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

Jump to bottom

[Improvement] Fetch runtime version with cuda-python instead of numba #1675

Open
wants to merge 4 commits into
base: branch-24.12
Choose a base branch
from
Open

[Improvement] Fetch runtime version with cuda-python instead of numba #1675

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
2acf3ad
initial commit
Matt711 Sep 9, 2024
5471669
update doc string
Matt711 Sep 9, 2024
47b1e53
check status code, update docstring
Matt711 Sep 9, 2024
1a21d61
Merge branch 'branch-24.12' into improvement/fetch-runtime-version-wi…
Matt711 Nov 5, 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
16 changes: 7 additions & 9 deletions python/rmm/rmm/_cuda/gpu.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,4 @@
# Copyright (c) 2020, NVIDIA CORPORATION.
# Copyright (c) 2020-2024, NVIDIA CORPORATION.

from cuda import cuda, cudart

Expand Down Expand Up @@ -78,15 +78,13 @@ def runtimeGetVersion():
The version is returned as (1000 major + 10 minor). For example,
CUDA 9.2 would be represented by 9020.

This calls numba.cuda.runtime.get_version() rather than cuda-python due to
current limitations in cuda-python.
This function automatically raises CUDARuntimeError with error message
and status code.
"""
# TODO: Replace this with `cuda.cudart.cudaRuntimeGetVersion()` when the
# limitation is fixed.
import numba.cuda

major, minor = numba.cuda.runtime.get_version()
return major * 1000 + minor * 10
status, version = cudart.getLocalRuntimeVersion()
if status != cudart.cudaError_t.cudaSuccess:
raise CUDARuntimeError(status)
return version


def getDeviceCount():
Expand Down
Loading