diff --git a/paddle/fluid/operators/lstmp_op.h b/paddle/fluid/operators/lstmp_op.h
index 05ecd3c1aec189776159b4c208a5e91aa0a77454..1f11e57dcb721012c7b8e50d7e138355685053da 100644
--- a/paddle/fluid/operators/lstmp_op.h
+++ b/paddle/fluid/operators/lstmp_op.h
@@ -405,10 +405,10 @@ class LSTMPGradKernel : public framework::OpKernel<T> {
       }
 
       int cur_batch_size = bend - bstart;
-      // lstm_value.output_value not used in bp, set to null
-      // lstm_grad.state_active_grad not used in bp, set to null
-      lstm_value.output_value = nullptr;
-      lstm_grad.state_active_grad = nullptr;
+      // lstmp_value.output_value not used in bp, set to null
+      // lstmp_grad.state_active_grad not used in bp, set to null
+      lstmp_value.output_value = nullptr;
+      lstmp_grad.state_active_grad = nullptr;
 
       math::LstmUnitGradFunctor<DeviceContext, T>::compute(
           device_ctx, lstmp_value, lstmp_grad, frame_size, cur_batch_size,