def test_host_alloc_mapped(self):
ary = cuda.mapped_array(10, dtype=np.uint32)
ary.fill(123)
self.assertTrue(all(ary == 123))
driver.device_memset(ary, 0, driver.device_memory_size(ary))
self.assertTrue(all(ary == 0))
self.assertTrue(sum(ary != 0) == 0)
def test_host_alloc_pinned(self):
ary = cuda.pinned_array(10, dtype=np.uint32)
ary.fill(123)
self.assertTrue(all(ary == 123))
devary = cuda.to_device(ary)
driver.device_memset(devary, 0, driver.device_memory_size(devary))
self.assertTrue(all(ary == 123))
devary.copy_to_host(ary)
self.assertTrue(all(ary == 0))
def test_host_alloc_pinned(self):
ary = cuda.pinned_array(10, dtype=np.uint32)
ary.fill(123)
self.assertTrue(all(ary == 123))
devary = cuda.to_device(ary)
driver.device_memset(devary, 0, driver.device_memory_size(devary))
self.assertTrue(all(ary == 123))
devary.copy_to_host(ary)
self.assertTrue(all(ary == 0))
def __init__(self,
shape,
strides,
dtype,
stream=0,
writeback=None,
gpu_data=None):
"""
Args
----
shape
array shape.
strides
array strides.
dtype
data type as np.dtype coercible object.
stream
cuda stream.
writeback
Deprecated.
gpu_data
user provided device memory for the ndarray data buffer
"""
if isinstance(shape, int):
shape = (shape, )
if isinstance(strides, int):
strides = (strides, )
dtype = np.dtype(dtype)
self.ndim = len(shape)
if len(strides) != self.ndim:
raise ValueError('strides not match ndim')
self._dummy = dummyarray.Array.from_desc(0, shape, strides,
dtype.itemsize)
self.shape = tuple(shape)
self.strides = tuple(strides)
self.dtype = dtype
self.size = int(functools.reduce(operator.mul, self.shape, 1))
# prepare gpu memory
if self.size > 0:
if gpu_data is None:
self.alloc_size = _driver.memory_size_from_info(
self.shape, self.strides, self.dtype.itemsize)
gpu_data = devices.get_context().memalloc(self.alloc_size)
else:
self.alloc_size = _driver.device_memory_size(gpu_data)
else:
# Make NULL pointer for empty allocation
gpu_data = _driver.MemoryPointer(context=devices.get_context(),
pointer=c_void_p(0),
size=0)
self.alloc_size = 0
self.gpu_data = gpu_data
self.__writeback = writeback # should deprecate the use of this
self.stream = stream
def test_host_alloc_mapped(self):
ary = cuda.mapped_array(10, dtype=np.uint32)
ary.fill(123)
self.assertTrue(all(ary == 123))
driver.device_memset(ary, 0, driver.device_memory_size(ary))
self.assertTrue(all(ary == 0))