!5820 fix ub fusion

Merge pull request !5820 from jjfeing/r0.7_ub_fusion

mindspore/_extends/parallel_compile/tbe_compiler/compiler.py

@@ -17,8 +17,6 @@ import json
 import os
 import sys
 from te.platform.cce_conf import te_set_version
-from te.platform.fusion_manager import op_build_cfg_dis, op_build_cfg_en, set_current_op_name, \
-    init_op_pattern, set_op_params, set_op_build_type, get_op_pattern, set_current_op_func_name
 from te.platform.fusion_util import fusion_op
 from common import check_kernel_info, get_args, get_build_in_impl_path, get_ddk_version
 
@@ -27,7 +25,6 @@ build_in_impl_path = get_build_in_impl_path()
 
 # op function list
 op_build = "compile"
-op_pre_build = "pre_build"
 fusion_pattern_start_flag = "fusion_pattern_start"
 fusion_pattern_end_flag = "fusion_pattern_end"
 
@@ -83,19 +80,7 @@ def build_op(build_type, json_str):
         else:
             op_module = __import__("impl."+op_name, globals(), locals(), [op_name], 0)
         # get function
-        if build_type == op_pre_build:
-            # set op parameter
-            op_build_cfg_dis()
-            set_current_op_func_name(op_name)
-            set_current_op_name(kernel_name)
-            init_op_pattern()
-            set_op_params(*outputs_args, *attrs_args, kernel_name=kernel_name)
-            set_op_build_type('prebuild')
-            if custom_flag:
-                py_fn_name = kernel_info['op_info']['name']
-            else:
-                py_fn_name = op_name
-        elif build_type == op_build:
+        if build_type == op_build:
             if custom_flag:
                 py_fn_name = kernel_info['op_info']['name']
             else:
@@ -106,13 +91,6 @@ def build_op(build_type, json_str):
         if op_func is None:
             raise ValueError("Op:{} function {} is not supported by Tbe.".format(op_name, build_type))
 
-        # pre build
-        if build_type == op_pre_build:
-            op_func(*inputs_args, *outputs_args, *attrs_args, kernel_name=kernel_name)
-            # disable only pattern configuration
-            op_build_cfg_en()
-            return get_op_pattern()
-
         # call function
         if kernel_name[0:19] == "bounding_box_encode":
             return op_func(*inputs_args, *outputs_args, *attrs_args, kernel_name_val=kernel_name)
@@ -120,8 +98,6 @@ def build_op(build_type, json_str):
         return op_func(*inputs_args, *outputs_args, *attrs_args, kernel_name=kernel_name)
 
     except Exception as e:
-        if build_type == op_pre_build:
-            op_build_cfg_en()
         raise RuntimeError(e)
 
 
@@ -136,14 +112,9 @@ def compile_fusion_op(json_str):
         Exception: If specific keyword is not found.
     """
     args = json.loads(json_str)
+    te_set_version(ddk_version)
     if 'fusion_op' not in args or not args['fusion_op']:
         raise ValueError("Json string Errors, key:fusion_op not found.")
-    if 'prebuild_ops' not in args or not args['prebuild_ops']:
-        raise ValueError("Json string Errors, key:prebuild_ops not found.")
-
-    pre_build_op_list = args['prebuild_ops']
-    for op in pre_build_op_list:
-        build_op(op_pre_build, json.dumps(op))
     fusion_op_arg = args['fusion_op']
     return fusion_op(json.dumps(fusion_op_arg))
 
@@ -159,8 +130,6 @@ def compile_with_json(json_str):
     json_info = json.loads(json_str)
     if "fusion_op" in json_info:
         ret = compile_fusion_op(json_str)
-    elif "compile_type" in json_info:
-        ret = build_op(op_pre_build, json_str)
     else:
         ret = build_op(op_build, json_str)
     return ret

mindspore/ccsrc/backend/kernel_compiler/kernel.h

@@ -37,7 +37,6 @@ enum FusionType {
   COMMREDUCE,
   SEGMENT,
   OPAQUE,
-  DYNAMIC,
   UNKNOWN_FUSION_TYPE = -1,
 };
 enum OpPattern {
@@ -80,8 +79,8 @@ class KernelPack {
   bool LoadKernelMeta(const std::string &json_f, const std::string &processor);
   bool ReadFromJsonFile(const std::string &json_f, const std::string &processor);
   const std::string Serialize() const;
-  const FlexArray *const GetJson() const { return json_; }
-  const FlexArray *const GetKernel() const { return kernel_; }
+  const FlexArray *GetJson() const { return json_; }
+  const FlexArray *GetKernel() const { return kernel_; }
   ~KernelPack() {
     if (json_) {
       delete[] json_;

mindspore/ccsrc/backend/kernel_compiler/kernel_fusion.cc

@@ -19,53 +19,36 @@
 #include <map>
 #include <string>
 #include <memory>
-#include <utility>
 #include "backend/kernel_compiler/tbe/tbe_kernel_build.h"
 #include "backend/kernel_compiler/tbe/tbe_kernel_parallel_build.h"
 #include "backend/kernel_compiler/tbe/tbe_utils.h"
 #include "backend/kernel_compiler/tbe/tbe_convert_utils.h"
+#include "utils/ms_context.h"
 
 namespace mindspore {
 namespace kernel {
 using mindspore::kernel::tbe::TbeUtils;
-static bool GenPreBuildKernelJson(const std::vector<AnfNodePtr> &compute_nodes,
-                                  std::vector<nlohmann::json> *prebuild_op_list) {
-  MS_EXCEPTION_IF_NULL(prebuild_op_list);
-  TbeKernelJsonCreator creator(PREBUILD);
-  for (const auto &anf_node : compute_nodes) {
-    nlohmann::json prebuild;
-    if (!creator.GenTbeSingleKernelJson(anf_node, &prebuild)) {
-      MS_LOG(ERROR) << "GenTbeSingleKernelJson failed";
-      return false;
-    }
-    (*prebuild_op_list).push_back(prebuild);
-  }
-  return true;
-}
-
 std::map<int32_t, KernelModPtr> KernelFusion(const std::vector<FusionScopeInfo> &fusion_scopes) {
   MS_LOG(INFO) << "kernel fusion build start, scope size:" << fusion_scopes.size();
   std::map<int32_t, KernelModPtr> kernel_mod_ret;
   auto build_manger = std::make_shared<ParallelBuildManager>();
   MS_EXCEPTION_IF_NULL(build_manger);
   for (const auto &fusion_scope_iter : fusion_scopes) {
-    auto scope_id = fusion_scope_iter.scope_id;
+    string fusion_kernel_name;
     nlohmann::json fusion_op;
-    string fusion_kernel = "te_fusion";
     if (!TbeKernelBuild::GenFusionScopeJson(fusion_scope_iter.input_nodes, fusion_scope_iter.compute_nodes, &fusion_op,
-                                            &fusion_kernel)) {
+                                            &fusion_kernel_name)) {
       continue;
     }
     // gen kernel_name & check cache
     std::string json_str = fusion_op.dump();
     size_t hash_id = std::hash<std::string>()(json_str);
-    auto json_name = fusion_kernel.append("_").append(std::to_string(hash_id));
+    auto context_ptr = MsContext::GetInstance();
+    MS_EXCEPTION_IF_NULL(context_ptr);
+    auto device_id = context_ptr->device_id();
+    auto json_name =
+      fusion_kernel_name.append("_").append(std::to_string(hash_id)).append("_").append(std::to_string(device_id));
     fusion_op["fusion_op_name"] = json_name;
-    // gen json for prebuild
-    std::vector<nlohmann::json> prebuild_op_list;
-    if (!GenPreBuildKernelJson(fusion_scope_iter.compute_nodes, &prebuild_op_list)) {
-      continue;
-    }
     // get io size
     std::vector<size_t> input_size_list;
     std::vector<size_t> output_size_list;
@@ -80,20 +63,20 @@ std::map<int32_t, KernelModPtr> KernelFusion(const std::vector<FusionScopeInfo>
       auto kernel_mod =
         build_manger->GenKernelMod(json_name, tbe::kProcessorAiCore, input_size_list, output_size_list, kernel_pack);
       if (kernel_mod != nullptr) {
-        kernel_mod_ret[scope_id] = kernel_mod;
+        kernel_mod_ret[fusion_scope_iter.scope_id] = kernel_mod;
         continue;
       }
     }
     // fusion build
     nlohmann::json fusion_json;
     fusion_json["fusion_op"] = fusion_op;
-    fusion_json["prebuild_ops"] = prebuild_op_list;
     auto task_id = build_manger->StartCompileOp(fusion_json);
     TbeUtils::SaveJsonInfo(json_name, fusion_json.dump());
     if (task_id < 0) {
       MS_EXCEPTION(ArgumentError) << "start compile failed.";
     }
-    build_manger->SaveTaskInfo(task_id, nullptr, json_name, input_size_list, output_size_list, scope_id);
+    build_manger->SaveTaskInfo(task_id, nullptr, json_name, input_size_list, output_size_list,
+                               fusion_scope_iter.scope_id);
   }
 
   int build_failed_num = 0;

mindspore/ccsrc/backend/kernel_compiler/kernel_fusion.h

@@ -16,6 +16,7 @@
 
 #ifndef MINDSPORE_CCSRC_BACKEND_KERNEL_COMPILER_KERNELFUSION_H_
 #define MINDSPORE_CCSRC_BACKEND_KERNEL_COMPILER_KERNELFUSION_H_
+#include <utility>
 #include <vector>
 #include <map>
 #include "backend/kernel_compiler/kernel.h"
@@ -25,11 +26,9 @@ namespace kernel {
  * @brief fuse op and return a callable mod
  */
 struct FusionScopeInfo {
-  FusionScopeInfo() {}
-  FusionScopeInfo(int32_t id, const std::vector<AnfNodePtr> &in, const std::vector<AnfNodePtr> &comp,
-                  const std::vector<AnfNodePtr> &out)
-      : scope_id(id), input_nodes(in), compute_nodes(comp), output_nodes(out) {}
-  int32_t scope_id;
+  FusionScopeInfo(int32_t id, std::vector<AnfNodePtr> in, std::vector<AnfNodePtr> comp, std::vector<AnfNodePtr> out)
+      : scope_id(id), input_nodes(std::move(in)), compute_nodes(std::move(comp)), output_nodes(std::move(out)) {}
+  int32_t scope_id{};
   std::vector<AnfNodePtr> input_nodes;
   std::vector<AnfNodePtr> compute_nodes;
   std::vector<AnfNodePtr> output_nodes;

mindspore/ccsrc/backend/kernel_compiler/oplib/oplib.h

@@ -40,14 +40,13 @@ class OpLib {
 
  private:
   static bool RegOpFromLocalInfo();
-  static bool DecodeOpInfo(const nlohmann::json &obj, const OpImplyType imply_type, const std::string &impl_path);
-  static bool DecodeAttr(const nlohmann::json &obj, const OpImplyType imply_type,
-                         const std::shared_ptr<OpInfo> &op_info);
+  static bool DecodeOpInfo(const nlohmann::json &obj, OpImplyType imply_type, const std::string &impl_path);
+  static bool DecodeAttr(const nlohmann::json &obj, OpImplyType imply_type, const std::shared_ptr<OpInfo> &op_info);
   static bool DecodeDtypeFormat(const nlohmann::json &dtype_format, const std::shared_ptr<OpIOInfo> &op_io,
                                 size_t index);
   static void DecodeTBESpecificInfo(const nlohmann::json &obj, const std::shared_ptr<OpInfo> &op_info);
   static void DecodeAKGSpecificInfo(const nlohmann::json &obj, const std::shared_ptr<OpInfo> &op_info);
-  static bool DecodeInputOutput(const nlohmann::json &obj, const OpImplyType imply_type, const OpIOType io_type,
+  static bool DecodeInputOutput(const nlohmann::json &obj, OpImplyType imply_type, OpIOType io_type,
                                 const std::shared_ptr<OpInfo> &op_info, const nlohmann::json &dtype_format);
   static bool GetRefInfo(const std::shared_ptr<OpInfo> &op_info);
   static bool CheckRepetition(const std::shared_ptr<OpInfo> &op_info);

mindspore/ccsrc/backend/kernel_compiler/tbe/tbe_adapter.cc

@@ -173,7 +173,7 @@ void TbeAdapter::NormalizeFuncName(std::string *func_name) {
   *func_name = name_tmp;
   auto iter = tbe_func_adapter_map.find(*func_name);
   if (iter != tbe_func_adapter_map.end()) {
-    MS_LOG(INFO) << "map actual op from me " << *func_name << " to tbe op" << iter->second;
+    MS_LOG(INFO) << "Map actual op from me: " << *func_name << " to tbe op: " << iter->second;
     *func_name = iter->second;
   }
 }

mindspore/ccsrc/backend/kernel_compiler/tbe/tbe_adapter.h

@@ -27,7 +27,7 @@
 //       the TBE back-end operator implementation difference
 namespace mindspore {
 namespace kernel {
-enum kCreaterType : int { SINGLE_BUILD = 0, PREBUILD, OP_SELECT_FORMAT, CHECK_SUPPORTED, OP_PRE_COMPILE };
+enum kCreaterType : int { SINGLE_BUILD = 0, OP_SELECT_FORMAT, CHECK_SUPPORTED, OP_PRE_COMPILE };
 namespace tbe {
 using FAttrsPass = void (*)(const AnfNodePtr &anf_node, const std::vector<std::shared_ptr<OpAttr>> &op_info_attrs,
                             nlohmann::json *attrs_json);

mindspore/ccsrc/backend/kernel_compiler/tbe/tbe_convert_utils.cc

@@ -63,7 +63,7 @@ const std::unordered_map<std::string, size_t> type_nbyte_maps = {
 
 const std::unordered_map<std::string, FusionType> fusion_type_maps = {
   {"CONVLUTION", FusionType::CONVLUTION}, {"ELEMWISE", FusionType::ELEMWISE}, {"COMMREDUCE", FusionType::COMMREDUCE},
-  {"SEGMENT", FusionType::SEGMENT},       {"DYNAMIC", FusionType::DYNAMIC},   {"OPAQUE", FusionType::OPAQUE},
+  {"SEGMENT", FusionType::SEGMENT},       {"OPAQUE", FusionType::OPAQUE},
 };
 
 TypeId DtypeToTypeId(const std::string &dtypes) {

mindspore/ccsrc/backend/kernel_compiler/tbe/tbe_kernel_build.h

@@ -41,8 +41,8 @@ class TbeKernelBuild {
                         std::vector<size_t> *output_size_list);
   // Ub Fuison
   static bool GenFusionScopeJson(const std::vector<AnfNodePtr> &input_nodes,
-                                 const std::vector<AnfNodePtr> &compute_nodes, nlohmann::json *fusion_str,
-                                 std::string *fusion_kernel);
+                                 const std::vector<AnfNodePtr> &compute_nodes, nlohmann::json *fusion_json,
+                                 std::string *fusion_kernel_name);
   static bool GetIOSize(const nlohmann::json &fusion_op_list, const std::vector<AnfNodePtr> &output_nodes,
                         std::vector<size_t> *input_size_list, std::vector<size_t> *output_size_list);
 
@@ -61,9 +61,14 @@ class TbeKernelBuild {
   static std::vector<size_t> GetDescOutputIndex(const std::vector<int> &output_used_nums);
   static bool GenFusionComputeOutputJson(const mindspore::CNodePtr &cnode,
                                          std::vector<nlohmann::json> *output_desc_list);
+  static void GenPreDescJson(nlohmann::json *output_desc);
+  static void GenFusionComputeCommonJson(const mindspore::CNodePtr &cnode, nlohmann::json *compute_op_str,
+                                         std::string *fusion_kernel_name);
+  static void GenFusionComputePreBuildJson(const mindspore::CNodePtr &cnode, nlohmann::json *compute_op_str);
   static void GenDescJson(const std::shared_ptr<mindspore::AnfNode> &anf_node, size_t node_out_idx,
                           size_t desc_output_idx, nlohmann::json *output_desc,
                           FusionDataType fusion_data_type = kFusionNormal);
+  static void GenSuffixDescJson(nlohmann::json *output_desc);
   static void GenReusedOutputDesc(const std::shared_ptr<mindspore::AnfNode> &anf_node, size_t index,
                                   size_t output_index, nlohmann::json *output_desc);
   static size_t GetIOSizeImpl(const nlohmann::json &desc);
@@ -76,6 +81,7 @@ class TbeKernelBuild {
   static bool IsDynamicInput(const CNodePtr &cnode);
   static size_t GetOptionalInput(const CNodePtr &cnode, bool is_dynamic_input);
   static std::string GetRealOpType(const std::string &origin_type);
+  static std::string GetNodeFusionType(const CNodePtr &cnode);
 };
 
 class TbeKernelJsonCreator {
@@ -84,14 +90,14 @@ class TbeKernelJsonCreator {
   ~TbeKernelJsonCreator() = default;
   bool GenTbeSingleKernelJson(const std::shared_ptr<AnfNode> &anf_node, nlohmann::json *kernel_json);
   std::string json_name() { return json_name_; }
+  bool GenTbeAttrJson(const std::shared_ptr<AnfNode> &anf_node, const std::shared_ptr<OpInfo> &op_info,
+                      nlohmann::json *attrs_json);
 
  private:
   bool GenTbeInputsJson(const std::shared_ptr<AnfNode> &anf_node, const std::shared_ptr<OpInfo> &op_info,
                         nlohmann::json *inputs_json);
   bool GenTbeOutputsJson(const std::shared_ptr<AnfNode> &anf_node, const std::shared_ptr<OpInfo> &op_info,
                          nlohmann::json *outputs_json);
-  bool GenTbeAttrJson(const std::shared_ptr<AnfNode> &anf_node, const std::shared_ptr<OpInfo> &op_info,
-                      nlohmann::json *attrs_json);
   static void ParseAttrValue(const std::string &type, const ValuePtr &value, nlohmann::json *attr_obj);
   bool GenInputDescJson(const std::shared_ptr<AnfNode> &anf_node, size_t real_input_index, bool value,
                         const std::shared_ptr<OpIOInfo> &input_ptr, const string &op_input_name, size_t input_i,

mindspore/ccsrc/backend/kernel_compiler/tbe/tbe_kernel_parallel_build.cc

@@ -33,42 +33,6 @@
 namespace mindspore {
 namespace kernel {
 using mindspore::kernel::tbe::TbeUtils;
-
-bool TbeOpParallelPreBuild(const std::vector<AnfNodePtr> &anf_nodes) {
-  auto build_manger = std::make_shared<ParallelBuildManager>();
-  MS_EXCEPTION_IF_NULL(build_manger);
-  for (const auto &anf_node : anf_nodes) {
-    // gen kernel json
-    MS_EXCEPTION_IF_NULL(anf_node);
-    nlohmann::json kernel_json;
-    TbeKernelJsonCreator creator(OP_PRE_COMPILE);
-    if (!creator.GenTbeSingleKernelJson(anf_node, &kernel_json)) {
-      MS_LOG(ERROR) << "GenTbeSingleKernelJson failed";
-      return false;
-    }
-    kernel_json["compile_type"] = "pre_build";
-    // op build
-    auto task_id = build_manger->StartCompileOp(kernel_json);
-    build_manger->SavePreTaskInfo(task_id, anf_node);
-  }
-  while (!build_manger->IsAllPreTaskFinish()) {
-    int task_id = -1;
-    std::string task_result;
-    std::string pre_build_result;
-    auto ret = build_manger->WaitOne(&task_id, &task_result, &pre_build_result);
-    if (!ret) {
-      MS_EXCEPTION(ArgumentError) << "Pre Build Failed. wait one ret:" << ret << ", task id:" << task_id;
-    }
-
-    if (task_result != "Success") {
-      MS_EXCEPTION(ArgumentError) << "task pre compile Failed, task id:" << task_id << ", cause:" << task_result;
-    }
-
-    build_manger->PreTaskFinishProcess(task_id, pre_build_result);
-  }
-  return true;
-}
-
 bool TbeOpParallelBuild(const std::vector<AnfNodePtr> &anf_nodes) {
   auto build_manger = std::make_shared<ParallelBuildManager>();
   MS_EXCEPTION_IF_NULL(build_manger);
@@ -123,15 +87,8 @@ bool TbeOpParallelBuild(const std::vector<AnfNodePtr> &anf_nodes) {
   return build_manger->GenSameOpKernelMod();
 }
 
-ParallelBuildManager::ParallelBuildManager() {}
-
 ParallelBuildManager::~ParallelBuildManager() { ResetTaskInfo(); }
 
-void ParallelBuildManager::SavePreTaskInfo(int32_t task_id, const mindspore::AnfNodePtr &anf_node) {
-  MS_LOG(INFO) << "SavePreTaskInfo, task id: " << task_id;
-  pre_task_map_[task_id] = anf_node;
-}
-
 void ParallelBuildManager::SaveTaskInfo(int32_t task_id, const mindspore::AnfNodePtr &anf_node,
                                         const std::string &json_name, const std::vector<size_t> &input_size_list,
                                         const std::vector<size_t> &output_size_list, int32_t scope_id) {
@@ -150,42 +107,11 @@ void ParallelBuildManager::SaveTaskInfo(int32_t task_id, const mindspore::AnfNod
   task_map_[task_id] = task_info;
 }
 
-bool ParallelBuildManager::IsAllPreTaskFinish() const {
-  MS_LOG(INFO) << "wait pre build process task_num: " << pre_task_map_.size();
-  return pre_task_map_.empty();
-}
-
 bool ParallelBuildManager::IsAllTaskFinish() const {
   MS_LOG(INFO) << "wait process task_num: " << task_map_.size();
   return task_map_.empty();
 }
 
-void ParallelBuildManager::PreTaskFinishProcess(int32_t task_id, const std::string &pre_build_result) {
-  auto task_iter = pre_task_map_.find(task_id);
-  if (task_iter == pre_task_map_.end()) {
-    MS_EXCEPTION(ArgumentError) << "can find pre task_id:" << task_id;
-  }
-  auto node = task_iter->second;
-  auto builder =
-    std::make_shared<kernel::KernelBuildInfo::KernelBuildInfoBuilder>(AnfAlgo::GetSelectKernelBuildInfo(node));
-  std::string start_flag = "fusion_pattern_start";
-  std::string end_flag = "fusion_pattern_end";
-  int start = pre_build_result.find(start_flag);
-  int end = pre_build_result.find(end_flag);
-  if (start != -1 && end != -1 && end >= start) {
-    std::string result = pre_build_result.substr(start + start_flag.size(), end - start - start_flag.size());
-    if (result == "") {
-      (void)pre_task_map_.erase(task_iter);
-      return;
-    }
-    transform(result.begin(), result.end(), result.begin(), ::toupper);
-    FusionType fusion_type = tbe::GetFusionType(result);
-    builder->SetFusionType(fusion_type);
-    AnfAlgo::SetSelectKernelBuildInfo(builder->Build(), node.get());
-  }
-  (void)pre_task_map_.erase(task_iter);
-}
-
 std::pair<int32_t, KernelModPtr> ParallelBuildManager::TaskFinishProcess(int32_t task_id, bool set_kernel_mod) {
   auto task_iter = task_map_.find(task_id);
   if (task_iter == task_map_.end()) {

mindspore/ccsrc/backend/kernel_compiler/tbe/tbe_kernel_parallel_build.h

@@ -28,7 +28,6 @@
 
 namespace mindspore {
 namespace kernel {
-bool TbeOpParallelPreBuild(const std::vector<AnfNodePtr> &anf_nodes);
 bool TbeOpParallelBuild(const std::vector<AnfNodePtr> &anf_nodes);
 
 struct KernelBuildTaskInfo {
@@ -42,9 +41,8 @@ struct KernelBuildTaskInfo {
 
 class ParallelBuildManager {
  public:
-  ParallelBuildManager();
+  ParallelBuildManager() = default;
   ~ParallelBuildManager();
-  void SavePreTaskInfo(int32_t task_id, const AnfNodePtr &anf_node);
   void SaveTaskInfo(int32_t task_id, const AnfNodePtr &anf_node, const std::string &json_name,
                     const std::vector<size_t> &input_size_list, const std::vector<size_t> &output_size_list,
                     int32_t scope_id = 0);
@@ -54,10 +52,7 @@ class ParallelBuildManager {
   bool SearchInCache(const std::string &json_name, const std::string &processor,
                      const std::vector<size_t> &input_size_list, const std::vector<size_t> &output_size_list,
                      AnfNode *node) const;
-
-  bool IsAllPreTaskFinish() const;
   bool IsAllTaskFinish() const;
-  void PreTaskFinishProcess(int32_t task_id, const std::string &pre_build_result);
   std::pair<int32_t, KernelModPtr> TaskFinishProcess(int32_t task_id, bool set_kernel_mod = true);
   KernelModPtr GenKernelMod(const string &json_name, const string &processor,
                             const std::vector<size_t> &input_size_list, const std::vector<size_t> &output_size_list,

mindspore/ccsrc/backend/session/ascend_session.cc

@@ -474,7 +474,6 @@ void AscendSession::InitRuntimeResource() {
 }
 
 void AscendSession::HardwareOptimize(const std::shared_ptr<KernelGraph> &kernel_graph) const {
-  device::ascend::KernelPreBuild(kernel_graph.get());
   MS_LOG(INFO) << "HardwareOptimize start!";
   opt::AscendBackendOptimization(kernel_graph);
   opt::AscendGraphKernelCommonProcess(kernel_graph);

mindspore/ccsrc/runtime/device/ascend/kernel_build_ascend.cc

@@ -19,7 +19,8 @@
 #include <vector>
 #include <string>
 #include <memory>
-
+#include <set>
+#include <map>
 #include "runtime/device/ascend/kernel_select_ascend.h"
 #include "runtime/device/kernel_info.h"
 #include "backend/kernel_compiler/kernel.h"
@@ -61,32 +62,6 @@ static kernel::KernelModPtr SerialCompileImpl(const AnfNodePtr &anf_node) {
   return kernel_mod_ptr;
 }
 
-static bool KernelPreBuildParallelCompile(const mindspore::session::KernelGraph *kernel_graph_ptr) {
-  MS_EXCEPTION_IF_NULL(kernel_graph_ptr);
-  std::vector<AnfNodePtr> tbe_nodes;
-  for (const auto &anf_node : kernel_graph_ptr->execution_order()) {
-    MS_EXCEPTION_IF_NULL(anf_node);
-    if (!AnfAlgo::IsRealKernel(anf_node)) {
-      continue;
-    }
-    KernelType kernel_type = AnfAlgo::GetKernelType(anf_node);
-    switch (kernel_type) {
-      case KernelType::TBE_KERNEL: {
-        if (AnfAlgo::GetKernelMod(anf_node) == nullptr &&
-            AnfAlgo::GetFusionType(anf_node) == kernel::FusionType::DYNAMIC) {
-          tbe_nodes.push_back(anf_node);
-        }
-        break;
-      }
-      default: {
-        break;
-      }
-    }
-  }
-  bool ret = kernel::TbeOpParallelPreBuild(tbe_nodes);
-  return ret;
-}
-
 static bool KernelBuildParallelCompile(const mindspore::session::KernelGraph *kernel_graph_ptr) {
   MS_EXCEPTION_IF_NULL(kernel_graph_ptr);
   std::vector<AnfNodePtr> tbe_nodes;
@@ -230,12 +205,6 @@ static bool IsAtomicNode(const CNodePtr &kernel_node) {
   return !(workspace_indexs.empty() && output_indexs.empty());
 }
 
-bool KernelPreBuild(const mindspore::session::KernelGraph *kernel_graph_ptr) {
-  MS_EXCEPTION_IF_NULL(kernel_graph_ptr);
-  bool ret = device::ascend::KernelPreBuildParallelCompile(kernel_graph_ptr);
-  return ret;
-}
-
 bool KernelBuild(const mindspore::session::KernelGraph *kernel_graph_ptr) {
   MS_EXCEPTION_IF_NULL(kernel_graph_ptr);
   TbeUtils::LoadCache();

mindspore/ccsrc/runtime/device/ascend/kernel_build_ascend.h

@@ -22,10 +22,6 @@
 namespace mindspore {
 namespace device {
 namespace ascend {
-/**
- * @brief kernel pre build for ascend.
- */
-bool KernelPreBuild(const mindspore::session::KernelGraph *kernel_graph_ptr);
 /**
  * @brief kernel build for ascend.
  */

mindspore/ccsrc/utils/utils.h

@@ -32,6 +32,7 @@ namespace mindspore {
 // op name. Op which not exists in operator/ops.h, so define it's name here
 constexpr auto kFour2FiveOpName = "Four2Five";
 constexpr auto kFive2FourOpName = "Five2Four";
+constexpr auto kConv2DOpName = "Conv2D";
 constexpr auto kConvBN1OpName = "ConvBN1";
 constexpr auto kBN2AddReluOpName = "BN2AddRelu";
 constexpr auto kBN2ReLUOpName = "BN2Relu";

mindspore/ops/_op_impl/tbe/matmul.py

@@ -17,7 +17,7 @@
 from mindspore.ops.op_info_register import op_info_register, TBERegOp, DataType
 
 matmul_op_info = TBERegOp("MatMul") \
-    .fusion_type("ELEMWISE") \
+    .fusion_type("OPAQUE") \
     .async_flag(False) \
     .binfile_name("matmul.so") \
     .compute_cost(10) \

tests/st/networks/models/resnet50/test_resnet50_imagenet.py

@@ -367,8 +367,7 @@ def test_resnet_and_resnet_thor_imagenet_4p():
         os.system("rm -rf " + str(i))
     print("End training...")
     assert acc > 0.15
-    # the original perf is: 20 in C75B100
-    assert cost < 22
+    assert cost < 20
 
     # THOR
     thor_acc = 0.0
@@ -384,5 +383,4 @@ def test_resnet_and_resnet_thor_imagenet_4p():
         os.system("rm -rf " + str(i))
     print("End training...")
     assert thor_acc > 0.22
-    # the original perf is: 21 in C75B100
-    assert thor_cost < 23
+    assert thor_cost < 21