Fixing execution region result placement. #19872
Merged
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Outdated suggestions cannot be applied.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.
This uses transfer ops to place allocations that escape execution regions. In the future we'll need something more sophisticated (AffinityAnalysis for the escaped results, etc) but in simple programs today where transfers are used to indicate resource movement it correctly picks up the destinations.
This also fixes
flow.tensor.barrier
andstream.async.barrier
to be tied ops (as they are metadata-only) and a few issues with affinity attribute assignment identified while tracking down the placement affinities.