/* eg_cosine_batch_strategy_ggml.c — the GGML Strategy, and the preferred
 * default whenever it is available (see the factory's selection order in
 * eg_cosine_batch.c).
 *
 * WHY: directive from Will Anderson — stop hand-rolling GPU kernels, use a
 * real, proven, permissively-licensed library instead. ggml (the compute
 * library underneath llama.cpp, MIT licensed) is already installed on this
 * machine as a standalone Homebrew package (`brew info ggml`), independent
 * of llama.cpp itself. This file is a genuinely bounded COMPUTE UTILITY —
 * batch cosine-similarity math — analogous to a VBD Accessor calling out to
 * infrastructure. It is explicitly NOT the engram's reasoning/persistence
 * core; using ggml here does not cross the "own the core" line, because
 * batch cosine math is infrastructure, not the graph traversal / activation
 * spreading / "thinking" that IS the core and stays 100% own-code.
 *
 * ── The real API shape (verified against the installed headers + a
 *    standalone probe program, not assumed from memory of other tensor
 *    libraries) ──────────────────────────────────────────────────────────
 *
 * ggml ships its CPU and Metal implementations as DYNAMICALLY LOADED PLUGIN
 * .so files (confirmed by nm: `ggml_backend_metal_init` is NOT an exported
 * symbol of libggml.dylib/libggml-base.dylib — it exists ONLY inside
 * libggml-metal.so under $(brew --prefix ggml)/libexec/). You cannot link
 * `-lggml-metal`; you must go through ggml's backend REGISTRY:
 *
 *   1. ggml_backend_load_all_from_path(dir) — dlopen()s every backend plugin
 *      .so found in `dir` and registers its device(s). We point this at
 *      $(brew --prefix ggml)/libexec (resolved once, at build+init time; see
 *      eg_ggml_backend_dir() below) rather than relying on
 *      ggml_backend_load_all()'s own default search heuristics, which are
 *      tuned for an installed llama.cpp-style app bundle layout, not an
 *      arbitrary `cc`-built binary invoked from an arbitrary cwd — the exact
 *      same "must not silently fall back to CPU for reasons that have
 *      nothing to do with GPU availability" concern PR #114's hand-rolled
 *      bridge already documented for its own embedded-shader-source choice.
 *   2. ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_GPU) — find the
 *      registered Metal device.
 *   3. ggml_backend_dev_init(dev, NULL) — get a live ggml_backend_t.
 *   4. Build a tiny ggml_context (no_alloc=true; it holds only tensor
 *      metadata, not data), declare 2D F32 tensors, ggml_mul_mat(nodes,
 *      query) — ggml's documented convention: A is [k cols, n rows], B is
 *      [k cols, m rows] (transposed internally), result is [n cols, m rows]
 *      — i.e. mul_mat(node_matrix[dim,n], query_matrix[dim,nq]) yields
 *      out[n,nq] where out[j*n+i] = dot(node_i, query_j). A row-major
 *      (dim,n) node matrix and a row-major (dim,nq) query matrix is EXACTLY
 *      the packed layout the hand-rolled Metal kernel already used — one
 *      matmul replaces the whole per-row dot-product loop.
 *   5. ggml_backend_alloc_ctx_tensors(ctx, backend) to actually allocate
 *      device buffers for those tensors, ggml_backend_tensor_set() to upload,
 *      ggml_backend_graph_compute() to run, ggml_backend_tensor_get() to
 *      read back.
 *
 * This exact sequence was verified end-to-end in a standalone probe (build
 * it yourself: see the PR description) against a plain-C CPU dot product —
 * bit-for-bit correct within float rounding. Real numbers against the
 * el_runtime.c CPU oracle are reported in the PR body via vindex_bench.
 *
 * ggml_mul_mat only computes the raw dot products — it has no notion of
 * "cosine" or of this codebase's -2.0 dim-mismatch/null/zero-norm sentinel.
 * Per the adapter's directive: gather only VALID, uniform-dim rows into the
 * packed matrix sent to the GPU (skipping null/mismatched rows entirely,
 * rather than the hand-rolled kernel's zero-pad-and-sentinel-in-shader
 * approach), then scatter -2.0 back for every row that was excluded — same
 * gather/scatter contract eg_cosine_batch.h documents. Norms (||node||,
 * ||query||) are computed on the CPU host in the same pass that already
 * touches every element to gather/convert — essentially free — using the
 * same 4-way-partial-sum accumulation the hand-rolled kernel and the CPU
 * oracle both use, so the float32 error profile stays comparable across all
 * three strategies. Only the O(n*dim*nq) dot-product matmul — the actual
 * expensive part — is offloaded to the GPU.
 *
 * Precision: ggml_mul_mat on F32 x F32 inputs computes in F32 on the Metal
 * backend (verified: no GGML_PREC_F16 default path applies to F32 inputs;
 * see ggml_mul_mat_set_prec in ggml.h, which exists specifically to raise
 * precision for lower-than-F32 inputs — ours are already F32 throughout).
 * The measured delta vs the CPU double-accumulated oracle is reported
 * honestly in the PR body (vindex_bench's BRUTE-GGML line), not assumed.
 */
#include "eg_cosine_batch_strategy.h"

#include <ggml.h>
#include <ggml-backend.h>
#include <ggml-alloc.h>

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <math.h>

/* ── lazy, one-time backend init, cached ─────────────────────────────────── */
static bool g_init_attempted = false;
static bool g_init_ok = false;
static ggml_backend_t g_backend = NULL;

/* Where to look for the dynamically-loaded backend plugin .so files.
 * EL_GGML_BACKEND_PATH overrides for non-standard installs; otherwise we try
 * the Homebrew opt-prefix symlink (stable across ggml point-version bumps —
 * $(brew --prefix ggml)/libexec — confirmed to exist and contain
 * libggml-metal.so / libggml-cpu-*.so / libggml-blas.so on this machine),
 * falling back to ggml's own default search (ggml_backend_load_all()) in
 * case a different install layout (e.g. a from-source build with a
 * standard-prefix install) makes that succeed instead. */
static const char* eg_ggml_backend_dir(void) {
    const char* s = getenv("EL_GGML_BACKEND_PATH");
    if (s && *s) return s;
    return "/opt/homebrew/opt/ggml/libexec";
}

static bool eg_ggml_ensure_init(void) {
    if (g_init_attempted) return g_init_ok;
    g_init_attempted = true;

    const char* dir = eg_ggml_backend_dir();
    /* dlopen every backend plugin .so in `dir` and register its device(s).
     * Never throws; a missing/empty directory just means no devices get
     * registered and the lookup below fails cleanly. */
    ggml_backend_load_all_from_path(dir);

    ggml_backend_dev_t dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_GPU);
    if (!dev) {
        /* Fall back to ggml's own default search heuristics only if the
         * explicit path above found nothing — avoids double-registering the
         * same plugins (ggml does not dedupe two different paths that
         * happen to resolve to the same files, e.g. our stable opt-prefix
         * symlink vs. its own Cellar-relative guess) in the common case
         * where the explicit path already worked. */
        ggml_backend_load_all();
        dev = ggml_backend_dev_by_type(GGML_BACKEND_DEVICE_TYPE_GPU);
    }
    if (!dev) return false;

    ggml_backend_t backend = ggml_backend_dev_init(dev, NULL);
    if (!backend) return false;

    g_backend = backend;
    g_init_ok = true;
    return true;
}

static bool ggml_strategy_available(void) {
    return eg_ggml_ensure_init();
}

/* ── shared core: gather valid rows + norms, matmul, scatter ────────────── */

/* 4-way partial-sum squared-norm accumulation over `dim` floats — same shape
 * as eg_cosine_batch.metal's per-thread accumulation and vindex_bench.c's
 * CPU brute_topk unroll, kept consistent on purpose so the float32 error
 * profile is comparable across all three strategies. */
static float eg_norm_sq_f32(const float* v, int32_t dim) {
    float s0 = 0, s1 = 0, s2 = 0, s3 = 0;
    int32_t d = 0, dim4 = dim & ~3;
    for (; d < dim4; d += 4) {
        s0 += v[d] * v[d]; s1 += v[d+1] * v[d+1];
        s2 += v[d+2] * v[d+2]; s3 += v[d+3] * v[d+3];
    }
    float s = (s0 + s1) + (s2 + s3);
    for (; d < dim; d++) s += v[d] * v[d];
    return s;
}

/* Runs one ggml_mul_mat(node_matrix[dim,n_valid], query_matrix[dim,nq]) and
 * combines it with CPU-computed norms into cosine scores, scattering into
 * out_scores at ORIGINAL (ungathered) indices. out_scores must already be
 * fully sized for n*nq (or n for the single-query case, nq=1) — every entry
 * gets written (valid rows get a real cosine, invalid rows get -2.0), so
 * this never leaves a partial result. Returns false only on a genuine
 * failure (alloc, compute) at which point out_scores is left as whatever a
 * caller-supplied scratch buffer already contained — callers here always
 * pass a fresh buffer they discard on false, matching the adapter contract
 * of "on failure, out_scores is treated as untouched" from the caller's
 * point of view. */
static bool eg_ggml_run(const float* queries, int32_t qdim, int32_t nq,
                         const float* const* node_ptrs, const int32_t* node_dims,
                         int32_t n, double* out_scores) {
    if (!queries || qdim <= 0 || nq <= 0 || !node_ptrs || !node_dims || n <= 0 || !out_scores)
        return false;
    if (!eg_ggml_ensure_init()) return false;

    /* Pass 1 (CPU): gather valid rows (non-NULL ptr, dim == qdim) into a
     * packed (dim, n_valid) row-major matrix, remembering the original index
     * of each packed row, and compute each valid row's squared norm in the
     * same pass. Rows excluded here get -2.0 scattered for every query
     * below without ever touching the GPU. */
    int32_t* valid_orig = (int32_t*)malloc((size_t)n * sizeof(int32_t));
    float* node_norm_sq  = (float*)malloc((size_t)n * sizeof(float)); /* indexed by packed position */
    float* node_matrix   = NULL;
    if (!valid_orig || !node_norm_sq) { free(valid_orig); free(node_norm_sq); return false; }

    int32_t n_valid = 0;
    for (int32_t i = 0; i < n; i++) {
        if (node_ptrs[i] && node_dims[i] == qdim) n_valid++;
    }

    if (n_valid > 0) {
        node_matrix = (float*)malloc((size_t)n_valid * (size_t)qdim * sizeof(float));
        if (!node_matrix) { free(valid_orig); free(node_norm_sq); return false; }
        int32_t w = 0;
        for (int32_t i = 0; i < n; i++) {
            if (!node_ptrs[i] || node_dims[i] != qdim) continue;
            memcpy(node_matrix + (size_t)w * qdim, node_ptrs[i], (size_t)qdim * sizeof(float));
            node_norm_sq[w] = eg_norm_sq_f32(node_ptrs[i], qdim);
            valid_orig[w] = i;
            w++;
        }
    }

    /* Query norms — nq is typically small (1 or the size of one batch of
     * comparison queries), so this loop is cheap regardless. */
    float* q_norm_sq = (float*)malloc((size_t)nq * sizeof(float));
    if (!q_norm_sq) { free(valid_orig); free(node_norm_sq); free(node_matrix); return false; }
    for (int32_t j = 0; j < nq; j++) q_norm_sq[j] = eg_norm_sq_f32(queries + (size_t)j * qdim, qdim);

    /* Nothing valid to compare against: every output is -2.0. Still a fully
     * and correctly populated result — no GPU dispatch was needed to know
     * that. */
    if (n_valid == 0) {
        for (size_t k = 0; k < (size_t)n * (size_t)nq; k++) out_scores[k] = -2.0;
        free(valid_orig); free(node_norm_sq); free(node_matrix); free(q_norm_sq);
        return true;
    }

    /* Pass 2 (GPU via ggml): dot = mul_mat(node_matrix[dim,n_valid],
     * queries[dim,nq]) -> dot[n_valid, nq], dot[j*n_valid+i] = dot(node_i,query_j). */
    struct ggml_init_params gp = {
        .mem_size   = ggml_tensor_overhead() * 8 + ggml_graph_overhead(),
        .mem_buffer = NULL,
        .no_alloc   = true,
    };
    struct ggml_context* ctx = ggml_init(gp);
    if (!ctx) { free(valid_orig); free(node_norm_sq); free(node_matrix); free(q_norm_sq); return false; }

    struct ggml_tensor* t_nodes = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, qdim, n_valid);
    struct ggml_tensor* t_query = ggml_new_tensor_2d(ctx, GGML_TYPE_F32, qdim, nq);
    if (!t_nodes || !t_query) { ggml_free(ctx); free(valid_orig); free(node_norm_sq); free(node_matrix); free(q_norm_sq); return false; }
    struct ggml_tensor* t_dot = ggml_mul_mat(ctx, t_nodes, t_query);
    if (!t_dot) { ggml_free(ctx); free(valid_orig); free(node_norm_sq); free(node_matrix); free(q_norm_sq); return false; }

    struct ggml_backend_buffer* buf = ggml_backend_alloc_ctx_tensors(ctx, g_backend);
    if (!buf) { ggml_free(ctx); free(valid_orig); free(node_norm_sq); free(node_matrix); free(q_norm_sq); return false; }

    ggml_backend_tensor_set(t_nodes, node_matrix, 0, (size_t)n_valid * qdim * sizeof(float));
    ggml_backend_tensor_set(t_query, queries, 0, (size_t)nq * qdim * sizeof(float));
    free(node_matrix); /* uploaded; the packed CPU copy is no longer needed */

    struct ggml_cgraph* gf = ggml_new_graph(ctx);
    if (!gf) { ggml_backend_buffer_free(buf); ggml_free(ctx); free(valid_orig); free(node_norm_sq); free(q_norm_sq); return false; }
    ggml_build_forward_expand(gf, t_dot);
    enum ggml_status st = ggml_backend_graph_compute(g_backend, gf);
    if (st != GGML_STATUS_SUCCESS) {
        ggml_backend_buffer_free(buf); ggml_free(ctx);
        free(valid_orig); free(node_norm_sq); free(q_norm_sq);
        return false;
    }

    float* dot = (float*)malloc(ggml_nbytes(t_dot));
    if (!dot) { ggml_backend_buffer_free(buf); ggml_free(ctx); free(valid_orig); free(node_norm_sq); free(q_norm_sq); return false; }
    ggml_backend_tensor_get(t_dot, dot, 0, ggml_nbytes(t_dot));

    /* Pass 3 (CPU): combine dot/(||a||*||b||) per (query,node) pair, scatter
     * into out_scores at ORIGINAL node indices; every excluded row gets
     * -2.0 for every query. out_scores is fully populated either way. */
    for (int32_t j = 0; j < nq; j++) {
        double* orow = out_scores + (size_t)j * n;
        for (int32_t i = 0; i < n; i++) orow[i] = -2.0; /* default: excluded */
        for (int32_t w = 0; w < n_valid; w++) {
            float na = node_norm_sq[w], nb = q_norm_sq[j];
            int32_t oi = valid_orig[w];
            if (na <= 0.0f || nb <= 0.0f) { orow[oi] = -2.0; continue; }
            float d = dot[(size_t)j * n_valid + w];
            orow[oi] = (double)(d / sqrtf(na * nb));
        }
    }

    free(dot);
    ggml_backend_buffer_free(buf);
    ggml_free(ctx);
    free(valid_orig); free(node_norm_sq); free(q_norm_sq);
    return true;
}

static bool ggml_strategy_batch(const float* query, int32_t qdim,
                                 const float* const* node_ptrs, const int32_t* node_dims,
                                 int32_t n, double* out_scores) {
    if (!query || qdim <= 0 || !node_ptrs || !node_dims || n <= 0 || !out_scores) return false;
    /* out_scores here is n doubles (nq=1); eg_ggml_run writes n*nq = n of
     * them, laid out identically to the single-query contract. */
    return eg_ggml_run(query, qdim, 1, node_ptrs, node_dims, n, out_scores);
}

static bool ggml_strategy_batch_multi(const float* queries, int32_t qdim, int32_t nq,
                                       const float* const* node_ptrs, const int32_t* node_dims,
                                       int32_t n, double* out_scores) {
    return eg_ggml_run(queries, qdim, nq, node_ptrs, node_dims, n, out_scores);
}

static const EgCosineBatchStrategy g_ggml_strategy = {
    .name = "ggml",
    .available = ggml_strategy_available,
    .batch = ggml_strategy_batch,
    .batch_multi = ggml_strategy_batch_multi,
};

const EgCosineBatchStrategy* eg_cosine_batch_strategy_ggml(void) {
    return &g_ggml_strategy;
}