Skip to content

Fix a race for CUDA event in CachingHostAllocator #237

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
fwyzard merged 1 commit into from
Jan 7, 2019
Merged

Fix a race for CUDA event in CachingHostAllocator #237

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
9 changes: 5 additions & 4 deletions HeterogeneousCore/CUDAServices/src/CachingHostAllocator.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -538,9 +538,6 @@ struct CachingHostAllocator
}
}

// Unlock
mutex.Unlock();

if (CubDebug(error = cudaGetDevice(&entrypoint_device))) return error;
if (entrypoint_device != search_key.device) {
if (CubDebug(error = cudaSetDevice(search_key.device))) return error;
Expand All @@ -550,7 +547,11 @@ struct CachingHostAllocator
// Insert the ready event in the associated stream (must have current device set properly)
if (CubDebug(error = cudaEventRecord(search_key.ready_event, search_key.associated_stream))) return error;
}
else

// Unlock
mutex.Unlock();

if (!recached)
{
// Free the allocation from the runtime and cleanup the event.
if (CubDebug(error = cudaFreeHost(d_ptr))) return error;
Expand Down