使用Ascend Graph API采集

采集性能原始数据方式一

参考以下示例通过GEInitialize传入option参数：

// 0. System init
  std::map<AscendString, AscendString> config = {{"ge.exec.deviceId", "0"},
                                    {"ge.graphRunMode", "1"},
                                    {"ge.exec.precision_mode", "allow_fp32_to_fp16"},
                                    {"ge.exec.profilingMode", "1"},
                                    {"ge.exec.profilingOptions",  R"({"output":"/tmp/profiling","training_trace":"on","fp_point":"","bp_point":""})"}};
  Status ret = ge::GEInitialize(config);
  if (ret != SUCCESS) {
    return FAILED;
  }

采集性能原始数据方式二

参考以下示例调用接口，采集Profiling性能数据：

  // 构造Graph，该步骤省略
  // ......

  // init ge
  std::map<std::string, std::string> ge_options = {{"ge.socVersion", "Ascend910"}, {"ge.graphRunMode", "1"}};
  ge::GEInitialize(ge_options);

  std::string profilerResultPath = "/home/test/prof";       //该路径需要提前创建
  uint32_t length = strlen("/home/test/prof");
  ret = ge::aclgrphProfInit(profilerResultPath.c_str(), length);     

  std::map<string, string> options = {{"a", "b"}, {"c", "d"}};
  uint32_t graphId = 0;

  ge::Session *session = new Session(options);
  ret = session->AddGraph(graphId, graph);

  uint32_t deviceid_list[1] = {0};
  uint32_t device_nums = 1;
  uint64_t data_type_config = ProfDataTypeConfig::kProfTaskTime | ProfDataTypeConfig::kProfAiCoreMetrics | ProfDataTypeConfig::kProfAicpu | ProfDataTypeConfig::kProfTrainingTrace;
  ProfAicoreEvents *aicore_events = NULL;
  ProfilingAicoreMetrics aicore_metrics = ProfilingAicoreMetrics::kAicoreArithmeticUtilization;  
  ge::aclgrphProfConfig *pro_config = ge::aclgrphProfCreateConfig(deviceid_list, device_nums, aicore_metrics, aicore_events, data_type_config);

  ge::aclgrphProfStart(pro_config);

  session->RunGraph(graphId, inputs_r, outputs_r);

  ge::aclgrphProfStop(pro_config);

  ge::aclgrphProfDestroyConfig(pro_config);

  ge::aclgrphProfFinalize();

  delete session;
  ge::GEFinalize();

采集数据说明

配置Ascend Graph API方式采集后请参见性能数据解析与导出（msprof命令）将原始数据文件解析并导出为可视化的timeline和summary文件。生成的Profiling数据如下表所示。