Skip to content

[SYCL][DOC] Introduce IPC for events in sycl_ext_oneapi_inter_process_communication#21334

Open
slawekptak wants to merge 17 commits intointel:syclfrom
slawekptak:ext_inter_process
Open

[SYCL][DOC] Introduce IPC for events in sycl_ext_oneapi_inter_process_communication#21334
slawekptak wants to merge 17 commits intointel:syclfrom
slawekptak:ext_inter_process

Conversation

@slawekptak
Copy link
Copy Markdown
Contributor

No description provided.

@slawekptak slawekptak requested a review from gmlueck February 20, 2026 12:08
@slawekptak slawekptak changed the title [SYCL][DOC] sycl_ext_oneapi_inter_process_communication minor changes [SYCL][DOC] Introduce IPC for events in sycl_ext_oneapi_inter_process_communication Mar 16, 2026
@slawekptak slawekptak marked this pull request as ready for review April 13, 2026 09:28
@slawekptak slawekptak requested a review from a team as a code owner April 13, 2026 09:28
@slawekptak slawekptak marked this pull request as draft April 13, 2026 09:28
@slawekptak slawekptak marked this pull request as ready for review April 13, 2026 11:50
_Returns:_ A pointer to an event which is synchronized with the event
represented by `handle_data`. The returned event is associated with context
`ctx`. Those events are synchronized in a sense, that when one of the events
gets signaled, that state is automatically represented in the other event.
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

What device is the event associated with? Does this API need to take a device parameter?

represented by `handle_data`. The returned event is associated with context
`ctx`. Those events are synchronized in a sense, that when one of the events
gets signaled, that state is automatically represented in the other event.

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

I think we should add a Remarks section:

Remarks: In order to avoid a resource leak, the event returned from this function must be passed to the close function when it is no longer needed.

But this makes me wonder why we need the close function at all. Why can't the SYCL runtime automatically close the event when the event object is destroyed?

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.

2 participants