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

Switched AST benchmarks from GoogleBench to NVBench #16952

Open
wants to merge 8 commits into
base: branch-24.12
Choose a base branch
from
Open

Switched AST benchmarks from GoogleBench to NVBench #16952

wants to merge 8 commits into from
+18 −35

Conversation

lamarrr
Copy link
Contributor

@lamarrr lamarrr commented Sep 27, 2024 •
edited
Loading

Description

This merge request switches the Benchmarking solution for the AST benchmark from GoogleBench to NVBench. It also refactors the L2 cache flushing functionality of cuda_event_timer into a separate function flush_L2_device_cache, since NVBench already performs the timing, synchronization, and timer setup necessary.

Checklist

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

@lamarrr lamarrr added feature request New feature or request non-breaking Non-breaking change labels Sep 27, 2024
@lamarrr lamarrr requested a review from a team as a code owner September 27, 2024 23:26
@github-actions github-actions bot added libcudf Affects libcudf (C++/CUDA) code. CMake CMake build issue labels Sep 27, 2024
karthikeyann
karthikeyann reviewed Sep 27, 2024
View reviewed changes
Copy link
Contributor

@karthikeyann karthikeyann left a comment

Choose a reason for hiding this comment

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

clean porting. appreciate the minimal diff.

cpp/benchmarks/ast/transform.cpp Outdated Show resolved Hide resolved
cpp/benchmarks/ast/transform.cpp Outdated Show resolved Hide resolved
bdice
bdice approved these changes Sep 27, 2024
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.

This is nice, thanks!

@bdice
Copy link
Contributor

bdice commented Sep 27, 2024

@lamarrr Can you avoid force-pushing? It's helpful for reviewers when we can see the history. I just reviewed as you pushed, and now I don't know how to easily compare the state before and after your push. Generally, force-pushing is a last resort for us, only if it's strictly needed.

@lamarrr
Copy link
Contributor Author

lamarrr commented Sep 27, 2024

@lamarrr Can you avoid force-pushing? It's helpful for reviewers when we can see the history. I just reviewed as you pushed, and now I don't know how to easily compare the state before and after your push. Generally, force-pushing is a last resort for us, only if it's strictly needed.

noted!

@lamarrr @PointKernel
fixed global memory read calculation for ast benchmark
ca95756 
Co-authored-by: Yunsong Wang <yunsongw@nvidia.com>
PointKernel
PointKernel approved these changes Sep 30, 2024
View reviewed changes
Copy link
Member

@PointKernel PointKernel left a comment

Choose a reason for hiding this comment

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

LGTM

Thanks for the quick turnaround and addressing all my review comments!

@lamarrr
Copy link
Contributor Author

lamarrr commented Oct 1, 2024

LGTM

Thanks for the quick turnaround and addressing all my review comments!

thank you

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@karthikeyann karthikeyann karthikeyann left review comments

@bdice bdice bdice approved these changes

@PointKernel PointKernel PointKernel approved these changes

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

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

Assignees
No one assigned
Labels
CMake CMake build issue feature request New feature or request 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.
4 participants
@lamarrr @bdice @karthikeyann @PointKernel