Skip to content

Don't launch stats counting kernels when stats not enabled #127

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
gmarkall merged 1 commit into from
Feb 20, 2025
Merged

Don't launch stats counting kernels when stats not enabled #127

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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: 5 additions & 1 deletion numba_cuda/numba/cuda/dispatcher.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -256,7 +256,11 @@ def bind(self):
"""
cufunc = self._codelibrary.get_cufunc()

if hasattr(self, "target_context") and self.target_context.enable_nrt:
if (
hasattr(self, "target_context")
and self.target_context.enable_nrt
and config.CUDA_NRT_STATS
):
rtsys.ensure_initialized()
rtsys.set_memsys_to_module(cufunc.module)
# We don't know which stream the kernel will be launched on, so
Expand Down
5 changes: 4 additions & 1 deletion numba_cuda/numba/cuda/tests/nrt/test_nrt.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -171,7 +171,10 @@ def foo():
arr = cuda_arange(5 * tmp[0]) # noqa: F841
return None

with override_config('CUDA_ENABLE_NRT', True):
with (
override_config('CUDA_ENABLE_NRT', True),
override_config('CUDA_NRT_STATS', True)
):
# Switch on stats
rtsys.memsys_enable_stats()
# check the stats are on
Expand Down
5 changes: 4 additions & 1 deletion numba_cuda/numba/cuda/tests/nrt/test_nrt_refct.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,7 +18,10 @@ def tearDown(self):
super(TestNrtRefCt, self).tearDown()

def run(self, result=None):
with override_config("CUDA_ENABLE_NRT", True):
with (
override_config("CUDA_ENABLE_NRT", True),
override_config('CUDA_NRT_STATS', True)
):
super(TestNrtRefCt, self).run(result)

def test_no_return(self):
Expand Down