Move fusion before AddDestroyHandler.

theano/sandbox/cuda/opt.py

@@ -62,7 +62,7 @@ optdb.register('gpu_opt',
 # inside the elemwise. When there is no float64 op, this is working.
 optdb.register('gpu_after_fusion',
                ProxyDB(gpu_seqopt),
-               optdb.__position__.get('elemwise_fusion', 71) + .1,
+               optdb.__position__.get('elemwise_fusion', 49) + .1,
                'gpu')
 
 
@@ -1338,9 +1338,10 @@ gpu_local_elemwise_fusion = tensor.opt.local_elemwise_fusion_op(
         max_inputs_to_GpuElemwise)
 if config.gpu.local_elemwise_fusion:
     _logger.debug("enabling optimization fusion of gpu elemwise in fast_run")
+    #Must be after cpu fusion at 40, gpu at 48.5 and before AddDestroyHandler at 49.5
     optdb.register('gpu_elemwise_fusion',
                    tensor.opt.FusionOptimizer(gpu_local_elemwise_fusion),
-                   71.00, 'fast_run', 'fusion',
+                   49, 'fast_run', 'fusion',
                    'local_elemwise_fusion', 'gpu')
 else:
     _logger.debug(("not enabling optimization fusion of gpu elemwise in "

theano/tensor/blas.py

@@ -1505,6 +1505,12 @@ class GemmOptimizer(Optimizer):
             callbacks_before = fgraph.execute_callbacks_times.copy()
             callback_before = fgraph.execute_callbacks_time
 
+        class Updater:
+            def on_import(self, fgraph, new_node, reason):
+                if new_node is not node:
+                    nodelist.append(new_node)
+        u = Updater()
+        fgraph.attach_feature(u)
         while did_something:
             nb_iter += 1
             t0 = time.time()
@@ -1551,6 +1557,7 @@ class GemmOptimizer(Optimizer):
                     except ReplacementDidntRemovedError, e:
                         nb_replacement_didn_t_remove += 1
                         self.warned = True
+        fgraph.remove_feature(u)
         if fgraph.profile:
             validate_time = fgraph.profile.validate_time - validate_before
             callback_time = fgraph.execute_callbacks_time - callback_before

theano/tensor/opt.py

@@ -4853,13 +4853,14 @@ class FusionOptimizer(Optimizer):
 
 if config.tensor.local_elemwise_fusion:
     _logger.debug("enabling optimization fusion elemwise in fast_run")
+    #Must be after gpu(48.5) and before AddDestroyHandler(49.5)
     compile.optdb.register('elemwise_fusion',
-                           FusionOptimizer(local_elemwise_fusion), 71.00,
+                           FusionOptimizer(local_elemwise_fusion), 49,
                            'fast_run', 'fusion', 'local_elemwise_fusion',
                            'FusionOptimizer')
 else:
     _logger.debug("not enabling optimization fusion elemwise in fast_run")
     compile.optdb.register('elemwise_fusion',
-                           FusionOptimizer(local_elemwise_fusion), 71.00,
+                           FusionOptimizer(local_elemwise_fusion), 49,
                            'fusion', 'local_elemwise_fusion',
                            'FusionOptimizer')