diff --git a/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID3057_FwFM_performance_1p.sh b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID3057_FwFM_performance_1p.sh
new file mode 100644
index 0000000000000000000000000000000000000000..1628b9c5292581707356711f8c5621913a8a0770
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID3057_FwFM_performance_1p.sh
@@ -0,0 +1,169 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+
+#集合通信参数,不需要修改
+
+export RANK_SIZE=1
+export JOB_ID=10087
+RANK_ID_START=0
+RankSize=1
+# 数据集路径,保持为空,不需要修改
+data_path=""
+#export ASCEND_SLOG_PRINT_TO_STDOUT=1
+
+#使能RT2.0
+export ENABLE_RUNTIME_V2=1
+
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="FwFM_ID3057_for_TensorFlow"
+#训练epoch
+train_epochs=5
+#训练batch_size
+batch_size=128
+#训练step
+train_steps=
+#学习率
+learning_rate=
+
+#维测参数，precision_mode需要模型审视修改
+precision_mode="allow_fp32_to_fp16"
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+
+# 帮助信息，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_performance_1P.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --precision_mode         precision mode(allow_fp32_to_fp16/force_fp16/must_keep_origin_dtype/allow_mix_precision)
+    --over_dump		           if or not over detection, default is False
+    --data_dump_flag		     data dump flag, default is False
+    --data_dump_step		     data dump step, default is 10
+    --profiling		           if or not profiling for performance debug, default is False
+	--data_path		           source data of training
+    -h/--help		             show help message
+    "
+    exit 1
+fi
+
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+#进入训练脚本目录，需要模型审视修改
+cd $cur_path/../examples
+
+sed -i "s|epochs=10|epochs=5|g" run_fwfm.py
+
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $ASCEND_DEVICE_ID"
+    export RANK_ID=$RANK_ID
+
+    #创建DeviceID输出目录，不需要修改
+    if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+    
+    #执行训练脚本，以下传参不需要修改，其他需要模型审视修改
+    #--data_dir, --model_dir, --precision_mode, --over_dump, --over_dump_path，--data_dump_flag，--data_dump_step，--data_dump_path，--profiling，--profiling_dump_path
+    nohup python3 run_fwfm.py \
+        --data_dir=${data_path} \
+        --precision_mode=${precision_mode} \
+        --profiling=${profiling} \
+        --profiling_dump_path=${profiling_dump_path} > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+done 
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+sed -i "s|epochs=5|epochs=10|g" run_fwfm.py
+
+#结果打印，不需要修改
+echo "------------------ Final result ------------------"
+# #输出性能FPS，需要模型审视修改
+
+Time=`cat $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|tr -d '\b\r'|grep -Eo "[0-9]*us/sample"|awk -F "us/sample" 'END {print $1}'`
+FPS=`awk 'BEGIN{printf "%.2f\n", 1 /'${Time}'*1000000}'`
+#打印，不需要修改
+echo "Final Performance item/sec : $FPS"
+
+
+# #输出训练精度,需要模型审视修改
+train_accuracy=`grep "test AUC" ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log|awk '{print $3}'`
+# #打印，不需要修改
+echo "Final Train Accuracy : ${train_accuracy}"
+echo "E2E Training Duration sec : $e2e_time"
+
+#性能看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'RT2'_'perf'
+
+##获取性能数据，不需要修改
+#吞吐量
+
+ActualFPS=${FPS}
+#单迭代训练时长
+TrainingTime=`awk 'BEGIN{printf "%.2f\n",'${BatchSize}'/'${FPS}'}'`
+
+#从train_$ASCEND_DEVICE_ID.log提取Loss到train_${CaseName}_loss.txt中，需要根据模型审视
+cat $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log|tr -d '\b\r'|grep -Eo " loss: [0-9]*\.[0-9]*"|awk -F " " '{print $2}' > $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+
+#最后一个迭代loss值，不需要修改
+ActualLoss=`awk 'END {print}' $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainAccuracy = ${train_accuracy}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+
diff --git a/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID4032_DCNMix_performance_1p.sh b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID4032_DCNMix_performance_1p.sh
new file mode 100644
index 0000000000000000000000000000000000000000..69844cd5f0e28fa8d0b685753919365a0e9b8dc1
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID4032_DCNMix_performance_1p.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+#集合通信参数,不需要修改
+export RANK_SIZE=1
+export JOB_ID=10087
+RANK_ID_START=0
+
+#使能RT2.0
+export ENABLE_RUNTIME_V2=1
+# 数据集路径,保持为空,不需要修改
+data_path=""
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="DCNMix_ID4032_for_TensorFlow"
+#训练epoch
+train_epochs=1
+#训练batch_size
+batch_size=10240
+#训练step
+train_steps=100
+#学习率
+learning_rate=
+
+#维测参数，precision_mode需要模型审视修改
+precision_mode="allow_fp32_to_fp16"
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+
+# 帮助信息，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_performance_1P.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --precision_mode         precision mode(allow_fp32_to_fp16/force_fp16/must_keep_origin_dtype/allow_mix_precision)
+    --over_dump		           if or not over detection, default is False
+    --data_dump_flag		     data dump flag, default is False
+    --data_dump_step		     data dump step, default is 10
+    --profiling		           if or not profiling for performance debug, default is False
+	--data_path		           source data of training
+    -h/--help		             show help message
+    "
+    exit 1
+fi
+
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+#进入训练脚本目录，需要模型审视修改
+cd $cur_path/../examples
+
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $ASCEND_DEVICE_ID"
+    export RANK_ID=$RANK_ID
+
+    #创建DeviceID输出目录，不需要修改
+    if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+    
+    #执行训练脚本，以下传参不需要修改，其他需要模型审视修改
+    #--data_dir, --model_dir, --precision_mode, --over_dump, --over_dump_path，--data_dump_flag，--data_dump_step，--data_dump_path，--profiling，--profiling_dump_path
+    nohup python3 run_dcnmix.py \
+        --data_path=${data_path} \
+        --train_batch_size=${batch_size} \
+        --eval_batch_size=${batch_size} \
+        --num_epochs=${train_epochs} \
+        --max_steps=${train_steps} \
+        --output_dir=${cur_path}/output/$ASCEND_DEVICE_ID/ckpt > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+done 
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+
+#结果打印，不需要修改
+echo "------------------ Final result ------------------"
+# #输出性能FPS，需要模型审视修改
+fps=`grep "examples\/sec" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | awk '{print $2}'|tail -n +5 |awk '{sum+=$1} END {print sum/NR}'`
+FPS=`awk 'BEGIN{printf "%.2f\n", '${fps}'}'`
+# #打印，不需要修改
+echo "Final Performance item/sec : $FPS"
+
+echo "E2E Training Duration sec : $e2e_time"
+
+#性能看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'RT2'_'perf'
+
+##获取性能数据，不需要修改
+#吞吐量
+TrainingTime=`awk 'BEGIN{printf "%.6f\n",'${BatchSize}'/'${FPS}'}'`
+
+ActualFPS=${FPS}
+grep ":loss =" $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log| awk '{print $3}' | sed 's/,//g' > $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+#最后一个迭代loss值，不需要修改
+ActualLoss=`awk 'END {print}' $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
diff --git a/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID4032_DCNMix_performance_8p.sh b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID4032_DCNMix_performance_8p.sh
new file mode 100644
index 0000000000000000000000000000000000000000..b0430aec697649cf28a1c81ebc21178d4d72b8a6
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepCTR_Series_for_TensorFlow/test/train_RT2_ID4032_DCNMix_performance_8p.sh
@@ -0,0 +1,153 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+#集合通信参数,不需要修改
+export RANK_SIZE=8
+export RANK_TABLE_FILE=${cur_path}/rank_8p.json
+export JOB_ID=10087
+RANK_ID_START=0
+
+#使能RT2.0
+export ENABLE_RUNTIME_V2=1
+# 数据集路径,保持为空,不需要修改
+data_path=""
+#基础参数，需要模型审视修改
+#网络名称，同目录名称
+Network="DCNMix_ID4032_for_TensorFlow"
+#训练epoch
+train_epochs=1
+#训练batch_size
+batch_size=10240
+#训练step
+train_steps=100
+#学习率
+learning_rate=
+
+#维测参数，precision_mode需要模型审视修改
+precision_mode="allow_fp32_to_fp16"
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+
+# 帮助信息，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_performance_1P.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --precision_mode         precision mode(allow_fp32_to_fp16/force_fp16/must_keep_origin_dtype/allow_mix_precision)
+    --over_dump		           if or not over detection, default is False
+    --data_dump_flag		     data dump flag, default is False
+    --data_dump_step		     data dump step, default is 10
+    --profiling		           if or not profiling for performance debug, default is False
+	--data_path		           source data of training
+    -h/--help		             show help message
+    "
+    exit 1
+fi
+
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+#进入训练脚本目录，需要模型审视修改
+cd $cur_path/../examples
+
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $RANK_ID"
+    export RANK_ID=$RANK_ID
+    export ASCEND_DEVICE_ID=$RANK_ID
+
+    #创建DeviceID输出目录，不需要修改
+    if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+    
+    #执行训练脚本，以下传参不需要修改，其他需要模型审视修改
+    #--data_dir, --model_dir, --precision_mode, --over_dump, --over_dump_path，--data_dump_flag，--data_dump_step，--data_dump_path，--profiling，--profiling_dump_path
+    nohup python3 run_dcnmix.py \
+        --data_path=${data_path} \
+        --train_batch_size=${batch_size} \
+        --eval_batch_size=${batch_size} \
+        --num_epochs=${train_epochs} \
+        --max_steps=${train_steps} \
+        --output_dir=${cur_path}/output/$ASCEND_DEVICE_ID/ckpt > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+done 
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+
+#结果打印，不需要修改
+echo "------------------ Final result ------------------"
+# #输出性能FPS，需要模型审视修改
+fps=`grep "examples\/sec" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | awk '{print $2}'|tail -n +5 |awk '{sum+=$1} END {print sum/NR}'`
+FPS=`awk 'BEGIN{printf "%.2f\n", '${fps}'}'`
+# #打印，不需要修改
+echo "Final Performance item/sec : $FPS"
+
+echo "E2E Training Duration sec : $e2e_time"
+
+#性能看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'RT2'_'perf'
+
+##获取性能数据，不需要修改
+#吞吐量
+TrainingTime=`awk 'BEGIN{printf "%.6f\n",'${BatchSize}'/'${FPS}'}'`
+
+ActualFPS=${FPS}
+grep ":loss =" $cur_path/output/$ASCEND_DEVICE_ID/train_$ASCEND_DEVICE_ID.log| awk '{print $3}' | sed 's/,//g' > $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt
+#最后一个迭代loss值，不需要修改
+ActualLoss=`awk 'END {print}' $cur_path/output/$ASCEND_DEVICE_ID/train_${CaseName}_loss.txt`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
diff --git a/TensorFlow/built-in/recommendation/DeepFM_ID0030_for_TensorFlow/test/train_RT2_performance_1p.sh b/TensorFlow/built-in/recommendation/DeepFM_ID0030_for_TensorFlow/test/train_RT2_performance_1p.sh
new file mode 100644
index 0000000000000000000000000000000000000000..f860ce5c383c4cdc65c5bb78d751137f309f9056
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepFM_ID0030_for_TensorFlow/test/train_RT2_performance_1p.sh
@@ -0,0 +1,162 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+
+#集合通信参数,不需要修改
+#保证rank table file 文件rank_table_8p.json存放在和test同级的configs目录下
+export RANK_SIZE=1
+batch_size=16000
+#unset RANK_TABLE_FILE
+#export RANK_TABLE_FILE=${cur_path}/../configs/rank_table_8p.json
+export JOB_ID=10087
+RANK_ID_START=0
+export FLAG_ENABLE_DUMP=False
+export DUMP_PATH=/var/log/npu/dump
+export DUMP_STEP="0|2"
+export DUMP_MODE="all"
+mkdir -p $DUMP_PATH
+
+#使能RT2.0
+export ENABLE_RUNTIME_V2=1
+# 数据集路径,保持为空,不需要修改
+data_path=""
+
+#设置默认日志级别,不需要修改
+#export ASCEND_GLOBAL_LOG_LEVEL=3
+
+#基础参数 需要模型审视修改
+#网络名称，同目录名称
+Network="DeepFM_ID0030_for_TensorFlow"
+
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+#参数校验，不需要修改
+if [[ $1 == --help || $1 == -h ]];then
+    echo"usage:./train_full_8p.sh <args>"
+    echo " "
+    echo "parameter explain:
+    --precision_mode           precision mode(allow_fp32_to_fp16/force_fp16/must_keep_origin_dtype/allow_mix_precision)
+    --over_dump		           if or not over detection, default is False
+    --data_dump_flag		   data dump flag, default is 0
+    --data_dump_step		   data dump step, default is 10
+    --profiling		           if or not profiling for performance debug, default is False
+    --autotune                 whether to enable autotune, default is False
+    --data_path		           source data of training
+    -h/--help		           show help message
+    "
+    exit 1
+fi
+
+#帮助信息，不需要修改
+
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --autotune* ]];then
+        autotune=`echo ${para#*=}`
+		autotune=True
+        #开autotune特有环境变量
+		export autotune=True
+		export REPEAT_TUNE=True
+		export ASCEND_DEVICE_ID=0
+		export ENABLE_TUNE_BANK=True
+		export TE_PARALLEL_COMPILER=32
+        mv $install_path/fwkacllib/data/rl/Ascend910/custom $install_path/fwkacllib/data/rl/Ascend910/custom_bak
+        mv $install_path/fwkacllib/data/tiling/Ascend910/custom $install_path/fwkacllib/data/tiling/Ascend910/custom_bak
+        autotune_dump_path=${cur_path}/output/autotune_dump
+        mkdir -p ${autotune_dump_path}/GA
+        mkdir -p ${autotune_dump_path}/rl
+        cp -rf $install_path/fwkacllib/data/tiling/Ascend910/custom ${autotune_dump_path}/GA/
+        cp -rf $install_path/fwkacllib/data/rl/Ascend910/custom ${autotune_dump_path}/RL/
+		sed -i 's/n_epoches = 20/n_epoches = 1/g' ../configs/configs.py 
+		sed -i 's/iteration_per_loop = 10/iteration_per_loop = 1/g' ../configs/config.py
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+          sed -i 's/n_epoches = 1/n_epoches = 20/g' ../configs/config.py 
+          sed -i 's/iteration_per_loop = 1/iteration_per_loop = 10/g' ../configs/config.py
+    exit 1	
+fi
+sed -i 's/record_path = "/autotest/CI_daily/ModelZoo_DeepFM_TF/data/deepfm"/record_path = "$data_path"/g' ../configs/config.py
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    #设置环境变量，不需要修改
+    echo "Device ID: $ASCEND_DEVICE_ID"
+    export RANK_ID=$RANK_ID
+    #export ASCEND_DEVICE_ID=$RANK_ID
+	#创建DeviceID输出目录
+	if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+
+EXEC_DIR=$(pwd)
+#RESULTS=results/1p
+#mkdir -p ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}		
+#rm -rf ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}/*
+#cd ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}
+#env > ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}.log
+
+    python3.7 ${EXEC_DIR}/../train.py > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 
+
+done
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+#结果打印，不需要修改
+echo "E2E training Duration sec: $e2e_time"
+
+#稳定性精度看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}_bs${BatchSize}_${RANK_SIZE}'p'_'RT2'_'perf'
+ActualFPS=`grep "fps" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | awk 'END {print $22}'`
+temp1=`echo "1000 * ${batch_size}"|bc`
+TrainingTime=`echo "scale=2;${temp1} / ${ActualFPS}"|bc`
+
+ActualLoss=`grep "loss" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | awk 'END {print $9}' |tr -d ,`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+sed -i -e '/ModuleNotFoundError/d' $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log
diff --git a/TensorFlow/built-in/recommendation/DeepFM_ID0030_for_TensorFlow/test/train_RT2_performance_8p.sh b/TensorFlow/built-in/recommendation/DeepFM_ID0030_for_TensorFlow/test/train_RT2_performance_8p.sh
new file mode 100644
index 0000000000000000000000000000000000000000..8af3778c21f2df0d33e626717f24947e236ec6bb
--- /dev/null
+++ b/TensorFlow/built-in/recommendation/DeepFM_ID0030_for_TensorFlow/test/train_RT2_performance_8p.sh
@@ -0,0 +1,173 @@
+#!/bin/bash
+
+#当前路径,不需要修改
+cur_path=`pwd`
+
+#集合通信参数,不需要修改
+#保证rank table file 文件rank_table_8p.json存放在和test同级的configs目录下
+export RANK_SIZE=8
+batch_size=16000
+export RANK_TABLE_FILE=${cur_path}/../configs/rank_table_8p.json
+export JOB_ID=10087
+RANK_ID_START=0
+
+export FLAG_ENABLE_DUMP=False
+export DUMP_PATH=/var/log/npu/dump
+export DUMP_STEP="0|2"
+export DUMP_MODE="all"
+mkdir -p $DUMP_PATH
+
+#使能RT2.0
+export ENABLE_RUNTIME_V2=1
+
+# 数据集路径,保持为空,不需要修改
+data_path=""
+
+#设置默认日志级别,不需要修改
+#export ASCEND_GLOBAL_LOG_LEVEL=3
+
+#基础参数 需要模型审视修改
+#网络名称，同目录名称
+Network="DeepFM_ID0030_for_TensorFlow"
+
+#维持参数，以下不需要修改
+over_dump=False
+data_dump_flag=False
+data_dump_step="10"
+profiling=False
+#参数校验，不需要修改
+for para in $*
+do
+    if [[ $para == --precision_mode* ]];then
+        precision_mode=`echo ${para#*=}`
+    elif [[ $para == --over_dump* ]];then
+        over_dump=`echo ${para#*=}`
+        over_dump_path=${cur_path}/output/overflow_dump
+        mkdir -p ${over_dump_path}
+    elif [[ $para == --data_dump_flag* ]];then
+        data_dump_flag=`echo ${para#*=}`
+        data_dump_path=${cur_path}/output/data_dump
+        mkdir -p ${data_dump_path}
+    elif [[ $para == --data_dump_step* ]];then
+        data_dump_step=`echo ${para#*=}`
+    elif [[ $para == --profiling* ]];then
+        profiling=`echo ${para#*=}`
+        profiling_dump_path=${cur_path}/output/profiling
+        mkdir -p ${profiling_dump_path}
+    elif [[ $para == --autotune* ]];then
+        autotune=`echo ${para#*=}`
+        mv $install_path/fwkacllib/data/rl/Ascend910/custom $install_path/fwkacllib/data/rl/Ascend910/custom_bak
+        mv $install_path/fwkacllib/data/tiling/Ascend910/custom $install_path/fwkacllib/data/tiling/Ascend910/custom_bak
+        autotune_dump_path=${cur_path}/output/autotune_dump
+        mkdir -p ${autotune_dump_path}/GA
+        mkdir -p ${autotune_dump_path}/rl
+        cp -rf $install_path/fwkacllib/data/tiling/Ascend910/custom ${autotune_dump_path}/GA/
+        cp -rf $install_path/fwkacllib/data/rl/Ascend910/custom ${autotune_dump_path}/rl/
+    elif [[ $para == --data_path* ]];then
+        data_path=`echo ${para#*=}`
+    elif [[ $para == --bind_core* ]]; then
+        bind_core=`echo ${para#*=}`
+        name_bind="_bindcore"
+    fi
+done
+
+#校验是否传入data_path,不需要修改
+if [[ $data_path == "" ]];then
+    echo "[Error] para \"data_path\" must be confing"
+    exit 1
+fi
+
+#autotune时，先开启autotune执行单P训练，不需要修改
+if [[ $autotune == True ]]; then
+     sh -x train_full_1p.sh --autotune=$autotune --data_path=$data_path
+    wait
+    cp -rf $install_path/fwkacllib/data/tiling/Ascend910/custom ${autotune_dump_path}/GA/
+    cp -rf $install_path/fwkacllib/data/rl/Ascend910/custom ${autotune_dump_path}/RL/
+    wait
+    autotune=False
+	export autotune=False
+	 
+	export RANK_SIZE=8
+    export RANK_TABLE_FILE=${cur_path}/../configs/rank_table_8p.json
+    export JOB_ID=10087
+    RANK_ID_START=0
+	unset TE_PARALLEL_COMPILER	 
+fi
+
+#训练开始时间，不需要修改
+start_time=$(date +%s)
+
+#进入训练脚本目录，需要模型审视修改
+for((RANK_ID=$RANK_ID_START;RANK_ID<$((RANK_SIZE+RANK_ID_START));RANK_ID++));
+do
+    echo "Device ID: $RANK_ID"
+    export RANK_ID=$RANK_ID
+    export ASCEND_DEVICE_ID=$RANK_ID
+    export DEVICE_ID=$RANK_ID
+    ASCEND_DEVICE_ID=$RANK_ID
+
+    if [ -d ${cur_path}/output/${ASCEND_DEVICE_ID} ];then
+        rm -rf ${cur_path}/output/${ASCEND_DEVICE_ID}
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    else
+        mkdir -p ${cur_path}/output/$ASCEND_DEVICE_ID/ckpt
+    fi
+	
+    EXEC_DIR=$(pwd)
+
+    #RESULTS=results/8p
+    #mkdir -p ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}		
+    #rm -rf ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}/*
+    #cd ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}
+    #env > ${EXEC_DIR}/${RESULTS}/${ASCEND_DEVICE_ID}.log
+    #start exec
+    #bind kernel
+    #num_cpus=$(getconf _NPROCESSORS_ONLN)
+    #num_cpus_per_device=$((num_cpus/8))
+
+    #start_id=$((num_cpus_per_device*ASCEND_DEVICE_ID))	
+    #end_id=$((num_cpus_per_device*ASCEND_DEVICE_ID+num_cpus_per_device-1))
+
+    corenum=`cat /proc/cpuinfo |grep 'processor' |wc -l`
+    let a=RANK_ID*${corenum}/8
+    let b=RANK_ID+1
+    let c=b*${corenum}/8-1
+    if [ "x${bind_core}" != x ];then
+        bind_core="taskset -c $a-$c"
+    fi
+    nohup ${bind_core} python3.7 ${EXEC_DIR}/../train.py > ${cur_path}/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log 2>&1 &
+done
+wait
+
+#训练结束时间，不需要修改
+end_time=$(date +%s)
+e2e_time=$(( $end_time - $start_time ))
+
+#结果打印，不需要修改
+echo "E2E training Duration sec: $e2e_time"
+
+#稳定性精度看护结果汇总
+#训练用例信息，不需要修改
+BatchSize=${batch_size}
+DeviceType=`uname -m`
+CaseName=${Network}${name_bind}_bs${BatchSize}_${RANK_SIZE}'p'_'RT2'_'perf'
+
+##获取性能数据
+ActualFPS=`grep "fps" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | awk 'END {print $22}'`
+temp1=`echo "1000 * ${batch_size} * ${RANK_SIZE}"|bc`
+TrainingTime=`echo "scale=2;${temp1} / ${ActualFPS}"|bc`
+#ActualFPS=`echo "${RANK_SIZE} * ${FPS}"|bc`
+
+ActualLoss=`grep "loss" $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log | awk 'END {print $9}' |tr -d ,`
+
+#关键信息打印到${CaseName}.log中，不需要修改
+echo "Network = ${Network}" > $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "RankSize = ${RANK_SIZE}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "BatchSize = ${BatchSize}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "DeviceType = ${DeviceType}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "CaseName = ${CaseName}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualFPS = ${ActualFPS}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "TrainingTime = ${TrainingTime}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "ActualLoss = ${ActualLoss}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+echo "E2ETrainingTime = ${e2e_time}" >> $cur_path/output/$ASCEND_DEVICE_ID/${CaseName}.log
+sed -i -e '/ModuleNotFoundError/d' $cur_path/output/${ASCEND_DEVICE_ID}/train_${ASCEND_DEVICE_ID}.log