Gemini代碼摘抄（一）Graph和init

Graph和init

---

在pagerank.cpp中對圖進行初始化：

  Graph<Empty> * graph;
  graph = new Graph<Empty>();

具體實現在graph.hpp中，設置threads和sockets，其中threads—cpus—partitions，sockets—nodes—machines，threads_per_socket表示每個節點（機器）上分到的線程數（分區數）：

 Graph() {
    threads = numa_num_configured_cpus();
    sockets = numa_num_configured_nodes();
    threads_per_socket = threads / sockets;

    init();
  }

init()函數設置分區數

void init() {
    edge_data_size = std::is_same<EdgeData, Empty>::value ? 0 : sizeof(EdgeData);
    unit_size = sizeof(VertexId) + edge_data_size;
    edge_unit_size = sizeof(VertexId) + unit_size;

    assert( numa_available() != -1 );
    assert( sizeof(unsigned long) == 8 ); // assume unsigned long is 64-bit

    char nodestring[sockets*2+1];
    nodestring[0] = '0';
    for (int s_i=1;s_i<sockets;s_i++) {
      nodestring[s_i*2-1] = ',';
      nodestring[s_i*2] = '0'+s_i;
    }
    struct bitmask * nodemask = numa_parse_nodestring(nodestring);
    numa_set_interleave_mask(nodemask);

    omp_set_dynamic(0);
    omp_set_num_threads(threads);
    thread_state = new ThreadState * [threads];
    local_send_buffer_limit = 16;
    local_send_buffer = new MessageBuffer * [threads];
    for (int t_i=0;t_i<threads;t_i++) {
      thread_state[t_i] = (ThreadState*)numa_alloc_onnode( sizeof(ThreadState), get_socket_id(t_i));
      local_send_buffer[t_i] = (MessageBuffer*)numa_alloc_onnode( sizeof(MessageBuffer), get_socket_id(t_i));
      local_send_buffer[t_i]->init(get_socket_id(t_i));
    }
    #pragma omp parallel for
    for (int t_i=0;t_i<threads;t_i++) {
      int s_i = get_socket_id(t_i);
      assert(numa_run_on_node(s_i)==0);
      #ifdef PRINT_DEBUG_MESSAGES
       printf("thread-%d bound to socket-%d\n", t_i, s_i);
      #endif
    }
    #ifdef PRINT_DEBUG_MESSAGES
     printf("threads=%d*%d\n", sockets, threads_per_socket);
     printf("interleave on %s\n", nodestring);
    #endif

    MPI_Comm_rank(MPI_COMM_WORLD, &partition_id);
    MPI_Comm_size(MPI_COMM_WORLD, &partitions);
    send_buffer = new MessageBuffer ** [partitions];
    recv_buffer = new MessageBuffer ** [partitions];
    for (int i=0;i<partitions;i++) {
      send_buffer[i] = new MessageBuffer * [sockets];
      recv_buffer[i] = new MessageBuffer * [sockets];
      for (int s_i=0;s_i<sockets;s_i++) {
        send_buffer[i][s_i] = (MessageBuffer*)numa_alloc_onnode( sizeof(MessageBuffer), s_i);
        send_buffer[i][s_i]->init(s_i);
        recv_buffer[i][s_i] = (MessageBuffer*)numa_alloc_onnode( sizeof(MessageBuffer), s_i);
        recv_buffer[i][s_i]->init(s_i);
      }
    }

    alpha = 8 * (partitions - 1);

    MPI_Barrier(MPI_COMM_WORLD);
  }

2.收到的邊數是收到的byte數除以每條邊的大小：

int recv_edges = recv_bytes / edge_unit_size;

3.點dst所在的分區號爲dst_part,
dst_part分區中點src的出邊加一
點dst的入度加一
點src的初度加一

__sync_fetch_and_add(&outgoing_adj_index[dst_part][src], 1);
__sync_fetch_and_add(&in_degree[dst], 1);
__sync_fetch_and_add(&out_degree[src], 1);

4.alpha值爲分區個數乘以8