Merge pull request #289 from nouiz/fix_import_floatX

doc/extending/ctype.txt

@@ -502,6 +502,26 @@ Final version
    double = Double()
 
 
+DeepCopyOp
+==========
+
+We have an internal Op called DeepCopyOp. It is used to make sure we
+respect the user vs Theano memory region as described in the :ref:`tutorial
+<aliasing>`. Theano has a Python implementation that calls the object's
+``copy()`` or ``deepcopy()`` method for Theano types for which it does not
+know how to generate C code.
+
+You can implement c_code for this op. You register it like this:
+
+.. code-block:: python
+
+   theano.compile.function_module.register_DeepCopyOp_c_code(YOUR_TYPE_CLASS, THE_C_CODE)
+
+In your C code, you should use %(iname)s and %(oname)s to represent
+the C variable names of the DeepCopyOp input and output
+respectively. See an example for the type ``CudaNdarrayType`` (GPU array)
+in the file `theano/sandbox/cuda/type.py`.
+
 Output Guard
 ============
 

theano/compile/function_module.py

@@ -129,7 +129,21 @@ class AliasedMemoryError(Exception):
 ### Function
 ###
 
+def register_DeepCopyOp_c_code(typ, code):
+    """ Tell DeepCopyOp how to generate C code for a Theano Type
+
+    :param typ: A Theano type. It must be the Theano class itself and not an
+                instance of the class.
+    :param code: C code that deep copies the Theano type 'typ'.
+                 Use %(iname)s and %(oname)s for the input and output C
+                 variable names respectively.
+    """
+    DeepCopyOp.c_codes[typ] = code
+
+
 class DeepCopyOp(theano.gof.Op):
+    c_codes = {}  # Theano Type, code
+
     def __init__(self):
         pass
 
@@ -175,19 +189,8 @@ class DeepCopyOp(theano.gof.Op):
         }
 
         """%locals()
-        elif isinstance(node.inputs[0].type, theano.sandbox.cuda.CudaNdarrayType):
-            return """
-        Py_XDECREF(%(oname)s);
-
-        %(oname)s = (CudaNdarray*)CudaNdarray_Copy(%(iname)s);
-
-        if (!%(oname)s)
-        {
-            PyErr_SetString(PyExc_ValueError, "DeepCopyOp: the copy failed!");
-            %(fail)s;
-        }
-
-        """%locals()
+        elif node.inputs[0].type.__class__ in self.c_codes:
+            return self.c_codes[node.inputs[0].type.__class__] % locals()
         else:
             super(DeepCopyOp, self).c_code(node, name, inames, onames, sub)
 

theano/sandbox/cuda/tests/test_tensor_op.py

 """
 This file test tensor op that should also operate on CudaNdaray.
 """
-import numpy
+import copy
+from nose.plugins.skip import SkipTest
 
-from theano import tensor
+import numpy
 
 import theano
+from theano import tensor
 import theano.tensor as T
 
 # Skip test if cuda_ndarray is not available.
-from nose.plugins.skip import SkipTest
 import theano.sandbox.cuda as cuda
 if cuda.cuda_available == False:
     raise SkipTest('Optional package cuda disabled')
@@ -105,3 +106,24 @@ def test_may_share_memory_cuda():
             raise Exception("An error was expected")
         except TypeError:
             pass
+
+
+def test_deepcopy():
+    a = cuda.fmatrix()
+    a_v = cuda.CudaNdarray(numpy.zeros((3, 4), dtype='float32'))
+
+    # We force the c code to check that we generate c code
+    mode = theano.Mode("c", mode_with_gpu.optimizer)
+    f = theano.function([a], a, mode=mode)
+    theano.printing.debugprint(f)
+    out = f(a_v)
+    assert out is not a_v
+    assert numpy.allclose(numpy.asarray(a_v), numpy.asarray(out))
+
+    # We force the python linker as the default code should work for this op
+    mode = theano.Mode("py", mode_with_gpu.optimizer)
+    f = theano.function([a], a, mode=mode)
+    theano.printing.debugprint(f)
+    out = f(a_v)
+    assert out is not a_v
+    assert numpy.allclose(numpy.asarray(a_v), numpy.asarray(out))

theano/sandbox/cuda/type.py

@@ -356,6 +356,19 @@ class CudaNdarrayType(Type):
 # to have OutputGuard generate C code for this type.
 theano.compile.mode.register_OutputGuard_c_code(CudaNdarrayType)
 
+# Register CudaNdarrayType to the DeepCopyOp list of types with c code.
+theano.compile.function_module.register_DeepCopyOp_c_code(CudaNdarrayType, """
+        Py_XDECREF(%(oname)s);
+
+        %(oname)s = (CudaNdarray*)CudaNdarray_Copy(%(iname)s);
+
+        if (!%(oname)s)
+        {
+            PyErr_SetString(PyExc_ValueError, "DeepCopyOp: the copy failed!");
+            %(fail)s;
+        }
+        """)
+
 
 # THIS WORKS
 # But CudaNdarray instances don't compare equal to one another, and what about __hash__ ?