Merge pull request #1214 from nouiz/infer_shape_broadcast_fix

theano/configdefaults.py

@@ -420,6 +420,11 @@ else:
                         " want theano to use.")
     default_openmp = count > 1
 
+# Disable it by default for now as currently only the ConvOp support
+# it And this cause slow down by default as we do not disable it for
+# too small convolution.
+default_openmp = False
+
 AddConfigVar('openmp',
              "Allow (or not) parallel computation on the CPU with OpenMP. "
              "This is the default value used when creating an Op that "

theano/gof/cmodule.py

@@ -1609,7 +1609,6 @@ class GCC_compiler(object):
 
         try:
             p = call_subprocess_Popen(cmd, stderr=subprocess.PIPE)
-            p.wait()
             compile_stderr = p.communicate()[1]
         except Exception:
             # An exception can occur e.g. if `g++` is not found.

theano/tensor/opt.py

@@ -820,7 +820,10 @@ class ShapeFeature(object):
                     shape_vars.append(self.lscalar_one)
                 else:
                     shape_vars.append(self.unpack(s[i]))
-            assert all([not r.type.broadcastable[i] or
+            assert all([not hasattr(r.type, "broadcastable") or
+                        not r.type.broadcastable[i] or
+                        # The two following comparison are a speed optimization
+                        # But we never timed this speed optimization!
                         self.lscalar_one.equals(shape_vars[i]) or
                         self.lscalar_one.equals(
                             T.extract_constant(shape_vars[i]))
@@ -866,8 +869,11 @@ class ShapeFeature(object):
                 merged_shape.append(r_shape[i])
             else:
                 merged_shape.append(other_shape[i])
-        assert all([(not r.type.broadcastable[i] and
+        assert all([(not hasattr(r.type, "broadcastable") or
+                     not r.type.broadcastable[i] and
                      not other_r.type.broadcastable[i]) or
+                    # The two following comparison are a speed optimization
+                    # But we never timed this speed optimization!
                     self.lscalar_one.equals(merged_shape[i]) or
                     self.lscalar_one.equals(
                         T.extract_constant(merged_shape[i]))
@@ -888,7 +894,10 @@ class ShapeFeature(object):
                 new_shape.append(self.unpack(s_i))
             else:
                 new_shape.append(s_j)
-        assert all([not r.type.broadcastable[i] or
+        assert all([not hasattr(r.type, "broadcastable") or
+                    not r.type.broadcastable[i] or
+                    # The two following comparison are a speed optimization
+                    # But we never timed this speed optimization!
                     self.lscalar_one.equals(new_shape[i]) or
                     self.lscalar_one.equals(T.extract_constant(new_shape[i]))
                     for i in range(r.ndim)])