def local_gpu_elemwise(node):
do_replace = False
gpu_out = False
# check for gpu_from_host(Elemwise)) and extract the Elemwise node
if node.op == gpu_from_host:
host_i, = node.inputs
if (host_i.owner and
isinstance(host_i.owner.op, tensor.Elemwise) and
len(host_i.clients) == 1):
node = host_i.owner
do_replace = True
gpu_out = True
# check for elemwise(..., host_from_gpu, ...)
if isinstance(node.op, tensor.Elemwise):
if numpy.any([i.owner and
i.owner.op == host_from_gpu
for i in node.inputs]):
do_replace = True
if numpy.all([_is_scalar(i)
for i in node.inputs]):
do_replace = False
if do_replace:
new_op = GpuElemwise(node.op.scalar_op)
gpu_elemwise = new_op(*(gpu_from_host(i) for i in node.inputs))
if gpu_out:
return [gpu_elemwise]
else:
return [host_from_gpu(gpu_elemwise)]
else:
return False
def local_gpu_elemwise(node):
do_replace = False
gpu_out = False
# check for gpu_from_host(Elemwise)) and extract the Elemwise node
if node.op == gpu_from_host:
host_i, = node.inputs
if (host_i.owner and isinstance(host_i.owner.op, tensor.Elemwise)
and len(host_i.clients) == 1):
node = host_i.owner
do_replace = True
gpu_out = True
# check for elemwise(..., host_from_gpu, ...)
if isinstance(node.op, tensor.Elemwise):
if numpy.any(
[i.owner and i.owner.op == host_from_gpu for i in node.inputs]):
do_replace = True
if numpy.all([_is_scalar(i) for i in node.inputs]):
do_replace = False
if do_replace:
new_op = GpuElemwise(node.op.scalar_op)
gpu_elemwise = new_op(*(gpu_from_host(i) for i in node.inputs))
if gpu_out:
return [gpu_elemwise]
else:
return [host_from_gpu(gpu_elemwise)]
else:
return False
def apply(self, fgraph):
for input in fgraph.inputs:
if isinstance(input.type, GpuArrayType):
continue
if (len(input.clients) == 1 and
(input.clients[0][0] == 'output' or
input.clients[0][0].op == gpu_from_host)):
continue
try:
new_input = host_from_gpu(gpu_from_host(input))
fgraph.replace_validate(input, new_input,
"InputToGpuOptimizer")
except TypeError, e:
# This could fail if the inputs are not TensorTypes
pass
def apply(self, fgraph):
for input in fgraph.inputs:
if isinstance(input.type, GpuArrayType):
continue
if (len(input.clients) == 1
and (input.clients[0][0] == 'output'
or input.clients[0][0].op == gpu_from_host)):
continue
try:
new_input = host_from_gpu(gpu_from_host(input))
fgraph.replace_validate(input, new_input,
"InputToGpuOptimizer")
except TypeError, e:
# This could fail if the inputs are not TensorTypes
pass
