Skip to content

[SYCL][PI] Fix PI_KERNEL_MAX_SUB_GROUP_SIZE query for devices without sub groups #9543

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

Merged
merged 6 commits into from
May 30, 2023

Conversation

0x12CC
Copy link
Contributor

@0x12CC 0x12CC commented May 19, 2023

Change the fallback behavior for PI_KERNEL_MAX_SUB_GROUP_SIZE to return the maximum sub group size for the device, rather than the maximum work group size for the kernel, on devices where sub groups are not supported. This change makes it consistent with the result of the PI_DEVICE_INFO_SUB_GROUP_SIZES_INTEL query.

…ub groups

Change the fallback behavior for `PI_KERNEL_MAX_SUB_GROUP_SIZE` to
return the maximum sub group size for the device, rather than the
maximum work group size for the kernel, on devices where sub groups are
not supported. This change makes it consistent with the result of the
`PI_DEVICE_INFO_SUB_GROUP_SIZES_INTEL` query.

Signed-off-by: Michael Aziz <michael.aziz@intel.com>
@0x12CC 0x12CC requested a review from a team as a code owner May 19, 2023 20:45
@0x12CC 0x12CC requested a review from aelovikov-intel May 19, 2023 20:45
@0x12CC 0x12CC changed the title [SYCL] Fix PI_KERNEL_MAX_SUB_GROUP_SIZE query for devices without sub groups [SYCL][PI] Fix PI_KERNEL_MAX_SUB_GROUP_SIZE query for devices without sub groups May 19, 2023
Signed-off-by: Michael Aziz <michael.aziz@intel.com>
@0x12CC 0x12CC temporarily deployed to aws May 19, 2023 21:39 — with GitHub Actions Inactive
@0x12CC 0x12CC temporarily deployed to aws May 19, 2023 22:44 — with GitHub Actions Inactive
@maarquitos14
Copy link
Contributor

Could you add comments in the code explaining why we need two calls to PI? I understand it's one to get the size and one to get the elements, correct me if I'm wrong.

Copy link
Contributor

@maarquitos14 maarquitos14 left a comment

Choose a reason for hiding this comment

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

LGTM

0x12CC added 2 commits May 25, 2023 11:44
Signed-off-by: Michael Aziz <michael.aziz@intel.com>
@0x12CC 0x12CC temporarily deployed to aws May 25, 2023 19:19 — with GitHub Actions Inactive
@0x12CC 0x12CC temporarily deployed to aws May 25, 2023 19:57 — with GitHub Actions Inactive
0x12CC added 2 commits May 30, 2023 07:03
Signed-off-by: Michael Aziz <michael.aziz@intel.com>
@0x12CC 0x12CC requested a review from steffenlarsen May 30, 2023 14:03
Copy link
Contributor

@steffenlarsen steffenlarsen left a comment

Choose a reason for hiding this comment

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

LGTM!

@0x12CC 0x12CC temporarily deployed to aws May 30, 2023 14:38 — with GitHub Actions Inactive
@0x12CC 0x12CC temporarily deployed to aws May 30, 2023 16:11 — with GitHub Actions Inactive
@steffenlarsen steffenlarsen merged commit 98cdf4c into intel:sycl May 30, 2023
@0x12CC 0x12CC deleted the kernel_max_sg_size branch May 30, 2023 17:22
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants