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

fix profiling execute_multipass #2239

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

fix profiling execute_multipass #2239

wants to merge 2 commits into from

Conversation

rjodinchr
Copy link
Contributor

  • fix clGetDeviceInfo(CL_DEVICE_MAX_WORK_ITEM_SIZES) by using the proper size

  • clamp localThreads[2] as for localThreads[0] and localThreads[2]

  • clamp all localThreads elements in regard of CL_MAX_WORK_GROUP_SIZE

  • fix the size using to create/read the output buffer

Fix #2238

@rjodinchr rjodinchr force-pushed the pr/execute-multipass branch 2 times, most recently from b9801df to b6193a8 Compare January 22, 2025 13:52
@rjodinchr
fix profiling execute_multipass
3d0cd94 
- fix clGetDeviceInfo(CL_DEVICE_MAX_WORK_ITEM_SIZES) by using the
proper size

- clamp all localThreads elements with regard to CL_MAX_WORK_GROUP_SIZE

- fix the size using to create/read the output buffer

Fix KhronosGroup#2238
@rjodinchr rjodinchr force-pushed the pr/execute-multipass branch from b6193a8 to 3d0cd94 Compare January 22, 2025 13:53
kpet
kpet previously approved these changes Feb 4, 2025
View reviewed changes
bashbaug
bashbaug previously approved these changes Feb 6, 2025
View reviewed changes
Copy link
Contributor

@bashbaug bashbaug left a comment

Choose a reason for hiding this comment

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

Works for me.

I was initially confused by the allocation, because it's allocating based on nChannels even though the kernel unconditionally writes four channels, but I guess it's OK because because we only ever call this function when nChannels is four.

@bashbaug
Copy link
Contributor

@rjodinchr can you please fix the merge conflict?

@rjodinchr rjodinchr dismissed stale reviews from bashbaug and kpet via ef84ed6 February 10, 2025 17:46
@CLAassistant
Copy link

CLAassistant commented Feb 10, 2025 •
edited
Loading

CLA assistant check
All committers have signed the CLA.

@bashbaug bashbaug requested a review from lakshmih February 11, 2025 16:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@bashbaug bashbaug bashbaug approved these changes

@kpet kpet kpet left review comments

@lakshmih lakshmih Awaiting requested review from lakshmih

Assignees
No one assigned
Labels
focused review
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

profiling execute_multipass issues
4 participants
@rjodinchr @bashbaug @CLAassistant @kpet