-
Notifications
You must be signed in to change notification settings - Fork 890
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
Limit the number of keys to calculate column sizes and page starts in PQ reader to 1B #17059
base: branch-24.12
Are you sure you want to change the base?
Limit the number of keys to calculate column sizes and page starts in PQ reader to 1B #17059
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
A couple small comments on type safety but generally looks good.
…thub.com/mhaseeb123/cudf into bug/limit-num-keys-for-ultra-wide-tables
|
||
// Manually create a int64_t `key_start` compatible counting_transform_iterator to avoid | ||
// implicit casting to size_type. | ||
auto const reduction_keys = thrust::make_transform_iterator( |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The smoking gun. cudf::detail::make_counting_transform_iterator
implicitly typecasts key_start
to size_type
causing all sorts of problems.
Description
This PR limits the number of keys to use at a time to calculate column
sizes
andpage_start_values
to 1B averting possible OOM and UB from implicit typecasting ofsize_t
iterator tosize_type
iterators inthrust::reduce_by_key
.Closes #16985
Closes #17086
Resolved
Checklist