Revert back to transferring all inputs by default.

doc/tutorial/using_gpu.txt

@@ -538,11 +538,9 @@ int, ...) however GPU support varies and some units can't deal with
 double (float64) or small (less than 32 bits like int16) data types.
 You will get an error at compile time or runtime if this is the case.
 
-Also, by default float inputs will get transferred to GPU, but int
-will not.  You can force the transfer of int inputs by setting the
-tag.target attribute to None or a context name.  You can also prevent
-a float value from getting transferred by setting its tag.target
-attribute to 'cpu'.
+By default all inputs will get transferred to GPU.  You can prevent an
+input from getting transferred by setting its tag.target attribute to
+'cpu'.
 
 Complex support is untested and most likely completely broken.
 

theano/sandbox/gpuarray/opt.py

@@ -172,12 +172,7 @@ class InputToGpuOptimizer(Optimizer):
                     for cl in input.clients)):
                 continue
 
-            if input.type.dtype.startswith('float'):
-                default = None
-            else:
-                default = 'cpu'
-
-            target = getattr(input.tag, 'target', default)
+            target = getattr(input.tag, 'target', None)
             if target == 'cpu':
                 continue