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

[FEA] Remove row coversion code since we have fixed the kernel visibility issue #14853

Closed
ttnghia opened this issue Jan 23, 2024 · 0 comments · Fixed by #15234
Closed

[FEA] Remove row coversion code since we have fixed the kernel visibility issue #14853

ttnghia opened this issue Jan 23, 2024 · 0 comments · Fixed by #15234
Labels
feature request New feature or request libcudf Affects libcudf (C++/CUDA) code. Spark Functionality that helps Spark RAPIDS

Comments

@ttnghia
Copy link
Contributor

ttnghia commented Jan 23, 2024

In #14664, we temporarily moved the row conversion code from spark-rapids-jni into libcudf. It is necessary to overcome a thrust/cub namespace visibility issue that triggers invalid memory access when calling to thrust::in(ex)clusive_scan (NVIDIA/spark-rapids-jni#1567).

Now we have fixes for the namespace visibility issue (rapidsai/rapids-cmake#523 and NVIDIA/cuCollections#422). Thus, we need to revert #14664 and move the code back to spark-rapids-jni.
@ttnghia ttnghia added feature request New feature or request Needs Triage Need team to review and classify libcudf Affects libcudf (C++/CUDA) code. Spark Functionality that helps Spark RAPIDS and removed Needs Triage Need team to review and classify labels Jan 23, 2024
@davidwendt davidwendt mentioned this issue Mar 4, 2024
Merged
3 tasks
@ttnghia ttnghia mentioned this issue Mar 5, 2024
Merged
rapids-bot bot pushed a commit that referenced this issue Mar 5, 2024
@ttnghia
Remove row conversion code from libcudf (#15234)
e612a8a 
This is to remove the row conversion code from libcudf. It was move from spark-rapids-jni (by #14664) to temporarily workaround the issue due to conflict of kernel names that causes invalid memory access when calling to `thrust::in(ex)clusive_scan` (NVIDIA/spark-rapids-jni#1567).

Now we have fixes for the namespace visibility issue (by marking all libcudf kenels private in rapidsai/rapids-cmake#523 and NVIDIA/cuCollections#422) and need to move back the code.

Closes #14853.

Authors:
  - Nghia Truong (https://github.com/ttnghia)

Approvers:
  - David Wendt (https://github.com/davidwendt)
  - Bradley Dice (https://github.com/bdice)

URL: #15234
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
feature request New feature or request libcudf Affects libcudf (C++/CUDA) code. Spark Functionality that helps Spark RAPIDS
Projects
cuDF/Dask/Numba/UCX
Archived in project
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

Remove row conversion code from libcudf ttnghia/cudf
1 participant
@ttnghia