Address comments from review

theano/sandbox/gpuarray/blockgemv.c

@@ -108,8 +108,16 @@ int APPLY_SPECIFIC(blockgemv)(PyGpuArrayObject *o, PyGpuArrayObject *W,
                                inp_list, offInp, PyGpuArray_STRIDES(h)[2] / gpuarray_get_elsize(h->ga.typecode),
                                1, out_list, offOut, PyGpuArray_STRIDES(out)[2] / gpuarray_get_elsize(out->ga.typecode),
                                PyGpuArray_DIMS(out)[1] * PyGpuArray_DIMS(h)[1] * PyGpuArray_DIMS(out)[0], 0);
+  } else if (out->ga.typecode == GA_HALF) {
+    err = blas_ops->sgemvBatch(cb_fortran, transA,
+                               PyGpuArray_DIMS(out)[2],
+                               PyGpuArray_DIMS(h)[2], 1,
+                               W_list, offW, lda,
+                               inp_list, offInp, PyGpuArray_STRIDES(h)[2] / gpuarray_get_elsize(h->ga.typecode),
+                               1, out_list, offOut, PyGpuArray_STRIDES(out)[2] / gpuarray_get_elsize(out->ga.typecode),
+                               PyGpuArray_DIMS(out)[1] * PyGpuArray_DIMS(h)[1] * PyGpuArray_DIMS(out)[0], 0);
   } else {
-    err = GA_DEVSUP_ERROR;
+    err = GA_INVALID_ERROR;
   }
   
   free(W_list);

theano/sandbox/gpuarray/blockger.c

@@ -97,8 +97,15 @@ int APPLY_SPECIFIC(blockger)(PyGpuArrayObject *o, PyGpuArrayObject *x,
                               y_list, offY, str_y, x_list, offX, str_x,
                               o_list, offOut, str_out,
                               PyGpuArray_DIMS(x)[0] * PyGpuArray_DIMS(x)[1] * PyGpuArray_DIMS(y)[1], 0);
+  } else if (out->ga.typecode == GA_HALF) {
+    err = blas_ops->hgerBatch(cb_fortran,
+                              PyGpuArray_DIMS(y)[2], PyGpuArray_DIMS(x)[2],
+                              *(float *)PyArray_GETPTR1(alpha, 0),
+                              y_list, offY, str_y, x_list, offX, str_x,
+                              o_list, offOut, str_out,
+                              PyGpuArray_DIMS(x)[0] * PyGpuArray_DIMS(x)[1] * PyGpuArray_DIMS(y)[1], 0);
   } else {
-    err = GA_DEVSUP_ERROR;
+    err = GA_INVALID_ERROR;
   }
   free(o_list);
   free(offOut);
@@ -107,7 +114,7 @@ int APPLY_SPECIFIC(blockger)(PyGpuArrayObject *o, PyGpuArrayObject *x,
   free(y_list);
   free(offY);
   if (err != GA_NO_ERROR) {
-    PyErr_SetString(PyExc_RuntimeError, "sgerBatch failed");
+    PyErr_SetString(PyExc_RuntimeError, "gerBatch failed");
     return -1;
   }
   *_out = out;

theano/sandbox/gpuarray/blocksparse.py

@@ -5,7 +5,7 @@ import os
 import numpy
 from theano import Apply, tensor
 from theano.gof import COp
-from theano.tensor import discrete_dtypes
+from theano.tensor import discrete_dtypes, as_tensor_variable
 
 from theano.gradient import grad_undefined
 
@@ -54,6 +54,8 @@ class GpuSparseBlockGemv(COp):
         o = as_gpuarray_variable(o, ctx)
         W = as_gpuarray_variable(W, ctx)
         h = as_gpuarray_variable(h, ctx)
+        inputIdx = as_tensor_variable(inputIdx)
+        outputIdx = as_tensor_variable(outputIdx)
         assert o.ndim == 3
         assert W.ndim == 4
         assert h.ndim == 3
@@ -123,6 +125,8 @@ class GpuSparseBlockOuter(COp):
         o = as_gpuarray_variable(o, ctx)
         x = as_gpuarray_variable(x, ctx)
         y = as_gpuarray_variable(y, ctx)
+        xIdx = as_tensor_variable(xIdx)
+        yIdx = as_tensor_variable(yIdx)
         if alpha is None:
             alpha = one
         return Apply(self, [o, x, y, xIdx, yIdx, alpha],