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

Jump to bottom

Introduce some more rolling window benchmarks #17787

Merged
merged 7 commits into from
Jan 28, 2025
Merged

Introduce some more rolling window benchmarks #17787

merged 7 commits into from
Jan 28, 2025

Conversation

wence-
Copy link
Contributor

@wence- wence- commented Jan 23, 2025 •
edited by vuule
Loading

Description

Before embarking on more rolling window performance optimizations and code changes, let's introduce some new benchmarks:

  • demonstrating bad algorithmic behavior of large window rolling aggregations;
  • of the range-based rolling interface.

Checklist

  • I am familiar with the Contributing Guidelines.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.

wence- added 2 commits January 23, 2025 12:04
@wence-
Add benchmarks of large-window-size rolling aggregations
294b2b3 
These demonstrate the O(m*n) behaviour of rolling aggregations for
columns of size n and windows of length m.
@wence-
Add benchmarks of range-based rolling windows
9778d78 
In constrast to fixed offset rolling windows these must also search an
orderby column to find the window bounds.
@wence- wence- requested review from a team as code owners January 23, 2025 12:39
@wence- wence- requested review from vuule and lamarrr January 23, 2025 12:39
@wence- wence- added improvement Improvement / enhancement to an existing function non-breaking Non-breaking change labels Jan 23, 2025
@github-actions github-actions bot added libcudf Affects libcudf (C++/CUDA) code. CMake CMake build issue labels Jan 23, 2025
bdice
bdice approved these changes Jan 23, 2025
View reviewed changes
Copy link
Contributor

@bdice bdice left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

One suggestion, all else looks fine.

cpp/benchmarks/rolling/grouped_range_rolling_sum.cu Show resolved Hide resolved
vuule
vuule reviewed Jan 24, 2025
View reviewed changes
Copy link
Contributor

@vuule vuule left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

looks great, just a few small suggestions

cpp/benchmarks/rolling/grouped_range_rolling_sum.cu Outdated Show resolved Hide resolved
cpp/benchmarks/rolling/grouped_range_rolling_sum.cu Outdated Show resolved Hide resolved
cpp/benchmarks/rolling/grouped_range_rolling_sum.cu Outdated Show resolved Hide resolved
cpp/benchmarks/rolling/range_rolling_sum.cu Outdated Show resolved Hide resolved
@wence- wence- mentioned this pull request Jan 24, 2025
Open
3 tasks
@wence- wence- requested a review from vuule January 27, 2025 15:56
@vyasr
Copy link
Contributor

vyasr commented Jan 28, 2025

/merge

@rapids-bot rapids-bot bot merged commit 52cb4e8 into rapidsai:branch-25.02 Jan 28, 2025
107 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@davidwendt davidwendt davidwendt left review comments

@vuule vuule vuule approved these changes

@bdice bdice bdice approved these changes

@lamarrr lamarrr Awaiting requested review from lamarrr lamarrr is a code owner automatically assigned from rapidsai/cudf-cpp-codeowners

Assignees

@wence- wence-

@vyasr vyasr

Labels
CMake CMake build issue improvement Improvement / enhancement to an existing function libcudf Affects libcudf (C++/CUDA) code. non-breaking Non-breaking change
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
5 participants
@wence- @vyasr @bdice @vuule @davidwendt