Merge pull request #69 from nouiz/blas_opt_fix

theano/misc/check_blas.py

@@ -144,6 +144,7 @@ if __name__ == "__main__":
         C1060/3.2         0.46s
         GTX550Ti/4.0      0.57s
         GT220/3.2RC       3.80s
+        GT210/4.0         6.35s
         8500GT/3.0       10.68s
         """
 

theano/tensor/blas.py

@@ -1114,14 +1114,27 @@ def _gemm_from_factored_list(lst):
     """
 
     # Make every pair in list have matching dtypes
+    # sM can be a tuple of 2 elements or a theano variable.
+    # We should not use __len__ as theano variables don't support
+    # it. I don't want to change this to isinstance(sM, tuple)
+    # as I'm not able to make a test that triggers this case.
     def is_pair(sM):
         try:
             s, M = sM
             return True
         except Exception:
             return False
-    lst = [(T.cast(sM[0],sM[1].type.dtype), sM[1])
-            for sM in lst if is_pair(sM)]
+
+    lst2 = []
+    # Remove the tuple that can't be casted correctly.
+    # This can happen when we try to cast a complex to a real
+    for sM in lst:
+        if is_pair(sM):
+            sm0, sm1 = sM
+            sm0 = T.as_tensor_variable(sm0)
+            if theano.scalar.upcast(sm0.dtype, sm1.dtype) == sm1.dtype:
+                lst2.append((T.cast(sm0, sm1.dtype), sM[1]))
+    lst = lst2
 
     # Try every pair in the sM_list, trying to turn it into a gemm operation
     for i in xrange(len(lst) - 1):

theano/tensor/tests/test_blas.py

@@ -578,7 +578,24 @@ def test_upcasting_scalar_nogemm():
     f = theano.function([w, v, t, alpha], rval)
     t = f.maker.env.toposort()
     assert numpy.sum([isinstance(n.op, Gemm) for n in t]) == 0
-    theano.printing.debugprint(f, print_type=True)
+    #theano.printing.debugprint(f, print_type=True)
+
+    v = T.fmatrix('v')
+    w = T.fmatrix('w')
+    t = T.fmatrix('t')
+    alpha = T.cscalar('a')
+
+    on_opt_error = config.on_opt_error
+    try:
+        config.on_opt_error = 'raise'
+        rval = T.dot(w, v) * alpha + t
+        f = theano.function([w, v, t, alpha], rval)
+    finally:
+        config.on_opt_error = on_opt_error
+
+    t = f.maker.env.toposort()
+    assert numpy.sum([isinstance(n.op, Gemm) for n in t]) == 0
+    #theano.printing.debugprint(f, print_type=True)
 
 def test_gemm_nested():
     X,Y,Z,a,b = T.dmatrix('X'), T.dmatrix('Y'), T.dmatrix('Z'), T.dscalar('a'), T.dscalar('b')