diff --git a/graphengine b/graphengine
index 622af6c1c50..cb39cb2ba7c 160000
--- a/graphengine
+++ b/graphengine
@@ -1 +1 @@
-Subproject commit 622af6c1c50034bea5a08bd409c5a410782bfe53
+Subproject commit cb39cb2ba7c9afb27373ad9e81f563ff9ddb9fcc
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_build.cc b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_build.cc
index cdb2fe10477..f7c02236c52 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_build.cc
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_build.cc
@@ -20,6 +20,8 @@
 #include <vector>
 #include <memory>
 #include <algorithm>
+#include <map>
+#include <climits>
 #include "runtime/device/kernel_runtime.h"
 #include "backend/kernel_compiler/aicpu/aicpu_kernel_mod.h"
 #include "backend/kernel_compiler/akg/akg_kernel_build.h"
@@ -218,7 +220,7 @@ void SetNodeInputs(const std::shared_ptr<AnfNode> &anf_node, mindspore::NodeDef
       mindspore::TensorShape_Dim *dim = tensorShape->add_dim();
       dim->set_size((::google::protobuf::int64)item);
     }
-    node_inputs->set_tensor_type((mindspore::DataType)input_data_type);
+    node_inputs->set_tensor_type(input_data_type);
     node_inputs->set_mem_device("HBM");
   }
 }
@@ -245,7 +247,7 @@ void SetNodeOutputs(const std::shared_ptr<AnfNode> &anf_node, mindspore::NodeDef
     }
     TypeId output_type = AnfAlgo::GetOutputDeviceDataType(anf_node, output_index);
     int32_t output_data_type = AicpuOpUtil::MsTypeToProtoType(output_type);
-    node_outputs->set_tensor_type((mindspore::DataType)output_data_type);
+    node_outputs->set_tensor_type(output_data_type);
     node_outputs->set_mem_device("HBM");
   }
 }
@@ -287,6 +289,109 @@ bool CreateNodeDefBytes(const std::shared_ptr<AnfNode> &anf_node,
   return true;
 }
 
+bool CreateExtInfo(const std::shared_ptr<AnfNode> &anf_node, const std::shared_ptr<AicpuOpKernelMod> &kernel_mod_ptr) {
+  if (!anf_node->isa<CNode>()) {
+    return true;
+  }
+
+  if (!AnfAlgo::IsDynamicShape(anf_node)) {
+    return true;
+  }
+
+  MS_LOG(INFO) << "CreateExtInfo start, " << anf_node->fullname_with_scope();
+
+  int32_t unknown_shape_type = UnknowShapeOpType::DEPEND_COMPUTE;
+  uint64_t ext_info_head_len = kExtInfoHeadSize;
+  std::string ext_info;
+  size_t input_num = AnfAlgo::GetInputTensorNum(anf_node);
+  size_t output_num = AnfAlgo::GetOutputTensorNum(anf_node);
+
+  // 1.addr:unknown shape type
+  uint64_t ext_info_len = ext_info.size();
+  ext_info_len += ext_info_head_len + sizeof(int32_t);
+
+  // 2.addr:input ShapeAndType
+  ext_info_len += ext_info_head_len + input_num * sizeof(ShapeAndType);
+
+  // 3.addr:output ShapeAndType
+  ext_info_len += ext_info_head_len + output_num * sizeof(ShapeAndType);
+
+  uint64_t ext_info_offset = ext_info.size();
+  ext_info.resize(ext_info_len, 0);
+  char *ext_info_buf = ext_info.data();
+
+  // deal1: unknown shape type
+  ExtInfo *info = reinterpret_cast<ExtInfo *>(ext_info_buf + ext_info_offset);
+  info->infoType = FWK_ADPT_EXT_SHAPE_TYPE;
+  info->infoLen = sizeof(int32_t);
+  ext_info_offset += ext_info_head_len;
+  int32_t *shape_type = reinterpret_cast<int32_t *>(ext_info_buf + ext_info_offset);
+  *shape_type = unknown_shape_type;
+  ext_info_offset += info->infoLen;
+
+  // deal2:input ShapeAndType
+  info = reinterpret_cast<ExtInfo *>(ext_info_buf + ext_info_offset);
+  info->infoType = FWK_ADPT_EXT_INPUT_SHAPE;
+  info->infoLen = input_num * sizeof(ShapeAndType);
+  ext_info_offset += ext_info_head_len;
+
+  ShapeAndType *inputs = reinterpret_cast<ShapeAndType *>(ext_info_buf + ext_info_offset);
+  for (size_t input_index = 0; input_index < input_num; input_index++) {
+    TypeId input_type = AnfAlgo::GetInputDeviceDataType(anf_node, input_index);
+    std::vector<size_t> input_shape;
+    int32_t input_data_type;
+    if (input_type == kObjectTypeString) {
+      auto cnode = anf_node->cast<CNodePtr>();
+      MS_EXCEPTION_IF_NULL(cnode);
+      auto input_node = cnode->inputs()[input_index + 1];
+      auto value_ptr = GetValueNode(input_node);
+      auto value = GetValue<std::string>(value_ptr);
+      input_shape.push_back(1);
+      input_shape.push_back(value.size());
+      input_data_type = AicpuOpUtil::MsTypeToProtoType(kTypeUnknown);
+    } else {
+      input_shape = AnfAlgo::GetInputDeviceShape(anf_node, input_index);
+      input_data_type = AicpuOpUtil::MsTypeToProtoType(input_type);
+    }
+    inputs[input_index].type = input_data_type;
+
+    size_t input_shape_index = 0;
+    for (; input_shape_index < input_shape.size(); input_shape_index++) {
+      inputs[input_index].dims[input_shape_index] = SizeToLong(input_shape[input_shape_index]);
+    }
+    if (input_shape.size() < kMaxShapeDims) {
+      inputs[input_index].dims[input_shape_index] = LLONG_MIN;
+    }
+  }
+  ext_info_offset += info->infoLen;
+
+  // deal3:output ShapeAndType
+  info = reinterpret_cast<ExtInfo *>(ext_info_buf + ext_info_offset);
+  info->infoType = FWK_ADPT_EXT_OUTPUT_SHAPE;
+  info->infoLen = output_num * sizeof(ShapeAndType);
+  ext_info_offset += ext_info_head_len;
+
+  ShapeAndType *outputs = reinterpret_cast<ShapeAndType *>(ext_info_buf + ext_info_offset);
+  for (size_t output_index = 0; output_index < output_num; output_index++) {
+    std::vector<size_t> output_shape = AnfAlgo::GetOutputDeviceShape(anf_node, output_index);
+    TypeId output_type = AnfAlgo::GetOutputDeviceDataType(anf_node, output_index);
+    int32_t output_data_type = AicpuOpUtil::MsTypeToProtoType(output_type);
+    outputs[output_index].type = output_data_type;
+
+    size_t output_shape_index = 0;
+    for (; output_shape_index < output_shape.size(); output_shape_index++) {
+      outputs[output_index].dims[output_shape_index] = SizeToLong(output_shape[output_shape_index]);
+    }
+    if (output_shape_index < kMaxShapeDims) {
+      outputs[output_index].dims[output_shape_index] = LLONG_MIN;
+    }
+  }
+
+  // set ext info
+  kernel_mod_ptr->SetExtInfo(ext_info);
+  return true;
+}
+
 KernelModPtr AicpuOpBuild(const std::shared_ptr<AnfNode> &anf_node) {
   MS_EXCEPTION_IF_NULL(anf_node);
   std::string op_name = AnfAlgo::GetCNodeName(anf_node);
@@ -300,6 +405,11 @@ KernelModPtr AicpuOpBuild(const std::shared_ptr<AnfNode> &anf_node) {
   if (!CreateNodeDefBytes(anf_node, kernel_mod_ptr)) {
     MS_LOG(EXCEPTION) << "Create nodeDefBytes faild!";
   }
+
+  if (!CreateExtInfo(anf_node, kernel_mod_ptr)) {
+    MS_LOG(EXCEPTION) << "Create nodeDefBytes faild!";
+  }
+
   if (!SetIOSize(anf_node, kernel_mod_ptr)) {
     MS_LOG(EXCEPTION) << "Set input output size list failed.";
   }
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.cc b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.cc
index d00fab381ec..c7d7a3f1a2a 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.cc
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.cc
@@ -43,6 +43,7 @@ AicpuOpKernelMod::~AicpuOpKernelMod() {
   input_size_list_.clear();
   output_size_list_.clear();
   workspace_size_list_.clear();
+  ext_info_.clear();
 }
 
 void AicpuOpKernelMod::SetInputSizeList(const std::vector<size_t> &size_list) { input_size_list_ = size_list; }
@@ -54,6 +55,7 @@ const std::vector<size_t> &AicpuOpKernelMod::GetWorkspaceSizeList() const { retu
 void AicpuOpKernelMod::SetInputList(const std::vector<int64_t> &inputList) { inputList_ = inputList; }
 void AicpuOpKernelMod::SetOutputList(const std::vector<int64_t> &outputList) { outputList_ = outputList; }
 void AicpuOpKernelMod::SetNodeDef(const std::string &nodeDef) { (void)node_def_str_.assign(nodeDef); }
+void AicpuOpKernelMod::SetExtInfo(const std::string &ext_info) { ext_info_ = ext_info; }
 void AicpuOpKernelMod::SetNodeName(const std::string &node_name) { node_name_ = node_name; }
 void AicpuOpKernelMod::SetAnfNode(const mindspore::AnfNodePtr &anf_node) {
   MS_EXCEPTION_IF_NULL(anf_node);
@@ -84,16 +86,30 @@ void AicpuOpKernelMod::CreateCpuKernelInfo(const std::vector<AddressPtr> &inputs
 
   auto node_def_len = node_def_str_.length();
   param_len += node_def_len;
+  param_len += sizeof(uint32_t);
+
+  AicpuParamHead aicpu_param_head;
+  aicpu_param_head.length = param_len;
+  aicpu_param_head.ioAddrNum = io_addrs_num;
+
+  if (ext_info_.empty()) {
+    MS_LOG(INFO) << "Static Shape Kernel";
+    aicpu_param_head.extInfoLength = 0;
+    aicpu_param_head.extInfoAddr = 0;
+  } else {
+    MS_LOG(INFO) << "Dynamic Kernel Ext Info size:" << ext_info_.size();
+  }
 
-  // Create taskArgs: AicpuParamHead + ioAddrs + notifyId + customizedAttr
-  AicpuParamHead paramHead = {static_cast<uint32_t>(param_len), static_cast<uint32_t>(io_addrs_num)};
   args_.clear();
-  (void)args_.append(reinterpret_cast<const char *>(&paramHead), sizeof(AicpuParamHead));
+  (void)args_.append(reinterpret_cast<const char *>(&aicpu_param_head), sizeof(AicpuParamHead));
   // TaskArgs append ioAddrs
   if (io_addrs_size != 0) {
     (void)args_.append(reinterpret_cast<const char *>(io_addrs.data()), io_addrs_size);
   }
 
+  // size for node_def
+  args_.append(reinterpret_cast<const char *>(&node_def_len), sizeof(uint32_t));
+
   // When it's aicpu customized ops, taskArgs should append customized attr
   if (node_def_len != 0) {
     (void)args_.append(reinterpret_cast<const char *>(node_def_str_.data()), node_def_len);
@@ -145,8 +161,9 @@ std::vector<TaskInfoPtr> AicpuOpKernelMod::GenTask(const std::vector<AddressPtr>
     node_name_ = kTopKV2;
   }
 
-  AicpuTaskInfoPtr task_info_ptr = make_shared<ge::model_runner::AicpuTaskInfo>(
-    kernel_name_, stream_id, node_so_, node_name_, node_def_str_, input_data_addrs, output_data_addrs, NeedDump());
+  AicpuTaskInfoPtr task_info_ptr =
+    make_shared<ge::model_runner::AicpuTaskInfo>(kernel_name_, stream_id, node_so_, node_name_, node_def_str_,
+                                                 ext_info_, input_data_addrs, output_data_addrs, NeedDump());
 
   MS_LOG(INFO) << "AicpuOpKernelMod GenTask end";
   return {task_info_ptr};
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.h b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.h
index 9bc75d11101..7d006cc67dd 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.h
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_kernel_mod.h
@@ -36,6 +36,7 @@ class AicpuOpKernelMod : public AscendKernelMod {
   void SetOutputList(const std::vector<int64_t> &outputList);
   void SetAnfNode(const AnfNodePtr &anf_node);
   void SetNodeDef(const std::string &nodeDef);
+  void SetExtInfo(const std::string &ext_info);
   void SetNodeName(const std::string &node_name);
 
   /**
@@ -58,6 +59,7 @@ class AicpuOpKernelMod : public AscendKernelMod {
   std::string node_def_str_;
   std::string node_name_;
   std::string node_so_;
+  std::string ext_info_;
   std::vector<int64_t> inputList_;
   std::vector<int64_t> outputList_;
   AnfNodePtr anf_node_;
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_util.h b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_util.h
index d68aef3f860..01a8f577189 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_util.h
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/aicpu_util.h
@@ -21,7 +21,6 @@
 #include <map>
 #include <string>
 #include "backend/kernel_compiler/kernel.h"
-
 namespace mindspore {
 namespace kernel {
 constexpr auto kInitDataSetQueue = "InitDataSetQueue";
@@ -50,6 +49,36 @@ struct AicpuParamHead {
   uint64_t extInfoAddr;    // extInfo address
 } __attribute__((packed));
 
+const uint32_t kExtInfoHeadSize = 8;
+struct ExtInfo {
+  int32_t infoType;  // extend type
+  uint32_t infoLen;  // length for infoMsg
+  char infoMsg[0];   // extend value
+} __attribute__((packed));
+
+// Extent info ShapeAndType
+const uint32_t kMaxShapeDims = 8;
+struct ShapeAndType {
+  int32_t type;
+  int64_t dims[kMaxShapeDims];
+} __attribute__((packed));
+
+// Extend Info type for task
+enum FWKTaskExtInfoType {
+  FWK_ADPT_EXT_SHAPE_TYPE = 0,
+  FWK_ADPT_EXT_INPUT_SHAPE,
+  FWK_ADPT_EXT_OUTPUT_SHAPE,
+  FWK_ADPT_EXT_INVALID
+};
+
+// for unknown shape op type
+enum UnknowShapeOpType {
+  DEPEND_IN_SHAPE = 1,     // op out shape get by input shape
+  DEPEND_CONST_VALUE = 2,  // op out shape get by const op value
+  DEPEND_SHAPE_RANGE = 3,  // op out shape get by range
+  DEPEND_COMPUTE = 4       // op out shape get by totally computing
+};
+
 class AicpuOpUtil {
  public:
   static int MsTypeToProtoType(TypeId ms_type);
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/attr.proto b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/attr.proto
index a0ab4bd1e76..fee2172c1d1 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/attr.proto
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/attr.proto
@@ -26,7 +26,7 @@ message AttrValue {
     repeated int64 i = 3 [ packed = true ];       //"array(int)"
     repeated float f = 4 [ packed = true ];       //"array(float)"
     repeated bool b = 5 [ packed = true ];        //"array(bool)"
-    repeated DataType type = 6 [ packed = true ]; //"array(type)"
+    repeated int32 type = 6 [ packed = true ]; //"array(type)"
     repeated TensorShape shape = 7;               //"array(shape)"
     repeated Tensor tensor = 8;                   //"array(tensor)"
   }
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/node_def.proto b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/node_def.proto
index b0c0e0f349b..b1a76957d59 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/node_def.proto
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/node_def.proto
@@ -18,9 +18,16 @@ package mindspore;
 import "attr.proto";
 import "tensor.proto";
 
+message DynamicIdx {
+  int32 idx = 1;
+  int32 num = 2;
+}
+
 message NodeDef {
   string op = 2;
   map<string, AttrValue> attrs = 3;
   repeated Tensor inputs = 4;
   repeated Tensor outputs = 5;
+  map<string, DynamicIdx> dym_inputs = 6;
+  map<string, DynamicIdx> dym_outputs = 7;
 }
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor.proto b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor.proto
index b4fd66595a1..1240a97ab73 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor.proto
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor.proto
@@ -26,9 +26,12 @@ message Tensor {
   TensorShape tensor_shape = 1;
 
   // tensor content data type
-  DataType tensor_type = 2;
+  int32 tensor_type = 2;
 
   // tensor memory device
   // data located memory device , "DDR" "HBM" OR "NONE"
   string mem_device = 3;
+  string name = 4;
+  uint64 data_ptr = 5;
+  uint64 data_size = 6;
 }
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor_shape.proto b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor_shape.proto
index 70534e8ebab..12b07e09673 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor_shape.proto
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/tensor_shape.proto
@@ -31,5 +31,5 @@ message TensorShape {
   bool unknown_rank = 3;
 
   // data format "NHWC" "NCHW" "NC1HWC0" OR "NONE"
-  string data_format = 4;
+  int32 data_format = 4;
 };
diff --git a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/types.proto b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/types.proto
index 574259d97df..4cbff252bf5 100644
--- a/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/types.proto
+++ b/mindspore/ccsrc/backend/kernel_compiler/aicpu/proto/types.proto
@@ -19,17 +19,30 @@ option cc_enable_arenas = true;
 package mindspore;
 
 enum DataType {
-  MS_UNKNOWN = 0;
-  MS_BOOL = 1;
+  MS_FLOAT32 = 0;
+  MS_FLOAT16 = 1;
   MS_INT8 = 2;
-  MS_UINT8 = 3;
-  MS_INT16 = 4;
-  MS_UINT16 = 5;
-  MS_INT32 = 6;
-  MS_UINT32 = 7;
-  MS_INT64 = 8;
-  MS_UINT64 = 9;
-  MS_FLOAT16 = 10;
-  MS_FLOAT32 = 11;
-  MS_FLOAT64 = 12;
+  MS_INT32 = 3;
+  MS_UINT8 = 4;
+  MS_INT16 = 6;
+  MS_UINT16 = 7;
+  MS_UINT32 = 8;
+  MS_INT64 = 9;
+  MS_UINT64 = 10;
+  MS_FLOAT64 = 11;
+  MS_BOOL = 12;
+  MS_STRING = 13;
+  MS_DUAL_SUB_INT8 = 14;
+  MS_DUAL_SUB_UINT8 = 15;
+  MS_COMPLEX64 = 16;
+  MS_COMPLEX128 = 17;
+  MS_QINT8 = 18;
+  MS_QINT16 = 19;
+  MS_QINT32 = 20;
+  MS_QUINT8 = 21;
+  MS_QUINT16 = 22;
+  MS_RESOURCE = 23;
+  MS_STRING_REF = 24;
+  MS_DUAL = 25;
+  MS_UNKNOWN = 26;
 }
diff --git a/mindspore/ccsrc/backend/session/anf_runtime_algorithm.cc b/mindspore/ccsrc/backend/session/anf_runtime_algorithm.cc
index f505d83299b..7b626980002 100644
--- a/mindspore/ccsrc/backend/session/anf_runtime_algorithm.cc
+++ b/mindspore/ccsrc/backend/session/anf_runtime_algorithm.cc
@@ -1197,6 +1197,19 @@ TypeId AnfRuntimeAlgorithm::GetPrevNodeOutputPrecision(const AnfNodePtr &node, s
   return GetCNodeOutputPrecision(kernel_with_index.first);
 }
 
+bool AnfRuntimeAlgorithm::IsDynamicShape(const AnfNodePtr &node) {
+  if (!node->isa<CNode>()) {
+    return false;
+  }
+  auto cnode = node->cast<CNodePtr>();
+  MS_EXCEPTION_IF_NULL(cnode);
+  auto has_attr = AnfAlgo::HasNodeAttr(kAttrIsDynamicShape, cnode);
+  if (!has_attr) {
+    return false;
+  }
+  return AnfAlgo::GetNodeAttr<bool>(node, kAttrIsDynamicShape);
+}
+
 bool AnfRuntimeAlgorithm::IsCondControlKernel(const CNodePtr &node) {
   MS_EXCEPTION_IF_NULL(node);
   if (node->inputs().empty()) {
diff --git a/mindspore/ccsrc/backend/session/anf_runtime_algorithm.h b/mindspore/ccsrc/backend/session/anf_runtime_algorithm.h
index 2fff066166a..d4a5f00a259 100644
--- a/mindspore/ccsrc/backend/session/anf_runtime_algorithm.h
+++ b/mindspore/ccsrc/backend/session/anf_runtime_algorithm.h
@@ -217,6 +217,7 @@ class AnfRuntimeAlgorithm {
   static TypeId GetCNodeOutputPrecision(const AnfNodePtr &node);
   // get fix output precision from prev node, input_idx is the input index of current node related to prev node.
   static TypeId GetPrevNodeOutputPrecision(const AnfNodePtr &node, size_t input_idx);
+  static bool IsDynamicShape(const AnfNodePtr &node);
   static bool IsCondControlKernel(const CNodePtr &node);
   static bool IsIndependentNode(const CNodePtr &node);
 };
diff --git a/mindspore/ccsrc/utils/utils.h b/mindspore/ccsrc/utils/utils.h
index af1243e9fc6..2678a40503f 100644
--- a/mindspore/ccsrc/utils/utils.h
+++ b/mindspore/ccsrc/utils/utils.h
@@ -269,6 +269,7 @@ constexpr auto kAttrPadDimSize = "pad_dim_size";
 constexpr auto kAttrNumSegments = "num_segments";
 constexpr auto kAttrBegin = "begin";
 constexpr auto kAttrSize = "size";
+constexpr auto kAttrIsDynamicShape = "is_dynamic_shape";
 
 // attr value
 constexpr auto kValueTargetSwitch = "target_switch";
diff --git a/mindspore/ops/_op_impl/aicpu/__init__.py b/mindspore/ops/_op_impl/aicpu/__init__.py
index b321db47e08..bb63d4bf32e 100644
--- a/mindspore/ops/_op_impl/aicpu/__init__.py
+++ b/mindspore/ops/_op_impl/aicpu/__init__.py
@@ -13,6 +13,7 @@
 # limitations under the License.
 
 """aicpu ops"""
+from .unique import _unique_aicpu
 from .init_data_set_queue import _init_data_set_queue_aicpu
 from .embedding_lookup import _embedding_lookup_aicpu
 from .padding import _padding_aicpu
diff --git a/mindspore/ops/_op_impl/aicpu/unique.py b/mindspore/ops/_op_impl/aicpu/unique.py
new file mode 100644
index 00000000000..849e9696093
--- /dev/null
+++ b/mindspore/ops/_op_impl/aicpu/unique.py
@@ -0,0 +1,31 @@
+# Copyright 2020 Huawei Technologies Co., Ltd
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+# ============================================================================
+
+"""Unique op"""
+from mindspore.ops.op_info_register import op_info_register, AiCPURegOp, DataType
+
+unique_op_info = AiCPURegOp("Unique") \
+    .fusion_type("OPAQUE") \
+    .input(0, "x", "required") \
+    .output(0, "y", "required") \
+    .output(1, "idx", "required") \
+    .dtype_format(DataType.I32_Default, DataType.I32_Default, DataType.I32_Default) \
+    .dtype_format(DataType.I64_Default, DataType.I64_Default, DataType.I64_Default) \
+    .get_op_info()
+
+@op_info_register(unique_op_info)
+def _unique_aicpu():
+    """Unique AiCPU register"""
+    return
diff --git a/mindspore/ops/operations/__init__.py b/mindspore/ops/operations/__init__.py
index aa8ba107d30..e296af83caf 100644
--- a/mindspore/ops/operations/__init__.py
+++ b/mindspore/ops/operations/__init__.py
@@ -91,6 +91,7 @@ from ._thor_ops import (CusBatchMatMul, CusCholeskyTrsm, CusFusedAbsMax1, CusImg
 from .sparse_ops import SparseToDense
 
 __all__ = [
+    'Unique',
     'ReverseSequence',
     'EditDistance',
     'CropAndResize',
diff --git a/mindspore/ops/operations/array_ops.py b/mindspore/ops/operations/array_ops.py
index eb066c44b75..ad7051b3a01 100644
--- a/mindspore/ops/operations/array_ops.py
+++ b/mindspore/ops/operations/array_ops.py
@@ -569,9 +569,9 @@ class Unique(Primitive):
         containing indices of elements in the input coressponding to the output tensor.
 
     Examples:
-        >>> x = Tensor(np.array([1, 2, 5, 2]), mindspore.float32)
+        >>> x = Tensor(np.array([1, 2, 5, 2]), mindspore.int32)
         >>> out = P.Unique()(x)
-        (Tensor([1, 2, 5], mindspore.int32), Tensor([0, 1, 2, 1], mindspore.float32))
+        (Tensor([1, 2, 5], mindspore.int32), Tensor([0, 1, 2, 1], mindspore.int32))
     """
     @prim_attr_register
     def __init__(self):
diff --git a/tests/st/networks/models/resnet50/test_resnet50_imagenet.py b/tests/st/networks/models/resnet50/test_resnet50_imagenet.py
index 220b9862085..845248ce367 100644
--- a/tests/st/networks/models/resnet50/test_resnet50_imagenet.py
+++ b/tests/st/networks/models/resnet50/test_resnet50_imagenet.py
@@ -367,7 +367,8 @@ def test_resnet_and_resnet_thor_imagenet_4p():
         os.system("rm -rf " + str(i))
     print("End training...")
     assert acc > 0.15
-    assert cost < 20
+    # the original perf is: 20 in C75B100
+    assert cost < 22
 
     # THOR
     thor_acc = 0.0
@@ -383,4 +384,5 @@ def test_resnet_and_resnet_thor_imagenet_4p():
         os.system("rm -rf " + str(i))
     print("End training...")
     assert thor_acc > 0.22
-    assert thor_cost < 21
+    # the original perf is: 21 in C75B100
+    assert thor_cost < 23
diff --git a/tests/ut/cpp/stub/tdt/tdt_mock.cc b/tests/ut/cpp/stub/tdt/tdt_mock.cc
index 45725de173a..6b9c6f95a4b 100644
--- a/tests/ut/cpp/stub/tdt/tdt_mock.cc
+++ b/tests/ut/cpp/stub/tdt/tdt_mock.cc
@@ -35,39 +35,5 @@ StatusFactory::StatusFactory() {}
 
 std::mutex& StatusFactory::GetMutex() { return GetInstance()->rwMutex_; }
 
-TsdClient* TsdClient::GetInstance() {
-  static TsdClient instance;
-  return &instance;
-}
-
-/**
- * @ingroup TsdClient
- * @brief 构造函数
- */
-TsdClient::TsdClient() { rankSize_ = 1; }
-
-/**
- * @ingroup TsdClient
- * @brief 析构函数
- */
-TsdClient::~TsdClient() = default;
-
-/**
- * @ingroup TsdClient
- * @brief framework发送拉起hccp和computer process的命令
- * @param [in] phyDeviceId : FMK传入物理ID
- * @param [in] phyDeviceId : FMK传入rankSize
- * @return TDT_OK:成功 或者其他错误码
- */
-TDT_StatusT TsdClient::Open(const uint32_t deviceId, const uint32_t rankSize) { return TDT_OK; }
-
-/**
- * @ingroup TsdClient
- * @brief 通知TsdClient关闭相关资源
- * @param 无
- * @return TDT_OK:成功 或者其他错误码
- */
-TDT_StatusT TsdClient::Close() { return TDT_OK; }
-
 }  // namespace tdt
 #endif  // TDT_MOCK_H