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Outdated suggestions cannot be applied.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.
Problem solved by the commit
A run-recipe defines how to execute a graph model using XRT.
How problem was solved, alternative solutions (if any) and why they were rejected
These changes contain a stand-alone runner class that reads and executes a run-recipe json file. The idea is to have tools generate the run-recipe along with xclbin and control code for kernels.
The format (schema) of the recipe json is loosely defined. The implementation of the runner drove some of the defintion of the json format.
A run-recipe is associated with exactly one xclbin which, when loaded into a region (partition) on the device, can run the recipe.
This is work-in-progress, base-lined, and validated for today's NPU TXN control code. The runner will change shortly when we obsolete xclbin for NPU.
The recipe will not work with Alveo as the runner uses xrt::runlist for execution and xrt::runlist is not supposed in Alveo.
Risks (if any) associated the changes in the commit
Unused code
What has been tested and how, request additional testing if necessary
NPU TXN ctrl code inference