-
Notifications
You must be signed in to change notification settings - Fork 232
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.
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
Replace whole-buffer slicing with direct refcounting #894
Conversation
Signed-off-by: Jason Lowe <jlowe@nvidia.com>
build |
Did you run any benchmarks to see if there was a change? |
Nothing rigorous like a microbenchmark. I did run My main motivation for implementing this was to cut down on the number of |
build |
#724 is starting to become quite annoying, seeing it fairly often in premerge CI. |
Signed-off-by: Jason Lowe <jlowe@nvidia.com>
Signed-off-by: Jason Lowe <jlowe@nvidia.com>
Signed-off-by: Jason Lowe <jlowe@nvidia.com>
…IDIA#894) Signed-off-by: spark-rapids automation <70000568+nvauto@users.noreply.github.com> Signed-off-by: spark-rapids automation <70000568+nvauto@users.noreply.github.com>
Fixes #585.
This changes occurrences where we were slicing the range of an entire buffer with a more direct increment of the reference count and reuse of the same buffer object. This cuts down on unnecessary object creation.