Skip to content

[SYCL] Fix rectangle argument order when passing to PI routines #2608

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 11 commits into from
Oct 20, 2020

Conversation

cperkinsintel
Copy link
Contributor

For 2D and 3D buffers and images, some of the arguments passed to the plugin interface are not always correct or in the right order. For example, with 2D buffer we pass height-in-bytes, rather than width-in-bytes as part of a region or offset argument. This fixes this, slightly expands the PI Trace, and and also adds testing so we can more easily observe and catch this. Note that presently, images and buffers use multidimensional range/ids in the reverse order of each other. This fix does not attempt to unify those representations, but comments have been added to help clarify this in the future.

Signed-off-by: Chris Perkins <[email protected]>
@cperkinsintel cperkinsintel marked this pull request as draft October 8, 2020 06:02
@cperkinsintel cperkinsintel marked this pull request as ready for review October 8, 2020 07:16
Copy link
Contributor

@s-kanaev s-kanaev left a comment

Choose a reason for hiding this comment

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

Didn't take a look at memory manager's source changes and the tests yet.
Though, there are some minor comments.

@s-kanaev
Copy link
Contributor

s-kanaev commented Oct 8, 2020

/summary:run

@cperkinsintel cperkinsintel requested a review from s-kanaev October 9, 2020 16:15
smaslov-intel
smaslov-intel previously approved these changes Oct 12, 2020
Copy link
Contributor

@s-kanaev s-kanaev left a comment

Choose a reason for hiding this comment

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

Didn't take a look at the test yet.

Signed-off-by: Chris Perkins <[email protected]>
@cperkinsintel
Copy link
Contributor Author

pinging reviewers.

@romanovvlad romanovvlad merged commit 70d6f87 into intel:sycl Oct 20, 2020
iclsrc pushed a commit that referenced this pull request Jul 5, 2024
They can be used as SPIR-V friendly calls as there is no obvious mapping
to any existing LLVM instruction.

The tests are basically copying the ones added in #2392

This change will address the second part of #2302 issue

Original commit:
KhronosGroup/SPIRV-LLVM-Translator@c75fab28b73642e
iclsrc pushed a commit that referenced this pull request Jul 26, 2024
They can be used as SPIR-V friendly calls as there is no obvious mapping
to any existing LLVM instruction.

The tests are basically copying the ones added in #2392

This change will address the second part of #2302 issue

Original commit:
KhronosGroup/SPIRV-LLVM-Translator@c75fab28b73642e
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.

5 participants