Function test_multi_graph

subprojects/llama.cpp/tests/test-barrier.cpp:138–213

}

static void test_multi_graph(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 graphs
    struct ggml_cgraph * gf0 = 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(gf0, out);
    }

    struct ggml_cgraph * gf1 = ggml_new_graph(ctx);
    {
        // Small graph with parallel ops with barriers
        // Use larger tensors to make sure work_data size is larger than gf0
        struct ggml_tensor * out = ggml_new_tensor_1d(ctx, GGML_TYPE_F32,  256);
        for (int i = 0; i < 4; i++) {
            struct ggml_tensor * a = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, 256, 128);
            out = ggml_mul_mat(ctx, a, out);

            struct ggml_tensor * d = ggml_new_tensor_2d(ctx, GGML_TYPE_Q4_0, 128, 256);
            out = ggml_mul_mat(ctx, d, out);
        }

        ggml_build_forward_expand(gf1, out);
    }


    // 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 gf0 n_nodes: " << ggml_graph_n_nodes(gf0)
              << "\n gf1 n_nodes: " << ggml_graph_n_nodes(gf1)
              << "\n   n_threads: " << n_threads
              << "\n    n_rounds: " << n_rounds
              << "\n";

    // In this test we keep changing the number of threads every 4th iteration