!1443 synchronize latest ascend softare suite 02 Apr 2021

From: @nicholas_yhr
Reviewed-by: @lilongfei15,@ljl0711
Signed-off-by: @lilongfei15

ge/analyzer/analyzer.cc

@@ -221,7 +221,10 @@ ge::Status Analyzer::SaveAnalyzerDataToFile(uint64_t session_id, uint64_t graph_
   try {
     json_file_ << jsn.dump(kJsonDumpLevel) << std::endl;
   } catch (nlohmann::detail::type_error &e) {
-    GELOGE(FAILED, "[Json.dump][GraphInfo]json.dump to analyze file [%s] failed because [%s], session_id:%lu, graph_id:%lu", json_file_name_.c_str(), e.what(), session_id, graph_id);
+    GELOGE(FAILED,
+           "[Json.dump][GraphInfo]json.dump to analyze file [%s] failed because [%s],"
+	         "session_id:%lu, graph_id:%lu",
+           json_file_name_.c_str(), e.what(), session_id, graph_id);
     ret_failed = true;
   }
   json_file_.close();
@@ -241,7 +244,9 @@ ge::Status Analyzer::DoAnalyze(DataInfo &data_info) {
   GE_CHECK_NOTNULL(graph_info);
   auto status = SaveOpInfo(desc, data_info, graph_info);
   if (status != SUCCESS) {
-    GELOGE(status, "[Check][SaveOpInfo]save op info: desc_name [%s] desc_type [%s] failed!", desc->GetName().c_str(), desc->GetType().c_str());
+    GELOGE(status,
+           "[Check][SaveOpInfo]save op info: desc_name [%s] desc_type [%s] failed!",
+           desc->GetName().c_str(), desc->GetType().c_str());
     return FAILED;
   }
   // create json file

ge/common/formats/format_transfers/datatype_transfer.cc

@@ -154,7 +154,8 @@ Status DataTypeTransfer::TransDataType(const CastArgs &args, TransResult &result
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to alloc the memory for dst buf %zu, data size %zu", total_size, args.src_data_size);
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to alloc the memory for dst buf %zu, data size %zu", total_size, args.src_data_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
   }
 

ge/common/formats/format_transfers/format_transfer_c1hwncoc0_hwcn.cc

@@ -73,7 +73,8 @@ Status CheckArgsForC1hwncoc0ToHwcn(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, int size, int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return ACL_ERROR_GE_MEMORY_ALLOCATION;

ge/common/formats/format_transfers/format_transfer_dhwcn_fracz3D.cc

@@ -94,7 +94,8 @@ Status TransFormatDhwckToFz3D(const TransArgs &args, TransResult &result) {
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -122,7 +123,8 @@ Status TransFormatDhwckToFz3D(const TransArgs &args, TransResult &result) {
                                args.data + src_idx * data_size, static_cast<size_t>(data_size));
               }
               if (ret != EOK) {
-                GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
+                GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                       "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
                        dst_offset, ret, pad_zero);
                 return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
               }

ge/common/formats/format_transfers/format_transfer_dhwnc_fracz3D_transpose.cc

@@ -95,7 +95,8 @@ Status TransFormatDhwncToFz3DTranspose(const TransArgs &args, TransResult &resul
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -123,7 +124,8 @@ Status TransFormatDhwncToFz3DTranspose(const TransArgs &args, TransResult &resul
                                args.data + src_idx * data_size, static_cast<size_t>(data_size));
               }
               if (ret != EOK) {
-                GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
+                GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                       "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
                        dst_offset, ret, pad_zero);
                 return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
               }

ge/common/formats/format_transfers/format_transfer_fractal_nz.cc

@@ -139,7 +139,8 @@ Status TransFormatFromNdToFracNz(const TransArgs &args, TransResult &result, con
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size](), std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -175,7 +176,8 @@ Status TransFormatFromNdToFracNz(const TransArgs &args, TransResult &result, con
         auto ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                             static_cast<size_t>(size * w0));
         if (ret != EOK) {
-          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                 "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
           return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
         }
       }
@@ -189,7 +191,8 @@ Status TransFormatFromNdToFracNz(const TransArgs &args, TransResult &result, con
         auto ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                             static_cast<size_t>(size));
         if (ret != EOK) {
-          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                 "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
           return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
         }
       }
@@ -210,7 +213,8 @@ Status TransFormatFromFracNzToNd(const TransArgs &args, TransResult &result, con
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -246,7 +250,8 @@ Status TransFormatFromFracNzToNd(const TransArgs &args, TransResult &result, con
         ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                        static_cast<size_t>(size * w0));
         if (ret != EOK) {
-          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                 "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
           return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
         }
       }
@@ -260,7 +265,8 @@ Status TransFormatFromFracNzToNd(const TransArgs &args, TransResult &result, con
         ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                        static_cast<size_t>(size));
         if (ret != EOK) {
-          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+          GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                 "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
           return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
         }
       }
@@ -274,14 +280,16 @@ Status TransFormatFromFracNzToNd(const TransArgs &args, TransResult &result, con
 
 Status FormatTransferFractalNz::TransFormat(const TransArgs &args, TransResult &result) {
   if (!IsDataTypeSupport(args.src_data_type)) {
-    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID, "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
+    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID,
+           "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());
     return ACL_ERROR_GE_DATATYPE_INVALID;
   }
   if (!CheckShape(args.src_format, args.src_shape) || !IsShapeValid(args.dst_shape)) {
-    GELOGE(ACL_ERROR_GE_SHAPE_INVALID, "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
+    GELOGE(ACL_ERROR_GE_SHAPE_INVALID,
+           "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());
@@ -325,7 +333,8 @@ Status FormatTransferFractalNz::TransShape(Format src_format, const ShapeVector
 
 Status FormatTransferFractalNzND::TransFormat(const TransArgs &args, TransResult &result) {
   if (!IsDataTypeSupport(args.src_data_type)) {
-    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID, "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
+    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID,
+           "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());
@@ -333,7 +342,8 @@ Status FormatTransferFractalNzND::TransFormat(const TransArgs &args, TransResult
   }
 
   if (!IsShapeValid(args.src_shape) || !CheckShape(args.dst_format, args.dst_shape)) {
-    GELOGE(ACL_ERROR_GE_SHAPE_INVALID, "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
+    GELOGE(ACL_ERROR_GE_SHAPE_INVALID,
+           "Trans format from %s to %s, src shape %s, dst shape %s, data type %s is not supported",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());

ge/common/formats/format_transfers/format_transfer_fractal_z.cc

@@ -127,7 +127,8 @@ Status TransFormatFromNchwToFz(const TransArgs &args, TransResult &result) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
       dst == nullptr,
-      GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+      GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+             "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
              TypeUtils::FormatToSerialString(args.src_format).c_str(),
              TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
       return ACL_ERROR_GE_MEMORY_ALLOCATION;);
@@ -173,8 +174,9 @@ Status TransFormatFromNchwToFz(const TransArgs &args, TransResult &result) {
             }
           }
           if (ret != EOK) {
-            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d pad mode %d", offset,
-                   ret, need_pad_zero);
+            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                   "Failed to operate the dst memory at offset %ld, error-code %d pad mode %d",
+                   offset, ret, need_pad_zero);
             return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
           }
         }
@@ -213,7 +215,8 @@ Status TransFormatHwcnToFz(const TransArgs &args, TransResult &result) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
       dst == nullptr,
-      GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+      GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+             "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
              TypeUtils::FormatToSerialString(args.src_format).c_str(),
              TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
       return ACL_ERROR_GE_MEMORY_ALLOCATION;);
@@ -235,7 +238,8 @@ Status TransFormatHwcnToFz(const TransArgs &args, TransResult &result) {
                              static_cast<size_t>(data_size));
             } else {
               if (protected_size < data_size) {
-                GELOGE(ACL_ERROR_GE_PARAM_INVALID, "Failed to operate the dst memory, protected_size is %ld and size is %ld",
+                GELOGE(ACL_ERROR_GE_PARAM_INVALID,
+                       "Failed to operate the dst memory, protected_size is %ld and size is %ld",
                        protected_size, data_size);
                 return ACL_ERROR_GE_PARAM_INVALID;
               }
@@ -247,7 +251,8 @@ Status TransFormatHwcnToFz(const TransArgs &args, TransResult &result) {
               }
             }
             if (ret != EOK) {
-              GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
+              GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                     "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
                      dst_offset, ret, pad_zero);
               return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
             }
@@ -288,7 +293,8 @@ Status TransFormatNhwcToFz(const TransArgs &args, TransResult &result) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
       dst == nullptr,
-      GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+      GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+             "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
              TypeUtils::FormatToSerialString(args.src_format).c_str(),
              TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
       return ACL_ERROR_GE_MEMORY_ALLOCATION;);
@@ -310,7 +316,8 @@ Status TransFormatNhwcToFz(const TransArgs &args, TransResult &result) {
                              static_cast<size_t>(data_size));
             } else {
               if (protected_size < data_size) {
-                GELOGE(ACL_ERROR_GE_PARAM_INVALID, "Failed to operate the dst memory, protected_size is %ld and size is %ld",
+                GELOGE(ACL_ERROR_GE_PARAM_INVALID,
+                       "Failed to operate the dst memory, protected_size is %ld and size is %ld",
                        protected_size, data_size);
                 return ACL_ERROR_GE_PARAM_INVALID;
               }
@@ -322,7 +329,8 @@ Status TransFormatNhwcToFz(const TransArgs &args, TransResult &result) {
               }
             }
             if (ret != EOK) {
-              GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
+              GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                     "Failed to operate the dst memory at offset %ld, error-code %d, pad mode %d",
                      dst_offset, ret, pad_zero);
               return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
             }

ge/common/formats/format_transfers/format_transfer_fractal_zz.cc

@@ -140,7 +140,8 @@ Status TransFormatFromNdToFracZz(const TransArgs &args, TransResult &result, con
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size](), std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -179,7 +180,8 @@ Status TransFormatFromNdToFracZz(const TransArgs &args, TransResult &result, con
           auto ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                               static_cast<size_t>(size * w0));
           if (ret != EOK) {
-            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                   "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
             return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
           }
         }
@@ -195,7 +197,8 @@ Status TransFormatFromNdToFracZz(const TransArgs &args, TransResult &result, con
           auto ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                               static_cast<size_t>(size));
           if (ret != EOK) {
-            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                   "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
             return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
           }
         }
@@ -217,7 +220,8 @@ Status TransFormatFromFracZzToNd(const TransArgs &args, TransResult &result, con
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size](), std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -257,7 +261,8 @@ Status TransFormatFromFracZzToNd(const TransArgs &args, TransResult &result, con
           auto ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                               static_cast<size_t>(size * w0));
           if (ret != EOK) {
-            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                   "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
             return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
           }
         }
@@ -273,7 +278,8 @@ Status TransFormatFromFracZzToNd(const TransArgs &args, TransResult &result, con
           auto ret = memcpy_s(dst.get() + dst_offset, static_cast<size_t>(protected_size), args.data + src_offset,
                               static_cast<size_t>(size));
           if (ret != EOK) {
-            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED, "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
+            GELOGE(ACL_ERROR_GE_MEMORY_OPERATE_FAILED,
+                   "Failed to operate the dst memory at offset %ld, error-code %d", dst_offset, ret);
             return ACL_ERROR_GE_MEMORY_OPERATE_FAILED;
           }
         }
@@ -288,14 +294,16 @@ Status TransFormatFromFracZzToNd(const TransArgs &args, TransResult &result, con
 
 Status FormatTransferFractalZz::TransFormat(const TransArgs &args, TransResult &result) {
   if (!IsDataTypeSupport(args.src_data_type)) {
-    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID, "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
+    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID,
+           "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());
     return ACL_ERROR_GE_DATATYPE_INVALID;
   }
   if (!CheckShape(args.src_format, args.src_shape) || !IsShapeValid(args.dst_shape)) {
-    GELOGE(ACL_ERROR_GE_SHAPE_INVALID, "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
+    GELOGE(ACL_ERROR_GE_SHAPE_INVALID,
+           "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());
@@ -339,7 +347,8 @@ Status FormatTransferFractalZz::TransShape(Format src_format, const ShapeVector
 
 Status FormatTransferFractalZzND::TransFormat(const TransArgs &args, TransResult &result) {
   if (!IsDataTypeSupport(args.src_data_type)) {
-    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID, "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
+    GELOGE(ACL_ERROR_GE_DATATYPE_INVALID,
+           "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());
@@ -347,7 +356,8 @@ Status FormatTransferFractalZzND::TransFormat(const TransArgs &args, TransResult
   }
 
   if (!IsShapeValid(args.src_shape) || !CheckShape(args.dst_format, args.dst_shape)) {
-    GELOGE(ACL_ERROR_GE_SHAPE_INVALID, "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
+    GELOGE(ACL_ERROR_GE_SHAPE_INVALID,
+           "Not support trans format from %s to %s, src shape %s, dst shape %s, data type %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), ShapeToString(args.src_shape).c_str(),
            ShapeToString(args.dst_shape).c_str(), TypeUtils::DataTypeToSerialString(args.src_data_type).c_str());

ge/common/formats/format_transfers/format_transfer_fracz_hwcn.cc

@@ -66,7 +66,7 @@ Status CheckArgsForFracZToHwcn(const TransArgs &args) {
         FmtToStr(ShapeToString(dst_shape));
     GE_ERRORLOG_AND_ERRORMSG(ACL_ERROR_GE_SHAPE_INVALID, error.c_str());
     return ACL_ERROR_GE_SHAPE_INVALID;
-  } 
+  }
 
   return SUCCESS;
 }
@@ -74,7 +74,8 @@ Status CheckArgsForFracZToHwcn(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, const int size, const int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return ACL_ERROR_GE_MEMORY_ALLOCATION;

ge/common/formats/format_transfers/format_transfer_fracz_nchw.cc

@@ -59,9 +59,10 @@ Status CheckArgsForFracZToNchw(const TransArgs &args) {
   }
   int64_t c1 = Ceil(dst_shape.at(kNchwC), c0);
   int64_t n0 = Ceil(dst_shape.at(kNchwN), static_cast<int64_t>(kNiSize));
-  if (src_shape.at(kFracZHWC1) != dst_shape.at(kNchwH) * dst_shape.at(kNchwW) * c1 || src_shape.at(kFracZC0) != c0 ||
-      src_shape.at(kFracZNi) != kNiSize || src_shape.at(kFracZN0) != n0) {
-    GELOGE(ACL_ERROR_GE_SHAPE_INVALID, "Failed to check relationship between src and dst shape, src shape %s, dst shape %s",
+  if (src_shape.at(kFracZHWC1) != dst_shape.at(kNchwH) * dst_shape.at(kNchwW) * c1 ||
+      src_shape.at(kFracZC0) != c0 || src_shape.at(kFracZNi) != kNiSize || src_shape.at(kFracZN0) != n0) {
+    GELOGE(ACL_ERROR_GE_SHAPE_INVALID,
+           "Failed to check relationship between src and dst shape, src shape %s, dst shape %s",
            ShapeToString(src_shape).c_str(), ShapeToString(dst_shape).c_str());
     return ACL_ERROR_GE_SHAPE_INVALID;
   }
@@ -72,7 +73,8 @@ Status CheckArgsForFracZToNchw(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, const int size, const int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return ACL_ERROR_GE_MEMORY_ALLOCATION;

ge/common/formats/format_transfers/format_transfer_fracz_nhwc.cc

@@ -59,9 +59,10 @@ Status CheckArgsForFracZToNhwc(const TransArgs &args) {
   }
   int64_t c1 = Ceil(dst_shape.at(kNhwcC), c0);
   int64_t n0 = Ceil(dst_shape.at(kNhwcN), static_cast<int64_t>(kNiSize));
-  if (src_shape.at(kFracZHWC1) != dst_shape.at(kNhwcH) * dst_shape.at(kNhwcW) * c1 || src_shape.at(kFracZC0) != c0 ||
-      src_shape.at(kFracZNi) != kNiSize || src_shape.at(kFracZN0) != n0) {
-    GELOGE(PARAM_INVALID, "Failed to check relationship between src and dst shape, src shape %s, dst shape %s",
+  if (src_shape.at(kFracZHWC1) != dst_shape.at(kNhwcH) * dst_shape.at(kNhwcW) * c1 ||
+      src_shape.at(kFracZC0) != c0 || src_shape.at(kFracZNi) != kNiSize || src_shape.at(kFracZN0) != n0) {
+    GELOGE(PARAM_INVALID,
+           "Failed to check relationship between src and dst shape, src shape %s, dst shape %s",
            ShapeToString(src_shape).c_str(), ShapeToString(dst_shape).c_str());
     return PARAM_INVALID;
   }
@@ -72,7 +73,8 @@ Status CheckArgsForFracZToNhwc(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, int size, int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(OUT_OF_MEMORY, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(OUT_OF_MEMORY,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return OUT_OF_MEMORY;
@@ -140,7 +142,7 @@ Status FormatTransferFracZNhwc::TransFormat(const TransArgs &args, TransResult &
     }
 
     GELOGE(INTERNAL_ERROR, "Get %ld total size from dst shape %s, src shape %s", total_size,
-        ShapeToString(args.dst_shape).c_str(), ShapeToString(args.src_shape).c_str());
+           ShapeToString(args.dst_shape).c_str(), ShapeToString(args.src_shape).c_str());
     return PARAM_INVALID;
   }
   GELOGD("Begin to trans format from FracZ to NHWC, src shape %s, data type %s, dst shape %s, memory size %ld",

ge/common/formats/format_transfers/format_transfer_hwcn_c1hwncoc0.cc

@@ -91,7 +91,8 @@ Status CheckArgsForHwcnToC1hwncoc0(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, const int size, const int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return ACL_ERROR_GE_MEMORY_ALLOCATION;

ge/common/formats/format_transfers/format_transfer_nc1hwc0_nchw.cc

@@ -72,7 +72,8 @@ Status CheckArgsForNc1hwc0ToNchw(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, const int size, const int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(OUT_OF_MEMORY, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(OUT_OF_MEMORY,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return OUT_OF_MEMORY;

ge/common/formats/format_transfers/format_transfer_nc1hwc0_nhwc.cc

@@ -61,7 +61,8 @@ Status CheckArgsForNc1hwc0ToNhwc(const TransArgs &args) {
   if (src_shape.at(kNc1hwc0H) != dst_shape.at(kNhwcH) || src_shape.at(kNc1hwc0W) != dst_shape.at(kNhwcW) ||
       src_shape.at(kNc1hwc0N) != dst_shape.at(kNhwcN) || src_shape.at(kNc1hwc0C0) != c0 ||
       src_shape.at(kNc1hwc0C1) != (Ceil(dst_shape.at(kNhwcC), c0))) {
-    GELOGE(ACL_ERROR_GE_SHAPE_INVALID, "Failed to check relationship between src and dst shape, src shape %s, dst shape %s",
+    GELOGE(ACL_ERROR_GE_SHAPE_INVALID,
+           "Failed to check relationship between src and dst shape, src shape %s, dst shape %s",
            ShapeToString(src_shape).c_str(), ShapeToString(dst_shape).c_str());
     return ACL_ERROR_GE_SHAPE_INVALID;
   }
@@ -72,7 +73,8 @@ Status CheckArgsForNc1hwc0ToNhwc(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, const int size, const int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return ACL_ERROR_GE_MEMORY_ALLOCATION;

ge/common/formats/format_transfers/format_transfer_nchw_fz_c04.cc

@@ -125,7 +125,8 @@ Status TransFormatFromNchwToFzC04(const TransArgs &args, TransResult &result) {
                   return ACL_ERROR_GE_INTERNAL_ERROR);
   auto t1 = h_o * w_o;
   auto t2 = n_o * c_o;
-  GE_IF_BOOL_EXEC(!CheckInt64MulOverflow(t1, t2), GELOGE(INTERNAL_ERROR, "int64 mul overflow.A[%ld], B[%ld]", t1, t2);
+  GE_IF_BOOL_EXEC(!CheckInt64MulOverflow(t1, t2),
+                  GELOGE(INTERNAL_ERROR, "int64 mul overflow.A[%ld], B[%ld]", t1, t2);
                   return ACL_ERROR_GE_INTERNAL_ERROR);
 
   int64_t total_ele_cnt = n_o * c_o * h_o * w_o;
@@ -140,7 +141,8 @@ Status TransFormatFromNchwToFzC04(const TransArgs &args, TransResult &result) {
 
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -212,7 +214,8 @@ Status PaddingNC(const TransArgs &args, TransArgs &args_tmp, std::shared_ptr<uin
                   return ACL_ERROR_GE_INTERNAL_ERROR);
   auto t1 = h_o * w_o;
   auto t2 = n_o * c_o;
-  GE_IF_BOOL_EXEC(!CheckInt64MulOverflow(t1, t2), GELOGE(ACL_ERROR_GE_INTERNAL_ERROR, "int64 mul overflow.A[%ld], B[%ld]", t1, t2);
+  GE_IF_BOOL_EXEC(!CheckInt64MulOverflow(t1, t2),
+                  GELOGE(ACL_ERROR_GE_INTERNAL_ERROR,"int64 mul overflow.A[%ld], B[%ld]", t1, t2);
                   return ACL_ERROR_GE_INTERNAL_ERROR);
 
   int64_t total_ele_cnt = n_o * c_o * h_o * w_o;
@@ -228,7 +231,8 @@ Status PaddingNC(const TransArgs &args, TransArgs &args_tmp, std::shared_ptr<uin
 
   dst.reset(new (std::nothrow) uint8_t[dst_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), dst_size);
     return ACL_ERROR_GE_MEMORY_ALLOCATION;
@@ -275,7 +279,8 @@ Status FormatTransferNchwToFZC04::TransFormat(const TransArgs &args, TransResult
   }
 
   std::vector<int64_t> expect_shape;
-  ret = TransShape(args_tmp.src_format, args_tmp.src_shape, args_tmp.src_data_type, args_tmp.dst_format, expect_shape);
+  ret = TransShape(args_tmp.src_format, args_tmp.src_shape, args_tmp.src_data_type,
+                   args_tmp.dst_format, expect_shape);
   if (ret != SUCCESS) {
     return ret;
   }

ge/common/formats/format_transfers/format_transfer_nhwc_nc1hwc0.cc

@@ -92,7 +92,8 @@ Status CheckArgsForNhwcToNc1hwc0(const TransArgs &args) {
 Status GetDstDataAfterTrans(const TransArgs &args, TransResult &result, const int size, const int64_t total_size) {
   std::shared_ptr<uint8_t> dst(new (std::nothrow) uint8_t[total_size], std::default_delete<uint8_t[]>());
   if (dst == nullptr) {
-    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION, "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
+    GELOGE(ACL_ERROR_GE_MEMORY_ALLOCATION,
+           "Failed to trans format from %s to %s, can not alloc the memory for dst buf %ld, shape %s",
            TypeUtils::FormatToSerialString(args.src_format).c_str(),
            TypeUtils::FormatToSerialString(args.dst_format).c_str(), total_size, ShapeToString(args.dst_shape).c_str());
     return ACL_ERROR_GE_MEMORY_ALLOCATION;

ge/generator/ge_generator.cc

@@ -592,8 +592,8 @@ Status GeGenerator::SetModelNameForDump(const GeRootModelPtr &ge_root_model) {
     ErrorManager::GetInstance().ATCReportErrMessage("E10000", {"parameter"}, {"output"});
     GELOGE(FAILED, "[Check][GetModelNameStep]Get model_name failed. Param --output is invalid, root graph name: %s",
            ge_root_model->GetRootGraph()->GetName().c_str());
-    REPORT_CALL_ERROR("E19999", "Get model_name failed. Param --output is invalid,",
-                      "root graph name: %s", ge_root_model->GetRootGraph()->GetName().c_str());
+    REPORT_CALL_ERROR("E19999", "Get model_name failed. Param --output is invalid, root graph name: %s",
+                      ge_root_model->GetRootGraph()->GetName().c_str());
     return PARAM_INVALID;
   }
   map<string, GeModelPtr> name_to_ge_model = ge_root_model->GetSubgraphInstanceNameToModel();

ge/graph/build/memory/block_mem_assigner.cc

@@ -597,11 +597,13 @@ void BlockMemAssigner::GetOutAndWorkSpaceMem(vector<int64_t> &all_memory_size) {
       int64_t size = 0;
       GE_IF_BOOL_EXEC(ge::TensorUtils::GetSize(output_desc, size) != SUCCESS, GELOGI("Get size failed"));
       GE_IF_BOOL_EXEC(size < 0,
-        GELOGE(FAILED, "[Check][TensorSize]tensor_size:%ld is invalid, maybe it is unknown shape node, Node_name:%s",
-          size, node_op_desc->GetName().c_str());
-        REPORT_INNER_ERROR("E19999", "tensor_size:%ld is invalid, maybe it is unknown shape node, Node_name:%s",
-          size, node_op_desc->GetName().c_str());
-        return;);
+                      GELOGE(FAILED, "[Check][TensorSize]tensor_size:%ld is invalid, "
+                             "maybe it is unknown shape node, Node_name:%s",
+                             size, node_op_desc->GetName().c_str());
+                      REPORT_INNER_ERROR("E19999", "tensor_size:%ld is invalid, "
+                                         "maybe it is unknown shape node, Node_name:%s",
+                                         size, node_op_desc->GetName().c_str());
+                      return;);
       batch_all_memory_size[batch_label].emplace_back(size);
       if (batch_total_size.find(batch_label) == batch_total_size.end()) {
         batch_total_size[batch_label] = size;
@@ -692,23 +694,23 @@ bool BlockMemAssigner::IsOutNodeSetContinuousInput(const NodePtr &n, uint32_t ou
     auto out_anchor = n->GetOutDataAnchor(out_index);
     GE_IF_BOOL_EXEC(out_anchor == nullptr,
                     GELOGE(FAILED, "[Check][Anchor]Node[%s] output[%u] anchor is null.",
-                      n->GetName().c_str(), out_index);
+                           n->GetName().c_str(), out_index);
                     REPORT_INNER_ERROR("E19999", "output anchor is null, node_name: %s output_index: %u.",
-                      n->GetName().c_str(), out_index);
+                                       n->GetName().c_str(), out_index);
                     return false;);
     for (auto const &peer_in_anchor : out_anchor->GetPeerInDataAnchors()) {
       GE_IF_BOOL_EXEC(peer_in_anchor == nullptr,
                       GELOGE(FAILED, "[Check][Anchor]Node[%s] output[%u] peer_in_anchor 0 is null.",
-                        n->GetName().c_str(), out_index);
+                             n->GetName().c_str(), out_index);
                       REPORT_INNER_ERROR("E19999", "output anchor peer is null, node_name: %s output_index: %u.",
-                        n->GetName().c_str(), out_index);
+                                         n->GetName().c_str(), out_index);
                       return false;);
       auto peer_node = peer_in_anchor->GetOwnerNode();
       GE_IF_BOOL_EXEC(peer_node == nullptr,
                       GELOGE(FAILED, "[Check][Node]Node[%s] output[%u] peer node is null.",
-                        n->GetName().c_str(), out_index);
+                             n->GetName().c_str(), out_index);
                       REPORT_INNER_ERROR("E19999", "output anchor peer node is null, node_name: %s output_index: %u.",
-                        n->GetName().c_str(), out_index);
+                                         n->GetName().c_str(), out_index);
                       return false;);
 
       // Get the continuous input type of the node, default is false
@@ -716,9 +718,9 @@ bool BlockMemAssigner::IsOutNodeSetContinuousInput(const NodePtr &n, uint32_t ou
       auto peer_in_node_desc = peer_node->GetOpDesc();
       GE_IF_BOOL_EXEC(peer_in_node_desc == nullptr,
                       GELOGE(FAILED, "[Check][OpDesc]Node[%s] output[%u] nodedesc is null.",
-                        n->GetName().c_str(), out_index);
+                             n->GetName().c_str(), out_index);
                       REPORT_INNER_ERROR("E19999", "output anchor peer op_desc is null, node_name:%s output_index:%u.",
-                        n->GetName().c_str(), out_index);
+                                         n->GetName().c_str(), out_index);
                       return false;);
 
       // If GetBool fail, is_input_continuous is false.
@@ -819,7 +821,7 @@ bool BlockMemAssigner::IsContinuousMemoryReuse(const NodePtr &n, const NodePtr &
         (in_anchor->GetPeerOutAnchor()->GetOwnerNode() == nullptr) ||
         (in_anchor->GetPeerOutAnchor()->GetOwnerNode()->GetOpDesc() == nullptr)) {
       GELOGE(FAILED, "[Check][OpDesc]Node[%s] output[%u] peer input node desc is null.",
-        n->GetName().c_str(), out_index);
+             n->GetName().c_str(), out_index);
       REPORT_INNER_ERROR("E19999", "get output anchor peer op_desc fail, node_name: %s output_index: %u.",
                          n->GetName().c_str(), out_index);
       return false;
@@ -1105,9 +1107,10 @@ MemoryBlock *BlockMemAssigner::ApplyMemory(size_t block_size, size_t real_size,
                                            OpMemoryType mem_type, const NodePtr &n, uint32_t out_index,
                                            const vector<bool> &workspace_reuse_flag, const bool is_op_reuse_mem,
                                            const bool continuous, int64_t memory_type) {
-  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(n == nullptr,
-    REPORT_INNER_ERROR("E19999", "Input parameter n(type:node_ptr) is null, apply memory failed");
-    return nullptr, "[Check][Param]Input parameter n(type:node_ptr) is null.");
+  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+      n == nullptr,
+      REPORT_INNER_ERROR("E19999", "Input parameter n(type:node_ptr) is null, apply memory failed");
+      return nullptr, "[Check][Param]Input parameter n(type:node_ptr) is null.");
   auto node_op_desc = n->GetOpDesc();
   GE_IF_BOOL_EXEC(node_op_desc == nullptr, return nullptr);
   std::string batch_label;
@@ -1159,10 +1162,12 @@ MemoryBlock *BlockMemAssigner::ApplyMemory(size_t block_size, size_t real_size,
   }
 
   auto block = new (std::nothrow) MemoryBlock(block_size, node_op_desc->GetStreamId(), is_reuse_memory, memory_type);
-  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(block == nullptr,
-    REPORT_INNER_ERROR("E19999", "new a memoryblock object failed. node_name:%s out_index:%u",
-      n->GetName().c_str(), out_index);
-    return nullptr, "[New][Object]new MemoryBlock failed, node_name:%s out_index:%u", n->GetName().c_str(), out_index);
+  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+      block == nullptr,
+      REPORT_INNER_ERROR("E19999", "new a memoryblock object failed. node_name:%s out_index:%u",
+                         n->GetName().c_str(), out_index);
+      return nullptr,
+      "[New][Object]new MemoryBlock failed, node_name:%s out_index:%u", n->GetName().c_str(), out_index);
 
   // Data and netoutput need zero copy block
   block->is_zero_copy_ = IsZeroCopyBlock(n, continuous);
@@ -1221,13 +1226,15 @@ void BlockMemAssigner::ContinuousOutRefCheck(bool &isAllOutputRef, bool &isOutpu
 
 Status BlockMemAssigner::ApplyContinuousMemory(const NodePtr &n, const vector<int64_t> &ranges,
                                                const bool is_op_reuse_mem) {
-  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(n == nullptr,
-    REPORT_INNER_ERROR("E19999", "Input parameter n(type:node_ptr) is null");
-    return INTERNAL_ERROR, "[check][param]Input parameter n(type:NodePtr) is null.");
+  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+      n == nullptr,
+      REPORT_INNER_ERROR("E19999", "Input parameter n(type:node_ptr) is null");
+      return INTERNAL_ERROR, "[check][param]Input parameter n(type:NodePtr) is null.");
   auto node_op_desc = n->GetOpDesc();
-  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(node_op_desc == nullptr,
-    REPORT_INNER_ERROR("E19999", "Input parameter n(type:OpDescPtr) is null");
-    return INTERNAL_ERROR, "[Check][Param]Input parameter n(type:OpDescPtr) is null");
+  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+      node_op_desc == nullptr,
+      REPORT_INNER_ERROR("E19999", "Input parameter n(type:OpDescPtr) is null");
+      return INTERNAL_ERROR, "[Check][Param]Input parameter n(type:OpDescPtr) is null");
 
   // continuous output support ref only when all output ref input
   bool isAllOutputRef = true;
@@ -1242,7 +1249,7 @@ Status BlockMemAssigner::ApplyContinuousMemory(const NodePtr &n, const vector<in
 
   if (!isAllOutputRef && isOutputHasRef) {
     REPORT_INNER_ERROR("E19999", "continuous output node ref part input, not support now. node_name:%s",
-      n->GetName().c_str());
+                       n->GetName().c_str());
     GELOGE(INTERNAL_ERROR, "[Check][OutRefStatus]continuous output node ref part input, not support, node_name:%s",
            n->GetName().c_str());
     return INTERNAL_ERROR;
@@ -1255,7 +1262,7 @@ Status BlockMemAssigner::ApplyContinuousMemory(const NodePtr &n, const vector<in
     auto output_op_desc = node_op_desc->GetOutputDescPtr(index);
     if (output_op_desc == nullptr) {
       REPORT_INNER_ERROR("E19999", "get output_desc failed, node_name:%s, output_index:%u",
-         n->GetName().c_str(), index);
+                         n->GetName().c_str(), index);
       GELOGE(INTERNAL_ERROR, "[Get][OutputDesc]node_name:%s, output_index:%u", n->GetName().c_str(), index);
       return INTERNAL_ERROR;
     }
@@ -1268,7 +1275,7 @@ Status BlockMemAssigner::ApplyContinuousMemory(const NodePtr &n, const vector<in
     int64_t size = 0;
     if (ge::TensorUtils::GetSize(*output_op_desc, size) != SUCCESS) {
       REPORT_CALL_ERROR("E19999", "get tensor_size failed, node_name:%s, output_index:%u",
-         n->GetName().c_str(), index);
+                        n->GetName().c_str(), index);
       GELOGE(INTERNAL_ERROR, "[Get][TensorSize]node_name:%s, output_index:%u", n->GetName().c_str(), index);
       return INTERNAL_ERROR;
     }
@@ -1310,7 +1317,7 @@ Status BlockMemAssigner::ApplyContinuousMemory(const NodePtr &n, const vector<in
     ++(block->ref_count_);
   } else {
     REPORT_CALL_ERROR("E19999", "apply continuousMemory failed, node_name:%s, total_size:%ld",
-         n->GetName().c_str(), total_size);
+                      n->GetName().c_str(), total_size);
     GELOGE(INTERNAL_ERROR, "[Apply][ContinuousMemory]node_name:%s, total_size:%ld", n->GetName().c_str(), total_size);
     return INTERNAL_ERROR;
   }
@@ -1319,26 +1326,33 @@ Status BlockMemAssigner::ApplyContinuousMemory(const NodePtr &n, const vector<in
 
 MemoryBlock *BlockMemAssigner::ApplyOutMemory(const NodePtr &n, uint32_t index, const vector<int64_t> &ranges,
                                               const bool is_op_reuse_mem, const bool continuous) {
-  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(n == nullptr,
-    REPORT_INNER_ERROR("E19999", "Input parameter n(type:NodePtr) is null");
-    return nullptr, "[Check][Param]Input parameter n(type:NodePtr) is null");
+  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+      n == nullptr,
+      REPORT_INNER_ERROR("E19999", "Input parameter n(type:NodePtr) is null");
+      return nullptr, "[Check][Param]Input parameter n(type:NodePtr) is null");
   auto node_op_desc = n->GetOpDesc();
-  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(node_op_desc == nullptr,
-    REPORT_INNER_ERROR("E19999", "Input parameter n(type:OpDescPtr) is null");
-    return nullptr, "[Check][Param]Input parameter n(type:OpDescPtr) is null");
+  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+      node_op_desc == nullptr,
+      REPORT_INNER_ERROR("E19999", "Input parameter n(type:OpDescPtr) is null");
+      return nullptr, "[Check][Param]Input parameter n(type:OpDescPtr) is null");
   MemoryBlock *block = nullptr;
   NodeIndexIO node_index_io(n, index, kOut);
   int64_t size = 0;
   auto output_op_desc = node_op_desc->GetOutputDescPtr(index);
-  GE_IF_BOOL_EXEC(output_op_desc == nullptr,
-    REPORT_INNER_ERROR("E19999", "get output_desc failed, node_name:%s, output_index:%u", n->GetName().c_str(), index);
-    GELOGE(FAILED, "[Get][OutputDesc]node_name:%s, output_index:%u", n->GetName().c_str(), index);
-    return nullptr);
+  GE_IF_BOOL_EXEC(
+      output_op_desc == nullptr,
+      REPORT_INNER_ERROR("E19999", "get output_desc failed, node_name:%s, output_index:%u",
+                         n->GetName().c_str(), index);
+      GELOGE(FAILED, "[Get][OutputDesc]node_name:%s, output_index:%u", n->GetName().c_str(), index);
+      return nullptr);
   GE_IF_BOOL_EXEC(ge::TensorUtils::GetSize(*output_op_desc, size) != SUCCESS, GELOGI("Get size failed"));
   size_t no_align_size = 0;
-  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(GetNoAlignSize(*node_op_desc, index, no_align_size) != SUCCESS,
-    REPORT_CALL_ERROR("E19999", "Get no align size failed, node_name:%s, output_index:%u", n->GetName().c_str(), index);
-    return nullptr, "[Get][TensorSize]Get no align size, node_name:%s, output_index:%u", n->GetName().c_str(), index);
+  GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+      GetNoAlignSize(*node_op_desc, index, no_align_size) != SUCCESS,
+      REPORT_CALL_ERROR("E19999", "Get no align size failed, node_name:%s, output_index:%u",
+                        n->GetName().c_str(), index);
+      return nullptr,
+      "[Get][TensorSize]Get no align size, node_name:%s, output_index:%u", n->GetName().c_str(), index);
 
   std::string symbol;
   bool reuse_input = false;
@@ -1346,9 +1360,9 @@ MemoryBlock *BlockMemAssigner::ApplyOutMemory(const NodePtr &n, uint32_t index,
     block = symbol_blocks_[symbol];
     GE_IF_BOOL_EXEC(block == nullptr,
       REPORT_INNER_ERROR("E19999", "get ref block failed, node_name:%s, symbol:%s",
-        node_op_desc->GetName().c_str(), node_index_io.ToString().c_str());
+                         node_op_desc->GetName().c_str(), node_index_io.ToString().c_str());
       GELOGE(FAILED, "[Get][RefBlock]node_name:%s, symbol:%s",
-        node_op_desc->GetName().c_str(), node_index_io.ToString().c_str());
+             node_op_desc->GetName().c_str(), node_index_io.ToString().c_str());
       return nullptr);
     // reduce old size
     size_t align_size = block->Size();
@@ -1392,24 +1406,28 @@ MemoryBlock *BlockMemAssigner::ApplyOutMemory(const NodePtr &n, uint32_t index,
     vector<bool> workspace_reuse_flag;
     block = ApplyMemory(block_size, size, no_align_size, kOutput, n, index,
                         workspace_reuse_flag, is_op_reuse_mem, continuous, memory_type);
-    GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(block == nullptr,
-      REPORT_CALL_ERROR("E19999", "apply out Memory failed, node_name:%s, block_size:%ld, out_index:%u",
-        n->GetName().c_str(), block_size, index);
-      return nullptr, "[Apply][Memory]node_name:%s, block_size:%ld, out_index:%u",
+    GE_CHK_BOOL_TRUE_EXEC_WITH_LOG(
+        block == nullptr,
+        REPORT_CALL_ERROR("E19999", "apply out Memory failed, node_name:%s, block_size:%ld, out_index:%u",
+                          n->GetName().c_str(), block_size, index);
+        return nullptr,
+        "[Apply][Memory]node_name:%s, block_size:%ld, out_index:%u",
         n->GetName().c_str(), block_size, index);
   }
   int out_count = 0;
-  GE_IF_BOOL_EXEC(index >= n->GetAllOutDataAnchors().size(),
-    REPORT_INNER_ERROR("E19999", "out index:%u exceed out_size:%lu, node_name:%s",
-      index, n->GetAllOutDataAnchors().size(), n->GetName().c_str());
-    GELOGE(FAILED, "[Check][OutIndex]index:%u exceed out_size:%lu, node_name:%s",
-      index, n->GetAllOutDataAnchors().size(), n->GetName().c_str());
-    return nullptr);
+  GE_IF_BOOL_EXEC(
+      index >= n->GetAllOutDataAnchors().size(),
+      REPORT_INNER_ERROR("E19999", "out index:%u exceed out_size:%lu, node_name:%s",
+                         index, n->GetAllOutDataAnchors().size(), n->GetName().c_str());
+      GELOGE(FAILED, "[Check][OutIndex]index:%u exceed out_size:%lu, node_name:%s",
+             index, n->GetAllOutDataAnchors().size(), n->GetName().c_str());
+      return nullptr);
   auto out_data_anchor = n->GetOutDataAnchor(index);
-  GE_IF_BOOL_EXEC(out_data_anchor == nullptr,
-    REPORT_INNER_ERROR("E19999", "out anchor is null, index:%u, node_name:%s", index, n->GetName().c_str());
-    GELOGE(FAILED, "[Check][OutAnchor]is null, index:%u, node_name:%s", index, n->GetName().c_str());
-    return nullptr);
+  GE_IF_BOOL_EXEC(
+      out_data_anchor == nullptr,
+      REPORT_INNER_ERROR("E19999", "out anchor is null, index:%u, node_name:%s", index, n->GetName().c_str());
+      GELOGE(FAILED, "[Check][OutAnchor]is null, index:%u, node_name:%s", index, n->GetName().c_str());
+      return nullptr);
   for (const auto &in_anchor : out_data_anchor->GetPeerInDataAnchors()) {
     auto owner_node = in_anchor->GetOwnerNode();
     auto op_desc = owner_node->GetOpDesc();
@@ -1616,12 +1634,13 @@ Status BlockMemAssigner::AssignOutputMemoryWithReuse(const NodePtr &node, vector
          op_desc->GetOutputsSize(), memorys_type.size());
   if (has_mem_type_attr && (memorys_type.size() != op_desc->GetOutputsSize())) {
     REPORT_INNER_ERROR("E19999", "Attr[%s] size:%zu not equal to node output size:%zu, node_name:%s",
-      ATTR_NAME_OUTPUT_MEM_TYPE_LIST.c_str(), memorys_type.size(),
-      op_desc->GetOutputsSize(), op_desc->GetName().c_str());
-    GELOGE(INTERNAL_ERROR,
-      "[Check][MemTypeAttr]Attr %s size:%zu not equal to node output size:%zu, node_name:%s",
-      ATTR_NAME_OUTPUT_MEM_TYPE_LIST.c_str(), memorys_type.size(),
-      op_desc->GetOutputsSize(), op_desc->GetName().c_str());
+                       ATTR_NAME_OUTPUT_MEM_TYPE_LIST.c_str(), memorys_type.size(),
+                       op_desc->GetOutputsSize(), op_desc->GetName().c_str());
+    GELOGE(
+        INTERNAL_ERROR,
+        "[Check][MemTypeAttr]Attr %s size:%zu not equal to node output size:%zu, node_name:%s",
+        ATTR_NAME_OUTPUT_MEM_TYPE_LIST.c_str(), memorys_type.size(),
+        op_desc->GetOutputsSize(), op_desc->GetName().c_str());
     return INTERNAL_ERROR;
   }
 
@@ -1748,9 +1767,11 @@ void BlockMemAssigner::AssignMemoryWithReuse(vector<int64_t> &ranges) {
 
     if (has_tvm_workspace_mem_type_attr && (temp.size() != tvm_workspace_memory_type.size())) {
       REPORT_INNER_ERROR("E19999", "Attr[%s]size:%zu is not equal to workspace size:%zu, node_name:%s",
-        TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(), tvm_workspace_memory_type.size(), temp.size(), n->GetName().c_str());
+                         TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(), tvm_workspace_memory_type.size(),
+                         temp.size(), n->GetName().c_str());
       GELOGE(INTERNAL_ERROR, "[Check][Attr]Attr %s size:%zu is not equal to workspace size:%zu, node_name:%s",
-        TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(), tvm_workspace_memory_type.size(), temp.size(), n->GetName().c_str());
+             TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(), tvm_workspace_memory_type.size(),
+             temp.size(), n->GetName().c_str());
       return;
     }
     for (size_t i = 0; i < temp.size(); i++) {
@@ -2160,10 +2181,11 @@ bool BlockMemAssigner::GetWorkSpaceMemoryType(const NodePtr &node, size_t index,
       ge::AttrUtils::GetListInt(op_desc, TVM_ATTR_NAME_WORKSPACE_TYPE, workspace_memory_type);
   if (has_workspace_mem_type_attr && (workspace_memory_type.size() <= index)) {
     REPORT_INNER_ERROR("E19999", "get workspace mem_type failed, "
-      "index %zu invalid, bigger than attr %s size:%zu, node_name:%s",
-      index, TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(), workspace_memory_type.size(), node->GetName().c_str());
+                       "index %zu invalid, bigger than attr %s size:%zu, node_name:%s",
+                       index, TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(),
+                       workspace_memory_type.size(), node->GetName().c_str());
     GELOGE(INTERNAL_ERROR, "[Get][WorkspaceMemType]index %zu invalid, bigger than attr %s size:%zu, node_name:%s",
-      index, TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(), workspace_memory_type.size(), node->GetName().c_str());
+           index, TVM_ATTR_NAME_WORKSPACE_TYPE.c_str(), workspace_memory_type.size(), node->GetName().c_str());
     return false;
   }
   memory_type = has_workspace_mem_type_attr ? workspace_memory_type[index] : RT_MEMORY_HBM;

ge/graph/build/memory/graph_mem_assigner.cc

@@ -496,7 +496,7 @@ Status GraphMemoryAssigner::AssignContinuousInputMemory(const ge::NodePtr &node,
     REPORT_INNER_ERROR("E19999", "find memory offset fail for mem_type:%ld, "
                        "when assign continuous input memory for node:%s, ", memory_type, node->GetName().c_str());
     GELOGE(FAILED, "[Find][MemOffset]fail for mem_type:%ld, when AssignContinuousInputMemory for node:%s",
-                    memory_type, node->GetName().c_str());
+           memory_type, node->GetName().c_str());
     return FAILED;
   }
   // The head and tail of hcom continuous input should be added 512
@@ -929,8 +929,8 @@ Status GraphMemoryAssigner::AssignReferenceMemory() {
 
     if (out_op_desc->GetOutputsSize() > output_list.size()) {
       REPORT_INNER_ERROR("E19999", "Output size:%zu more than output offset size:%zu, judge invalid in node:%s "
-                       "when AssignReferenceMemory",
-                       out_op_desc->GetOutputsSize(), output_list.size(), node->GetName().c_str());
+                         "when AssignReferenceMemory",
+                         out_op_desc->GetOutputsSize(), output_list.size(), node->GetName().c_str());
       GELOGE(ge::FAILED, "[Check][InnerData]Output size:%zu more than output offset size:%zu, invalid in node:%s",
              out_op_desc->GetOutputsSize(), output_list.size(), node->GetName().c_str());
       return ge::FAILED;

ge/graph/load/model_manager/davinci_model.cc

@@ -2875,23 +2875,16 @@ Status DavinciModel::UpdateKnownNodeArgs(const vector<void *> &inputs, const vec
   GELOGI("DavinciModel::UpdateKnownNodeArgs in");
   GE_CHK_STATUS_RET(CreateKnownZeroCopyMap(inputs, outputs),
                     "DavinciModel::UpdateKnownNodeArgs create map for input/output zero copy.");
-  if (!base_addr_not_changed_) {
-    total_io_addrs_.clear();
-    orig_total_io_addrs_.clear();
-    for (size_t task_index = 0; task_index < task_list_.size(); ++task_index) {
-      auto &task = task_list_[task_index];
-      if (task != nullptr) {
-        Status ret = task->UpdateArgs();
-        if (ret != SUCCESS) {
-          GELOGE(FAILED, "task %zu created by davinci model is nullptr.", task_index);
-          return FAILED;
-        }
+  total_io_addrs_.clear();
+  for (size_t task_index = 0; task_index < task_list_.size(); ++task_index) {
+    auto &task = task_list_[task_index];
+    if (task != nullptr) {
+      Status ret = task->UpdateArgs();
+      if (ret != SUCCESS) {
+        GELOGE(FAILED, "task %zu created by davinci model is nullptr.", task_index);
+        return FAILED;
       }
     }
-    // cache latest iterator io addr
-    orig_total_io_addrs_ = total_io_addrs_;
-  } else {
-    total_io_addrs_ = orig_total_io_addrs_;
   }
   GE_CHK_STATUS_RET(UpdateKnownZeroCopyAddr(total_io_addrs_, false), "DavinciModel::UpdateKnownZeroCopyAddr failed.");
 
@@ -2931,6 +2924,14 @@ Status DavinciModel::InitTaskInfo(domi::ModelTaskDef &model_task_def) {
   return SUCCESS;
 }
 
+Status DavinciModel::CheckCapability(rtFeatureType_t featureType, int32_t featureInfo, bool &is_support) const {
+  int64_t value = RT_CAPABILITY_SUPPORT;
+  auto rt_ret = rtGetRtCapability(featureType, featureInfo, &value);
+  GE_CHK_BOOL_RET_STATUS(rt_ret == RT_ERROR_NONE, FAILED, "call rtGetRtCapability failed!");
+  is_support = (value == RT_CAPABILITY_SUPPORT) ? true : false;
+  return SUCCESS;
+}
+
 Status DavinciModel::MallocKnownArgs() {
   GELOGI("DavinciModel::MallocKnownArgs in");
   const auto &model_task_def = ge_model_->GetModelTaskDefPtr();
@@ -2949,20 +2950,22 @@ Status DavinciModel::MallocKnownArgs() {
       return ret;
     }
   }
+  rtError_t rt_ret;
   // malloc args memory
-  if (total_args_size_ == 0) {
-    GELOGW("DavinciModel::MallocKnownArgs total_args_size_ equals to zero.");
-    return SUCCESS;
-  }
+  bool is_support = false;
+  GE_CHK_STATUS_RET_NOLOG(CheckCapability(FEATURE_TYPE_MEMORY, MEMORY_INFO_TS_4G_LIMITED, is_support));
+  auto mem_type = is_support ? RT_MEMORY_TS_4G : RT_MEMORY_HBM;
 
-  rtError_t rt_ret = rtMalloc(&args_, total_args_size_, RT_MEMORY_HBM);
-  if (rt_ret != RT_ERROR_NONE) {
-    GELOGE(RT_FAILED, "Call rtMalloc failed, ret: 0x%X", rt_ret);
-    return RT_ERROR_TO_GE_STATUS(rt_ret);
+  if (total_args_size_ != 0) {
+    rt_ret = rtMalloc(&args_, total_args_size_, mem_type);
+    if (rt_ret != RT_ERROR_NONE) {
+      GELOGE(RT_FAILED, "Call rtMalloc failed, ret: 0x%X", rt_ret);
+      return RT_ERROR_TO_GE_STATUS(rt_ret);
+    }
   }
   // malloc dynamic and static hybrid memory
   if (total_hybrid_args_size_ != 0) {
-    rt_ret = rtMalloc(&hybrid_addrs_, total_hybrid_args_size_, RT_MEMORY_HBM);
+    rt_ret = rtMalloc(&hybrid_addrs_, total_hybrid_args_size_, mem_type);
     if (rt_ret != RT_ERROR_NONE) {
       GELOGE(RT_FAILED, "Call rtMalloc failed, ret: 0x%X", rt_ret);
       return RT_ERROR_TO_GE_STATUS(rt_ret);
@@ -2971,7 +2974,7 @@ Status DavinciModel::MallocKnownArgs() {
   // malloc fixed addr memory, eg: rts op
   if (total_fixed_addr_size_ != 0) {
     GELOGI("Begin to allocate fixed addr.");
-    rt_ret = rtMalloc(&fixed_addrs_, total_fixed_addr_size_, RT_MEMORY_HBM);
+    rt_ret = rtMalloc(&fixed_addrs_, total_fixed_addr_size_, mem_type);
     if (rt_ret != RT_ERROR_NONE) {
       GELOGE(RT_FAILED, "Call rtMalloc failed, ret: 0x%X", rt_ret);
       return RT_ERROR_TO_GE_STATUS(rt_ret);

ge/graph/load/model_manager/davinci_model.h

@@ -530,11 +530,11 @@ class DavinciModel {
   }
   void SetKnownNode(bool known_node) { known_node_ = known_node; }
   bool IsKnownNode() { return known_node_; }
+  Status CheckCapability(rtFeatureType_t featureType, int32_t featureInfo, bool &is_support) const;
   Status MallocKnownArgs();
   Status UpdateKnownNodeArgs(const vector<void *> &inputs, const vector<void *> &outputs);
   Status CreateKnownZeroCopyMap(const vector<void *> &inputs, const vector<void *> &outputs);
   Status UpdateKnownZeroCopyAddr(vector<void *> &total_io_addrs, bool update_args = true);
-  void SetKnownNodeAddrNotChanged(bool base_addr_not_changed) { base_addr_not_changed_ = base_addr_not_changed; }
 
   Status GetOrigInputInfo(uint32_t index, OriginInputInfo &orig_input_info) const;
   Status GetAllAippInputOutputDims(uint32_t index, vector<InputOutputDims> &input_dims,
@@ -1007,8 +1007,6 @@ class DavinciModel {
   map<const void *, void *> known_input_data_info_;
   map<const void *, void *> known_output_data_info_;
   vector<void *> total_io_addrs_;
-  vector<void *> orig_total_io_addrs_;
-  bool base_addr_not_changed_ = false;
 
   vector<vector<int64_t>> batch_info_;
   vector<vector<int64_t>> combined_batch_info_;

ge/graph/load/model_manager/model_utils.cc

@@ -384,7 +384,8 @@ Status ModelUtils::GetVarAddr(const RuntimeParam &model_param, const ConstOpDesc
   switch (mem_type) {
     case RT_MEMORY_RDMA_HBM:
       if (offset < 0) {
-        GELOGE(PARAM_INVALID, "rdma var addr is invalid, addr=%p", reinterpret_cast<uint8_t *>(offset));
+        GELOGE(PARAM_INVALID, "rdma var addr is invalid, addr=%p",
+               reinterpret_cast<uint8_t *>(static_cast<uintptr_t>(offset)));
         return PARAM_INVALID;
       }
       var_addr = reinterpret_cast<uint8_t *>(static_cast<uintptr_t>(offset));

ge/graph/load/model_manager/task_info/kernel_task_info.cc

@@ -124,7 +124,8 @@ Status KernelTaskInfo::Init(const domi::TaskDef &task_def, DavinciModel *davinci
       return FAILED;
     }
 
-    ret = InitTVMTask(args_offset_tmp[0], kernel_def);
+    io_addr_offset_ = args_offset_tmp[0];
+    ret = InitTVMTask(io_addr_offset_, kernel_def);
   } else if (kernel_type_ == ccKernelType::CUSTOMIZED) {
     ret = InitAICPUCustomTask(context.op_index(), kernel_def);
   } else if (kernel_type_ == ccKernelType::AI_CPU || kernel_type_ == ccKernelType::CUST_AI_CPU) {
@@ -380,7 +381,8 @@ Status KernelTaskInfo::Distribute() {
   GELOGD("KernelTaskInfo Distribute Start.");
   if (davinci_model_->IsKnownNode()) {
     if (kernel_type_ == ccKernelType::TE) {
-      args_ = davinci_model_->GetCurrentArgsAddr(args_offset_);
+      args_ = l2_buffer_on_ ? davinci_model_->GetCurrentHybridArgsAddr(hybrid_args_offset_)
+                            : davinci_model_->GetCurrentArgsAddr(args_offset_);
     } else if (kernel_type_ == ccKernelType::AI_CPU || kernel_type_ == ccKernelType::CUST_AI_CPU) {
       args_ = davinci_model_->GetCurrentHybridArgsAddr(hybrid_args_offset_);
     }
@@ -449,29 +451,41 @@ void KernelTaskInfo::SetIoAddrs(const OpDescPtr &op_desc) {
   }
 }
 
+Status KernelTaskInfo::CopyNoncontinuousArgs(uint16_t offset) {
+  GE_CHECK_NOTNULL(davinci_model_);
+  // copy new io addrs
+  vector<void *> io_addrs = io_addrs_;
+  davinci_model_->UpdateKnownZeroCopyAddr(io_addrs);
+  auto addr_size = kAddrLen * io_addrs.size();
+
+  // copy io addr
+  errno_t sec_ret = memcpy_s(args_addr.get() + offset, addr_size, io_addrs.data(), addr_size);
+  if (sec_ret != EOK) {
+    GELOGE(FAILED, "memcpy failed, ret: %d", sec_ret);
+    return FAILED;
+  }
+
+  // copy args to device
+  rtError_t rt_ret = rtMemcpy(args_, args_size_, args_addr.get(), args_size_, RT_MEMCPY_HOST_TO_DEVICE);
+  if (rt_ret != RT_ERROR_NONE) {
+    GELOGE(RT_FAILED, "Call rt api(rtMemcpy) failed, ret: 0x%X", rt_ret);
+    return RT_ERROR_TO_GE_STATUS(rt_ret);
+  }
+  GELOGD("Copy noncontinuous args success, kernel type %d.", kernel_type_);
+  return SUCCESS;
+}
+
 Status KernelTaskInfo::UpdateArgs() {
   GELOGI("KernelTaskInfo::UpdateArgs in.");
+  GE_CHECK_NOTNULL(davinci_model_);
   if (kernel_type_ == ccKernelType::TE) {
+    if (l2_buffer_on_) {
+      return CopyNoncontinuousArgs(io_addr_offset_);
+    }
     davinci_model_->SetTotalIOAddrs(io_addrs_);
   } else if (kernel_type_ == ccKernelType::AI_CPU || kernel_type_ == ccKernelType::CUST_AI_CPU) {
-    vector<void *> io_addrs = io_addrs_;
-    davinci_model_->UpdateKnownZeroCopyAddr(io_addrs);
-    uintptr_t io_addr = reinterpret_cast<uintptr_t>(args_addr.get()) + sizeof(aicpu::AicpuParamHead);
-    auto addrs_size = sizeof(uint64_t) * io_addrs.size();
-    errno_t sec_ret = memcpy_s(reinterpret_cast<void *>(io_addr), addrs_size, io_addrs.data(), addrs_size);
-    if (sec_ret != EOK) {
-      GELOGE(FAILED, "memcpy failed, ret: %d", sec_ret);
-      return FAILED;
-    }
-    // copy args to device
-    rtError_t rt_ret = rtMemcpy(args_, args_size_, args_addr.get(), args_size_, RT_MEMCPY_HOST_TO_DEVICE);
-    if (rt_ret != RT_ERROR_NONE) {
-      GELOGE(RT_FAILED, "Call rt api(rtMemcpy) failed, ret: 0x%X", rt_ret);
-      return RT_ERROR_TO_GE_STATUS(rt_ret);
-    }
+    return CopyNoncontinuousArgs(sizeof(aicpu::AicpuParamHead));
   }
-
-  GELOGI("KernelTaskInfo::UpdateArgs success.");
   return SUCCESS;
 }
 
@@ -516,8 +530,8 @@ Status KernelTaskInfo::UpdateL2Data(const domi::KernelDef &kernel_def) {
     return SUCCESS;
   }
 
-  char *sm_contrl = const_cast<char *>(sm_desc.data());
-  rtL2Ctrl_t *l2_ctrl_info = reinterpret_cast<rtL2Ctrl_t *>(sm_contrl);
+  char *sm_control = const_cast<char *>(sm_desc.data());
+  rtL2Ctrl_t *l2_ctrl_info = reinterpret_cast<rtL2Ctrl_t *>(sm_control);
   uint64_t gen_base_addr = davinci_model_->GetRtBaseAddr();
 
   // There is no weight for te op now. Update L2_mirror_addr by data memory base.
@@ -545,19 +559,31 @@ Status KernelTaskInfo::UpdateL2Data(const domi::KernelDef &kernel_def) {
   return SUCCESS;
 }
 
+void KernelTaskInfo::SetContinuousArgs(uint32_t args_size, DavinciModel *davinci_model) {
+  args_offset_ = davinci_model->GetTotalArgsSize();
+  davinci_model->SetTotalArgsSize(args_size);
+}
+
+void KernelTaskInfo::SetNoncontinuousArgs(uint32_t args_size, DavinciModel *davinci_model) {
+  hybrid_args_offset_ = davinci_model->GetHybridArgsSize();
+  davinci_model->SetHybridArgsSize(args_size);
+}
+
 Status KernelTaskInfo::CalculateArgs(const domi::TaskDef &task_def, DavinciModel *davinci_model) {
+  GE_CHECK_NOTNULL(davinci_model);
   const domi::KernelDef &kernel_def = task_def.kernel();
   const domi::KernelContext &context = kernel_def.context();
   kernel_type_ = static_cast<ccKernelType>(context.kernel_type());
+  uint32_t args_size = kernel_def.args_size();
   if (kernel_type_ == ccKernelType::TE) {
-    uint32_t args_size = kernel_def.args_size();
-    args_offset_ = davinci_model->GetTotalArgsSize();
-    davinci_model->SetTotalArgsSize(args_size);
-    GELOGI("kernel task name , args_size %u, args_offset %u", args_size, args_offset_);
+    if (kernel_def.sm_desc().empty()) {
+      SetContinuousArgs(args_size, davinci_model);
+      return SUCCESS;
+    }
+    l2_buffer_on_ = true;
+    SetNoncontinuousArgs(args_size, davinci_model);
   } else if (kernel_type_ == ccKernelType::AI_CPU || kernel_type_ == ccKernelType::CUST_AI_CPU) {
-    hybrid_args_offset_ = davinci_model->GetHybridArgsSize();
-    davinci_model->SetHybridArgsSize(kernel_def.args_size());
-    GELOGI("aicpu kernel task name , args_size %u, args_offset %u", kernel_def.args_size(), hybrid_args_offset_);
+    SetNoncontinuousArgs(args_size, davinci_model);
   }
   return SUCCESS;
 }
@@ -568,8 +594,23 @@ Status KernelTaskInfo::InitTVMTask(uint16_t offset, const domi::KernelDef &kerne
   // get tvm op desc
   OpDescPtr op_desc = davinci_model_->GetOpByIndex(ctx_.opIndex);
   GE_CHECK_NOTNULL(op_desc);
+
+  args_addr = std::unique_ptr<uint8_t[]>(new (std::nothrow) uint8_t[args_size_]);
+  errno_t sec_ret = memcpy_s(args_addr.get(), args_size_, kernel_def.args().data(), args_size_);
+  if (sec_ret != EOK) {
+    GELOGE(FAILED, "memcpy failed, ret: %d", sec_ret);
+    return FAILED;
+  }
+
+  Status ge_ret = UpdateL2Data(kernel_def);
+  // update origin l2 data
+  if (ge_ret != SUCCESS) {
+    return ge_ret;
+  }
+
   if (davinci_model_->IsKnownNode()) {
-    args_ = davinci_model_->GetCurrentArgsAddr(args_offset_);
+    args_ = l2_buffer_on_ ? davinci_model_->GetCurrentHybridArgsAddr(hybrid_args_offset_)
+                          : davinci_model_->GetCurrentArgsAddr(args_offset_);
     InitDumpTask(offset);
     return SUCCESS;
   }
@@ -609,12 +650,6 @@ Status KernelTaskInfo::InitTVMTask(uint16_t offset, const domi::KernelDef &kerne
     GELOGE(RT_FAILED, "Call rt api failed, ret: 0x%X", rt_ret);
     return RT_ERROR_TO_GE_STATUS(rt_ret);
   }
-  vector<uint8_t> args_info(args_size_);
-  errno_t sec_ret = memcpy_s(args_info.data(), args_size_, kernel_def.args().data(), args_size_);
-  if (sec_ret != EOK) {
-    GELOGE(FAILED, "memcpy failed, ret: %d", sec_ret);
-    return FAILED;
-  }
 
   if ((args_size_ <= offset) || (args_size_ - offset < kAddrLen * tensor_device_addrs.size())) {
     GELOGE(FAILED, "offset >= kernelInfo.argsSize or copy content beyond applied memory.");
@@ -628,7 +663,7 @@ Status KernelTaskInfo::InitTVMTask(uint16_t offset, const domi::KernelDef &kerne
     GELOGE(RT_FAILED, "Call rt api failed, ret: 0x%X", rt_ret);
     return RT_ERROR_TO_GE_STATUS(rt_ret);
   }
-  sec_ret = memcpy_s(args_info.data() + offset, args_size_ - offset, tensor_device_addrs.data(),
+  sec_ret = memcpy_s(args_addr.get() + offset, args_size_ - offset, tensor_device_addrs.data(),
                      kAddrLen * tensor_device_addrs.size());
   if (sec_ret != EOK) {
     GELOGE(FAILED, "memcpy failed, ret: %d", sec_ret);
@@ -640,19 +675,13 @@ Status KernelTaskInfo::InitTVMTask(uint16_t offset, const domi::KernelDef &kerne
   GE_CHK_BOOL_TRUE_EXEC_INFO(davinci_model_->GetOpDugReg(), dump_args_ = static_cast<char *>(args_) + offset,
                              "Op debug is open in TVM task info");
 
-  Status ge_ret = UpdateL2Data(kernel_def);
-  // update origin l2 data
-  if (ge_ret != SUCCESS) {
-    return ge_ret;
-  }
-
   vector<void *> virtual_io_addrs;  // use virtual address for zero copy key.
   virtual_io_addrs.insert(virtual_io_addrs.end(), input_data_addrs.begin(), input_data_addrs.end());
   virtual_io_addrs.insert(virtual_io_addrs.end(), output_data_addrs.begin(), output_data_addrs.end());
   if (op_desc->GetType() == ATOMICADDRCLEAN) {
     virtual_io_addrs.insert(virtual_io_addrs.end(), workspace_data_addrs.begin(), workspace_data_addrs.end());
   }
-  davinci_model_->SetZeroCopyAddr(op_desc, virtual_io_addrs, args_info.data(), args_, args_size_, offset);
+  davinci_model_->SetZeroCopyAddr(op_desc, virtual_io_addrs, args_addr.get(), args_, args_size_, offset);
 
   GELOGD("Do InitTVMTask end");
   return SUCCESS;

ge/graph/load/model_manager/task_info/kernel_task_info.h

@@ -129,6 +129,9 @@ class KernelTaskInfo : public TaskInfo {
   bool IsL1FusionOp(const OpDescPtr &op_desc);
   void SetIoAddrs(const OpDescPtr &op_desc);
   void InitDumpTask(uint32_t offset);
+  void SetContinuousArgs(uint32_t args_size, DavinciModel *davinci_model);
+  void SetNoncontinuousArgs(uint32_t args_size, DavinciModel *davinci_model);
+  Status CopyNoncontinuousArgs(uint16_t offset);
 
   // For super kernel
   Status SaveSKTDumpInfo();
@@ -163,6 +166,8 @@ class KernelTaskInfo : public TaskInfo {
   uint32_t hybrid_args_offset_ = 0;
   int64_t fixed_addr_offset_ = 0;
   std::unique_ptr<uint8_t[]> args_addr = nullptr;
+  uint16_t io_addr_offset_ = 0;
+  bool l2_buffer_on_ = false;
   bool call_save_dump_ = false;
 
   // aicpu ext_info device mem

ge/graph/passes/base_pass.cc

@@ -30,8 +30,15 @@ constexpr int kMaxRePassTimes = 10000;
 constexpr size_t kMaxOneInNodes = 1000;
 // Each iteration, we take about 0.3k memory on the stack, we should change the recursion to loop later
 constexpr int kMaxRecursiveDepth = 20;
+struct DuringPassNodeSets {
+  std::unordered_set<Node *> nodes_seen;
+  std::unordered_set<NodePtr> nodes_deleted;
+  std::unordered_set<NodePtr> nodes_re_pass;
+  std::unordered_set<NodePtr> nodes_re_pass_immediately;
+  std::unordered_set<NodePtr> nodes_last;
+};
 
-void GetAllNodesNoInputEdge(const ComputeGraphPtr &graph, std::queue<NodePtr> &input_edge_nodes,
+void GetAllNodesNoInputEdge(const ComputeGraphPtr &graph, std::deque<NodePtr> &input_edge_nodes,
                             std::unordered_set<Node *> &nodes_seen, std::unordered_set<NodePtr> &nodes_last) {
   nodes_last.clear();
   for (auto &node : graph->GetDirectNode()) {
@@ -40,7 +47,7 @@ void GetAllNodesNoInputEdge(const ComputeGraphPtr &graph, std::queue<NodePtr> &i
     }
     size_t in_nums = node->GetInNodes().size();
     if (in_nums == 0) {
-      input_edge_nodes.push(node);
+      input_edge_nodes.push_back(node);
       nodes_seen.insert(node.get());
     } else if (in_nums > kMaxOneInNodes) {
       nodes_last.insert(node);
@@ -48,7 +55,7 @@ void GetAllNodesNoInputEdge(const ComputeGraphPtr &graph, std::queue<NodePtr> &i
   }
 }
 
-void AddNextIterNodes(const Node::Vistor<NodePtr> &nodes, std::queue<NodePtr> &nodes_to_pass,
+void AddNextIterNodes(const Node::Vistor<NodePtr> &nodes, std::deque<NodePtr> &nodes_to_pass,
                       std::unordered_set<Node *> &nodes_seen, std::unordered_set<NodePtr> &nodes_last) {
   for (auto &node : nodes) {
     if (node == nullptr) {
@@ -60,13 +67,30 @@ void AddNextIterNodes(const Node::Vistor<NodePtr> &nodes, std::queue<NodePtr> &n
 
     bool all_in_nodes_seen = node->IsAllInNodesSeen(nodes_seen);
     if (all_in_nodes_seen && nodes_seen.insert(node.get()).second) {
-      nodes_to_pass.push(node);
+      nodes_to_pass.push_back(node);
     }
   }
 }
 
-Status RunPasses(NodePtr &node, const NamesToPass &names_to_passes, std::unordered_set<NodePtr> &nodes_re_pass,
-                 std::unordered_set<NodePtr> &nodes_deleted, std::unordered_set<Node *> &nodes_seen) {
+void PushToRePassIfSeen(NodePtr &node, const std::pair<std::string, BaseNodePass *> &name_to_pass,
+                        std::unordered_set<Node *> &nodes_seen, std::unordered_set<NodePtr> &nodes_to_re_pass,
+                        std::unordered_set<NodePtr> &nodes_re_pass) {
+  for (const auto &node_to_re_pass : nodes_to_re_pass) {
+    if (node_to_re_pass == nullptr) {
+      GELOGW("Found null re-pass node when executing %s on node %s type %s", name_to_pass.first.c_str(),
+             node->GetName().c_str(), node->GetType().c_str());
+      continue;
+    }
+    if (nodes_seen.count(node_to_re_pass.get()) > 0 || node_to_re_pass->IsAllInNodesSeen(nodes_seen)) {
+      GELOGD("The node %s will be re-pass.", node_to_re_pass->GetName().c_str());
+      nodes_re_pass.insert(node_to_re_pass);
+    } else {
+      GELOGD("The node %s are not all seen, don't set repass this time", node_to_re_pass->GetName().c_str());
+    }
+  }
+}
+
+Status RunPasses(NodePtr &node, const NamesToPass &names_to_passes, DuringPassNodeSets &during_pass_node_set) {
   if (node == nullptr) {
     GELOGE(FAILED, "parameter is null.");
     return FAILED;
@@ -90,22 +114,15 @@ Status RunPasses(NodePtr &node, const NamesToPass &names_to_passes, std::unorder
     }
 
     auto nodes_to_re_pass = name_to_pass.second->GetNodesNeedRePass();
-    for (const auto &node_to_re_pass : nodes_to_re_pass) {
-      if (node_to_re_pass == nullptr) {
-        GELOGW("Found null re-pass node when executing %s on node %s type %s", name_to_pass.first.c_str(),
-               node->GetName().c_str(), node->GetType().c_str());
-        continue;
-      }
-      if (nodes_seen.count(node_to_re_pass.get()) > 0 || node_to_re_pass->IsAllInNodesSeen(nodes_seen)) {
-        GELOGD("The node %s will be re-pass later", node_to_re_pass->GetName().c_str());
-        nodes_re_pass.insert(node_to_re_pass);
-      } else {
-        GELOGD("The node %s are not all seen, don't set repass this time", node_to_re_pass->GetName().c_str());
-      }
-    }
+    PushToRePassIfSeen(node, name_to_pass, during_pass_node_set.nodes_seen, nodes_to_re_pass,
+                       during_pass_node_set.nodes_re_pass);
+
+    auto nodes_to_re_pass_immediately = name_to_pass.second->GetNodesNeedRePassImmediately();
+    PushToRePassIfSeen(node, name_to_pass, during_pass_node_set.nodes_seen, nodes_to_re_pass_immediately,
+                       during_pass_node_set.nodes_re_pass_immediately);
 
     auto nodes_deleted_by_pass = name_to_pass.second->GetNodesDeleted();
-    nodes_deleted.insert(nodes_deleted_by_pass.begin(), nodes_deleted_by_pass.end());
+    during_pass_node_set.nodes_deleted.insert(nodes_deleted_by_pass.begin(), nodes_deleted_by_pass.end());
     if (nodes_deleted_by_pass.count(node) > 0) {
       GELOGD("The node %s was deleted by pass %s, stop the remain passes", node->GetName().c_str(),
              name_to_pass.first.c_str());
@@ -181,36 +198,33 @@ Status GEPass::Run(const NamesToPass &names_to_passes) {
 
 Status GEPass::RunPassesOneGraph(const NamesToPass &names_to_passes) {
   GELOGD("Begin to run pass on graph, passes count %zu", names_to_passes.size());
-  std::queue<NodePtr> nodes;
-  std::unordered_set<Node *> nodes_seen;
-  std::unordered_set<NodePtr> nodes_deleted;
-  std::unordered_set<NodePtr> nodes_re_pass;
-  std::unordered_set<NodePtr> nodes_last;
-  GetAllNodesNoInputEdge(graph_, nodes, nodes_seen, nodes_last);
+  std::deque<NodePtr> nodes;
+  DuringPassNodeSets during_pass_node_set;
+  GetAllNodesNoInputEdge(graph_, nodes, during_pass_node_set.nodes_seen, during_pass_node_set.nodes_last);
   GELOGD("Start points count %zu", nodes.size());
   int re_pass_times = 0;
 
   do {
-    for (auto &node : nodes_re_pass) {
-      nodes.push(node);
-      nodes_seen.insert(node.get());
+    for (auto &node : during_pass_node_set.nodes_re_pass) {
+      nodes.push_back(node);
+      during_pass_node_set.nodes_seen.insert(node.get());
     }
-    nodes_re_pass.clear();
+    during_pass_node_set.nodes_re_pass.clear();
 
     while (!nodes.empty()) {
       NodePtr node = nodes.front();
-      nodes.pop();
+      nodes.pop_front();
 
-      (void)nodes_re_pass.erase(node);
+      (void)during_pass_node_set.nodes_re_pass.erase(node);
       GE_IF_BOOL_EXEC(node == nullptr, GELOGW("node is null"); continue);
-      if (nodes_deleted.count(node) > 0) {
+      if (during_pass_node_set.nodes_deleted.count(node) > 0) {
         GELOGD("The node %s was deleted before, skip it.", node->GetName().c_str());
         continue;
       }
 
-      AddNextIterNodes(node->GetOutNodes(), nodes, nodes_seen, nodes_last);
+      AddNextIterNodes(node->GetOutNodes(), nodes, during_pass_node_set.nodes_seen, during_pass_node_set.nodes_last);
 
-      auto ret = RunPasses(node, names_to_passes, nodes_re_pass, nodes_deleted, nodes_seen);
+      auto ret = RunPasses(node, names_to_passes, during_pass_node_set);
       if (ret != SUCCESS) {
         GELOGE(ret, "Failed to process passes on node %s type %s, error code: %u",
                node->GetName().c_str(), node->GetType().c_str(), ret);
@@ -227,7 +241,7 @@ Status GEPass::RunPassesOneGraph(const NamesToPass &names_to_passes) {
       if (has_sub_graph) {
         GELOGD("There are subgraphs on node %s, run passes for for the second time", node->GetName().c_str());
         SetFlagOption(kOptimizeAfterSubGraph, names_to_passes);
-        ret = RunPasses(node, names_to_passes, nodes_re_pass, nodes_deleted, nodes_seen);
+        ret = RunPasses(node, names_to_passes, during_pass_node_set);
         if (ret != SUCCESS) {
           GELOGE(ret, "Failed to process passes on node %s type %s, error code: %u",
                  node->GetName().c_str(), node->GetType().c_str(), ret);
@@ -239,16 +253,21 @@ Status GEPass::RunPassesOneGraph(const NamesToPass &names_to_passes) {
         // should be called each time at the begin of the iteration
         ClearOption(names_to_passes);
       }
+      for (const auto &node : during_pass_node_set.nodes_re_pass_immediately) {
+        GELOGD("The node %s will be re-pass immediately.", node->GetName().c_str());
+        nodes.push_front(node);
+      }
+      during_pass_node_set.nodes_re_pass_immediately.clear();
     }
 
-    for (auto &node : nodes_last) {
-      bool all_in_nodes_seen = node->IsAllInNodesSeen(nodes_seen);
-      if (all_in_nodes_seen && nodes_seen.insert(node.get()).second) {
-        nodes.push(node);
+    for (auto &node : during_pass_node_set.nodes_last) {
+      bool all_in_nodes_seen = node->IsAllInNodesSeen(during_pass_node_set.nodes_seen);
+      if (all_in_nodes_seen && during_pass_node_set.nodes_seen.insert(node.get()).second) {
+        nodes.push_back(node);
       }
     }
-    nodes_last.clear();
-  } while ((!nodes_re_pass.empty() || !nodes.empty()) && ++re_pass_times < kMaxRePassTimes);
+    during_pass_node_set.nodes_last.clear();
+  } while ((!during_pass_node_set.nodes_re_pass.empty() || !nodes.empty()) && ++re_pass_times < kMaxRePassTimes);
 
   if (re_pass_times == kMaxRePassTimes) {
     GELOGW("re_pass_times should not come to %d", kMaxRePassTimes);

ge/graph/passes/base_pass.h

@@ -53,6 +53,8 @@ class BaseNodePass {
 
   std::unordered_set<NodePtr> GetNodesNeedRePass() { return nodes_need_re_pass_; }
 
+  std::unordered_set<NodePtr> GetNodesNeedRePassImmediately() { return nodes_need_re_pass_immediately_; }
+
   std::unordered_set<NodePtr> GetNodesDeleted() { return nodes_deleted_; }
 
   void SetOption(NodePassOption option, const std::string &value) { options_[option] = value; }
@@ -62,6 +64,7 @@ class BaseNodePass {
   void init() {
     nodes_need_re_pass_.clear();
     nodes_deleted_.clear();
+    nodes_need_re_pass_immediately_.clear();
   }
 
  protected:
@@ -80,6 +83,14 @@ class BaseNodePass {
   void AddRePassNode(NodePtr &node) { nodes_need_re_pass_.insert(node); }
 
   ///
+  /// Add a node to be optimized immediately again. If you add a new node to the graph, or
+  /// change a node connections, and you want to make sure the node will be
+  /// optimized by other passes, call this function.
+  /// @param node
+  ///
+  void AddImmediateRePassNode(NodePtr &node) { nodes_need_re_pass_immediately_.insert(node); }
+
+  ///
   /// Add a node and it's input/output data nodes to be optimized again.
   /// @param node
   ///
@@ -109,6 +120,7 @@ class BaseNodePass {
 
  private:
   std::unordered_set<NodePtr> nodes_need_re_pass_;
+  std::unordered_set<NodePtr> nodes_need_re_pass_immediately_;
   std::unordered_set<NodePtr> nodes_deleted_;
   std::map<NodePassOption, std::string> options_;
 };

ge/graph/passes/infershape_pass.cc

@@ -25,6 +25,7 @@
 
 namespace ge {
 Status InferShapePass::Run(NodePtr &node) {
+  // kOptimizeAfterSubGraph exist means after subgraph
   auto ret = ShapeRefiner::InferShapeAndType(node, !OptionExists(kOptimizeAfterSubGraph));
   if (ret != GRAPH_SUCCESS) {
     // select INFERSHAPE failed info
@@ -41,6 +42,20 @@ Status InferShapePass::Run(NodePtr &node) {
     GELOGE(GE_GRAPH_INFERSHAPE_FAILED, "infershape failed. node: %s", node->GetName().c_str());
     return GE_GRAPH_INFERSHAPE_FAILED;
   }
+  bool need_repass = false;
+  auto has_attr = AttrUtils::GetBool(node->GetOpDesc(), "need_infer_again_", need_repass);
+  if (has_attr) {
+    if (!OptionExists(kOptimizeAfterSubGraph)) {
+      return SUCCESS;
+    }
+    if (need_repass) {
+      AddImmediateRePassNode(node);
+      GELOGD("Node %s need repass immediately.", node->GetName().c_str());
+    } else {
+      // clear attr on while
+      node->GetOpDesc()->DelAttr("need_infer_again_");
+    }
+  }
   return SUCCESS;
 }
 }  // namespace ge

ge/graph/preprocess/graph_preprocess.cc

@@ -1772,8 +1772,8 @@ Status GraphPrepare::CheckUserInput(const std::vector<GeTensor> &user_input) {
         if (dim < UNKNOWN_DIM_NUM) {
           std::string situation = "data dim[" + std::to_string(i) + "][" + std::to_string(dim) + "]" ;
           std::string reason = "it need >= -2";
-          REPORT_INPUT_ERROR(
-            "E19025", std::vector<std::string>({"situation", "reason"}),std::vector<std::string>({situation, reason}));
+          REPORT_INPUT_ERROR("E19025", std::vector<std::string>({"situation", "reason"}),
+                             std::vector<std::string>({situation, reason}));
           GELOGE(GE_GRAPH_INIT_FAILED, "[Check][InputDim]data dim %zu is not supported, need >= -2, real:%ld.", i, dim);
           return GE_GRAPH_INIT_FAILED;
         }

ge/graph/preprocess/insert_op/util_insert_aipp_op.cc

@@ -212,7 +212,7 @@ Status InsertNewOpUtil::CheckGraph(const ComputeGraphPtr &graph) {
         }
       }
     }
-    GE_CHK_LOG_AND_ERRORMSG((aippNodes.size() == 0) || (aippNodes.size() == next_nodes_cnt), 
+    GE_CHK_LOG_AND_ERRORMSG((aippNodes.size() == 0) || (aippNodes.size() == next_nodes_cnt),
         PARAM_INVALID,
         "Can not config part of outputs of Data node to support AIPP, config all "
         "of the outputs of Data to support AIPP, or config none of them");

ge/host_kernels/gather_v2_kernel.cc

@@ -407,7 +407,8 @@ Status GatherV2Kernel::Compute(const OpDescPtr op_desc_ptr, const vector<ConstGe
   // check input data type
   auto x_data_type = tensor0->GetTensorDesc().GetDataType();
   if (supported_type.find(x_data_type) == supported_type.end()) {
-    GELOGI("GatherV2Kernel does not support this Data type:%s.", TypeUtils::DataTypeToSerialString(x_data_type).c_str());
+    GELOGI("GatherV2Kernel does not support this Data type:%s.",
+           TypeUtils::DataTypeToSerialString(x_data_type).c_str());
     return NOT_CHANGED;
   }
   // calc output shape

ge/hybrid/executor/hybrid_model_async_executor.cc

@@ -67,6 +67,7 @@ Status HybridModelAsyncExecutor::Start(const std::shared_ptr<ModelListener> &lis
   future_ = std::async(std::launch::async, [&]() -> Status {
     GetThreadLocalContext() = *executor_->GetContext()->ge_context;
     GetContext().SetSessionId(executor_->GetContext()->session_id);
+    GetContext().SetContextId(executor_->GetContext()->context_id);
     return RunInternal();
   });
 
@@ -105,7 +106,7 @@ Status HybridModelAsyncExecutor::Init() {
   executor_ = std::unique_ptr<HybridModelExecutor>(new(std::nothrow) HybridModelExecutor(model_, device_id_, stream_));
   GE_CHECK_NOTNULL(executor_);
   GE_CHK_STATUS_RET(executor_->Init(), "Failed to init hybrid engine");
-  GE_CHK_STATUS_RET(DumpOpDebug(),"Dump op debug failed in hybrid engine");
+  GE_CHK_STATUS_RET(DumpOpDebug(), "Dump op debug failed in hybrid engine");
 
   GELOGI("HybridModel stage nums:%zu", model_->GetRootGraphItem()->NumGroups());
   if (model_->GetRootGraphItem()->NumGroups() >= kMinimumPiplineStages) {
@@ -166,6 +167,7 @@ Status HybridModelAsyncExecutor::RunInternal() {
     } else {
       GELOGI("HybridModel will execute in singleline mode");
       ge::GetContext().SetSessionId(executor_->GetContext()->session_id);
+      ge::GetContext().SetContextId(executor_->GetContext()->context_id);
       ret = executor_->Execute(args);
     }
     ret = HandleResult(ret, current_data.index, args, data_wrapper->GetOutput());

ge/hybrid/executor/node_state.cc

@@ -35,12 +35,14 @@ ShapeInferenceState::ShapeInferenceState(const NodeItem &node_item) : node_item(
          node_item.NodeName().c_str(),
          this->num_pending_shapes_);
 
-  for (int i = 0; i < node_item.num_inputs; ++i){
-    input_tensor_desc.emplace_back(*node_item.MutableInputDesc(i));
+  input_tensor_desc.resize(node_item.num_inputs);
+  for (int i = 0; i < node_item.num_inputs; ++i) {
+    node_item.GetInputDesc(i, input_tensor_desc[i]);
   }
 
-  for (int i = 0; i < node_item.num_outputs; ++i){
-    output_tensor_desc.emplace_back(*node_item.MutableOutputDesc(i));
+  output_tensor_desc.resize(node_item.num_outputs);
+  for (int i = 0; i < node_item.num_outputs; ++i) {
+    node_item.GetOutputDesc(i, output_tensor_desc[i]);
   }
 }
 

ge/hybrid/executor/subgraph_executor.cc

@@ -227,6 +227,7 @@ Status SubgraphExecutor::PrepareNodes(int group) {
       if (node_item.is_dynamic) {
         auto prepare_future = pre_run_pool_.commit([this, p_node_state]() -> Status {
           GetContext().SetSessionId(context_->session_id);
+          GetContext().SetContextId(context_->context_id);
           GE_CHK_STATUS_RET_NOLOG(InferShape(shape_inference_engine_.get(), *p_node_state));
           return PrepareForExecution(context_, *p_node_state);
         });
@@ -273,10 +274,8 @@ Status SubgraphExecutor::PrepareNodes(int group) {
 }
 
 Status SubgraphExecutor::InferShape(ShapeInferenceEngine *shape_inference_engine, NodeState &node_state) const {
-  GetContext().SetSessionId(context_->context_id);
   HYBRID_CHK_STATUS_RET(shape_inference_engine->InferShape(node_state),
                         "[%s] Failed to InferShape.", node_state.GetName().c_str());
-  GetContext().SetSessionId(context_->session_id);
   HYBRID_CHK_STATUS_RET(shape_inference_engine->PropagateOutputShapes(node_state),
                         "[%s] Failed to PropagateOutputShapes.", node_state.GetName().c_str());
   return SUCCESS;
@@ -345,6 +344,7 @@ Status SubgraphExecutor::ScheduleTasks(int group) {
   GELOGD("[%s] Start to schedule prepare workers.", graph_item_->GetName().c_str());
   auto prepare_future = std::async(std::launch::async, [&]() -> Status {
     GetContext().SetSessionId(context_->session_id);
+    GetContext().SetContextId(context_->context_id);
     auto ret = PrepareNodes(group);
     ready_queue_.Push(nullptr);
     return ret;

ge/hybrid/model/hybrid_model.h

@@ -135,6 +135,7 @@ class HybridModel {
   std::string model_name_;
   GeRootModelPtr ge_root_model_;
   std::map<uint32_t, NodeItem *> input_nodes_;
+  ComputeGraphPtr root_graph_;
   std::map<std::string, NodePtr> device_variable_nodes_; //lint !e148
   std::map<std::string, NodePtr> host_variable_nodes_; //lint !e148
   std::map<std::string, std::unique_ptr<TensorValue>> variable_tensors_;

ge/hybrid/model/hybrid_model_builder.cc

@@ -136,12 +136,12 @@ Status HybridModelBuilder::Build() {
   GE_CHK_STATUS_RET(RecoverGraphUnknownFlag(), "[%s] Failed to RecoverGraphUnknownFlag", GetGraphName());
   GE_CHK_STATUS_RET(IndexSpecialNodes(), "[%s] Failed to index nodes", GetGraphName());
   GE_CHK_STATUS_RET(IndexTaskDefs(), "[%s] Failed to index task defs", GetGraphName());
+  GE_CHK_STATUS_RET(InitWeights(), "[%s] Failed to init weights", GetGraphName());
   GE_CHK_STATUS_RET(LoadGraph(), "[%s] Failed to load graph", GetGraphName());
   GE_CHK_STATUS_RET(AssignUninitializedConstantOps(), "[%s] Failed to assign uninitialized constants", GetGraphName());
   GE_CHK_STATUS_RET(TransAllVarData(), "[%s] Failed to trans all var data", GetGraphName());
   GE_CHK_STATUS_RET(CopyVarData(), "[%s] Failed to copy var data", GetGraphName());
   GE_CHK_STATUS_RET(InitModelMem(), "[%s] Failed to init memory", GetGraphName());
-  GE_CHK_STATUS_RET(InitWeights(), "[%s] Failed to init weights", GetGraphName());
   GE_CHK_STATUS_RET(InitConstantOps(), "[%s] Failed to init constant op", GetGraphName());
   GE_CHK_STATUS_RET(InitVariableTensors(), "[%s] Failed to init variables", GetGraphName());
   GE_CHK_STATUS_RET(LoadTasks(), "[%s] Failed to load tasks", GetGraphName());
@@ -599,9 +599,10 @@ Status HybridModelBuilder::MergeNetOutputNode(ComputeGraph &graph) {
   return SUCCESS;
 }
 
-Status HybridModelBuilder::UnfoldSubgraphs(ComputeGraph &root_graph, ComputeGraphPtr &merged_graph) {
+Status HybridModelBuilder::UnfoldSubgraphs(ComputeGraphPtr &root_graph, ComputeGraphPtr &merged_graph) {
   merged_graph = MakeShared<ComputeGraph>("MergedGraph");
-  for (const auto &node : root_graph.GetDirectNode()) {
+  merged_graph->SetGraphUnknownFlag(root_graph->GetGraphUnknownFlag());
+  for (const auto &node : root_graph->GetDirectNode()) {
     GE_CHECK_NOTNULL(node);
     auto op_desc = node->GetOpDesc();
     GE_CHECK_NOTNULL(op_desc);
@@ -631,7 +632,7 @@ Status HybridModelBuilder::UnfoldSubgraphs(ComputeGraph &root_graph, ComputeGrap
         }
       }
     }
-    GE_CHK_GRAPH_STATUS_RET(UnfoldSubgraph(root_graph, *merged_graph, *subgraph),
+    GE_CHK_GRAPH_STATUS_RET(UnfoldSubgraph(root_graph, merged_graph, *subgraph),
                             "[%s] Failed to merge subgraph.",
                             subgraph->GetName().c_str());
   }
@@ -647,18 +648,19 @@ Status HybridModelBuilder::UnfoldSubgraphs(ComputeGraph &root_graph, ComputeGrap
     return a_level < b_level;
   });
 
-  for (auto &remained_subgraph : root_graph.GetAllSubgraphs()) {
+  for (auto &remained_subgraph : root_graph->GetAllSubgraphs()) {
     GELOGD("Adding subgraph [%s] to merged-graph.", remained_subgraph->GetName().c_str());
     GE_CHK_GRAPH_STATUS_RET(merged_graph->AddSubgraph(remained_subgraph),
                             "Failed to add subgraph [%s]",
                             remained_subgraph->GetName().c_str());
+    remained_subgraph->SetParentGraph(merged_graph);
   }
 
   return SUCCESS;
 }
 
-Status HybridModelBuilder::UnfoldSubgraph(ComputeGraph &root_graph,
-                                          ComputeGraph &parent_graph,
+Status HybridModelBuilder::UnfoldSubgraph(ComputeGraphPtr &root_graph,
+                                          ComputeGraphPtr &parent_graph,
                                           ComputeGraph &sub_graph) {
   auto parent_node = sub_graph.GetParentNode();
   GE_CHECK_NOTNULL(parent_node);
@@ -687,15 +689,23 @@ Status HybridModelBuilder::UnfoldSubgraph(ComputeGraph &root_graph,
       }
     }
 
-    parent_graph.AddNode(sub_node);
+    if (!sub_node->GetOpDesc()->GetSubgraphInstanceNames().empty()) {
+      for (size_t i = 0; i < sub_node->GetOpDesc()->GetSubgraphInstanceNames().size(); ++i) {
+        auto sub_sub_graph = NodeUtils::GetSubgraph(*sub_node, i);
+        GE_CHECK_NOTNULL(sub_sub_graph);
+        sub_sub_graph->SetParentGraph(parent_graph);
+      }
+    }
+    parent_graph->AddNode(sub_node);
     GELOGD("[%s::%s] added to parent graph: [%s].",
            sub_graph.GetName().c_str(),
            sub_node->GetName().c_str(),
-           parent_graph.GetName().c_str());
+           parent_graph->GetName().c_str());
+    sub_node->SetOwnerComputeGraph(parent_graph);
   }
 
   GELOGD("[%s] Done merging subgraph. remove it from root graph.", sub_graph.GetName().c_str());
-  root_graph.RemoveSubgraph(sub_graph.GetName());
+  root_graph->RemoveSubgraph(sub_graph.GetName());
   return SUCCESS;
 }
 
@@ -747,14 +757,14 @@ Status HybridModelBuilder::LoadGraph() {
     GELOGI("Before merging subgraphs DirectNodesSize = %zu, GetAllNodesSize = %zu",
            root_graph->GetDirectNodesSize(),
            root_graph->GetAllNodesSize());
-    GE_CHK_GRAPH_STATUS_RET(UnfoldSubgraphs(*root_graph, merged_graph), "Failed to unfold subgraphs.");
+    GE_CHK_GRAPH_STATUS_RET(UnfoldSubgraphs(root_graph, merged_graph), "Failed to unfold subgraphs.");
     root_graph = std::move(merged_graph);
     GELOGI("After merging subgraphs DirectNodesSize = %zu, GetAllNodesSize = %zu",
            root_graph->GetDirectNodesSize(),
            root_graph->GetAllNodesSize());
   }
 
-  root_graph_ = root_graph;
+  hybrid_model_.root_graph_ = root_graph;
   // Reset node id by topological order across all subgraphs
   int64_t index = 0;
   for (const auto &node : root_graph->GetAllNodes()) {
@@ -1030,9 +1040,13 @@ Status HybridModelBuilder::InitWeights() {
     GELOGI("Init weight mem successfully, weight base %p, weight size = %zu",
            weight_base,
            sub_weight_buffer->GetSize());
-    auto root_graph = GraphUtils::GetComputeGraph(subgraph_model.second->GetGraph());
-    hybrid_model_.weight_buffer_map_.emplace(root_graph->GetName(),std::move(sub_weight_buffer));
-    for (auto &node : root_graph->GetDirectNode()) {
+    auto subgraph = GraphUtils::GetComputeGraph(subgraph_model.second->GetGraph());
+    if (subgraph != ge_root_model_->GetRootGraph()) {
+      subgraph = ge_root_model_->GetRootGraph()->GetSubgraph(subgraph_model.first);
+    }
+    GE_CHECK_NOTNULL(subgraph);
+    hybrid_model_.weight_buffer_map_.emplace(subgraph->GetName(), std::move(sub_weight_buffer));
+    for (auto &node : subgraph->GetDirectNode()) {
       if (node->GetType() != CONSTANT) {
         continue;
       }
@@ -2044,7 +2058,7 @@ Status HybridModelBuilder::CollectParallelGroups(NodeItem *node_item) {
       GELOGD("[%s] Start to get parallel group from subgraph: %s",
              node_item->NodeName().c_str(),
              subgraph_name.c_str());
-      auto subgraph = root_graph_->GetSubgraph(subgraph_name);
+      auto subgraph = hybrid_model_.root_graph_->GetSubgraph(subgraph_name);
       GE_CHECK_NOTNULL(subgraph);
       for (const auto &sub_node : subgraph->GetAllNodes()) {
         std::string parallel_group;

ge/hybrid/model/hybrid_model_builder.h

@@ -47,8 +47,8 @@ class HybridModelBuilder {
   static Status HandleDtString(const GeTensor &tensor, void *var_addr);
   static Status MergeInputNodes(ComputeGraph &compute_graph);
   static Status MergeNetOutputNode(ComputeGraph &compute_graph);
-  static Status UnfoldSubgraphs(ComputeGraph &root_graph, ComputeGraphPtr &merged_graph);
-  static Status UnfoldSubgraph(ComputeGraph &root_graph, ComputeGraph &parent_graph, ComputeGraph &sub_graph);
+  static Status UnfoldSubgraphs(ComputeGraphPtr &root_graph, ComputeGraphPtr &merged_graph);
+  static Status UnfoldSubgraph(ComputeGraphPtr &root_graph, ComputeGraphPtr &parent_graph, ComputeGraph &sub_graph);
   static Status BuildInputMapping(GraphItem &graph_item,
                                   std::vector<NodeItem *> &data_nodes,
                                   bool is_root_graph);
@@ -100,7 +100,6 @@ class HybridModelBuilder {
   NodeItem *MutableNodeItem(const NodePtr &node);
 
   GeRootModelPtr ge_root_model_;
-  ComputeGraphPtr root_graph_;
   std::map<std::string, GeModelPtr> subgraph_models_;
   std::map<std::string, NodePtr> constant_op_nodes_;
   std::map<std::string, std::set<NodeItem *>> parallel_group_to_nodes_;

ge/hybrid/model/node_item.cc

@@ -297,7 +297,7 @@ void NodeItem::SetToDynamic() {
   }
 }
 
-GeTensorDescPtr NodeItem::MutableInputDesc(int index) const {
+GeTensorDescPtr NodeItem::DoGetInputDesc(int index) const {
   if (!has_optional_inputs) {
     return op_desc->MutableInputDesc(static_cast<uint32_t>(index));
   }
@@ -314,6 +314,40 @@ GeTensorDescPtr NodeItem::MutableInputDesc(int index) const {
   return op_desc->MutableInputDesc(input_desc_indices_[index]);
 }
 
+GeTensorDescPtr NodeItem::MutableInputDesc(int index) const {
+  std::lock_guard<std::mutex> lk(mu_);
+  return DoGetInputDesc(index);
+}
+
+Status NodeItem::GetInputDesc(int index, GeTensorDesc &tensor_desc) const {
+  std::lock_guard<std::mutex> lk(mu_);
+  auto input_desc = DoGetInputDesc(index);
+  GE_CHECK_NOTNULL(input_desc);
+  tensor_desc = *input_desc;
+  return SUCCESS;
+}
+
+Status NodeItem::GetOutputDesc(int index, GeTensorDesc &tensor_desc) const {
+  std::lock_guard<std::mutex> lk(mu_);
+  auto output_desc = op_desc->MutableOutputDesc(static_cast<uint32_t>(index));
+  GE_CHECK_NOTNULL(output_desc);
+  tensor_desc = *output_desc;
+  return SUCCESS;
+}
+
+GeTensorDescPtr NodeItem::MutableOutputDesc(int index) const {
+  std::lock_guard<std::mutex> lk(mu_);
+  return op_desc->MutableOutputDesc(static_cast<uint32_t>(index));
+}
+
+Status NodeItem::UpdateInputDesc(int index, const GeTensorDesc &tensor_desc) {
+  std::lock_guard<std::mutex> lk(mu_);
+  auto input_desc = DoGetInputDesc(index);
+  GE_CHECK_NOTNULL(input_desc);
+  *input_desc = tensor_desc;
+  return SUCCESS;
+}
+
 Status NodeItem::GetCanonicalInputIndex(uint32_t index, int &canonical_index) const {
   if (!has_optional_inputs) {
     canonical_index = index;

ge/hybrid/model/node_item.h

@@ -17,6 +17,7 @@
 #ifndef GE_HYBRID_MODEL_NODE_ITEM_H_
 #define GE_HYBRID_MODEL_NODE_ITEM_H_
 
+#include <mutex>
 #include <vector>
 #include "external/ge/ge_api_error_codes.h"
 #include "graph/node.h"
@@ -57,12 +58,16 @@ struct NodeItem {
 
   bool IsInputShapeStatic(int index) const;
 
-  GeTensorDescPtr MutableOutputDesc(int index) const {
-    return op_desc->MutableOutputDesc(static_cast<uint32_t>(index));
-  }
+  GeTensorDescPtr MutableOutputDesc(int index) const;
+
+  Status UpdateInputDesc(int index, const GeTensorDesc &tensor_desc);
 
   GeTensorDescPtr MutableInputDesc(int index) const;
 
+  Status GetInputDesc(int index, GeTensorDesc &tensor_desc) const;
+
+  Status GetOutputDesc(int index, GeTensorDesc &tensor_desc) const;
+
   Status GetCanonicalInputIndex(uint32_t index, int &canonical_index) const;
 
   bool IsControlOp() const;
@@ -113,9 +118,11 @@ struct NodeItem {
   Status ResolveDynamicState();
   Status ResolveStaticInputsAndOutputs();
   void ResolveUnknownShapeType();
+  GeTensorDescPtr DoGetInputDesc(int index) const;
 
   std::vector<bool> is_input_shape_static_;
   std::vector<uint32_t> input_desc_indices_;
+  mutable std::mutex mu_;
 };
 }  // namespace hybrid
 }  // namespace ge

ge/hybrid/node_executor/aicore/aicore_op_task.cc

@@ -307,11 +307,9 @@ Status AiCoreOpTask::UpdateTilingInfo(TaskContext &context) {
 
   auto execution_context = context.GetExecutionContext();
 
-  GetContext().SetSessionId(execution_context->context_id);
   RECORD_EXECUTION_EVENT(execution_context, context.GetNodeName(), "[CalcTilingInfo] Start");
   GE_CHK_STATUS_RET(CalcTilingInfo(node, tiling_info));
   RECORD_EXECUTION_EVENT(execution_context, context.GetNodeName(), "[CalcTilingInfo] End");
-  GetContext().SetSessionId(execution_context->session_id);
 
   // update op args by tiling info
   block_dim_ = static_cast<uint32_t>(tiling_info.block_dim);

ge/hybrid/node_executor/compiledsubgraph/known_node_executor.cc

@@ -105,11 +105,6 @@ Status KnownNodeTask::Init(TaskContext &context) {
         "known node task allocate workspace failed.");
     RECORD_EXECUTION_EVENT(context.GetExecutionContext(), context.GetNodeName(),
                            "[KnownNodeTask_AllocateWorkspace] End, size %zu", davinci_model_->TotalMemSize());
-    bool addr_not_changed = false;
-    if (davinci_model_->GetRuntimeParam().mem_base == buffer) {
-      addr_not_changed = true;
-    }
-    davinci_model_->SetKnownNodeAddrNotChanged(addr_not_changed);
     // update mem base
     davinci_model_->UpdateMemBase(static_cast<uint8_t *>(buffer));
     GELOGI("KnownNodeTask::Init mem base is %p, size %lu.",

ge/hybrid/node_executor/controlop/control_op_executor.cc

@@ -237,8 +237,8 @@ Status WhileOpNodeTask::DoExecuteAsync(TaskContext &task_context, const std::fun
   }
 
   bool is_continue = false;
-  GE_CHK_STATUS_RET(ExecuteOneLoop(task_context, is_continue),
-                    "[%s] Failed to execute iteration 0.",
+  GE_CHK_STATUS_RET(ExecuteCond(task_context, is_continue),
+                    "[%s] Failed to execute cond-subgraph",
                     task_context.GetNodeName());
   if (!is_continue) {
     for (int i = 0; i < task_context.NumInputs(); ++i) {
@@ -259,42 +259,28 @@ Status WhileOpNodeTask::DoExecuteAsync(TaskContext &task_context, const std::fun
   }
 
   // backup original input tensor desc
-  std::vector<GeTensorDesc> ori_input_desc;
+  std::vector<GeTensorDesc> ori_input_desc(task_context.NumInputs());
   for (int i = 0; i < task_context.NumInputs(); ++i) {
-    auto tensor_desc = task_context.GetInputDesc(i);
-    GE_CHECK_NOTNULL(tensor_desc);
-    ori_input_desc.emplace_back(*tensor_desc);
+    GE_CHK_STATUS_RET_NOLOG(task_context.GetInputDesc(i, ori_input_desc[i]));
   }
 
-  int iteration = 1;
-  while (true) {
+  int iteration = 0;
+  while (is_continue) {
+    ++iteration;
     GELOGD("[%s] Start to execute, iteration = %d", task_context.GetNodeName(), iteration);
     GE_CHK_STATUS_RET(ExecuteOneLoop(task_context, is_continue),
                       "[%s] Failed to execute iteration %d.",
                       task_context.GetNodeName(),
                       iteration);
-
-    if (!is_continue) {
-      GELOGD("[%s] Quit from loop. current iteration = %d", task_context.GetNodeName(), iteration);
-      break;
-    }
-
-    ++iteration;
   }
-
-  for (int i = 0; i < task_context.NumInputs(); ++i) {
-    auto input_tensor = task_context.GetInput(i);
-    auto tensor_desc = task_context.MutableInputDesc(i);
-    GE_CHECK_NOTNULL(input_tensor);
-    GE_CHECK_NOTNULL(tensor_desc);
-    // restore original input tensor desc
-    *tensor_desc = std::move(ori_input_desc[i]);
-    GE_CHK_STATUS_RET_NOLOG(task_context.SetOutput(i, *input_tensor));
-  }
-
+  GELOGD("[%s] Quit from loop. current iteration = %d", task_context.GetNodeName(), iteration);
   if (done_callback) {
     done_callback();
   }
+
+  for (int i = 0; i < task_context.NumInputs(); ++i) {
+    GE_CHK_STATUS_RET_NOLOG(task_context.UpdateInputDesc(i, ori_input_desc[i]));
+  }
   return SUCCESS;
 }
 
@@ -379,13 +365,6 @@ Status WhileOpNodeTask::MoveOutputs2Inputs(TaskContext &task_context) {
 }
 
 Status WhileOpNodeTask::ExecuteOneLoop(TaskContext &task_context, bool &is_continue) const {
-  GE_CHK_STATUS_RET(ExecuteCond(task_context, is_continue),
-                    "[%s] Failed to execute cond-subgraph",
-                    task_context.GetNodeName());
-  if (!is_continue) {
-    return SUCCESS;
-  }
-
   GELOGD("[%s] Start to execute body-subgraph.", task_context.GetNodeName());
   GE_CHK_STATUS_RET(ExecuteSubgraph(body_, task_context, nullptr),
                     "[%s] Failed to execute cond-subgraph", task_context.GetNodeName());
@@ -396,6 +375,17 @@ Status WhileOpNodeTask::ExecuteOneLoop(TaskContext &task_context, bool &is_conti
                     "[%s] Failed to move outputs to inputs",
                     task_context.GetNodeName());
 
+  GE_CHK_STATUS_RET(ExecuteCond(task_context, is_continue),
+                    "[%s] Failed to execute cond-subgraph",
+                    task_context.GetNodeName());
+
+  if (!is_continue) {
+    for (int i = 0; i < task_context.NumInputs(); ++i) {
+      auto input_desc = task_context.GetInput(i);
+      GE_CHECK_NOTNULL(input_desc);
+      GE_CHK_STATUS_RET_NOLOG(task_context.SetOutput(i, *input_desc));
+    }
+  }
   return SUCCESS;
 }
 

ge/hybrid/node_executor/controlop/control_op_executor.h

@@ -80,7 +80,6 @@ class WhileOpNodeTask : public ControlOpNodeTask {
   Status ExecuteCond(TaskContext &task_context, bool &is_continue) const;
 
   static Status MoveOutputs2Inputs(TaskContext &task_context);
-
   Status ExecuteOneLoop(TaskContext &task_context, bool &is_continue) const;
 
  private:

ge/hybrid/node_executor/task_context.cc

@@ -554,5 +554,16 @@ NodeState *TaskContext::GetNodeState() const {
   return node_state_;
 }
 
+Status TaskContext::GetInputDesc(int index, GeTensorDesc &tensor_desc) const {
+  return node_item_->GetInputDesc(index, tensor_desc);
+}
+
+Status TaskContext::UpdateInputDesc(int index, const GeTensorDesc &tensor_desc) {
+  return const_cast<NodeItem *>(node_item_)->UpdateInputDesc(index, tensor_desc);
+}
+
+Status TaskContext::GetOutputDesc(int index, GeTensorDesc &tensor_desc) const {
+  return node_item_->GetOutputDesc(index, tensor_desc);
+}
 }  // namespace hybrid
 }  // namespace ge

ge/hybrid/node_executor/task_context.h

@@ -50,9 +50,12 @@ class TaskContext {
   const char *GetNodeName() const;
   TensorValue *MutableInput(int index);
   ConstGeTensorDescPtr GetInputDesc(int index) const;
+  Status GetInputDesc(int index, GeTensorDesc &tensor_desc) const;
   ConstGeTensorDescPtr GetOutputDesc(int index) const;
+  Status GetOutputDesc(int index, GeTensorDesc &tensor_desc) const;
   GeTensorDescPtr MutableInputDesc(int index) const;
   GeTensorDescPtr MutableOutputDesc(int index) const;
+  Status UpdateInputDesc(int index, const GeTensorDesc &tensor_desc);
   void ReleaseInputsAndOutputs();
   bool NeedCallback();
   void ReleaseInput(int index);

ge/ir_build/atc_ir_common.cc

@@ -34,6 +34,8 @@ const int64_t kDynamicImageSizeNum = 2;
 const size_t kMaxDynamicDimNum = 100;
 const size_t kMaxNDDimNum = 4;
 const size_t kMinNDDimNum = 1;
+const size_t kSquareBracketsSize = 2;
+const size_t kRangePairSize = 2;
 // datatype/formats from user to GE, Unified to util interface file later
 const std::map<std::string, ge::DataType> kOutputTypeSupportDatatype = {
     {"FP32", ge::DT_FLOAT}, {"FP16", ge::DT_FLOAT16}, {"UINT8", ge::DT_UINT8}};
@@ -292,7 +294,8 @@ bool ParseSingleShapeRange(std::string &shape_range, vector<pair<int64_t, int64_
     }
   }
 
-  bool is_square_brackets = (square_brackets[0] == '[') && (square_brackets[1] == ']') && (square_brackets.size() == 2);
+  bool is_square_brackets = (square_brackets[0] == '[') && (square_brackets[1] == ']') &&
+                            (square_brackets.size() == kSquareBracketsSize);
   if (!is_square_brackets) {
     ErrorManager::GetInstance().ATCReportErrMessage("E10048", {"shape_range", "reason", "sample"},
                                                     {shape_range, kInputShapeRangeInvalid, kInputShapeRangeSample2});
@@ -320,7 +323,7 @@ bool ParseSingleShapeRange(std::string &shape_range, vector<pair<int64_t, int64_
       } else {
         range_pair = std::make_pair(range_value, range_value);
       }
-    } else if (range_pair_set.size() == 2) {
+    } else if (range_pair_set.size() == kRangePairSize) {
       // unknown dim, should get range.
       long range_left = 0;
       if (!StringToLongNoThrow(range_pair_set.at(0), range_left)) {
@@ -332,9 +335,10 @@ bool ParseSingleShapeRange(std::string &shape_range, vector<pair<int64_t, int64_
       }
       if (range_left < 0 || (range_right < 0)) {
         ErrorManager::GetInstance().ATCReportErrMessage("E10048", {"shape_range", "reason", "sample"},
-                                                        {shape_range, kInputShapeRangeInvalid, kInputShapeRangeSample3});
+            {shape_range, kInputShapeRangeInvalid, kInputShapeRangeSample3});
         GELOGE(PARAM_INVALID,
-               "Parse input parameter [--input_shape_range]'s shape range[%s] failed, reason: %s, correct sample is %s.",
+               "Parse input parameter [--input_shape_range]'s shape range[%s] failed,"
+               "reason: %s, correct sample is %s.",
                shape_range.c_str(), kInputShapeRangeInvalid, kInputShapeRangeSample3);
         return false;
       }
@@ -383,7 +387,7 @@ bool ParseInputShapeRange(const std::string &shape_range,
     }
     shape_range_map.emplace(make_pair(StringUtils::Trim(shape_range_pair_vec[0]), shape_range_val));
   }
-  
+
   return true;
 }
 
@@ -402,7 +406,7 @@ Status CheckDynamicInputParamValid(string &dynamic_batch_size, string &dynamic_i
   if (param_size == 0) {
     if (!input_shape_range.empty()) {
       std::map<string, std::vector<std::pair<int64_t, int64_t>>> shape_range_map;
-      if(!ParseInputShapeRange(input_shape_range, shape_range_map)) {
+      if (!ParseInputShapeRange(input_shape_range, shape_range_map)) {
         GELOGE(ge::PARAM_INVALID, "Failed to parse input shape range: %s", input_shape_range.c_str());
         return ge::PARAM_INVALID;
       }

ge/session/omg.cc

@@ -793,7 +793,7 @@ FMK_FUNC_HOST_VISIBILITY Status ParseGraph(ge::Graph &graph, const std::map<stri
   std::string input_shape_range;
   ParseAtcParms(atc_params, INPUT_SHAPE_RANGE, input_shape_range);
   GE_RETURN_WITH_LOG_IF_ERROR(UpdateDynamicInputShapeRange(compute_graph, input_shape_range),
-                             "Update input shape range failed");
+                              "Update input shape range failed");
 
   GELOGI("ATC parser success.");
 

inc/framework/common/debug/ge_log.h

@@ -42,9 +42,9 @@ class GE_FUNC_VISIBILITY GeLog {
  public:
   static uint64_t GetTid() {
 #ifdef __GNUC__
-    thread_local static uint64_t tid = static_cast<uint64_t>(syscall(__NR_gettid));
+    uint64_t tid = static_cast<uint64_t>(syscall(__NR_gettid));
 #else
-    thread_local static uint64_t tid = static_cast<uint64_t>(GetCurrentThreadId());
+    uint64_t tid = static_cast<uint64_t>(GetCurrentThreadId());
 #endif
     return tid;
   }

inc/framework/common/string_util.h

@@ -52,7 +52,7 @@ class GE_FUNC_VISIBILITY StringUtils {
     return s;
   }
   // lint -esym(551,*)
-  static std::string &Rtrim(std::string &s) {  /*lint !e618*/
+  static std::string &Rtrim(std::string &s) { /*lint !e618*/
 #if __cplusplus >= 201103L
     (void)s.erase(s.begin(), std::find_if(s.begin(), s.end(), [](int c) { return !std::isspace(c); }));
 #else
@@ -76,8 +76,8 @@ class GE_FUNC_VISIBILITY StringUtils {
   ///  @param [in] delim  separator
   ///  @return string array after segmentation
   ///
-  static std::vector<std::string> Split(const std::string &str, char delim) {
-    std::vector<std::string> elems;
+  static std::vector<std::string> Split(const std::string &str, char delim) { /*lint !e1077*/
+    std::vector<std::string> elems;                                           /*lint !e1077*/
 
     if (str.empty()) {
       elems.emplace_back("");

metadef

@@ -1 +1 @@
-Subproject commit 0c4602a4615a9368b06633a5087e2114518f29ca
+Subproject commit 8cf3c51d53a9f4ebd6d601a2383f62788e3b8176

tests/ut/ge/common/format_transfer_unittest.cc

@@ -52,34 +52,34 @@ TEST_F(UtestFormatTransfer, build_unsupported_transfer) {
   EXPECT_EQ(transfer2, nullptr);
 }
 
-// TEST_F(UtestFormatTransfer, get_size_by_data_type) {
-//   EXPECT_EQ(GetSizeByDataType(DT_FLOAT), 4);
-//   EXPECT_EQ(GetSizeByDataType(DT_FLOAT16), 2);
-//   EXPECT_EQ(GetSizeByDataType(DT_INT8), 1);
-//   EXPECT_EQ(GetSizeByDataType(DT_INT16), 2);
-//   EXPECT_EQ(GetSizeByDataType(DT_UINT16), 2);
-//   EXPECT_EQ(GetSizeByDataType(DT_UINT8), 1);
-//   EXPECT_EQ(GetSizeByDataType(DT_INT32), 4);
-//   EXPECT_EQ(GetSizeByDataType(DT_INT64), 8);
-//   EXPECT_EQ(GetSizeByDataType(DT_UINT32), 4);
-//   EXPECT_EQ(GetSizeByDataType(DT_UINT64), 8);
-//   EXPECT_EQ(GetSizeByDataType(DT_BOOL), 1);
-//   EXPECT_EQ(GetSizeByDataType(DT_DOUBLE), 8);
-//   EXPECT_EQ(GetSizeByDataType(DT_STRING), -1);
-//   EXPECT_EQ(GetSizeByDataType(DT_DUAL_SUB_INT8), 1);
-//   EXPECT_EQ(GetSizeByDataType(DT_DUAL_SUB_UINT8), 1);
-//   EXPECT_EQ(GetSizeByDataType(DT_COMPLEX64), 8);
-//   EXPECT_EQ(GetSizeByDataType(DT_COMPLEX128), 16);
-//   EXPECT_EQ(GetSizeByDataType(DT_QINT8), 1);
-//   EXPECT_EQ(GetSizeByDataType(DT_QINT16), 2);
-//   EXPECT_EQ(GetSizeByDataType(DT_QINT32), 4);
-//   EXPECT_EQ(GetSizeByDataType(DT_QUINT8), 1);
-//   EXPECT_EQ(GetSizeByDataType(DT_QUINT16), 2);
-//   EXPECT_EQ(GetSizeByDataType(DT_RESOURCE), -1);
-//   EXPECT_EQ(GetSizeByDataType(DT_STRING_REF), -1);
-//   EXPECT_EQ(GetSizeByDataType(DT_DUAL), 5);
-//   EXPECT_EQ(GetSizeByDataType(DT_UNDEFINED), -1);
-//   EXPECT_EQ(DT_UNDEFINED, 27);
-// }
+TEST_F(UtestFormatTransfer, get_size_by_data_type) {
+  EXPECT_EQ(GetSizeByDataType(DT_FLOAT), 4);
+  EXPECT_EQ(GetSizeByDataType(DT_FLOAT16), 2);
+  EXPECT_EQ(GetSizeByDataType(DT_INT8), 1);
+  EXPECT_EQ(GetSizeByDataType(DT_INT16), 2);
+  EXPECT_EQ(GetSizeByDataType(DT_UINT16), 2);
+  EXPECT_EQ(GetSizeByDataType(DT_UINT8), 1);
+  EXPECT_EQ(GetSizeByDataType(DT_INT32), 4);
+  EXPECT_EQ(GetSizeByDataType(DT_INT64), 8);
+  EXPECT_EQ(GetSizeByDataType(DT_UINT32), 4);
+  EXPECT_EQ(GetSizeByDataType(DT_UINT64), 8);
+  EXPECT_EQ(GetSizeByDataType(DT_BOOL), 1);
+  EXPECT_EQ(GetSizeByDataType(DT_DOUBLE), 8);
+  EXPECT_EQ(GetSizeByDataType(DT_STRING), -1);
+  EXPECT_EQ(GetSizeByDataType(DT_DUAL_SUB_INT8), 1);
+  EXPECT_EQ(GetSizeByDataType(DT_DUAL_SUB_UINT8), 1);
+  EXPECT_EQ(GetSizeByDataType(DT_COMPLEX64), 8);
+  EXPECT_EQ(GetSizeByDataType(DT_COMPLEX128), 16);
+  EXPECT_EQ(GetSizeByDataType(DT_QINT8), 1);
+  EXPECT_EQ(GetSizeByDataType(DT_QINT16), 2);
+  EXPECT_EQ(GetSizeByDataType(DT_QINT32), 4);
+  EXPECT_EQ(GetSizeByDataType(DT_QUINT8), 1);
+  EXPECT_EQ(GetSizeByDataType(DT_QUINT16), 2);
+  EXPECT_EQ(GetSizeByDataType(DT_RESOURCE), 8);
+  EXPECT_EQ(GetSizeByDataType(DT_STRING_REF), -1);
+  EXPECT_EQ(GetSizeByDataType(DT_DUAL), 5);
+  EXPECT_EQ(GetSizeByDataType(DT_UNDEFINED), -1);
+  EXPECT_EQ(DT_UNDEFINED, 28);
+}
 }  // namespace formats
 }  // namespace ge

tests/ut/ge/graph/load/davinci_model_unittest.cc

@@ -141,6 +141,12 @@ TEST_F(UtestDavinciModel, init_success) {
   ProfilingManager::Instance().is_load_profiling_ = false;
 }
 
+TEST_F(UtestDavinciModel, CheckCapability) {
+  DavinciModel model(0, nullptr);
+  bool is_support = false;
+  (void)model.CheckCapability(FEATURE_TYPE_MEMORY, MEMORY_INFO_TS_4G_LIMITED, is_support);
+}
+
 TEST_F(UtestDavinciModel, init_data_op) {
   DavinciModel model(0, nullptr);
   model.ge_model_ = make_shared<GeModel>();

tests/ut/ge/graph/load/model_utils_unittest.cc

@@ -67,4 +67,22 @@ TEST_F(UtestModelUtils, get_var_addr_rdma_hbm) {
   EXPECT_EQ(reinterpret_cast<uint8_t *>(offset), var_addr);
   VarManager::Instance(runtime_param.session_id)->Destory();
 }
+
+TEST_F(UtestModelUtils, get_var_addr_rdma_hbm_negative_offset) {
+  uint8_t test = 2;
+  uint8_t *pf = &test;
+  RuntimeParam runtime_param;
+  runtime_param.session_id = 0;
+  runtime_param.logic_var_base = 0;
+  runtime_param.var_base = pf;
+
+  int64_t offset = -1;
+  EXPECT_EQ(VarManager::Instance(runtime_param.session_id)->Init(0, 0, 0, 0), SUCCESS);
+  EXPECT_NE(VarManager::Instance(runtime_param.session_id)->var_resource_, nullptr);
+  VarManager::Instance(runtime_param.session_id)->var_resource_->var_offset_map_[offset] = RT_MEMORY_RDMA_HBM;
+  std::shared_ptr<OpDesc> op_desc = std::make_shared<OpDesc>("test", "test");
+  uint8_t *var_addr = nullptr;
+  EXPECT_NE(ModelUtils::GetVarAddr(runtime_param, op_desc, offset, var_addr), SUCCESS);
+  VarManager::Instance(runtime_param.session_id)->Destory();
+}
 }  // namespace ge

tests/ut/ge/hybrid/ge_hybrid_unittest.cc

@@ -256,3 +256,77 @@ TEST_F(UtestGeHybrid, init_weight_success) {
   HybridModelExecutor executor(model_ptr, device_id, stream);
   executor.Init();
 }
+
+TEST_F(UtestGeHybrid, unfold_subgraphs_success) {
+ComputeGraphPtr merged_graph = nullptr;
+
+ComputeGraphPtr sub_sub_graph1 = std::make_shared<ComputeGraph>("while_cond");
+OpDescPtr sub_sub_graph_while_cond_data_op_desc = CreateOpDesc("cond_data", DATA);
+NodePtr sub_sub_graph_while_cond_data_node = sub_sub_graph1->AddNode(sub_sub_graph_while_cond_data_op_desc);
+
+ComputeGraphPtr sub_sub_graph2 = std::make_shared<ComputeGraph>("while_body");
+/*OpDescPtr sub_sub_graph_while_body_const_op_desc = CreateOpDesc("body_const", CONSTANT);
+NodePtr sub_sub_graph_while_body_const_node = sub_sub_graph2->AddNode(sub_sub_graph_while_body_const_op_desc);*/
+OpDescPtr sub_sub_graph_while_body_data_op_desc = CreateOpDesc("body_data", DATA);
+NodePtr sub_sub_graph_while_body_data_node = sub_sub_graph2->AddNode(sub_sub_graph_while_body_data_op_desc);
+sub_sub_graph2->SetGraphUnknownFlag(true);
+/*OpDescPtr sub_sub_graph_while_body_add_op_desc = CreateOpDesc("body_add", ADD);
+NodePtr sub_sub_graph_while_body_add_node = sub_sub_graph2->AddNode(sub_sub_graph_while_body_add_node);
+sub_sub_graph_while_body_add_node->AddLinkFrom(sub_sub_graph_while_body_data_node);
+sub_sub_graph_while_body_add_node->AddLinkFrom(sub_sub_graph_while_body_const_node);*/
+
+ComputeGraphPtr sub_graph = std::make_shared<ComputeGraph>("sub_graph");
+OpDescPtr sub_graph_while_op_desc = CreateOpDesc("while", WHILE);
+NodePtr sub_graph_while_node = sub_graph->AddNode(sub_graph_while_op_desc);
+sub_graph->SetGraphUnknownFlag(true);
+sub_graph_while_node->GetOpDesc()->AddSubgraphName("while_cond");
+sub_graph_while_node->GetOpDesc()->AddSubgraphName("while_body");
+sub_graph_while_node->GetOpDesc()->SetSubgraphInstanceName(0, "while_cond");
+sub_graph_while_node->GetOpDesc()->SetSubgraphInstanceName(1, "while_body");
+
+ComputeGraphPtr root_graph = std::make_shared<ComputeGraph>("root_graph");
+auto partitioned_call_op_desc = MakeShared<OpDesc>("partitioned_call", PARTITIONEDCALL);
+auto partitioned_call_node = root_graph->AddNode(partitioned_call_op_desc);
+partitioned_call_node->GetOpDesc()->AddSubgraphName("sub_graph");
+partitioned_call_node->GetOpDesc()->SetSubgraphInstanceName(0, "sub_graph");
+
+root_graph->AddSubGraph(sub_sub_graph1);
+root_graph->AddSubGraph(sub_sub_graph2);
+sub_sub_graph1->SetParentGraph(root_graph);
+sub_sub_graph2->SetParentGraph(root_graph);
+sub_sub_graph1->SetParentNode(sub_graph_while_node);
+sub_sub_graph2->SetParentNode(sub_graph_while_node);
+
+root_graph->AddSubGraph(sub_graph);
+sub_graph->SetParentNode(partitioned_call_node);
+sub_graph->SetParentGraph(root_graph);
+
+GeRootModelPtr root_model = MakeShared<ge::GeRootModel>(root_graph);
+HybridModel hybrid_model(root_model);
+HybridModelBuilder hybrid_model_builder(hybrid_model);
+
+// subgraph num before unfold: 1
+EXPECT_EQ(root_graph->GetAllSubgraphs().size(), 3);
+// num of nodes in root_graph before unfold: 1, name: partitioned_call
+EXPECT_EQ(root_graph->GetDirectNodesSize(), 1);
+EXPECT_EQ(root_graph->GetDirectNode().at(0)->GetName(), "partitioned_call");
+// two sub_sub_graphs: while cond & while body, their parent graph is "subgraph" before unfold
+EXPECT_EQ(sub_sub_graph1->GetParentGraph()->GetName(), "root_graph");
+EXPECT_EQ(sub_sub_graph1->GetParentGraph()->GetName(), "root_graph");
+// node "cond_data" & "body_data" has owner compute graph "subgraph" before unfold
+EXPECT_EQ(sub_graph_while_node->GetOwnerComputeGraph()->GetName(), "sub_graph");
+
+// unfold success
+EXPECT_EQ(hybrid_model_builder.UnfoldSubgraphs(root_graph, merged_graph), SUCCESS);
+
+// subgraph num after unfold: 0
+EXPECT_EQ(merged_graph->GetAllSubgraphs().size(), 2);
+// num of nodes in MergedGraph after unfold: 1, name: while
+EXPECT_EQ(merged_graph->GetDirectNodesSize(), 1);
+EXPECT_EQ(merged_graph->GetDirectNode().at(0)->GetName(), "while");
+// two sub_sub_graphs: while cond & while body, their parent graph is "MergedGraph" after unfold
+EXPECT_EQ(sub_sub_graph1->GetParentGraph()->GetName(), "MergedGraph" );
+EXPECT_EQ(sub_sub_graph1->GetParentGraph()->GetName(), "MergedGraph");
+// node "cond_data" & "body_data" has owner compute graph "MergedGraph" before unfold
+EXPECT_EQ(sub_graph_while_node->GetOwnerComputeGraph()->GetName(), "MergedGraph");
+}