def test_binary_op_list_slow_path(self, device, dtype, op):
# note(mkozuki): why `n_expected_cudaLaunchKernels=0`?
# In this test, foreach functions don't go through fast path,
# but as there is only one tensor in each list of tensors,
# `cudaLaunchKernel` is 1 so ForeachFuncWrapper internal assert fails.
foreach_op, native_op, foreach_op_, native_op_ = self._get_funcs(op, n_expected_cudaLaunchKernels=0)
# 0-strides
tensor1 = make_tensor((10, 10), dtype=dtype, device=device)
tensor2 = make_tensor((1,), device=device, dtype=dtype).expand_as(tensor1)
inputs = ([tensor1], [tensor2])
self._binary_test(dtype, foreach_op, native_op, inputs, is_fastpath=False, is_inplace=False)
self._binary_test(dtype, foreach_op_, native_op_, inputs, is_fastpath=False, is_inplace=True)
# different strides
tensor1 = torch.zeros(10, 10, device=device, dtype=dtype)
tensor2 = torch.ones(10, 10, device=device, dtype=dtype)
inputs = ([tensor1], [tensor2.t()])
self._binary_test(dtype, foreach_op, native_op, inputs, is_fastpath=False, is_inplace=False)
self._binary_test(dtype, foreach_op_, native_op_, inputs, is_fastpath=False, is_inplace=True)
# non contiguous
tensor1 = make_tensor((5, 2, 1, 3), device=device, dtype=dtype, noncontiguous=True)
tensor2 = make_tensor((5, 2, 1, 3), device=device, dtype=dtype, noncontiguous=True)
self.assertFalse(tensor1.is_contiguous())
self.assertFalse(tensor2.is_contiguous())
inputs = ([tensor1], [tensor2])
self._binary_test(dtype, foreach_op, native_op, inputs, is_fastpath=False, is_inplace=False)
self._binary_test(dtype, foreach_op_, native_op_, inputs, is_fastpath=False, is_inplace=True)
# sliced tensor
tensor1 = make_tensor((5, 2, 1, 3), device=device, dtype=dtype)
tensor2 = make_tensor((5, 2, 1, 3 * 7), device=device, dtype=dtype)[:, :, :, ::7]
inputs = ([tensor1], [tensor2])
self._binary_test(dtype, foreach_op, native_op, inputs, is_fastpath=False, is_inplace=False)
self._binary_test(dtype, foreach_op_, native_op_, inputs, is_fastpath=False, is_inplace=True)
def _test_pointwise_op(self,
device,
dtype,
opinfo,
N,
is_fastpath,
disable_fastpath,
*,
values=None):
n_expected_cudaLaunchKernels = N if disable_fastpath else 1
op, ref, inplace_op, inplace_ref = self._get_funcs(
opinfo, n_expected_cudaLaunchKernels)
inputs = [
opinfo.sample_inputs(device,
dtype,
N,
noncontiguous=not is_fastpath),
opinfo.sample_inputs(device,
dtype,
N,
noncontiguous=not is_fastpath),
opinfo.sample_inputs(device,
dtype,
N,
noncontiguous=not is_fastpath),
]
self._pointwise_test(dtype,
op,
ref,
inputs,
is_fastpath,
is_inplace=False,
values=values)
self._pointwise_test(dtype,
inplace_op,
inplace_ref,
inputs,
is_fastpath,
is_inplace=True,
values=values)
# Tests of implicit broadcasting
inputs = [
opinfo.sample_inputs(device,
dtype,
N,
noncontiguous=not is_fastpath,
same_size=True),
[
make_tensor((N - i, 1),
device=device,
dtype=dtype,
noncontiguous=not is_fastpath) for i in range(N)
],
[
make_tensor((1, N - i),
device=device,
dtype=dtype,
noncontiguous=not is_fastpath) for i in range(N)
],
]
self._pointwise_test(dtype,
op,
ref,
inputs,
is_fastpath and disable_fastpath,
is_inplace=False,
values=values)
self._pointwise_test(dtype,
inplace_op,
inplace_ref,
inputs,
is_fastpath and disable_fastpath,
is_inplace=True,
values=values)
def _test_binary_op_tensorlists(self, device, dtype, opinfo, N,
is_fastpath, disable_fastpath):
n_expected_cudaLaunchKernels = N if disable_fastpath else 1
op, ref, inplace_op, inplace_ref = self._get_funcs(
opinfo, n_expected_cudaLaunchKernels)
inputs = [
opinfo.sample_inputs(device,
dtype,
N,
noncontiguous=not is_fastpath),
opinfo.sample_inputs(device,
dtype,
N,
noncontiguous=not is_fastpath),
]
self._binary_test(dtype,
op,
ref,
inputs,
is_fastpath,
is_inplace=False)
self._binary_test(dtype,
inplace_op,
inplace_ref,
inputs,
is_fastpath,
is_inplace=True)
if opinfo.supports_alpha_param:
alpha = None
if dtype in torch.testing.get_all_int_dtypes():
alpha = 3
elif dtype.is_complex:
alpha = complex(3, 3)
else:
alpha = 3.14
self._binary_test(dtype,
op,
ref,
inputs,
is_fastpath,
is_inplace=False,
alpha=alpha)
self._binary_test(dtype,
inplace_op,
inplace_ref,
inputs,
is_fastpath,
is_inplace=True,
alpha=alpha)
# Tests of implicit broadcasting
# When sizes of tensors don't match, foreach functions are supposed to choose slow path
# even if this methods's argument `is_fastpath` is True.
# `cudaLaunchKernel` will be equal to `N`. For assert in `ForeachFuncWrapper` to pass,
# we pass `is_fastpath and disable_fastpath` to `_binary_test`'s argument of is_fastpath.
# as n_expected_cudaLaunchKernels is N if disable_fastpath.
inputs = [
opinfo.sample_inputs(device,
dtype,
N,
noncontiguous=not is_fastpath),
[
make_tensor((N - i, 1),
device=device,
dtype=dtype,
noncontiguous=not is_fastpath) for i in range(N)
],
]
self._binary_test(dtype,
op,
ref,
inputs,
is_fastpath and disable_fastpath,
is_inplace=False)
self._binary_test(dtype,
inplace_op,
inplace_ref,
inputs,
is_fastpath and disable_fastpath,
is_inplace=True)