Add submodelId in dyanamic shape

ge/graph/load/graph_loader.cc

@@ -320,10 +320,10 @@ Status GraphLoader::GetMemoryInfo(int64_t &free) {
   return SUCCESS;
 }
 
-Status GraphLoader::DestroyAicpuKernel(uint64_t session_id, uint32_t model_id) {
+Status GraphLoader::DestroyAicpuKernel(uint64_t session_id, uint32_t model_id, uint32_t sub_model_id) {
   auto model_manager = ModelManager::GetInstance();
   GE_CHECK_NOTNULL(model_manager);
-  Status ret = model_manager->DestroyAicpuKernel(session_id, model_id);
+  Status ret = model_manager->DestroyAicpuKernel(session_id, model_id, sub_model_id);
   if (ret != SUCCESS) {
     GELOGE(ret, "Destroy aicpu kernel failed.");
     return ret;

ge/graph/load/graph_loader.h

@@ -68,7 +68,7 @@ class GraphLoader {
                              const std::vector<GeTensorDesc> &input_desc, OutputData &output_data,
                              std::vector<GeTensorDesc> &output_desc);
 
-  static Status DestroyAicpuKernel(uint64_t session_id, uint32_t model_id);
+  static Status DestroyAicpuKernel(uint64_t session_id, uint32_t model_id, uint32_t sub_model_id);
 
   static Status DestroyAicpuSessionForInfer(uint32_t model_id);
 

ge/graph/load/new_model_manager/davinci_model.h

@@ -136,6 +136,20 @@ class DavinciModel {
   ///
   void SetId(uint32_t model_id) { model_id_ = model_id; }
 
+  ///
+  /// @ingroup ge
+  /// @brief Get SubModelId
+  /// @return sub model ID
+  ///
+  uint32_t SubModelId() const { return sub_model_id_; }
+
+  ///
+  /// @ingroup ge
+  /// @brief Set SubModelId
+  /// @return sub model ID
+  ///
+  void SetSubModelId(uint32_t sub_model_id) { sub_model_id_ = sub_model_id; }
+
   static void *Run(DavinciModel *model_pointer);
 
   ///
@@ -815,6 +829,7 @@ class DavinciModel {
 
   uint32_t model_id_;
   uint32_t runtime_model_id_;
+  uint32_t sub_model_id_ = 0;
   string name_;
 
   // used for inference data dump

ge/graph/load/new_model_manager/model_manager.cc

@@ -81,7 +81,8 @@ ModelManager::ModelManager() {
   session_id_bias_ = 0;
 }
 
-Status ModelManager::KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType op_type, uint64_t session_id, uint32_t model_id) {
+Status ModelManager::KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType op_type, uint64_t session_id, uint32_t model_id,
+                                    uint32_t sub_model_id) {
   STR_FWK_OP_KERNEL param_base = {};
   void *devicebase = nullptr;
   void *aicpu_kernel_addr = nullptr;
@@ -91,10 +92,11 @@ Status ModelManager::KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType op_type, u
   param_base.fwkKernelBase.fwk_kernel.sessionID = session_id;
   if (op_type == aicpu::FWKAdapter::FWKOperateType::FWK_ADPT_KERNEL_DESTROY) {
     std::vector<uint64_t> v_aicpu_kernel;
-    std::string model_key = std::to_string(session_id) + "_" + std::to_string(model_id);
+    std::string model_key = std::to_string(session_id) + "_" + std::to_string(model_id) + "_" +
+                            std::to_string(sub_model_id);
     auto iter = model_aicpu_kernel_.find(model_key);
     if (iter != model_aicpu_kernel_.end()) {
-      GELOGD("kernel destroy session_id %lu, model_id %u.", session_id, model_id);
+      GELOGD("kernel destroy session_id %lu, model_id %u, sub_model_id %u..", session_id, model_id, sub_model_id);
       v_aicpu_kernel = model_aicpu_kernel_.at(model_key);
       // Insert size of aicpu kernel vector in the first element
       v_aicpu_kernel.insert(v_aicpu_kernel.begin(), v_aicpu_kernel.size());
@@ -192,7 +194,7 @@ void ModelManager::DestroyAicpuSession(uint64_t session_id) {
       GE_CHK_RT(rtSetDevice(static_cast<int32_t>(GetContext().DeviceId())));
     }
 
-    Status ret = KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType::FWK_ADPT_SESSION_DESTROY, session_id, 0);
+    Status ret = KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType::FWK_ADPT_SESSION_DESTROY, session_id, 0, 0);
     if (ret != SUCCESS) {
       GELOGW("The session: %lu destroy failed.", session_id);
     } else {
@@ -226,12 +228,14 @@ ge::Status ModelManager::DestroyAicpuSessionForInfer(uint32_t model_id) {
   return SUCCESS;
 }
 
-ge::Status ModelManager::DestroyAicpuKernel(uint64_t session_id, uint32_t model_id) {
+ge::Status ModelManager::DestroyAicpuKernel(uint64_t session_id, uint32_t model_id, uint32_t sub_model_id) {
   GELOGD("destroy aicpu kernel in session_id %lu, model_id %u.", session_id, model_id);
   std::lock_guard<std::mutex> lock(map_mutex_);
-  std::string model_key = std::to_string(session_id) + "_" + std::to_string(model_id);
+  std::string model_key = std::to_string(session_id) + "_" + std::to_string(model_id) + "_" +
+                          std::to_string(sub_model_id);
   if (model_aicpu_kernel_.find(model_key) != model_aicpu_kernel_.end()) {
-    Status ret = KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType::FWK_ADPT_KERNEL_DESTROY, session_id, model_id);
+    Status ret = KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType::FWK_ADPT_KERNEL_DESTROY, session_id, model_id,
+                                sub_model_id);
     if (ret != SUCCESS) {
       GELOGE(FAILED, "Destroy aicpu kernel failed.");
       return FAILED;
@@ -240,10 +244,12 @@ ge::Status ModelManager::DestroyAicpuKernel(uint64_t session_id, uint32_t model_
   return SUCCESS;
 }
 
-ge::Status ModelManager::CreateAicpuKernel(uint64_t session_id, uint32_t model_id, uint64_t kernel_id) {
+ge::Status ModelManager::CreateAicpuKernel(uint64_t session_id, uint32_t model_id, uint32_t sub_model_id,
+                                           uint64_t kernel_id) {
   std::lock_guard<std::mutex> lock(map_mutex_);
   std::vector<uint64_t> v_aicpu_kernel;
-  std::string model_key = std::to_string(session_id) + "_" + std::to_string(model_id);
+  std::string model_key = std::to_string(session_id) + "_" + std::to_string(model_id) + "_" +
+                          std::to_string(sub_model_id);
   if (model_aicpu_kernel_.find(model_key) != model_aicpu_kernel_.end()) {
     v_aicpu_kernel = model_aicpu_kernel_.at(model_key);
   }
@@ -378,7 +384,8 @@ Status ModelManager::DeleteModel(uint32_t id) {
   auto hybrid_model_it = hybrid_model_map_.find(id);
   if (it != model_map_.end()) {
     uint64_t session_id = it->second->GetSessionId();
-    std::string model_key = std::to_string(session_id) + "_" + std::to_string(id);
+    std::string model_key = std::to_string(session_id) + "_" + std::to_string(id)  + "_" +
+                            std::to_string(it->second->SubModelId());
     auto iter_aicpu_kernel = model_aicpu_kernel_.find(model_key);
     if (iter_aicpu_kernel != model_aicpu_kernel_.end()) {
       (void)model_aicpu_kernel_.erase(iter_aicpu_kernel);
@@ -1224,7 +1231,8 @@ Status ModelManager::ExecuteModel(uint32_t model_id, rtStream_t stream, bool asy
     // Zero copy is enabled by default, no need to judge.
     uint64_t session_id_davinci = davinci_model->GetSessionId();
     uint32_t model_id_davinci = davinci_model->GetModelId();
-    Status status = DestroyAicpuKernel(session_id_davinci, model_id_davinci);
+    uint32_t sub_model_id = davinci_model->SubModelId();
+    Status status = DestroyAicpuKernel(session_id_davinci, model_id_davinci, sub_model_id);
     if (status != SUCCESS) {
       GELOGW("Destroy specified aicpu kernel failed, session id is %lu, model id is %u.", session_id_davinci,
              model_id_davinci);
@@ -1244,7 +1252,7 @@ Status ModelManager::CreateAicpuSession(uint64_t session_id) {
   auto it = sess_ids_.find(session_id);
   // never been created by any model
   if (it == sess_ids_.end()) {
-    Status ret = KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType::FWK_ADPT_SESSION_CREATE, session_id, 0);
+    Status ret = KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType::FWK_ADPT_SESSION_CREATE, session_id, 0, 0);
     if (ret == SUCCESS) {
       (void)sess_ids_.insert(session_id);
       GELOGI("The session: %lu create success.", session_id);

ge/graph/load/new_model_manager/model_manager.h

@@ -273,7 +273,8 @@ class FMK_FUNC_HOST_VISIBILITY FMK_FUNC_DEV_VISIBILITY ModelManager {
 
   std::shared_ptr<hybrid::HybridDavinciModel> GetHybridModel(uint32_t id);
 
-  ge::Status KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType op_type, uint64_t session_id, uint32_t model_id);
+  ge::Status KernelLaunchEx(aicpu::FWKAdapter::FWKOperateType op_type, uint64_t session_id, uint32_t model_id,
+                            uint32_t sub_model_id);
 
   ge::Status CreateAicpuSession(uint64_t session_id);
 
@@ -281,9 +282,9 @@ class FMK_FUNC_HOST_VISIBILITY FMK_FUNC_DEV_VISIBILITY ModelManager {
 
   void DestroyAicpuSession(uint64_t session_id);
 
-  ge::Status DestroyAicpuKernel(uint64_t session_id, uint32_t model_id);
+  ge::Status DestroyAicpuKernel(uint64_t session_id, uint32_t model_id, uint32_t sub_model_id);
 
-  ge::Status CreateAicpuKernel(uint64_t session_id, uint32_t model_id, uint64_t kernel_id);
+  ge::Status CreateAicpuKernel(uint64_t session_id, uint32_t model_id, uint32_t sub_model_id, uint64_t kernel_id);
 
   ge::Status DestroyAicpuSessionForInfer(uint32_t model_id);
 

ge/graph/load/new_model_manager/task_info/kernel_ex_task_info.cc

@@ -97,7 +97,8 @@ Status KernelExTaskInfo::Init(const domi::TaskDef &task_def, DavinciModel *davin
 
   // 2.2 Collect aicpu kernel
   uint64_t kernel_id = fwk_op_kernel.fwkKernelBase.fwk_kernel.kernelID;
-  GE_IF_BOOL_EXEC(ModelManager::GetInstance()->CreateAicpuKernel(session_id, davinci_model->Id(), kernel_id) != SUCCESS,
+  GE_IF_BOOL_EXEC(ModelManager::GetInstance()->CreateAicpuKernel(session_id, davinci_model->Id(),
+                                                                 davinci_model->SubModelId(), kernel_id) != SUCCESS,
                   GELOGE(FAILED, "CreateAicpuKernel error.");
                   return FAILED;)
   // 2.3 Create session

ge/graph/manager/graph_manager.cc

@@ -2466,7 +2466,7 @@ Status GraphManager::CheckAndReleaseMemory(const GeModelPtr &ge_model, const Gra
       GELOGE(RT_FAILED, "[GraphManager:] rtSetDevice failed, modelId=%u, graphId=%u.", model_id, graph_id);
       continue;
     }
-    result = GraphLoader::DestroyAicpuKernel(session_id, model_id);
+    result = GraphLoader::DestroyAicpuKernel(session_id, model_id, 0);
     if (result != SUCCESS) {
       GELOGW("[GraphManager:] destroy aicpu kernel failed when dynamic memory, modelId=%u, graphId=%u.", model_id,
              graph_id);

ge/hybrid/node_executor/compiledsubgraph/known_node_executor.cc

@@ -127,11 +127,18 @@ Status KnownNodeTask::Init(TaskContext &context) {
     if (dump_properties.IsDumpOpen()) {
       davinci_model_->SetDumpProperties(dump_properties);
     }
+    int32_t device_id = 0;
+    rtError_t rt_ret = rtGetDevice(&device_id);
+    if (rt_ret != RT_ERROR_NONE || device_id < 0) {
+      GELOGE(rt_ret, "Call rtGetDevice failed, ret = 0x%X, device_id = %d.", rt_ret, device_id);
+      return RT_ERROR_TO_GE_STATUS(rt_ret);
+    }
+    davinci_model_->SetDeviceId(device_id);
     GE_CHK_STATUS_RET(davinci_model_->Init(), "KnownNodeExecutor::InitDavinciModel failed.");
     load_flag_ = true;
   } else {
     GE_CHK_STATUS_RET(ModelManager::GetInstance()->DestroyAicpuKernel(davinci_model_->GetSessionId(),
-            davinci_model_->Id()), "KnownNodeTask::Init destroy aicpu kernel failed.");
+            davinci_model_->Id(), davinci_model_->SubModelId()), "KnownNodeTask::Init destroy aicpu kernel failed.");
   }
   GELOGI("[%s] KnownNodeExecutor::Init success.", context.GetNodeName());
   return SUCCESS;
@@ -165,8 +172,9 @@ Status KnownNodeExecutor::LoadTask(const HybridModel &model, const NodePtr &node
 
   // set known node flag as true
   davinci_model->SetKnownNode(true);
+  davinci_model->SetId(model.GetModelId());
   // set model id as root node's node id
-  davinci_model->SetId(node->GetOpDesc()->GetId());
+  davinci_model->SetSubModelId(node->GetOpDesc()->GetId());
   GELOGD("KnownNodeExecutor::LoadTask node id %ld.", node->GetOpDesc()->GetId());
 
   GE_CHK_STATUS_RET(davinci_model->Assign(ge_model), "KnownNodeExecutor::LoadTask davincimodel assign failed.");