-
Notifications
You must be signed in to change notification settings - Fork 798
[SYCL][DOC] Add design document for SYCL-RTC #19698
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
Conversation
Signed-off-by: Julian Oppermann <[email protected]>
@intel/dpcpp-doc-reviewers @intel/dpcpp-devops-reviewers The workflow to generate documentation seems to be broken due to a dependency version mismatch: https://github.com/intel/llvm/actions/runs/16728105137/job/47349068323?pr=19698 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall, text looks good to me, just two minor comments.
I think we should also include this new file in sycl/doc/index.rst
.
code module into smaller units (either as requested by the user, or required by | ||
the ESIMD mode), and to compute the properties that need to be passed to the | ||
SYCL runtime when the device images are loaded. | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We could mention the code duplication and the plans to remove it in the future here.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Awesome!
*preprocessed* source string, i.e. with all `#include` directives resolved. We | ||
additionally compute a hash value of the rendered command-line arguments, and | ||
append it to the hash of the preprocessed source to obtain the final cache key. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I'd expect clang's PCH to have to deal with the same issue. Have you looked into re-using that infrastructure?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No, while we did some non-SYCL (due to lack of support at the time) experiments with PCHs, we have not specifically looked into reusing any hashing infra from there.
Signed-off-by: Julian Oppermann <[email protected]>
Signed-off-by: Julian Oppermann <[email protected]>
No description provided.