Merged

theano/sandbox/cuda/tests/test_basic_ops.py

@@ -318,11 +318,11 @@ def test_elemwise3():
     a = tcn.shared_constructor(theano._asarray(numpy.random.rand(*shape), dtype='float32'), 'a')
     b = tensor.fvector()
     print b.type
-    print tensor.constant(1).type
-    print (1 + b).type
-    print (1 + b**a).type
-    print tensor.exp((1 + b**a)).type
-    f = pfunc([b], [], updates=[(a, (a+b).dimshuffle([2,0,3,1]) * tensor.exp(1 +
+    fone = tensor.constant(1, dtype='float32')
+    print (fone + b).type
+    print (fone + b**a).type
+    print tensor.exp((fone + b**a)).type
+    f = pfunc([b], [], updates=[(a, (a+b).dimshuffle([2,0,3,1]) * tensor.exp(fone +
         b**a).dimshuffle([2,0,3,1]))], mode=mode_with_gpu)
     has_elemwise = False
     for i, node in enumerate(f.maker.env.toposort()):

theano/sandbox/cuda/tests/test_opt.py

@@ -144,7 +144,8 @@ def test_opt_gpujoin_joinvectors_elemwise_then_minusone():
 def test_print_op():
     """ Test that print ops don't block gpu optimization"""
     b = tensor.fmatrix()
-    f = theano.function([b],theano.printing.Print()(b)*2, mode=mode_with_gpu)
+    ftwo = tensor.constant(2, dtype='float32')
+    f = theano.function([b],theano.printing.Print()(b) * ftwo, mode=mode_with_gpu)
     #theano.printing.debugprint(f)
     #print f.maker.env.toposort()
 #[GpuFromHost(<TensorType(float32, matrix)>), <theano.printing.Print object at 0x3581210>(GpuFromHost.0), GpuElemwise{mul}(CudaNdarray{[[ 2.]]}, <theano.printing.Print object at 0x3581210>.0), HostFromGpu(GpuElemwise{mul}.0)]

theano/tensor/tests/test_basic.py

@@ -3606,11 +3606,13 @@ class TestARange(unittest.TestCase):
 
         if config.cast_policy == 'custom':
             assert out.dtype == start.type.dtype
-        elif config.cast_policy in ('numpy', 'numpy+floatX'):
+        elif config.cast_policy == 'numpy':
             numpy_dtype = numpy.arange(numpy.array(0, dtype=start.dtype),
                                        numpy.array(1, dtype=stop.dtype),
                                        numpy.array(1, dtype=step.dtype)).dtype
             assert out.dtype == numpy_dtype
+        elif config.cast_policy == 'numpy+floatX':
+            assert out.dtype == config.floatX
         else:
             raise NotImplementedError(config.cast_policy)
         arg_vals = [ (0,5,1), (2,11,4), (-5,1.1,1.2), (1.3,2,-2.1), (10,2,2) ]
@@ -3622,7 +3624,8 @@ class TestARange(unittest.TestCase):
                 expected_val = numpy.arange(start_v, stop_v, step_v,
                                             dtype=start.type.dtype)
             elif config.cast_policy in ('numpy', 'numpy+floatX'):
-                expected_val = numpy.arange(start_v_, stop_v_, step_v_)
+                expected_val = numpy.arange(start_v_, stop_v_, step_v_,
+                                            dtype=out.dtype)
             else:
                 raise NotImplementedError(config.cast_policy)
             assert numpy.all(f_val == expected_val)

theano/tensor/tests/test_opt.py

@@ -785,7 +785,7 @@ class test_fusion(unittest.TestCase):
             (fx-(fy/fz),(fx,fy,fz),(fxv,fyv,fzv),1,fxv-(fyv/fzv),'float32'),
             (fx-theano.tensor.true_div(fy,ftwo),(fx,fy),(fxv,fyv),1,fxv-(fyv/2),'float32'),
             (fx-theano.tensor.true_div(fy,fz),(fx,fy,fz),(fxv,fyv,fzv),1,fxv-(fyv/fzv),'float32'),
-            (fx-theano.tensor.int_div(ix*100,iy*1000),(fx,ix,iy),(fxv,ixv,iyv),4,fxv-((ixv*100)//(iyv*1000)),'float64'),#int32 - float32 = float64 #No c_code for int_div#40
+            (fx-theano.tensor.int_div(ix*100,iy*1000),(fx,ix,iy),(fxv,ixv,iyv),4,fxv-((ixv*100)//(iyv*1000)), {'custom': 'float64', 'numpy+floatX': config.floatX, 'numpy': 'float64'}), #No c_code for int_div#40
             (fx-(fy/ftwo),(fx,fy),(fxv,fyv),1,fxv-(fyv/2),'float32'),
             (fx-(fy%fz),(fx,fy,fz),(fxv,fyv,fzv),1,fxv-(fyv%fzv),'float32'),
             (fx-(fy>fz),(fx,fy,fz),(fxv,fyv,fzv),1,fxv-(fyv>fzv),'float32'),
@@ -805,10 +805,10 @@ class test_fusion(unittest.TestCase):
             (fx-fy+theano.tensor.round(fz),(fx,fy,fz),(fxv,fyv,fzv),1,fxv-fyv+numpy.round(fzv),'float32'),
             (ix-iy+theano.tensor.iround(fz),(ix,iy,fz),(ixv,iyv,fzv),1,ixv-iyv+numpy.round(fzv),'int64'),
             # Bit op
-            (fx-theano.tensor.or_(iy,iz),(fx,iy,iz),(fxv,iyv,izv),1,fxv-(iyv|izv),'float64'),
-            (fx-theano.tensor.xor(iy,iz),(fx,iy,iz),(fxv,iyv,izv),1,fxv-(iyv^izv),'float64'),#60
-            (fx-theano.tensor.and_(iy,iz),(fx,iy,iz),(fxv,iyv,izv),1,fxv-(iyv&izv),'float64'),
-            (fx-theano.tensor.invert(iy),(fx,iy),(fxv,iyv),1,fxv-(~iyv),'float64'),
+            (fx-theano.tensor.or_(iy,iz),(fx,iy,iz),(fxv,iyv,izv),1,fxv-(iyv|izv), {'custom': 'float64', 'numpy+floatX': config.floatX, 'numpy': 'float64'}),
+            (fx-theano.tensor.xor(iy,iz),(fx,iy,iz),(fxv,iyv,izv),1,fxv-(iyv^izv), {'custom': 'float64', 'numpy+floatX': config.floatX, 'numpy': 'float64'}),#60
+            (fx-theano.tensor.and_(iy,iz),(fx,iy,iz),(fxv,iyv,izv),1,fxv-(iyv&izv), {'custom': 'float64', 'numpy+floatX': config.floatX, 'numpy': 'float64'}),
+            (fx-theano.tensor.invert(iy),(fx,iy),(fxv,iyv),1,fxv-(~iyv), {'custom': 'float64', 'numpy+floatX': config.floatX, 'numpy': 'float64'}),
 
             (fx-theano.tensor.cast(fy,dtype='float64'),(fx,fy),(fxv,fyv),1,
                               fxv-numpy.asarray(fyv,'float64'),'float64'),
@@ -834,6 +834,8 @@ class test_fusion(unittest.TestCase):
         fail3=[]
         fail4=[]
         for id, [g, sym_inputs, val_inputs, nb_elemwise, answer, out_dtype] in enumerate(cases):
+            if isinstance(out_dtype, dict):
+                out_dtype = out_dtype[config.cast_policy]
             if gpu and (out_dtype!='float32' or any(i.dtype != 'float32' for i in g.owner.inputs)):
                 print "Skip test %d as the gpu code currently supports only float32" % id
                 continue