Merge pull request #1771 from nouiz/fast_compile

theano/sandbox/gpuarray/blas.py

@@ -200,13 +200,13 @@ from theano.gof import local_optimizer, LocalOptGroup
 from theano.tensor.opt import in2out
 
 
-@local_optimizer([gpugemv_no_inplace])
+@local_optimizer([gpugemv_no_inplace], inplace=True)
 def local_inplace_gpuagemv(node):
     if node.op == gpugemv_no_inplace:
         return [gpugemv_inplace(*node.inputs)]
 
 
-@local_optimizer([gpugemm_no_inplace])
+@local_optimizer([gpugemm_no_inplace], inplace=True)
 def local_inplace_gpuagemm(node):
     if node.op == gpugemm_no_inplace:
         return [gpugemm_inplace(*node.inputs)]

theano/sandbox/gpuarray/tests/test_subtensor.py

@@ -26,4 +26,6 @@ class G_subtensor(T_subtensor):
                              dtype='float32',
                              ignore_topo=(HostFromGpu, GpuFromHost,
                                           DeepCopyOp))
+        # GPU opt can't run in fast_compile only.
+        self.fast_compile = False
         assert self.sub == GpuSubtensor