Skip to content

CUDA BFloat16 neg #45240

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
zasdfgbnm wants to merge 4 commits into from
Closed

CUDA BFloat16 neg #45240

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
43cfb34
CUDA BFloat16 neg
zasdfgbnm Sep 23, 2020
a0867e8
Merge branch 'master' of https://github.com/pytorch/pytorch into bflo…
zasdfgbnm Sep 24, 2020
b2bee63
Merge branch 'master' of github.com:pytorch/pytorch into bfloat-neg
zasdfgbnm Sep 25, 2020
19493fa
Merge branch 'bfloat-neg' of github.com:pytorch/pytorch into bfloat-neg
zasdfgbnm Sep 25, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 2 additions & 4 deletions aten/src/ATen/native/cuda/UnarySignKernels.cu
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -22,10 +22,8 @@ void logical_not_kernel_cuda(TensorIterator& iter) {

void neg_kernel_cuda(TensorIterator& iter) {
AT_DISPATCH_ALL_TYPES_AND_COMPLEX_AND2(ScalarType::Half, at::ScalarType::BFloat16, iter.dtype(), "neg_cuda", [&]() {
AT_SKIP_BFLOAT16_IF_NOT_ROCM(scalar_t, "neg_cuda", [&] {
gpu_kernel(iter, []GPU_LAMBDA(scalar_t a) -> scalar_t {
return -a;
});
gpu_kernel(iter, []GPU_LAMBDA(scalar_t a) -> scalar_t {
return -a;
});
});
}
Expand Down
2 changes: 1 addition & 1 deletion torch/testing/_internal/common_methods_invocations.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -336,7 +336,7 @@ def sample_inputs(self, device, dtype, requires_grad=False):
ref=np.negative,
dtypes=all_types_and_complex_and(torch.half, torch.bfloat16),
dtypesIfCPU=all_types_and_complex_and(torch.half, torch.bfloat16),
dtypesIfCUDA=all_types_and_complex_and(torch.half)),
dtypesIfCUDA=all_types_and_complex_and(torch.half, torch.bfloat16)),
UnaryUfuncInfo('sin',
ref=np.sin,
handles_large_floats=False,
Expand Down