diff --git a/python/paddle/fluid/layers/nn.py b/python/paddle/fluid/layers/nn.py
index 429b9b0b5a..6b1e782239 100755
--- a/python/paddle/fluid/layers/nn.py
+++ b/python/paddle/fluid/layers/nn.py
@@ -1198,7 +1198,7 @@ def chunk_eval(input,
 
 
 @deprecated(since="2.0.0", update_to="paddle.nn.functional.softmax")
-def softmax(input, use_cudnn=False, name=None, axis=-1):
+def softmax(input, use_cudnn=True, name=None, axis=-1):
     r"""
     This operator implements the softmax layer. The calculation process is as follows:
 
diff --git a/python/paddle/nn/functional/activation.py b/python/paddle/nn/functional/activation.py
index 915668de19..45ffd422ac 100644
--- a/python/paddle/nn/functional/activation.py
+++ b/python/paddle/nn/functional/activation.py
@@ -843,7 +843,7 @@ def softmax(x, axis=-1, dtype=None, name=None):
 
     if (dtype is not None) and (not isinstance(dtype, core.VarDesc.VarType)):
         dtype = convert_np_dtype_to_dtype_(dtype)
-    use_cudnn = True if axis is -1 else False
+    use_cudnn = True
 
     if in_dygraph_mode():
         outs_cast = x if dtype is None \