Several optimizations possible

theano/sandbox/cuda/tests/test_abstractconv.py

@@ -249,7 +249,10 @@ class TestConv2d(unittest.TestCase):
             self.run_fwd(inputs_shape=i, filters_shape=f, subsample=s,
                          verify_grad=True, mode=mode, device='gpu',
                          provide_shape=provide_shape, border_mode=b,
-                         filter_flip=flip, target_op=GpuCorrMM)
+                         filter_flip=flip,
+                         target_op=(GpuCorrMM,
+                                    GpuCorrMM_gradWeights,
+                                    GpuCorrMM_gradInputs))
             self.run_gradweight(inputs_shape=i, filters_shape=f,
                                 output_shape=o, subsample=s,
                                 verify_grad=True, mode=mode, device='gpu',