[RELAY] Refactor FoldConstant to skip TNonComputationalOps #6720
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
jwfromm
reviewed
Oct 20, 2020
|
LGTM, thanks! |
jwfromm
approved these changes
Oct 20, 2020
jroesch
approved these changes
Oct 20, 2020
junrushao
reviewed
Oct 22, 2020
Co-authored-by: Junru Shao <junrushao1994@gmail.com>
…or-tvm into non-computational
|
@junrushao1994 now that this is passing CI, can you take a final look and merge this? |
|
Sorry for being late. It looks good! Thanks! |
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Oct 29, 2020
* add TNonComputational to qnn ops and change FoldConstant * remove comments * check if op in nonComputational map * forgot to mark device_copy op as TNonComputational * hacky fix to fuseops pass * fix typo * manually skip device_copy in fold_constant * Update src/relay/transforms/fold_constant.cc Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com>
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 2, 2020
* add TNonComputational to qnn ops and change FoldConstant * remove comments * check if op in nonComputational map * forgot to mark device_copy op as TNonComputational * hacky fix to fuseops pass * fix typo * manually skip device_copy in fold_constant * Update src/relay/transforms/fold_constant.cc Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com>
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Dec 4, 2020
* add TNonComputational to qnn ops and change FoldConstant * remove comments * check if op in nonComputational map * forgot to mark device_copy op as TNonComputational * hacky fix to fuseops pass * fix typo * manually skip device_copy in fold_constant * Update src/relay/transforms/fold_constant.cc Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com>
trevor-m
pushed a commit
to neo-ai/tvm
that referenced
this pull request
Dec 4, 2020
* add TNonComputational to qnn ops and change FoldConstant * remove comments * check if op in nonComputational map * forgot to mark device_copy op as TNonComputational * hacky fix to fuseops pass * fix typo * manually skip device_copy in fold_constant * Update src/relay/transforms/fold_constant.cc Co-authored-by: Junru Shao <junrushao1994@gmail.com> Co-authored-by: Junru Shao <junrushao1994@gmail.com>
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.
This PR refactors FoldConstant to skip TNonComputational ops, instead of explicitly checking for those ops. It also makes all QNN ops TNonComputational. This allows the constant folder to be applied to graphs containing QNN ops.
@jroesch @jwfromm please take a look!