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

Intentionally leak static CUDA resources to avoid crash (part 2) #462

Merged
merged 4 commits into from
Sep 12, 2024
Merged

Intentionally leak static CUDA resources to avoid crash (part 2) #462

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ccaa81f
Intentionally leak static CUDA resources
kingcrimsontianyu Sep 10, 2024
f919ce4
Reformat
kingcrimsontianyu Sep 10, 2024
df06a5d
Add references in the comment
kingcrimsontianyu Sep 11, 2024
49c1bd0
Add more clarifying comments
kingcrimsontianyu Sep 11, 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
18 changes: 8 additions & 10 deletions cpp/include/kvikio/posix_io.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,16 +42,14 @@ class StreamsByThread {

public:
StreamsByThread() = default;
~StreamsByThread() noexcept
{
for (auto& [_, stream] : _streams) {
try {
CUDA_DRIVER_TRY(cudaAPI::instance().StreamDestroy(stream));
} catch (const CUfileException& e) {
kingcrimsontianyu marked this conversation as resolved.
Show resolved Hide resolved
std::cerr << e.what() << std::endl;
}
}
}

// Here we intentionally do not destroy in the destructor the CUDA resources
// (e.g. CUstream) with static storage duration, but instead let them leak
// on program termination. This is to prevent undefined behavior in CUDA. See
// <https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#initialization>
// This also prevents crash (segmentation fault) if clients call
// cuDevicePrimaryCtxReset() or cudaDeviceReset() before program termination.
~StreamsByThread() = default;
madsbk marked this conversation as resolved.
Show resolved Hide resolved

static CUstream get(CUcontext ctx, std::thread::id thd_id)
{
Expand Down