bytes);
    uint8_t *expected_c = malloc(dst_bytes);
    uint8_t *expected_n = malloc(dst_bytes);
    int *alphas = malloc(n_edges*sizeof(int));
    int *betas  = malloc(n_edges*sizeof(int));
    int8_t (*tc0s)[4] = malloc(n_edges * 4);
    if (!master || !expected_c || !expected_n || !alphas || !betas || !tc0s) {
        fprintf(stderr, "alloc fail\n"); return 1;
    }

    for (int i = 0; i < n_edges; i++) {
        gen_tile(master + (size_t)i * TILE_BYTES);
        gen_thresholds(&alphas[i], &betas[i], tc0s[i]);
    }

    /* C ref expected. */
    memcpy(expected_c, master, dst_bytes);
    for (int i = 0; i < n_edges; i++)
        daedalus_h264_v_loop_filter_luma_ref(
            expected_c + (size_t)i * TILE_BYTES + EDGE_OFF,
            TILE_STRIDE, alphas[i], betas[i], tc0s[i]);

    /* NEON expected. */
    memcpy(expected_n, master, dst_bytes);
    for (int i = 0; i < n_edges; i++)
        ff_h264_v_loop_filter_luma_neon(
            expected_n + (size_t)i * TILE_BYTES + EDGE_OFF,
            TILE_STRIDE, alphas[i], betas[i], tc0s[i]);

    /* Parity check C ref vs NEON. */
    int cn_mis = 0;
    for (size_t b = 0; b < dst_bytes; b++)
        if (expected_c[b] != expected_n[b]) cn_mis++;
    printf("  C ref vs NEON parity: %d/%zu byte mismatches\n", cn_mis, dst_bytes);
    if (cn_mis > 0) {
        fprintf(stderr, "ERROR: C ref disagrees with NEON before QPU.\n");
        return 1;
    }

    /* Populate meta SSBO (Phase 5 RED-2: enforce m.x >= 4*stride). */
    uint32_t *meta = (uint32_t *) buf_meta.mapped;
    uint32_t stride_u8 = TILE_STRIDE;
    for (int i = 0; i < n_edges; i++) {
        uint32_t mx = (uint32_t)((size_t)i * TILE_BYTES + EDGE_OFF);
        assert(mx >= 4 * stride_u8 && "Phase 5 RED-2 contract violated");
        meta[4*i + 0] = mx;
        meta[4*i + 1] = ((uint32_t)alphas[i]) | (((uint32_t)betas[i]) << 8);
        /* Pack tc0[0..3] as 4 int8 in low 32 bits of m.z. */
        meta[4*i + 2] = ((uint32_t)(uint8_t)tc0s[i][0])
                      | (((uint32_t)(uint8_t)tc0s[i][1]) << 8)
                      | (((uint32_t)(uint8_t)tc0s[i][2]) << 16)
                      | (((uint32_t)(uint8_t)tc0s[i][3]) << 24);
        meta[4*i + 3] = 0;
    }
    memcpy(buf_dst.mapped, master, dst_bytes);

    /* Pipeline. */
    v3d_pipeline pipe = {0};
    if (v3d_runner_create_pipeline(r, spv_path, /*n_ssbos=*/2,
                                   /*push_const_size=*/sizeof(push_consts),
                                   &pipe)) return 1;
    v3d_buffer binds[2] = { buf_meta, buf_dst };
    if (v3d_runner_bind_buffers(r, &pipe, binds, 2)) return 1;

    const uint32_t edges_per_wg = 16;
    uint32_t wg_count = (uint32_t)((n_edges + edges_per_wg - 1) / edges_per_wg);
    printf("  dispatch: %u WGs × 256 invocations = %u edges\n",
           wg_count, wg_count * edges_per_wg);

    push_consts pc = {
        .n_edges = (uint32_t) n_edges,
        .dst_stride_u8 = stride_u8,
    };

    VkCommandBuffer cb = v3d_runner_alloc_cmdbuf(r);
    if (cb == VK_NULL_HANDLE) return 1;
    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, sizeof(pc), &pc);
    vkCmdDispatch(cb, wg_count, 1, 1);
    vkEndCommandBuffer(cb);

    /* M1 3-way. */
    printf("\n=== M1₈: QPU vs C ref vs NEON ===\n");
    memcpy(buf_dst.mapped, master, dst_bytes);
    if (v3d_runner_submit_wait(r, cb)) return 1;

    int qc_mis = 0, qn_mis = 0, prints = 0;
    for (int i = 0; i < n_edges; i++) {
        uint8_t *q = (uint8_t *) buf_dst.mapped + (size_t)i * TILE_BYTES;
        uint8_t *c = expected_c + (size_t)i * TILE_BYTES;
        uint8_t *n = expected_n + (size_t)i * TILE_BYTES;
        int qc = memcmp(q, c, TILE_BYTES);
        int qn = memcmp(q, n, TILE_BYTES);
        if (qc) qc_mis++;
        if (qn) qn_mis++;
        if ((qc || qn) && prints < 3) {
            fprintf(stderr, "MISMATCH edge %d alpha=%d beta=%d tc0=[%d,%d,%d,%d]\n",
                    i, alphas[i], betas[i],
                    tc0s[i][0], tc0s[i][1], tc0s[i][2], tc0s[i][3]);
            prints++;
        }
    }
    printf("  QPU vs C ref: %d/%d edges bit-exact (%.4f%%)\n",
           n_edges - qc_mis, n_edges, 100.0 * (n_edges - qc_mis) / n_edges);
    printf("  QPU vs NEON:  %d/%d edges bit-exact (%.4f%%)\n",
           n_edges - qn_mis, n_edges, 100.0 * (n_edges - qn_mis) / n_edges);
    if (qc_mis || qn_mis) {
        fprintf(stderr, "REFUSING to measure throughput on a broken kernel.\n");
        return 1;
    }

    if (verify_only) {
        v3d_runner_destroy_pipeline(r, &pipe);
        v3d_runner_destroy_buffer(r, &buf_dst);
        v3d_runner_destroy_buffer(r, &buf_meta);
        v3d_runner_destroy(r);
        return 0;
    }

    /* M2 throughput. */
    printf("\n=== M2₈: QPU throughput ===\n");
    for (int i = 0; i < 5; i++) {
        memcpy(buf_dst.mapped, master, dst_bytes);
        if (v3d_runner_submit_wait(r, cb)) return 1;
    }

    double t0 = now_seconds();
    for (int i = 0; i < iters; i++) {
        memcpy(buf_dst.mapped, master, dst_bytes);
        if (v3d_runner_submit_wait(r, cb)) return 1;
    }
    double t1 = now_seconds();

    double s0 = now_seconds();
    for (int i = 0; i < iters; i++) memcpy(buf_dst.mapped, master, dst_bytes);
    double s1 = now_seconds();

    double kernel_seconds = (t1 - t0) - (s1 - s0);
    double total = (double) n_edges * iters;
    double medges = total / kernel_seconds / 1e6;

    printf("  edges/dispatch: %d\n", n_edges);
    printf("  iters:          %d\n", iters);
    printf("  total edges:    %.0f\n", total);
    printf("  elapsed (kern) = %.6f s\n", kernel_seconds);
    printf("  M2₈ throughput = %.3f Medge/s\n", medges);
    printf("  per-edge       = %.1f ns\n", kernel_seconds / total * 1e9);
    printf("  per-dispatch   = %.1f us\n", kernel_seconds / iters * 1e6);

    double M3_8 = 91.947;
    double R8 = medges / M3_8;
    printf("\n  Cycle 8 NEON M3₈ = %.3f Medge/s\n", M3_8);
    printf("  R₈ = M2₈/M3₈     = %.3f\n", R8);
    if      (R8 >= 1.0) printf("  decision band     = GREEN\n");
    else if (R8 >= 0.5) printf("  decision band     = YELLOW (M4 decides)\n");
    else if (R8 >= 0.1) printf("  decision band     = ORANGE (M4 may rescue)\n");
    else                printf("  decision band     = RED (structural)\n");

    /* H.264 1080p30 floor: 8 Medge/s worst, 3 realistic. */
    printf("  H.264 1080p30 worst-case floor: %.2fx margin (8.0 Medge/s req'd)\n", medges / 8.0);

    v3d_runner_destroy_pipeline(r, &pipe);
    v3d_runner_destroy_buffer(r, &buf_dst);
    v3d_runner_destroy_buffer(r, &buf_meta);
    v3d_runner_destroy(r);
    free(master); free(expected_c); free(expected_n);
    free(alphas); free(betas); free(tc0s);
    return 0;
}