Fix GpuToGpu

theano/gpuarray/basic_ops.py

@@ -529,15 +529,22 @@ class GpuToGpu(Op):
     def c_code(self, node, name, inputs, outputs, sub):
         return """
         Py_XDECREF(%(out)s);
-        %(out)s = pygpu_transfer(%(inp)s, %(ctx)s, 0);
+        %(out)s = pygpu_empty(%(inp)s->ga.nd,
+                              %(inp)s->ga.dimensions,
+                              %(inp)s->ga.typecode,
+                              GpuArray_IS_C_CONTIGUOUS(&(%(inp)s->ga)) ? GA_C_ORDER:GA_F_ORDER,
+                              %(ctx)s, Py_None);
         if (%(out)s == NULL) {
             %(fail)s
         }
+        if (pygpu_transfer(%(out)s, %(inp)s)) {
+            %(fail)s
+        }
         """ % {'inp': inputs[0], 'ctx': sub['params'],
                'out': outputs[0], 'fail': sub['fail']}
 
     def c_code_cache_version(self):
-        return (0,)
+        return (1,)
 
 
 class GpuAlloc(HideC, Alloc):

theano/gpuarray/tests/test_basic_ops.py

@@ -15,10 +15,10 @@ from theano.tensor.tests import test_basic
 from theano.tensor.tests.test_basic import rand, safe_make_node
 from theano.tests import unittest_tools as utt
 
-from ..type import (GpuArrayType, get_context,
+from ..type import (GpuArrayType, get_context, list_contexts,
                     gpuarray_shared_constructor)
 from ..basic_ops import (
-    host_from_gpu, HostFromGpu, GpuFromHost, GpuReshape,
+    host_from_gpu, HostFromGpu, GpuFromHost, GpuReshape, GpuToGpu,
     GpuAlloc, GpuAllocEmpty, GpuContiguous,
     gpu_join, GpuJoin, GpuSplit, GpuEye, gpu_contiguous)
 from ..subtensor import GpuSubtensor
@@ -182,6 +182,24 @@ def test_transfer_cpu_gpu():
     assert numpy.all(fv == av)
 
 
+def test_transfer_gpu_gpu():
+    ctxs = list_contexts()
+    if len(ctxs) <= 1:
+        raise SkipError("Need more then 1 context to test multi-gpu transfer")
+
+    g = GpuArrayType(dtype='float32', broadcastable=(False, False),
+                          context_name=ctxs[0])()
+
+    av = numpy.asarray(rng.rand(5, 4), dtype='float32')
+    gv = gpuarray.array(av, context=get_context(ctxs[0]))
+    gv2 = gpuarray.array(av, context=get_context(ctxs[1]))
+
+    f = theano.function([g], GpuToGpu(ctxs[1])(g))
+    theano.printing.debugprint(f)
+    fv = f(gv)
+    assert GpuArrayType.values_eq(fv, gv2)
+
+
 def test_transfer_strided():
     # This is just to ensure that it works in theano
     # libgpuarray has a much more comprehensive suit of tests to