Function test_active

subprojects/llama.cpp/tests/test-barrier.cpp:82–136

}

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

    struct ggml_context * ctx = ggml_init(params);

    // Create graph
    struct ggml_cgraph * gf = ggml_new_graph(ctx);

    // Small graph with, parallel ops with barriers
    struct ggml_tensor * out = ggml_new_tensor_1d(ctx, GGML_TYPE_F32,  64);
    for (int i = 0; i < 2; i++) {
        struct ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, 64, 128);
        out = ggml_mul_mat(ctx, a, out);

        struct ggml_tensor * d = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, 128, 64);
        out = ggml_mul_mat(ctx, d, out);
    }

    ggml_build_forward_expand(gf, out);
    int n_nodes = ggml_graph_n_nodes(gf);

    // Create threadpool
    struct ggml_threadpool_params tpp  = ggml_threadpool_params_default(n_threads);
    struct ggml_threadpool* threadpool = ggml_threadpool_new(&tpp);
    if (!threadpool) {
        fprintf(stderr, "threadpool create failed : n_threads %d\n", n_threads);
        exit(1);
    }

    std::cerr << "graph-compute with"
              << "\n n_threads: " << n_threads
              << "\n   n_nodes: " << n_nodes
              << "\n  n_rounds: " << n_rounds
              << "\n";
    // ggml_graph_print(gf);

    // In this test we keep changing the number of threads every 4th iteration
    // to test for race conditions in that path

    for (int i=0; i < n_rounds; i++) {
        struct ggml_cplan cplan = ggml_graph_plan(gf, (i % 4) == 0 ? 1 : n_threads, threadpool);

        std::vector<uint8_t> work_data(cplan.work_size);
        cplan.work_data = work_data.data();

        ggml_graph_compute(gf, &cplan);
    }

    ggml_threadpool_free(threadpool);
    ggml_free(ctx);
}

static void test_multi_graph(int n_threads, int n_rounds) {
    struct ggml_init_params params = {