diff --git a/config/data_dump.json b/config/data_dump.json
index fc08f78590..f1e8177eaf 100644
--- a/config/data_dump.json
+++ b/config/data_dump.json
@@ -1,14 +1,16 @@
 {
   "DumpSettings": {
     "net_name": "ResNet50",
-    "mode": 1,
+    "dump_mode": 1,
+    "op_debug_mode": 3,
     "iteration": 0,
     "kernels": ["Default/Conv2D-op2", "Default/TensorAdd-op10"]
   },
 
   "DumpSettingsSpec": {
     "net_name": "net name eg:ResNet50",
-    "mode": "0: dump all kernels, 1: dump kernels in kernels list",
+    "dump_mode": "0: dump all kernels, 1: dump kernels in kernels list",
+    "op_debug_mode": "0: close debug, 1: debug ai-core overflow, 2: debug atomic overflow, 3: debug all overflow",
     "iteration": "specified iteration ",
     "kernels": "op's full scope name which need to be dump"
   }
diff --git a/graphengine b/graphengine
index 103f2d1019..6d12411003 160000
--- a/graphengine
+++ b/graphengine
@@ -1 +1 @@
-Subproject commit 103f2d1019dc50d781d7a964551d9f1f50b3b009
+Subproject commit 6d12411003164d88eaed62e1ead33761cbfa15ef
diff --git a/mindspore/ccsrc/debug/data_dump_parser.cc b/mindspore/ccsrc/debug/data_dump_parser.cc
index cd441694a0..dedbbdeb4f 100644
--- a/mindspore/ccsrc/debug/data_dump_parser.cc
+++ b/mindspore/ccsrc/debug/data_dump_parser.cc
@@ -20,9 +20,15 @@
 #include "utils/context/ms_context.h"
 #include "debug/common.h"
 
-constexpr auto kDataDumpConfigPtah = "DATA_DUMP_CONFIG_PATH";
-constexpr auto kEnableDataDump = "ENABLE_DATA_DUMP";
-constexpr auto kDataDumpPath = "DATA_DUMP_PATH";
+static constexpr auto kDataDumpConfigPtah = "DATA_DUMP_CONFIG_PATH";
+static constexpr auto kEnableDataDump = "ENABLE_DATA_DUMP";
+static constexpr auto kDataDumpPath = "DATA_DUMP_PATH";
+static constexpr auto kConfigDumpMode = "dump_mode";
+static constexpr auto kConfigOpDebugMode = "op_debug_mode";
+static constexpr auto kConfigNetName = "net_name";
+static constexpr auto kConfigIteration = "iteration";
+static constexpr auto kConfigKernels = "kernels";
+
 namespace mindspore {
 void DataDumpParser::ResetParam() {
   enable_ = false;
@@ -132,8 +138,11 @@ bool DataDumpParser::NeedDump(const std::string &op_full_name) const {
 }
 
 bool DataDumpParser::IsConfigExist(const nlohmann::json &dump_settings) const {
-  if (dump_settings.find("mode") == dump_settings.end() || dump_settings.find("net_name") == dump_settings.end() ||
-      dump_settings.find("iteration") == dump_settings.end() || dump_settings.find("kernels") == dump_settings.end()) {
+  if (dump_settings.find(kConfigDumpMode) == dump_settings.end() ||
+      dump_settings.find(kConfigNetName) == dump_settings.end() ||
+      dump_settings.find(kConfigOpDebugMode) == dump_settings.end() ||
+      dump_settings.find(kConfigIteration) == dump_settings.end() ||
+      dump_settings.find(kConfigKernels) == dump_settings.end()) {
     MS_LOG(ERROR) << "[DataDump] DumpSettings keys are not exist.";
     return false;
   }
@@ -141,10 +150,11 @@ bool DataDumpParser::IsConfigExist(const nlohmann::json &dump_settings) const {
 }
 
 bool DataDumpParser::ParseDumpSetting(const nlohmann::json &dump_settings) {
-  auto mode = dump_settings.at("mode");
-  auto net_name = dump_settings.at("net_name");
-  auto iteration = dump_settings.at("iteration");
-  auto kernels = dump_settings.at("kernels");
+  auto mode = dump_settings.at(kConfigDumpMode);
+  auto op_debug_mode = dump_settings.at(kConfigOpDebugMode);
+  auto net_name = dump_settings.at(kConfigNetName);
+  auto iteration = dump_settings.at(kConfigIteration);
+  auto kernels = dump_settings.at(kConfigKernels);
   if (!(mode.is_number() && net_name.is_string() && iteration.is_number() && kernels.is_array())) {
     MS_LOG(ERROR) << "[DataDump] Element's type in Dump config json is invalid.";
     enable_ = false;
@@ -155,6 +165,7 @@ bool DataDumpParser::ParseDumpSetting(const nlohmann::json &dump_settings) {
   auto context_ptr = MsContext::GetInstance();
   MS_EXCEPTION_IF_NULL(context_ptr);
   dump_mode_ = mode;
+  op_debug_mode_ = op_debug_mode;
   net_name_ = net_name;
   dump_step_ = iteration;
   for (const auto &kernel : kernels) {
diff --git a/mindspore/ccsrc/debug/data_dump_parser.h b/mindspore/ccsrc/debug/data_dump_parser.h
index 750c2a92f7..cf0f7eebb5 100644
--- a/mindspore/ccsrc/debug/data_dump_parser.h
+++ b/mindspore/ccsrc/debug/data_dump_parser.h
@@ -38,6 +38,7 @@ class DataDumpParser {
   bool enable() const { return enable_; }
   const std::string &net_name() const { return net_name_; }
   uint32_t dump_mode() const { return dump_mode_; }
+  uint32_t op_debug_mode() const { return op_debug_mode_; }
   uint32_t dump_step() const { return dump_step_; }
   void MatchKernel(const std::string &kernel_name);
   void PrintUnusedKernel();
@@ -54,6 +55,7 @@ class DataDumpParser {
   std::mutex lock_;
   bool enable_{false};
   std::string net_name_;
+  uint32_t op_debug_mode_{0};
   uint32_t dump_mode_{0};
   uint32_t dump_step_{0};
   std::map<std::string, uint32_t> kernel_map_;
diff --git a/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.cc b/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.cc
index aafbf75765..09161f6697 100644
--- a/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.cc
+++ b/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.cc
@@ -97,7 +97,10 @@ AscendKernelRuntime::~AscendKernelRuntime() { graph_model_map_.clear(); }
 void AscendKernelRuntime::ClearGraphModelMap() {
   for (auto &iter : graph_data_dumper_) {
     MS_LOG(INFO) << "[DataDump] Unload data dumper:" << iter.first;
-    iter.second->UnloadDumpInfo();
+    auto &data_dumper = iter.second;
+    MS_EXCEPTION_IF_NULL(data_dumper);
+    data_dumper->UnloadDumpInfo();
+    data_dumper->OpDebugUnregister();
   }
   graph_data_dumper_.clear();
   // tell users which dump kernel name not used
@@ -113,18 +116,29 @@ void AscendKernelRuntime::ClearGraphModelMap() {
 }
 
 void AscendKernelRuntime::ClearGraphRuntimeResource(uint32_t graph_id) {
-  MS_LOG(DEBUG) << "Clear graph:" << graph_id << " runtime resource";
-  auto iter = graph_model_map_.find(graph_id);
-  if (iter == graph_model_map_.end()) {
+  MS_LOG(DEBUG) << "Clear graph:" << graph_id << " data dumper";
+  if (auto dumper_iter = graph_data_dumper_.find(graph_id); dumper_iter != graph_data_dumper_.end()) {
+    MS_LOG(DEBUG) << "Unload dump info " << graph_id;
+    auto &data_dumper = dumper_iter->second;
+    MS_EXCEPTION_IF_NULL(data_dumper);
+    data_dumper->UnloadDumpInfo();
+    data_dumper->OpDebugUnregister();
+    graph_data_dumper_.erase(dumper_iter);
+  } else {
     MS_LOG(DEBUG) << "GraphId:" << graph_id << " not found";
-    return;
   }
-  MS_LOG(DEBUG) << "Ge UnloadModel " << iter->first;
-  auto ret = ModelRunner::Instance().UnloadModel(iter->first);
-  if (!ret) {
-    MS_LOG(ERROR) << "UnloadModel failed";
+
+  MS_LOG(DEBUG) << "Clear graph:" << graph_id << " runtime resource";
+  if (auto model_iter = graph_model_map_.find(graph_id); model_iter != graph_model_map_.end()) {
+    MS_LOG(DEBUG) << "Ge UnloadModel " << graph_id;
+    auto ret = ModelRunner::Instance().UnloadModel(graph_id);
+    if (!ret) {
+      MS_LOG(ERROR) << "UnloadModel failed";
+    }
+    graph_model_map_.erase(model_iter);
+  } else {
+    MS_LOG(DEBUG) << "GraphId:" << graph_id << " not found";
   }
-  graph_model_map_.erase(iter);
 }
 
 bool AscendKernelRuntime::NeedDestroyHccl() {
@@ -505,15 +519,25 @@ bool AscendKernelRuntime::LoadTask(const session::KernelGraph *graph) {
   bool status =
     ModelRunner::Instance().LoadDavinciModel(device_id_, 0, model_iter->first, model_iter->second, listener);
   if (!status) {
-    MS_LOG(EXCEPTION) << "Load Task Failed";
+    MS_LOG(EXCEPTION) << "Load Model Failed";
   }
+
+  std::function<void *()> model_handle =
+    std::bind(&ModelRunner::GetModelHandle, &ModelRunner::Instance(), model_iter->first);
+  DistributeDebugTask(NOT_NULL(graph), NOT_NULL(model_handle));
+
+  status = ModelRunner::Instance().DistributeTask(model_iter->first);
+  if (!status) {
+    MS_LOG(EXCEPTION) << "Distribute Task Failed";
+  }
+
   if (ProfilingManager::GetInstance().IsProfiling()) {
     auto task_ids = ModelRunner::Instance().GetTaskIdList(model_iter->first);
     auto stream_ids = ModelRunner::Instance().GetStreamIdList(model_iter->first);
     ProfilingUtils::ReportProfilingData(task_ids, stream_ids, NOT_NULL(graph));
   }
 
-  LaunchDataDump(NOT_NULL(graph));
+  LaunchDataDump(graph->graph_id());
 
   if (!ModelRunner::Instance().LoadModelComplete(model_iter->first)) {
     MS_LOG(ERROR) << "Call ge runtime LoadModelComplete failed";
@@ -522,20 +546,35 @@ bool AscendKernelRuntime::LoadTask(const session::KernelGraph *graph) {
   return true;
 }
 
-void AscendKernelRuntime::LaunchDataDump(NotNull<const session::KernelGraph *> graph) {
+void AscendKernelRuntime::DistributeDebugTask(NotNull<const session::KernelGraph *> graph,
+                                              NotNull<std::function<void *()>> model_handle) {
   if (!DataDumpParser::GetInstance().DumpEnabled()) {
     return;
   }
-  auto runtime_info_map = ModelRunner::Instance().GetRuntimeInfoMap(graph->graph_id());
-  auto data_dumper = std::make_shared<DataDumper>(graph.get(), runtime_info_map);
+  auto data_dumper = std::make_shared<DataDumper>(graph.get(), model_handle);
   MS_EXCEPTION_IF_NULL(data_dumper);
-  data_dumper->LoadDumpInfo();
   auto ret = graph_data_dumper_.try_emplace(graph->graph_id(), data_dumper);
+  data_dumper->OpDebugRegister();
   if (!ret.second) {
     MS_LOG(WARNING) << "[DataDump] Insert graphId:" << graph->graph_id() << " data dumper failed";
   }
 }
 
+void AscendKernelRuntime::LaunchDataDump(GraphId graph_id) {
+  if (!DataDumpParser::GetInstance().DumpEnabled()) {
+    return;
+  }
+  auto runtime_info_map = ModelRunner::Instance().GetRuntimeInfoMap(graph_id);
+  if (auto dumper_iter = graph_data_dumper_.find(graph_id); dumper_iter != graph_data_dumper_.end()) {
+    auto &data_dumper = dumper_iter->second;
+    MS_EXCEPTION_IF_NULL(data_dumper);
+    data_dumper->set_runtime_info(runtime_info_map);
+    data_dumper->LoadDumpInfo();
+  } else {
+    MS_LOG(EXCEPTION) << "GraphId:" << graph_id << " not found";
+  }
+}
+
 void AscendKernelRuntime::DebugTaskIdName(GraphId graph_id) {
   auto runtime_info_map = ModelRunner::Instance().GetRuntimeInfoMap(graph_id);
   for (auto iter : runtime_info_map) {
diff --git a/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.h b/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.h
index c4d82b0567..b7c0002b54 100644
--- a/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.h
+++ b/mindspore/ccsrc/runtime/device/ascend/ascend_kernel_runtime.h
@@ -63,12 +63,13 @@ class AscendKernelRuntime : public KernelRuntime {
   bool GraphWithEmptyTaskList(const session::KernelGraph *graph) const;
   bool CheckGraphIdValid(GraphId graph_id) const;
   static void DebugTaskIdName(GraphId graph_id);
+  void DistributeDebugTask(NotNull<const session::KernelGraph *> graph, NotNull<std::function<void *()>> model_handle);
+  void LaunchDataDump(GraphId graph_id);
 
   rtContext_t rt_context_{nullptr};
   bool initialized_{false};
   unordered_map<GraphId, vector<std::shared_ptr<TaskInfo>>> task_map_;
   unordered_map<GraphId, std::shared_ptr<ge::model_runner::DavinciModel>> graph_model_map_;
-  void LaunchDataDump(NotNull<const session::KernelGraph *> graph);
   unordered_map<GraphId, std::shared_ptr<DataDumper>> graph_data_dumper_;
 };
 
diff --git a/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.cc b/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.cc
index 69b125dd02..e907b1d525 100644
--- a/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.cc
+++ b/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.cc
@@ -22,36 +22,53 @@
 #include "backend/session/anf_runtime_algorithm.h"
 #include "runtime/mem.h"
 #include "runtime/kernel.h"
+#include "runtime/rt_model.h"
 #include "runtime/device/ascend/dump/ge_dump.h"
 #include "proto/op_mapping_info.pb.h"
 #include "utils/context/ms_context.h"
 #include "debug/data_dump_parser.h"
 
-constexpr uint32_t kAicpuLoadFlag = 1;
-constexpr uint32_t kAicpuUnloadFlag = 0;
-constexpr uint32_t kTupleTaskId = 0;
-constexpr uint32_t kTupleStreamId = 1;
-constexpr uint32_t kTupleArgs = 2;
-constexpr uint32_t kCurrentStepTensorIndex = 0;
-constexpr uint32_t kCurrentEpochTensorIndex = 1;
-constexpr uint32_t kStepsPerEpochTensorIndex = 2;
+static constexpr uint32_t kAicpuLoadFlag = 1;
+static constexpr uint32_t kAicpuUnloadFlag = 0;
+static constexpr uint32_t kTupleTaskId = 0;
+static constexpr uint32_t kTupleStreamId = 1;
+static constexpr uint32_t kTupleArgs = 2;
+static constexpr uint32_t kCurrentStepTensorIndex = 0;
+static constexpr uint32_t kCurrentEpochTensorIndex = 1;
+static constexpr uint32_t kStepsPerEpochTensorIndex = 2;
+static constexpr uint64_t kOpDebugShape = 2048;
+static constexpr uint64_t kOpDebugHostMemSize = 2048;
+static constexpr uint64_t kOpDebugDevMemSize = sizeof(void *);
+static constexpr uint8_t kNoOverflow = 0;
+static constexpr uint8_t kAiCoreOverflow = (0x1 << 0);
+static constexpr uint8_t kAtomicOverflow = (0x1 << 1);
+static constexpr uint8_t kAllOverflow = (kAiCoreOverflow | kAtomicOverflow);
+static const std::map<uint32_t, std::string> kOverflowModeStr = {{kNoOverflow, "NoOverflow"},
+                                                                 {kAiCoreOverflow, "AiCoreOverflow"},
+                                                                 {kAtomicOverflow, "AtomicOverflow"},
+                                                                 {kAllOverflow, "AllOverflow"}};
+constexpr const char *kNodeNameOpDebug = "Node_OpDebug";
+constexpr const char *kOpTypeOpDebug = "Opdebug";
 
 namespace mindspore {
 namespace device {
 namespace ascend {
-void DumpKernelOutput(const CNodePtr &kernel, void *args, NotNull<aicpu::dump::Task *> task);
-void DumpKernelInput(const CNodePtr &kernel, void *args, NotNull<aicpu::dump::Task *> task);
-void RtLoadDumpData(const aicpu::dump::OpMappingInfo &dump_info, void **ptr);
+static void DumpKernelOutput(const CNodePtr &kernel, void *args, NotNull<aicpu::dump::Task *> task);
+static void DumpKernelInput(const CNodePtr &kernel, void *args, NotNull<aicpu::dump::Task *> task);
+static void RtLoadDumpData(const aicpu::dump::OpMappingInfo &dump_info, void **ptr);
 
 DataDumper::~DataDumper() {
   ReleaseDevMem(&dev_load_mem_);
   ReleaseDevMem(&dev_unload_mem_);
+  ReleaseDevMem(&op_debug_buffer_addr_);
+  ReleaseDevMem(&op_debug_dump_args_);
 }
 
 void DataDumper::LoadDumpInfo() {
   MS_LOG(INFO) << "[DataDump] LoadDumpInfo start";
   MS_EXCEPTION_IF_NULL(kernel_graph_);
   aicpu::dump::OpMappingInfo dump_info;
+  SetOpDebugMappingInfo(NOT_NULL(&dump_info));
   SetOpMappingInfo(NOT_NULL(&dump_info));
 
   auto kernels = kernel_graph_->execution_order();
@@ -134,7 +151,7 @@ bool DataDumper::KernelNeedDump(const CNodePtr &kernel) const {
 
 void DataDumper::UnloadDumpInfo() {
   if (!load_flag_) {
-    MS_LOG(WARNING) << "Load not success, no need to unload";
+    MS_LOG(WARNING) << "[DataDump] Load not success, no need to unload";
     return;
   }
   MS_LOG(INFO) << "[DataDump] UnloadDumpInfo start. graphId:" << graph_id_;
@@ -194,6 +211,84 @@ void DataDumper::ConstructDumpTask(NotNull<const CNodePtr &> kernel, NotNull<aic
   DumpKernelInput(kernel, args, dump_task);
 }
 
+void DataDumper::SetOpDebugMappingInfo(NotNull<aicpu::dump::OpMappingInfo *> dump_info) const {
+  MS_LOG(INFO) << "[DataDump] Add op debug info to OpMappingInfo, task id = " << debug_task_id_
+               << ", stream id = " << debug_stream_id_;
+  aicpu::dump::Task task;
+  task.set_end_graph(false);
+  task.set_task_id(debug_task_id_);
+  task.set_stream_id(debug_stream_id_);
+  task.mutable_op()->set_op_name(kNodeNameOpDebug);
+  task.mutable_op()->set_op_type(kOpTypeOpDebug);
+
+  aicpu::dump::Output output;
+  output.set_data_type(ge::proto::DataType::DT_UINT8);
+  output.set_format(GeFormat::kFormat_ND);
+
+  output.mutable_shape()->add_dim(kOpDebugShape);
+
+  output.set_original_name(kNodeNameOpDebug);
+  output.set_original_output_index(0);
+  output.set_original_output_format(GeFormat::kFormat_ND);
+  output.set_original_output_data_type(ge::proto::DataType::DT_UINT8);
+  // due to lhisi virtual addr bug, cannot use args now
+  output.set_address(static_cast<uint64_t>(reinterpret_cast<uintptr_t>(op_debug_dump_args_)));
+  output.set_size(kOpDebugHostMemSize);
+
+  task.mutable_output()->Add(std::move(output));
+  dump_info->mutable_task()->Add(std::move(task));
+}
+
+void DataDumper::OpDebugRegister() {
+  uint32_t op_debug_mode = DataDumpParser::GetInstance().op_debug_mode();
+  auto iter = kOverflowModeStr.find(op_debug_mode);
+  if (iter == kOverflowModeStr.end()) {
+    MS_LOG(EXCEPTION) << "Invalid op debug mode " << op_debug_mode;
+  }
+  MS_LOG(INFO) << "[DataDump] Op debug mode is " << iter->second;
+  if (op_debug_mode == kNoOverflow) {
+    return;
+  }
+
+  rtError_t rt_ret = rtMalloc(&op_debug_buffer_addr_, kOpDebugHostMemSize, RT_MEMORY_DDR);
+  if (rt_ret != RT_ERROR_NONE) {
+    MS_LOG(EXCEPTION) << "[DataDump] Call rtMalloc failed, ret = " << rt_ret;
+  }
+
+  rt_ret = rtMalloc(&op_debug_dump_args_, kOpDebugDevMemSize, RT_MEMORY_HBM);
+  if (rt_ret != RT_ERROR_NONE) {
+    MS_LOG(EXCEPTION) << "[DataDump] Call rtMalloc failed, ret = " << rt_ret;
+  }
+
+  rt_ret =
+    rtMemcpy(op_debug_dump_args_, sizeof(void *), &op_debug_buffer_addr_, sizeof(void *), RT_MEMCPY_HOST_TO_DEVICE);
+  if (rt_ret != RT_ERROR_NONE) {
+    MS_LOG(EXCEPTION) << "[DataDump] Call rtMemcpy failed, ret = " << rt_ret;
+  }
+
+  rt_ret = rtDebugRegister(model_handle_(), op_debug_mode, op_debug_buffer_addr_, &debug_stream_id_, &debug_task_id_);
+  if (rt_ret != RT_ERROR_NONE) {
+    MS_LOG(EXCEPTION) << "[DataDump] Call rtDebugRegister failed, ret = " << rt_ret;
+  }
+
+  MS_LOG(INFO) << "[DataDump] Distribute op debug task, task id = " << debug_task_id_
+               << ", stream id = " << debug_stream_id_;
+}
+
+void DataDumper::OpDebugUnregister() {
+  uint32_t op_debug_mode = DataDumpParser::GetInstance().op_debug_mode();
+  if (op_debug_mode == kNoOverflow) {
+    MS_LOG(INFO) << "[DataDump] Op debug mode is no overflow, no need to unregister.";
+    return;
+  }
+
+  MS_LOG(INFO) << "[DataDump] Start.";
+  rtError_t rt_ret = rtDebugUnRegister(model_handle_());
+  if (rt_ret != RT_ERROR_NONE) {
+    MS_LOG(EXCEPTION) << "[DataDump] Call rtDebugUnRegister failed, ret = " << rt_ret;
+  }
+}
+
 void RtLoadDumpData(const aicpu::dump::OpMappingInfo &dump_info, void **ptr) {
   std::string proto_str;
   size_t proto_size = dump_info.ByteSizeLong();
diff --git a/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.h b/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.h
index aa7069acca..5dbbb92a78 100644
--- a/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.h
+++ b/mindspore/ccsrc/runtime/device/ascend/dump/data_dumper.h
@@ -21,6 +21,7 @@
 #include <memory>
 #include <string>
 #include <vector>
+#include <functional>
 #include "backend/session/kernel_graph.h"
 
 namespace aicpu {
@@ -36,25 +37,38 @@ namespace ascend {
 using RuntimeInfo = std::tuple<uint32_t, uint32_t, void *>;
 class DataDumper {
  public:
-  DataDumper(const session::KernelGraph *kernel_graph,
-             const std::map<std::string, std::shared_ptr<RuntimeInfo>> &runtime_info_map)
-      : load_flag_(false),
+  DataDumper(const session::KernelGraph *kernel_graph, NotNull<std::function<void *()>> model_handle)
+      : model_handle_(model_handle),
+        debug_task_id_(-1),
+        debug_stream_id_(-1),
+        op_debug_buffer_addr_(nullptr),
+        op_debug_dump_args_(nullptr),
+        load_flag_(false),
         dev_load_mem_(nullptr),
         dev_unload_mem_(nullptr),
         graph_id_(UINT32_MAX),
-        kernel_graph_(kernel_graph),
-        runtime_info_map_(runtime_info_map) {}
+        kernel_graph_(kernel_graph) {}
   ~DataDumper();
+  void set_runtime_info(const std::map<std::string, std::shared_ptr<RuntimeInfo>> &runtime_info) {
+    runtime_info_map_ = runtime_info;
+  }
   void LoadDumpInfo();
-
   void UnloadDumpInfo();
+  void OpDebugRegister();
+  void OpDebugUnregister();
 
  private:
   void ReleaseDevMem(void **ptr) const;
   bool KernelNeedDump(const CNodePtr &kernel) const;
   void SetOpMappingInfo(NotNull<aicpu::dump::OpMappingInfo *> dump_info) const;
+  void SetOpDebugMappingInfo(NotNull<aicpu::dump::OpMappingInfo *> dump_info) const;
   void ConstructDumpTask(NotNull<const CNodePtr &> kernel, NotNull<aicpu::dump::Task *> dump_task) const;
 
+  std::function<void *()> model_handle_;
+  uint32_t debug_task_id_;
+  uint32_t debug_stream_id_;
+  void *op_debug_buffer_addr_;
+  void *op_debug_dump_args_;
   bool load_flag_;
   void *dev_load_mem_;
   void *dev_unload_mem_;
diff --git a/tests/ut/cpp/stub/ge/ge_task_launch_stub.cc b/tests/ut/cpp/stub/ge/ge_task_launch_stub.cc
index 234ffdaf6b..e2502baf8b 100644
--- a/tests/ut/cpp/stub/ge/ge_task_launch_stub.cc
+++ b/tests/ut/cpp/stub/ge/ge_task_launch_stub.cc
@@ -38,6 +38,10 @@ bool ModelRunner::RunModel(uint32_t model_id, const ge::InputData &input_data, g
   return true;
 }
 
+void *ModelRunner::GetModelHandle(uint32_t model_id) const { return nullptr; }
+
+bool ModelRunner::DistributeTask(uint32_t model_id) { return true; }
+
 const std::vector<uint32_t> &ModelRunner::GetTaskIdList(uint32_t model_id) const {
   static std::vector<uint32_t> task_id_list;
   return task_id_list;
diff --git a/tests/ut/cpp/stub/tasksink/task_sink_stub.cc b/tests/ut/cpp/stub/tasksink/task_sink_stub.cc
index 967fbda4e5..4f909ec2d5 100644
--- a/tests/ut/cpp/stub/tasksink/task_sink_stub.cc
+++ b/tests/ut/cpp/stub/tasksink/task_sink_stub.cc
@@ -28,6 +28,8 @@ bool TaskGenerator::GenTasks(const std::vector<CNodePtr> &anf_node_list, std::ve
 }  // namespace tasksink
 void DataDumper::LoadDumpInfo() {}
 void DataDumper::UnloadDumpInfo() {}
+void DataDumper::OpDebugRegister() {}
+void DataDumper::OpDebugUnregister() {}
 DataDumper::~DataDumper() {}
 }  // namespace ascend
 }  // namespace device