Break lazy accumulation of graphs

[jerome-habana]

Habana bridge lazily accumulates ops. This change
ensures we break graph exectuion across different stages to
get better performance and optimal resource usage.

Signed-off-by: Jerome [email protected]

What does this PR do?

Fixes #<issue_number>

Does your PR introduce any breaking changes? If yes, please list them.

Before submitting

• Was this discussed/approved via a GitHub issue? (not for typos and docs)
• Did you read the contributor guideline, Pull Request section?
• Did you make sure your PR does only one thing, instead of bundling different changes together?
• Did you make sure to update the documentation with your changes? (if necessary)
• Did you write any new necessary tests? (not for typos and docs)
• Did you verify new and existing tests pass locally with your changes?
• Did you list all the breaking changes introduced by this pull request?
• Did you update the CHANGELOG? (not for typos, docs, test updates, or minor internal changes/refactors)

PR review

Anyone in the community is welcome to review the PR.
Before you start reviewing, make sure you have read the review guidelines. In short, see the following bullet-list:

• Is this pull request ready for review? (if not, please submit in draft mode)
• Check that all items from Before submitting are resolved
• Make sure the title is self-explanatory and the description concisely explains the PR
• Add labels and milestones (and optionally projects) to the PR so it can be classified

Did you have fun?

Make sure you had fun coding 🙃

[kaushikb11]

@jerome-habana Are there any benchmarks with and without this PR changes?

[jerome-habana]

@jerome-habana Are there any benchmarks with and without this PR changes?

For simple models, the change will not have any visible impact. However, for larger models, we can see considerable gain in performance. The results are presented in PyTorch model repository of habana.