def prepare_node(self, node, storage_map, compute_map, impl):
# Postpone the ufunc building to the last minutes
# NumPy ufunc support only up to 31 inputs.
# But our c code support more.
if (len(node.inputs) < 32 and
(self.nfunc is None or
self.scalar_op.nin != len(node.inputs)) and
self.ufunc is None and
impl == 'py'):
ufunc = numpy.frompyfunc(self.scalar_op.impl,
len(node.inputs),
self.scalar_op.nout)
if self.scalar_op.nin > 0:
# We can reuse it for many nodes
self.ufunc = ufunc
else:
node.tag.ufunc = ufunc
# Numpy ufuncs will sometimes perform operations in
# float16, in particular when the input is int8.
# This is not something that we want, and we do not
# do it in the C code, so we specify that the computation
# should be carried out in the returned dtype.
# This is done via the "sig" kwarg of the ufunc, its value
# should be something like "ff->f", where the characters
# represent the dtype of the inputs and outputs.
# NumPy 1.10.1 raise an error when giving the signature
# when the input is complex. So add it only when inputs is int.
out_dtype = node.outputs[0].dtype
if (out_dtype in float_dtypes and
isinstance(self.nfunc, numpy.ufunc) and
node.inputs[0].dtype in discrete_dtypes):
char = numpy.sctype2char(out_dtype)
sig = char * node.nin + '->' + char * node.nout
node.tag.sig = sig
node.tag.fake_node = Apply(
self.scalar_op,
[get_scalar_type(dtype=input.type.dtype).make_variable()
for input in node.inputs],
[get_scalar_type(dtype=output.type.dtype).make_variable()
for output in node.outputs])
self.scalar_op.prepare_node(node.tag.fake_node, None, None, impl)
评论列表
文章目录
