Skip to content

[BOO] Sync after profiling to fix flaky event loss #1329

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

Draft
rkayaith wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

[BOO] Sync after profiling to fix flaky event loss #1329

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: 6 additions & 0 deletions iree/turbine/kernel/boo/driver/driver.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -547,8 +547,14 @@ def pause_and_collect_mem():
)
pause_and_collect_mem()
if prof is not None:
for device in devices:
torch.cuda.synchronize(device)
prof.step()

# Ensure all GPU work and profiler cleanup is complete before returning.
# Without this, subsequent profiling sessions may lose events.
pause_and_collect_mem()

if results is None:
results = ()
if isinstance(results, torch.Tensor):
Expand Down
Loading