diff --git a/mindspore/lite/nnacl/fp16/exp_fp16.h b/mindspore/lite/nnacl/fp16/exp_fp16.h
index 1f23d1ea72..f9db27c09e 100644
--- a/mindspore/lite/nnacl/fp16/exp_fp16.h
+++ b/mindspore/lite/nnacl/fp16/exp_fp16.h
@@ -59,7 +59,7 @@ static inline void single_exp_fp16(float16_t src, float16_t *dst) {
   int integer = (float)src / param[0];
   float decimal = (float)src - integer * param[0];
   int int_exp = (integer + 127) << 23;
-  float decimal_exp =
+  const float decimal_exp =
     1.0f + decimal * (1.0f + decimal * (0.5f + decimal * (param[3] + decimal * (param[2] + decimal * param[1]))));
   *dst = (float16_t)(*((float *)&int_exp) * decimal_exp);
 }
diff --git a/mindspore/lite/nnacl/fp32/conv_depthwise_fp32.c b/mindspore/lite/nnacl/fp32/conv_depthwise_fp32.c
index 1cfc5e4a04..08b0332ffb 100644
--- a/mindspore/lite/nnacl/fp32/conv_depthwise_fp32.c
+++ b/mindspore/lite/nnacl/fp32/conv_depthwise_fp32.c
@@ -330,7 +330,7 @@ bool CheckConvDw1DWinograd(const ConvParameter *conv_param, int thread_num) {
          conv_param->stride_h_ == 1 && conv_param->dilation_h_ == 1 && conv_param->dilation_w_ == 1 &&
          conv_param->pad_u_ == 1 && conv_param->pad_d_ == 1 && conv_param->pad_l_ == 1 && conv_param->pad_r_ == 1 &&
          conv_param->input_channel_ == conv_param->output_channel_ &&
-         conv_param->output_h_ / thread_num >= 4;  // better had more than 4 rows for each thread
+         conv_param->output_h_ >= thread_num * 4;  // better had more than 4 rows for each thread
 }
 
 void ConvDw3x3RowLeft(const float *src, float *line, int lw, int channel) {
diff --git a/mindspore/lite/nnacl/fp32_grad/pooling_grad.c b/mindspore/lite/nnacl/fp32_grad/pooling_grad.c
index d775b9b554..cd80ee470f 100644
--- a/mindspore/lite/nnacl/fp32_grad/pooling_grad.c
+++ b/mindspore/lite/nnacl/fp32_grad/pooling_grad.c
@@ -144,8 +144,7 @@ void MaxPoolingGrad(const float *input_ptr, const float *dy_ptr, float *output_p
               int xw = yw * stride_w + kw - pad_w;
               int val_idx = (xw + in_w * xh) * channel + ic;
 #ifdef ENABLE_ARM
-              unsigned int val_idx_vec[] = {val_idx, val_idx + 1, val_idx + 2, val_idx + 3};
-              uint32x4_t index = vld1q_u32(val_idx_vec);
+              uint32x4_t index = {val_idx, val_idx + 1, val_idx + 2, val_idx + 3};
               float32x4_t in = vld1q_f32(inPtr + val_idx);
               max_idx = MaxIndex(in, &max_val, index, max_idx);
 #else
diff --git a/mindspore/lite/src/runtime/kernel/npu/npu_kernel.h b/mindspore/lite/src/runtime/kernel/npu/npu_kernel.h
index ed912c7718..92652603f1 100644
--- a/mindspore/lite/src/runtime/kernel/npu/npu_kernel.h
+++ b/mindspore/lite/src/runtime/kernel/npu/npu_kernel.h
@@ -27,7 +27,6 @@ using mindspore::kernel::LiteKernel;
 using mindspore::lite::RET_ERROR;
 using mindspore::lite::RET_OK;
 namespace mindspore::kernel {
-#define NPU_MEMORY_MAX 200 * 1024 * 1024
 class NPUKernel : public LiteKernel {
  public:
   NPUKernel(OpParameter *parameter, const std::vector<lite::Tensor *> &inputs,
@@ -65,12 +64,6 @@ kernel::LiteKernel *NPUKernelCreator(const std::vector<lite::Tensor *> &inputs,
     free(opParameter);
     return nullptr;
   }
-  if (inputs[0]->Size() > NPU_MEMORY_MAX) {
-    MS_LOG(ERROR) << "Npu does not support input tensor size greater than 200MB";
-    free(opParameter);
-    return nullptr;
-  }
-
   auto *kernel = new (std::nothrow) T(opParameter, inputs, outputs, ctx, primitive);
   if (kernel == nullptr) {
     MS_LOG(ERROR) << "kernel " << opParameter->name_ << "is nullptr.";
diff --git a/mindspore/lite/test/run_benchmark_nets.sh b/mindspore/lite/test/run_benchmark_nets.sh
index 76d39fc6e3..3e6c680df6 100755
--- a/mindspore/lite/test/run_benchmark_nets.sh
+++ b/mindspore/lite/test/run_benchmark_nets.sh
@@ -2309,16 +2309,6 @@ if [[ ${backend} == "all" || ${backend} == "npu" ]]; then
 fi
 
 # Check benchmark result and return value
-if [[ ${backend} == "all" || ${backend} == "x86" ]]; then
-      wait ${Run_x86_PID}
-      Run_x86_status=$?
-
-      if [[ ${Run_x86_status} != 0 ]];then
-          echo "Run_x86 failed"
-          cat ${run_x86_log_file}
-          isFailed=1
-      fi
-fi
 if [[ ${backend} == "all" || ${backend} == "x86-sse" ]]; then
       wait ${Run_x86_sse_PID}
       Run_x86_sse_status=$?
@@ -2339,6 +2329,16 @@ if [[ ${backend} == "all" || ${backend} == "x86-avx" ]]; then
           isFailed=1
       fi
 fi
+if [[ ${backend} == "all" || ${backend} == "x86" ]]; then
+      wait ${Run_x86_PID}
+      Run_x86_status=$?
+
+      if [[ ${Run_x86_status} != 0 ]];then
+          echo "Run_x86 failed"
+          cat ${run_x86_log_file}
+          isFailed=1
+      fi
+fi
 
 if [[ ${backend} == "all" || ${backend} == "arm64_fp32" ]]; then
       if [[ ${Run_arm64_fp32_status} != 0 ]];then