Skip to content

Accept zero BAR size for integrated GPUs in cuFile test #3169

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

Merged
isVoid merged 2 commits into from
Oct 21, 2026
Merged

Accept zero BAR size for integrated GPUs in cuFile test #3169

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
bdb6910
Accept zero BAR size for integrated GPUs in cuFile test
isVoid Oct 20, 2026
3ff8bda
Merge main and carry BAR-size test fix into cuda_bindings_13
isVoid Oct 21, 2026
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: 4 additions & 2 deletions cuda_bindings_13/tests/test_cufile.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1851,8 +1851,10 @@ def test_get_bar_size_in_kb():

# Verify BAR size is a reasonable value
assert isinstance(bar_size_kb, int), "BAR size should be an integer"
# Tegra devices may report 0 BAR size, which is acceptable
min_bar_size = 0 if get_tegra_kind() else 1
err, integrated = cuda.cuDeviceGetAttribute(cuda.CUdevice_attribute.CU_DEVICE_ATTRIBUTE_INTEGRATED, 0)
assert err == cuda.CUresult.CUDA_SUCCESS
# Integrated GPUs (including GB10 and Tegra) need not expose PCIe BAR memory.
min_bar_size = 0 if integrated else 1
assert bar_size_kb >= min_bar_size, f"BAR size should be >= {min_bar_size}"

logging.info(f"GPU BAR size: {bar_size_kb} KB ({bar_size_kb / 1024 / 1024:.2f} GB)")
Expand Down
Loading