-
Notifications
You must be signed in to change notification settings - Fork 808
[SYCL][Graph] Add spec wording for graph-owned memory allocations #18001
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
- Using sycl_ext_oneapi_async_memory_alloc extension - Spec wording for graph support of the feature - Usage guide guidance for library authors - Usage guide examples of explicit and queue recording usage with and without mem pools
d204eb0
to
960c904
Compare
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
- Improve whole-graph update conditions list. - Remove unnecessary non-normative note about returned pointers. - Fix duplicate exception sections in finalize() definition.
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
- Remove references to removed features from async alloc spec - Improve links to async alloc spec - Minor rewording of spec changes - New usage guide example using in-order queue
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
- Fix broken links to base spec - Make get_required_mem_size noexcept - Minor wording improvements - Add end_recording to example snippets
@gmlueck Not sure if you've done a detailed review of this already but it should be good to go now if you would like to take another look at it. |
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
- Change error code for host/shared allocation use - Reword finalize to clarify multiple executable graphs
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.
Looks good!
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
sycl/doc/extensions/experimental/sycl_ext_oneapi_graph.asciidoc
Outdated
Show resolved
Hide resolved
I will be OOO for the rest of the week, so I approved. I think you understand my concern in the remaining comments, and I trust that you will address them. |
- Clarify zero-initialization behavior - Clarify error when recording subgraph with allocations
@intel/llvm-gatekeepers This should be good to merge now, thanks! |
Uh oh!
There was an error while loading. Please reload this page.