Skip to content
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

Skip test when atomic operations are not supported on GPU. #7117

Merged
merged 8 commits into from
Feb 21, 2024
Merged

Skip test when atomic operations are not supported on GPU. #7117

Changes from 3 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
b174ba0
Skip test when atomic operations are not supported on GPU.
drivanov Feb 13, 2024
9f29957
Fixing lint problems
drivanov Feb 13, 2024
e9c74fa
Merge branch 'master' into test_ops
drivanov Feb 14, 2024
18b7553
Changes suggested by @frozenbugs
drivanov Feb 20, 2024
82b5045
Merge branch 'test_ops' of https://github.com/drivanov/dgl into test_ops
drivanov Feb 20, 2024
219d53a
Fixing lint problems
drivanov Feb 20, 2024
491cb45
Fixing lint problems
drivanov Feb 20, 2024
8f569ec
Merge branch 'master' into test_ops
drivanov Feb 20, 2024
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
10 changes: 5 additions & 5 deletions tests/python/common/ops/test_ops.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -413,14 +413,14 @@ def test_gather_mm_idx_b(feat_size, dtype, tol):
and not torch.cuda.is_bf16_supported()
):
pytest.skip("BF16 is not supported.")

if (
F._default_context_str == "gpu"
and dtype == torch.float16
if F._default_context_str == "gpu" and (
dtype == torch.float16
and torch.cuda.get_device_capability() < (7, 0)
or dtype == torch.bfloat16
and torch.cuda.get_device_capability() < (8, 0)
frozenbugs marked this conversation as resolved.
Show resolved Hide resolved
):
pytest.skip(
f"FP16 is not supported for atomic operations on GPU with "
f"{dtype} is not supported for atomic operations on GPU with "
f"cuda capability ({torch.cuda.get_device_capability()})."
)

Expand Down
Loading