Function main

tests/test-opt.cpp:88–138

}

int main(void) {
    struct ggml_init_params params = {
        /* .mem_size   = */ 1024*1024*1024,
        /* .mem_buffer = */ NULL,
        /* .no_alloc   = */ false,
    };

    struct ggml_context * ctx = ggml_init(params);

    int64_t ne1[4] = {4, 128, 1, 1};
    int64_t ne2[4] = {4, 256, 1, 1};
    int64_t ne3[4] = {128, 256, 1, 1};

    struct ggml_tensor * a = get_random_tensor(ctx, 2, ne1, -1, +1);
    struct ggml_tensor * b = get_random_tensor(ctx, 2, ne2, -1, +1);
    ggml_set_param(ctx, a);
    ggml_set_param(ctx, b);

    struct ggml_tensor * c = get_random_tensor(ctx, 2, ne3, -1, +1);

    struct ggml_tensor * ab = ggml_mul_mat(ctx, a, b);
    struct ggml_tensor * d  = ggml_sub(ctx, c, ab);
    struct ggml_tensor * e  = ggml_sum(ctx, ggml_sqr(ctx, d));

    struct ggml_cgraph * ge = ggml_new_graph_custom(ctx, GGML_DEFAULT_GRAPH_SIZE, true);
    ggml_build_forward_expand(ge, e);
    ggml_graph_reset(ge);

    ggml_graph_compute_with_ctx(ctx, ge, /*n_threads*/ 1);

    const float fe = ggml_get_f32_1d(e, 0);
    printf("%s: e = %.4f\n", __func__, fe);

    struct ggml_opt_params opt_params = ggml_opt_default_params(GGML_OPT_ADAM);

    ggml_opt(ctx, opt_params, e);

    ggml_graph_reset(ge);

    ggml_graph_compute_with_ctx(ctx, ge, /*n_threads*/ 1);

    const float fe_opt = ggml_get_f32_1d(e, 0);
    printf("%s: original  e = %.4f\n", __func__, fe);
    printf("%s: optimized e = %.4f\n", __func__, fe_opt);

    const bool success = (fe_opt <= fe);
    assert(success);

    ggml_free(ctx);
    return success ? 0 : -1;
}
// int64_t ne1[4] = {4, 128, 1, 1};
// int64_t ne2[4] = {4, 256, 1, 1};;
// int64_t ne3[4] = {128, 256, 1, 1};