CRASH FIX: same fix crash to the new gpu back-end

theano/sandbox/gpuarray/elemwise.py

@@ -1281,7 +1281,10 @@ class GpuCAReduceCuda(HideC, CAReduce):
                     n_threads.z += 1;
                 else
                     break;
-            }""" % locals()
+            }
+            //Maximum for Fermi GPU on that dimensions.
+            n_threads.z = std::min(n_threads.z, (unsigned)64);
+        """ % locals()
 
         if len(self.reduce_mask) == 2:
             threads_y = ''
@@ -1601,6 +1604,8 @@ class GpuCAReduceCuda(HideC, CAReduce):
                 n_threads.z += 1;
             }
             n_threads.z -= 1;
+            //Maximum for Fermi GPU on that dimensions.
+            n_threads.z = std::min(n_threads.z, (unsigned)64);
 
             dim3 n_blocks(1,1,1);
             %(makecall)s

theano/sandbox/gpuarray/tests/test_elemwise.py

@@ -126,11 +126,13 @@ class test_GpuCAReduceCuda(test_GpuCAReduceCPY):
              ((4100,4,3),[1,2]),((5,4100,3),[1,2]),((5,4,4100),[1,2]),#011
              #((4100,4,3),[0,2]),((5,4100,3),[0,2]),((5,4,4100),[0,2]),#101 ##not implemented
              ((4100,4,3),[0,1,2]),((5,4100,3),[0,1,2]),((5,4,4100),[0,1,2]),#111
+             ((65,4,3),[0,1,2]),((5,65,3),[0,1,2]),((5,4,65),[0,1,2]),#111
 
              ((4100,4,3,2),[2,3]),((4,4100,3,2),[2,3]),((4,3,4100,2),[2,3]),((4,3,2,4100),[2,3]),#0011
              ((4100,4,3,2),[1,3]),((4,4100,3,2),[1,3]),((4,3,4100,2),[1,3]),((4,3,2,4100),[1,3]),#0101
              ((4100,4,3,2),[0,2,3]),((4,4100,3,2),[0,2,3]),((4,3,4100,2),[0,2,3]),#((4,3,2,4100),[0,2,3]),#1011
              ((4100,4,3,2),[1,2,3]),((4,4100,3,2),[1,2,3]),((4,3,4100,2),[1,2,3]),((4,3,2,4100),[1,2,3]),#0111
+             ((65,4,3,2),[1,2,3]),((4,65,3,2),[1,2,3]),((4,3,65,2),[1,2,3]),((4,3,2,65),[1,2,3]),#0111
              ((4100,2,3,4),[0,1,2,3]),((2,4100,3,4),[0,1,2,3]),((2,3,4100,4),[0,1,2,3]),((2,3,4,4100),[0,1,2,3]),((128,1,3,3), [0,1,2,3]),#1111
 
              #test pattern implemented by reshape