Give info on how to enable fft conv on only 1 Theano fct.

doc/library/tensor/basic.txt

@@ -1695,6 +1695,7 @@ Gradient / Differentiation
     :return: Returns lists of gradients with respect to `wrt` and `end`,
             respectively.
 
+    .. versionadded:: 0.6.1
 
 .. _R_op_list:
 

doc/library/tensor/nnet/conv.txt

@@ -38,7 +38,15 @@ TODO: Give examples for how to use these things! They are pretty complicated.
       that it requires CUDA >= 5.0, scikits.cuda >= 0.5.0 and PyCUDA to run.
       To desactivate the fft optimization on a specific nnet.conv2d
       while the optimization flags are active, you can set its parameters
-      version to 'no_fft'
+      version to 'no_fft'. To enable for just one Theano function:
+
+      .. code-block:: python
+
+          mode = theano.compile.get_default_mode()
+          mode = mode.including('conv_fft_valid', 'conv_fft_full')
+
+          f = theano.function(..., mode=mode)
+
     - :func:`conv3D <theano.tensor.nnet.Conv3D.conv3D>`
       3D Convolution. Doesn't work on the GPU.
     - :func:`conv3d_fft <theano.sandbox.cuda.fftconv.conv3d_fft>`
@@ -49,6 +57,15 @@ TODO: Give examples for how to use these things! They are pretty complicated.
       This is not enabled by default because it has some restrictions on
       input and uses more memory. Also note that it requires CUDA >= 5.0,
       scikits.cuda >= 0.5.0 and PyCUDA to run.
+      To enable for just one Theano function:
+
+      .. code-block:: python
+
+          mode = theano.compile.get_default_mode()
+          mode = mode.including('conv3d_fft', 'convgrad3d_fft', 'convtransp3d_fft')
+
+          f = theano.function(..., mode=mode)
+
     - :func:`conv3d2d <theano.tensor.nnet.conv3d2d.conv3d>`
       Another conv3d implementation that uses the conv2d with data reshaping.
       It is faster in some cases than conv3d, specifically on the GPU.