!20317 [MSLITE][DEVELOP] sync r1.3 fix bug: delegate model input & output, affinity mode value

Merge pull request !20317 from yangruoqi713/master_bug

mindspore/lite/src/cxx_api/context.cc

@@ -39,7 +39,7 @@ struct Context::Data {
   int32_t thread_num = 2;
   bool enable_parallel_ = false;
   std::vector<int32_t> affinity_core_list_;
-  int affinity_mode_ = 2;
+  int affinity_mode_ = 0;
   std::shared_ptr<Delegate> delegate = nullptr;
 };
 
@@ -80,6 +80,7 @@ void Context::SetThreadNum(int32_t thread_num) {
   }
   data_->thread_num = thread_num;
 }
+
 int32_t Context::GetThreadNum() const {
   if (data_ == nullptr) {
     MS_LOG(ERROR) << "Invalid context.";
@@ -111,9 +112,9 @@ void Context::SetThreadAffinity(int mode) {
     return;
   }
   data_->affinity_mode_ = mode;
-
   return;
 }
+
 int Context::GetThreadAffinityMode() const {
   if (data_ == nullptr) {
     MS_LOG(ERROR) << "Invalid context.";
@@ -131,6 +132,7 @@ void Context::SetThreadAffinity(const std::vector<int> &core_list) {
 
   return;
 }
+
 std::vector<int32_t> Context::GetThreadAffinityCoreList() const {
   if (data_ == nullptr) {
     MS_LOG(ERROR) << "Invalid context.";
@@ -221,6 +223,7 @@ void CPUDeviceInfo::SetEnableFP16(bool is_fp16) {
   }
   data_->params[kModelOptionCpuEnableFP16] = is_fp16;
 }
+
 bool CPUDeviceInfo::GetEnableFP16() const {
   if (data_ == nullptr) {
     MS_LOG(ERROR) << "Invalid context.";
@@ -251,6 +254,7 @@ void KirinNPUDeviceInfo::SetFrequency(int frequency) {
   }
   data_->params[kModelOptionKirinNpuFrequency] = frequency;
 }
+
 int KirinNPUDeviceInfo::GetFrequency() const {
   if (data_ == nullptr) {
     MS_LOG(ERROR) << "Invalid context.";

mindspore/lite/src/cxx_api/converters.cc

@@ -60,6 +60,11 @@ Status A2L_ConvertContext(Context *a_context, lite::Context *l_context) {
     cpu_context->SetAllocator(l_context->allocator);
   }
 
+  if (!IsAffinityModeValid(a_context->GetThreadAffinityMode())) {
+    MS_LOG(ERROR)
+      << "Invalid affinity mode, only supports 0: no affinities, 1: big cores first, 2: little cores first.";
+    return kLiteInputParamInvalid;
+  }
   lite::CpuBindMode mode = A2L_ConvertAffinityMode(a_context->GetThreadAffinityMode());
 
   lite::DeviceInfo cpu_info = {0};

mindspore/lite/src/cxx_api/converters.h

@@ -55,6 +55,10 @@ inline lite::CpuBindMode A2L_ConvertAffinityMode(int affinity_mode) {
   }
 }
 
+inline bool IsAffinityModeValid(int affinity_mode) {
+  return affinity_mode >= lite::NO_BIND && affinity_mode <= lite::MID_CPU;
+}
+
 Status A2L_ConvertContext(Context *a_context, lite::Context *l_context);
 
 Status A2L_ConvertConfig(const TrainCfg *a_train_cfg, lite::TrainCfg *l_train_cfg);

mindspore/lite/src/delegate/npu/npu_graph.cc

@@ -22,6 +22,14 @@
 #include "src/delegate/npu/transpose_kernel.h"
 namespace mindspore {
 NPUGraph::~NPUGraph() {
+  for (int i = 0; i < all_kernels_.size(); i++) {
+    for (auto output : all_kernels_[i]->outputs()) {
+      if (find(outputs_.begin(), outputs_.end(), output) != outputs_.end()) {
+        free(output.MutableData());
+        output.SetData(nullptr);
+      }
+    }
+  }
   for (auto *kernel : all_kernels_) {
     delete kernel;
   }

mindspore/lite/src/inner_context.cc

@@ -30,6 +30,7 @@ InnerContext::InnerContext(const Context *context) {
   this->allocator = context->allocator;
   this->thread_num_ = context->thread_num_;
   this->enable_parallel_ = context->enable_parallel_;
+  this->affinity_core_list_ = context->affinity_core_list_;
   SetContextDevice(context);
 #if defined(ENABLE_ARM) && defined(ENABLE_FP16)
   CpuInfo cpu_info;

mindspore/lite/src/lite_session.cc

@@ -710,6 +710,7 @@ void LiteSession::BindThread(bool if_bind) {
 }
 
 LiteSession::~LiteSession() {
+  delegate_.reset();
   bool expected = false;
   if (!is_running_.compare_exchange_strong(expected, true)) {
     MS_LOG(ERROR) << "Not support multi-threading";

mindspore/lite/src/mindrt_executor.cc

@@ -112,7 +112,12 @@ void MindrtExecutor::TransferGraphOutput() {
                     reinterpret_cast<float *>(dst_tensor->data_c()), dst_tensor->ElementsNum());
     } else {
       dst_tensor->set_data(src_tensor->data());
-      src_tensor->set_data(nullptr);
+      if (src_tensor->own_data() == true && src_tensor->allocator() == nullptr) {
+        dst_tensor->set_own_data(false);
+        src_tensor->IncRefCount();
+      } else {
+        src_tensor->set_data(nullptr);
+      }
     }
     src_tensor->DecRefCount();
   }
@@ -128,8 +133,12 @@ void MindrtExecutor::FreeOutputTensor() {
     } else {
       if (dst_tensor->data_type() == src_tensor->data_type()) {
         /* user set graph-output-tensor from outside */
-        src_tensor->set_data(dst_tensor->data());
-        src_tensor->set_own_data(false);
+        if (dst_tensor->data() == nullptr || dst_tensor->own_data() == false) {
+          src_tensor->set_own_data(true);
+        } else {
+          src_tensor->set_data(dst_tensor->data());
+          src_tensor->set_own_data(false);
+        }
         src_tensor->set_allocator(nullptr);
       }
     }

mindspore/lite/src/scheduler.cc

@@ -172,9 +172,11 @@ int Scheduler::ReplaceDelegateKernels(std::vector<kernel::LiteKernel *> *dst_ker
     kernels.push_back((*dst_kernels)[i]->kernel());
   }
 
+  ms_inputs_ = LiteTensorsToMSTensors(inputs_);
+  ms_outputs_ = LiteTensorsToMSTensors(outputs_);
   auto schema_version = static_cast<SchemaVersion>(VersionManager::GetInstance()->GetSchemaVersion());
-  DelegateModel *model = new (std::nothrow) DelegateModel(
-    &kernels, LiteTensorsToMSTensors(inputs_), LiteTensorsToMSTensors(outputs_), primitives_, schema_version);
+  DelegateModel *model =
+    new (std::nothrow) DelegateModel(&kernels, ms_inputs_, ms_outputs_, primitives_, schema_version);
   if (model == nullptr) {
     MS_LOG(ERROR) << "New delegate model failed.";
     return RET_NULL_PTR;

mindspore/lite/src/scheduler.h

@@ -124,6 +124,8 @@ class Scheduler {
   std::vector<Tensor *> *src_tensors_;
   const std::vector<Tensor *> &inputs_;
   const std::vector<Tensor *> &outputs_;
+  std::vector<mindspore::MSTensor> ms_inputs_;
+  std::vector<mindspore::MSTensor> ms_outputs_;
   std::vector<size_t> graph_output_node_indexes_;
   std::map<int, OpParameter *> op_parameters_;
   bool is_train_session_ = false;