diff --git a/mindspore/ccsrc/runtime/device/ascend/ascend_bucket.cc b/mindspore/ccsrc/runtime/device/ascend/ascend_bucket.cc
index 6a818df9dcb..2a8bb0f5fc8 100644
--- a/mindspore/ccsrc/runtime/device/ascend/ascend_bucket.cc
+++ b/mindspore/ccsrc/runtime/device/ascend/ascend_bucket.cc
@@ -55,7 +55,7 @@ void AscendBucket::AllocateAllReduceAddr() {
     auto origin_size = device_address->GetSize();
     auto align_size = MemoryManager::GetCommonAlignSize(origin_size);
     origin_size_list.emplace_back(origin_size);
-    align_size_list_.emplace_back(align_size);
+    (void)align_size_list_.emplace_back(align_size);
     total_size += align_size;
     memcpy_input_addrs_.emplace_back(std::make_shared<kernel::Address>(
       static_cast<uint8_t *>(device_address->GetMutablePtr()), device_address->GetSize()));
diff --git a/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.cc b/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.cc
index 06654aad6dd..7e7060658e8 100644
--- a/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.cc
+++ b/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.cc
@@ -213,12 +213,12 @@ nlohmann::json ConstructInputs(const std::vector<size_t> &input_shape, const std
   real_input[name] = src;
   real_input[ori_format] = kOpFormat_NCHW;
   for (auto shape : output_shape) {
-    real_input[ori_shape].push_back(shape);
+    (void)real_input[ori_shape].emplace_back(shape);
   }
   real_input[param_type] = param_type_required;
   // obtain inputs shape
   for (auto shape : input_shape) {
-    real_input[shape_str].push_back(shape);
+    (void)real_input[shape_str].emplace_back(shape);
   }
   real_input[valid] = true;
   input_json.push_back(real_input);
@@ -235,12 +235,12 @@ nlohmann::json ConstructOutputs(const std::vector<size_t> &output_shape, mindspo
   real_output[name] = dst;
   real_output[ori_format] = kOpFormat_NCHW;
   for (auto shape : output_shape) {
-    real_output[ori_shape].push_back(shape);
+    (void)real_output[ori_shape].emplace_back(shape);
   }
   real_output[param_type] = param_type_required;
   // obtain outputs shape
   for (auto shape : output_shape) {
-    real_output[shape_str].push_back(shape);
+    (void)real_output[shape_str].emplace_back(shape);
   }
   real_output[valid] = true;
   output_json.push_back(real_output);
@@ -342,7 +342,7 @@ bool AscendDeviceAddress::SyncDeviceToHost(const ShapeVector &shape, size_t size
   return sync_ok;
 }
 
-void AscendDeviceAddress::LaunchTransData(kernel::KernelModPtr kernel_mod_ptr, void *output_address_ptr,
+void AscendDeviceAddress::LaunchTransData(const kernel::KernelModPtr &kernel_mod_ptr, void *output_address_ptr,
                                           size_t output_size, const std::vector<size_t> &workspace_size_list) const {
   MS_EXCEPTION_IF_NULL(kernel_mod_ptr);
   auto input_address = std::make_shared<kernel::Address>();
@@ -383,7 +383,7 @@ void AscendDeviceAddress::LaunchTransData(kernel::KernelModPtr kernel_mod_ptr, v
 }
 
 kernel::KernelModPtr AscendDeviceAddress::CompileTransDataAndObtainKernelMod(const nlohmann::json &kernel_json) const {
-  static std::set<std::string> constructed_kernel;
+  static std::set<std::string> constructed_kernel = {};
   auto build_manager = std::make_shared<kernel::ParallelBuildManager>();
   MS_EXCEPTION_IF_NULL(build_manager);
   std::string processor = process_aicore;
@@ -394,7 +394,7 @@ kernel::KernelModPtr AscendDeviceAddress::CompileTransDataAndObtainKernelMod(con
   std::string json_name = kernel_json[op_info_str][kernel_name_str];
   // op build
   if (constructed_kernel.find(json_name) == constructed_kernel.end()) {
-    auto task_id = build_manager->StartCompileOp(kernel_json);
+    auto task_id = kernel::ParallelBuildManager::StartCompileOp(kernel_json);
     build_manager->SaveTaskInfo(task_id, nullptr, json_name, input_size_list, output_size_list);
   }
   while (!build_manager->IsAllTaskFinish()) {
@@ -410,7 +410,7 @@ kernel::KernelModPtr AscendDeviceAddress::CompileTransDataAndObtainKernelMod(con
     }
     (void)build_manager->TaskFinishProcess(task_id, build_result, false);
   }
-  constructed_kernel.insert(json_name);
+  (void)constructed_kernel.insert(json_name);
   // search cache
   auto cached_kernel_pack = TbeUtils::SearchCache(json_name, processor);
   MS_EXCEPTION_IF_NULL(cached_kernel_pack);
diff --git a/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.h b/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.h
index b25da1d0526..e9b51068b33 100644
--- a/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.h
+++ b/mindspore/ccsrc/runtime/device/ascend/ascend_device_address.h
@@ -58,7 +58,7 @@ class AscendDeviceAddress : public DeviceAddress {
                                                         mindspore::TypeId type, void *host_ptr) const;
   void SyncStream() const;
 
-  void LaunchTransData(kernel::KernelModPtr kernel_mod_ptr, void *output_address_ptr, size_t output_size,
+  void LaunchTransData(const kernel::KernelModPtr &kernel_mod_ptr, void *output_address_ptr, size_t output_size,
                        const std::vector<size_t> &workspace_size_list) const;
   std::vector<size_t> GetDeviceShape(std::vector<size_t> *host_shape) const;
   std::vector<size_t> GetWorkspaceSizeList(const nlohmann::json &kernel_json) const;
diff --git a/mindspore/ccsrc/runtime/device/ascend/ascend_launch_atomic_clean.cc b/mindspore/ccsrc/runtime/device/ascend/ascend_launch_atomic_clean.cc
index 9b02f713874..a67810b83a1 100644
--- a/mindspore/ccsrc/runtime/device/ascend/ascend_launch_atomic_clean.cc
+++ b/mindspore/ccsrc/runtime/device/ascend/ascend_launch_atomic_clean.cc
@@ -85,8 +85,8 @@ std::shared_ptr<session::KernelGraph> AscendLaunchAtomicClean::ObtainAtomicClean
   if (dtype_size == 0) {
     MS_LOG(EXCEPTION) << "Divide by zero.";
   }
-  int64_t shape = total_size_ / dtype_size;
-  std::vector<std::vector<int64_t>> input_shapes = {{shape}};
+  auto shape = total_size_ / dtype_size;
+  std::vector<std::vector<int64_t>> input_shapes = {{static_cast<int64_t>(shape)}};
   std::vector<std::vector<size_t>> output_shapes = {};
   auto atomic_clean_graph = session::SingleKernelGraph::ConstructKernelGraphBasedOnSingleOp(
     kAtomicAddrCleanOpName, input_dtypes, input_shapes, output_dtypes, output_shapes);
diff --git a/mindspore/ccsrc/runtime/device/ascend/ascend_launch_kernel.cc b/mindspore/ccsrc/runtime/device/ascend/ascend_launch_kernel.cc
index 430623721a4..4dbefe2fa7b 100644
--- a/mindspore/ccsrc/runtime/device/ascend/ascend_launch_kernel.cc
+++ b/mindspore/ccsrc/runtime/device/ascend/ascend_launch_kernel.cc
@@ -47,6 +47,9 @@ void AscendLaunchKernel::KernelSelect(std::shared_ptr<session::KernelGraph> kern
 
 void AscendLaunchKernel::KernelBuild(std::shared_ptr<session::KernelGraph> kernel_graph) {
   MS_EXCEPTION_IF_NULL(kernel_graph);
-  device::ascend::KernelBuild(kernel_graph->execution_order());
+  auto ret = device::ascend::KernelBuild(kernel_graph->execution_order());
+  if (!ret) {
+    MS_LOG(ERROR) << "kernel build failed";
+  }
 }
 }  // namespace mindspore::device::ascend
diff --git a/mindspore/ccsrc/runtime/device/bucket.cc b/mindspore/ccsrc/runtime/device/bucket.cc
index cbaa9239b54..f1e5ba34556 100644
--- a/mindspore/ccsrc/runtime/device/bucket.cc
+++ b/mindspore/ccsrc/runtime/device/bucket.cc
@@ -111,7 +111,7 @@ void Bucket::CalculateMean() {
 void Bucket::UpdateTensorOutputAddr(uint8_t *addr) {
   uint8_t *tensor_output = addr;
   for (size_t i = 0; i < bucket_size_; ++i) {
-    new_tensor_output_addrs_.emplace_back(tensor_output);
+    (void)new_tensor_output_addrs_.emplace_back(tensor_output);
     tensor_output += align_size_list_[i];
   }
 }
diff --git a/mindspore/ccsrc/runtime/device/kernel_runtime.cc b/mindspore/ccsrc/runtime/device/kernel_runtime.cc
index db219965ed0..65c90092e59 100644
--- a/mindspore/ccsrc/runtime/device/kernel_runtime.cc
+++ b/mindspore/ccsrc/runtime/device/kernel_runtime.cc
@@ -1016,7 +1016,7 @@ void KernelRuntime::ClearOutputAddress(const std::vector<AnfNodePtr> &inputs,
   }
 }
 
-bool KernelRuntime::LaunchTaskBasedOnSingleKernel(kernel::KernelModPtr kernel_mod_ptr,
+bool KernelRuntime::LaunchTaskBasedOnSingleKernel(const kernel::KernelModPtr &kernel_mod_ptr,
                                                   const AddressPtrList &kernel_inputs,
                                                   const AddressPtrList &kernel_outputs,
                                                   const AddressPtrList &kernel_workspaces) const {
diff --git a/mindspore/ccsrc/runtime/device/kernel_runtime.h b/mindspore/ccsrc/runtime/device/kernel_runtime.h
index eb00173616c..454ea48b884 100644
--- a/mindspore/ccsrc/runtime/device/kernel_runtime.h
+++ b/mindspore/ccsrc/runtime/device/kernel_runtime.h
@@ -63,7 +63,7 @@ class KernelRuntime {
   virtual bool GenDynamicKernel(const session::KernelGraph *graph) = 0;
   virtual bool RunDynamicKernelAsync(const session::KernelGraph *graph) = 0;
   bool LaunchKernel(const session::KernelGraph *graph);
-  bool LaunchTaskBasedOnSingleKernel(kernel::KernelModPtr kernel_mod_ptr, const AddressPtrList &kernel_inputs,
+  bool LaunchTaskBasedOnSingleKernel(const kernel::KernelModPtr &kernel_mod_ptr, const AddressPtrList &kernel_inputs,
                                      const AddressPtrList &kernel_outputs,
                                      const AddressPtrList &kernel_workspaces) const;
   virtual void AssignStaticMemoryInput(const session::KernelGraph *graph);