daedalus-fourier/tests/bench_h264_primitives.c

/* SPDX-License-Identifier: BSD-2-Clause */
/* CLOCK_MONOTONIC under -std=c11 -CMAKE_C_EXTENSIONS=OFF. */
#define _POSIX_C_SOURCE 200809L
/*
 * bench_h264_primitives — NEON-path latency baseline for the H.264
 * primitive library landed across PRs #9–#23.
 *
 * Each kernel is exercised at a representative per-frame N for 1080p
 * (8160 MBs); the per-kernel total + ns/op + ms/frame are reported.
 * Lets us answer "what's the total NEON-only budget for the H.264
 * decode at 1080p" — useful for sizing intercept-patch decisions
 * (which kernels NEED QPU shaders vs which are budget-fine on NEON).
 *
 * NOT a ctest — produces wall-time numbers, doesn't pass/fail.
 *
 * Invoke:   ./build/bench_h264_primitives [iters]
 *           (default iters = 50, post-warmup = 5)
 *
 * NB: results are inherently approximate — single-core, includes
 * loop overhead + memory access patterns that may not match what
 * a real decode would hit (we touch a small set of pages repeatedly).
 * The numbers are useful for relative comparison and order-of-
 * magnitude sizing, not absolute perf claims.
 */

#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
#define LUMA_4x4_PER_MB   16   /* if transform_8x8=0 */
#define LUMA_8x8_PER_MB   4    /* if transform_8x8=1 */
#define CHROMA_4x4_PER_MB 8    /* 4 Cb + 4 Cr */
#define DEBLOCK_LUMA_EDGES_PER_MB 4    /* 4 horiz + 4 vert internal+MB-edge — ~4 each */
#define DEBLOCK_CHROMA_EDGES_PER_MB 2  /* 2 each direction */

/* Standard benchmark loop.  fn() is called n times per iteration. */
typedef void (*bench_fn)(void);

static double bench_ns(const char *name, int iters, int warmup,
                        int ops_per_iter, bench_fn fn)
{
    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 %8.2f 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. */

static daedalus_ctx *ctx;

/* --- 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 void bench_idct4(void) {
    daedalus_dispatch_h264_idct4(ctx, DAEDALUS_SUBSTRATE_CPU,
                                  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 void bench_idct8(void) {
    daedalus_dispatch_h264_idct8(ctx, DAEDALUS_SUBSTRATE_CPU,
                                  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 void bench_deblock_v(void) {
    daedalus_dispatch_h264_deblock_luma_v(ctx, DAEDALUS_SUBSTRATE_CPU,
                                           deblock_dst, 16, 256, deblock_meta);
}

static void bench_deblock_h(void) {
    daedalus_dispatch_h264_deblock_luma_h(ctx, DAEDALUS_SUBSTRATE_CPU,
                                           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 void bench_qpel_mc20(void) {
    daedalus_dispatch_h264_qpel_mc20(ctx, DAEDALUS_SUBSTRATE_CPU,
                                      qpel_dst, qpel_src, 16, 256, qpel_meta);
}
static void bench_qpel_mc02(void) {
    daedalus_dispatch_h264_qpel_mc02(ctx, DAEDALUS_SUBSTRATE_CPU,
                                      qpel_dst, qpel_src, 16, 256, qpel_meta);
}
static void bench_qpel_mc22(void) {
    daedalus_dispatch_h264_qpel_mc22(ctx, DAEDALUS_SUBSTRATE_CPU,
                                      qpel_dst, qpel_src, 16, 256, qpel_meta);
}

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;
    }

    /* 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: each block at offset i*16 (row layout matters less
     * here since we're just measuring per-block latency). */
    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: src and dst at row 3 col 3 of each 16x16 tile. */
    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), substrate=CPU NEON\n",
           iters, warmup);
    printf("Per-call N is set per kernel; ns/op is per BLOCK or EDGE.\n\n");

    double idct4_ns   = bench_ns("IDCT 4x4 luma",     iters, warmup, 1024, bench_idct4);
    double idct8_ns   = bench_ns("IDCT 8x8 luma",     iters, warmup,  256, bench_idct8);
    double debl_v_ns  = bench_ns("Deblock luma_v",    iters, warmup,  256, bench_deblock_v);
    double debl_h_ns  = bench_ns("Deblock luma_h",    iters, warmup,  256, bench_deblock_h);
    double qmc20_ns   = bench_ns("qpel mc20 (8x8)",   iters, warmup,  256, bench_qpel_mc20);
    double qmc02_ns   = bench_ns("qpel mc02 (8x8)",   iters, warmup,  256, bench_qpel_mc02);
    double qmc22_ns   = bench_ns("qpel mc22 (8x8)",   iters, warmup,  256, bench_qpel_mc22);

    /* Per-frame budget summary at 1080p (8160 MBs).  Worst-case
     * assumptions:
     *   - All MBs are transform_4x4 (16 4x4 IDCTs each) — so 130,560
     *     IDCT 4x4 blocks per frame.  If High profile transform_8x8,
     *     it'd be 32,640 IDCT 8x8 blocks instead.
     *   - All MBs are intra (no MC — qpel zero) OR all inter (no
     *     intra prediction).  We report MC at "all inter, all qpel
     *     mc22" worst case.
     *   - Deblock: ~4 luma_v + 4 luma_h edges per MB; assume all 8
     *     edges trigger filtering. */
    printf("\nProjected 1080p frame budgets (worst-case, CPU NEON only):\n");
    printf("  IDCT 4x4 (all-4x4 MBs):       %7.2f ms   (%d blocks)\n",
           idct4_ns * MBS_1080P * 16 / 1e6, MBS_1080P * 16);
    printf("  IDCT 8x8 (all-8x8 MBs):       %7.2f ms   (%d blocks)\n",
           idct8_ns * MBS_1080P * 4 / 1e6, MBS_1080P * 4);
    printf("  Deblock luma_v (all MBs):     %7.2f ms   (%d edges)\n",
           debl_v_ns * MBS_1080P * 4 / 1e6, MBS_1080P * 4);
    printf("  Deblock luma_h (all MBs):     %7.2f ms   (%d edges)\n",
           debl_h_ns * MBS_1080P * 4 / 1e6, MBS_1080P * 4);
    printf("  qpel mc22 (all 8x8 blocks):   %7.2f ms   (%d blocks)\n",
           qmc22_ns * MBS_1080P * 4 / 1e6, MBS_1080P * 4);

    double sum_idct_4x4 = idct4_ns * MBS_1080P * 16 / 1e6;
    double sum_deblock  = (debl_v_ns + debl_h_ns) * MBS_1080P * 4 / 1e6;
    double sum_mc       = qmc22_ns * MBS_1080P * 4 / 1e6;  /* worst-case all-mc22 */
    printf("\n  Sum (IDCT 4x4 + deblock luma + MC all-mc22): %7.2f ms\n",
           sum_idct_4x4 + sum_deblock + sum_mc);
    printf("  30 fps deadline:                              33.33 ms\n");
    printf("  Margin:                                       %+.2f ms\n",
           33.33 - (sum_idct_4x4 + sum_deblock + sum_mc));
    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");
    (void) qmc20_ns; (void) qmc02_ns;

    daedalus_ctx_destroy(ctx);
    return 0;
}