make the profiler in gpu mode output more info that can help find why op are not on the gpu.

theano/compile/profilemode.py

@@ -311,11 +311,11 @@ class ProfileMode(Mode):
         from theano.tensor.basic import as_tensor_variable
         print
         print "List of apply that don't have float64 as input but have float64 in outputs. Usefull to know if we forgot some cast when using floatX=float32 or gpu code."
-        print '<Apply> <inputs type> <outputs type>'
+        print '<Apply> <Apply position> <fct name> <inputs type> <outputs type>'
         for fct in fct_call.keys():
-            for node in fct.maker.env.toposort():
+            for idx, node in enumerate(fct.maker.env.toposort()):
                 if any(hasattr(i,'dtype') and i.dtype=='float64' for i in node.outputs) and not any(hasattr(i,'dtype') and i.dtype=='float64' for i in node.inputs):
-                    print str(node),str([getattr(i,'dtype',None) for i in node.inputs]),str([getattr(i,'dtype',None) for i in node.outputs])
+                    print str(node), idx, fct.name, str([getattr(i,'dtype',None) for i in node.inputs]),str([getattr(i,'dtype',None) for i in node.outputs])
                         
         if any([x[2].__name__.startswith("Gpu") for x in sotimes]):
             cpu=[]
@@ -336,6 +336,13 @@ class ProfileMode(Mode):
             print "Spent %.3fs(%.3f%%) in cpu Op, %.3fs(%.3f%%) in gpu Op and %.3fs(%.3f%%) transfert Op"%(
                 sum_cpu, sum_cpu/local_time*100, sum_gpu, sum_gpu/local_time*100, sum_trans, sum_trans/local_time*100)
 
+            print "Theano function input that are float64"
+            print "<fct name> <input name> <input type> <str input>"
+            for fct in fct_call.keys():
+                for i in fct.input_storage:
+                    if i.type.dtype=='float64':
+                        print fct.name, i.name, i.type, i
+
 register_mode('PROFILE_MODE',ProfileMode())
 
 #needed to print the profile at the end automatically