[SYCL][Graph] Implement dynamic command-groups #380
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
EwanC
force-pushed
the
ewan/dyn_cgf_impl
branch
2 times, most recently
from
6f38259
to
62c50d3
Compare
Bensuo
reviewed
Oct 17, 2024
fabiomestre
reviewed
Oct 17, 2024
fabiomestre
reviewed
Oct 18, 2024
EwanC
force-pushed
the
ewan/dyn_cgf_impl
branch
7 times, most recently
from
12decab
to
319c43e
Compare
Bensuo
approved these changes
Oct 30, 2024
EwanC
force-pushed
the
ewan/dyn_cgf_impl
branch
from
319c43e
to
288324b
Compare
Implement Dynamic Command-Group feature specified in PR [[SYCL][Graph] Add specification for kernel binary updates](intel#14896) This feature enables updating `ur_kernel_handle_t` objects in graph nodes between executions as well as parameters and execution range of nodes. This functionality is currently supported on CUDA & HIP which are used for testing in the new E2E tests. Level Zero support will follow shortly, resulting in the removal of the `XFAIL` labels from the E2E tests. The code for adding nodes to a graph has been refactored to split out verification of edges, and marking memory objects used in a node, as separate helper functions. This allows path for adding a command-group node to do this functions over each CG in the list before creating the node itself. The `dynamic_parameter_impl` code has also been refactored so the code is shared for updating a dynamic parameter used in both a regular kernel node and a dynamic command-group node. See the addition to the design doc for further details on the implementation.
Create helper function for getting UR details out of CG.
EwanC
force-pushed
the
ewan/dyn_cgf_impl
branch
from
288324b
to
331d19b
Compare
EwanC
force-pushed
the
ewan/dyn_cgf_impl
branch
from
331d19b
to
3737c98
Compare
|
I've taken the upstream PR for this git branch out of draft, as I want to get some |
fabiomestre
approved these changes
Nov 4, 2024
|
Closing in favor of upstream PR intel#14896 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Implementation of dynamic kernel binaries from intel#14896
Same git branch of used in intel#15700 for CI testing, but can do internal team reviews on this fork to make that PR look less messy.