def reduce(self, arg, stream=0):
assert len(list(self.functions.keys())[0]) == 2, "must be a binary " \
"ufunc"
assert arg.ndim == 1, "must use 1d array"
n = arg.shape[0]
gpu_mems = []
if n == 0:
raise TypeError("Reduction on an empty array.")
elif n == 1: # nothing to do
return arg[0]
# always use a stream
stream = stream or cuda.stream()
with stream.auto_synchronize():
# transfer memory to device if necessary
if devicearray.is_cuda_ndarray(arg):
mem = arg
else:
mem = cuda.to_device(arg, stream)
# do reduction
out = self.__reduce(mem, gpu_mems, stream)
# use a small buffer to store the result element
buf = np.array((1,), dtype=arg.dtype)
out.copy_to_host(buf, stream=stream)
return buf[0]
def reduce(self, arg, stream=0):
assert len(list(self.functions.keys())[0]) == 2, "must be a binary " \
"ufunc"
assert arg.ndim == 1, "must use 1d array"
n = arg.shape[0]
gpu_mems = []
if n == 0:
raise TypeError("Reduction on an empty array.")
elif n == 1: # nothing to do
return arg[0]
# always use a stream
stream = stream or cuda.stream()
with stream.auto_synchronize():
# transfer memory to device if necessary
if devicearray.is_cuda_ndarray(arg):
mem = arg
else:
mem = cuda.to_device(arg, stream)
# do reduction
out = self.__reduce(mem, gpu_mems, stream)
# use a small buffer to store the result element
buf = np.array((1,), dtype=arg.dtype)
out.copy_to_host(buf, stream=stream)
return buf[0]
def argsort(self, keys, begin_bit=0, end_bit=None):
"""Similar to ``RadixSort.sort`` but returns the new sorted indices.
:type keys: numpy.ndarray
:param keys: Keys to sort inplace
:type begin_bit: int
:param begin_bit: The first bit to sort
:type end_bit: int
:param end_bit: Optional. The last bit to sort
:return: The indices indicating the new ordering as an array on the CUDA
device or on the host.
"""
d_vals = self.init_arg(keys.size)
self.sort(keys, vals=d_vals, begin_bit=begin_bit, end_bit=end_bit)
res = d_vals
if not is_cuda_ndarray(keys):
res = res.copy_to_host(stream=self.stream)
return res
def is_device_array(self, obj):
return devicearray.is_cuda_ndarray(obj)
def is_device_array(self, obj):
return devicearray.is_cuda_ndarray(obj)