[refactor][relay pass] Separate analysis and transform passes #5035
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
zhiics
force-pushed
the
passes
branch
2 times, most recently
from
98d18c3
to
b298a2f
Compare
|
Let us remove the pass folder and just do relay/transforms and relay/analysis |
|
@tqchen updated. PTAL. Thanks. |
tqchen
approved these changes
Mar 11, 2020
|
@zhiics please rebase against the master |
comaniac
approved these changes
Mar 11, 2020
icemelon
approved these changes
Mar 12, 2020
trevor-m
pushed a commit
to trevor-m/tvm
that referenced
this pull request
Apr 16, 2020
…#5035) * [refactor][relay pass] Separate analysis and transform passes into different subfolders * remove pass folder
zhiics
added a commit
to neo-ai/tvm
that referenced
this pull request
Apr 17, 2020
…#5035) * [refactor][relay pass] Separate analysis and transform passes into different subfolders * remove pass folder
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Outdated suggestions cannot be applied.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.
As we are incrementally adding more and more passes to Relay. It makes sense to separate these passes into
analysisandtransformsnamespaces. This makes the code cleaner and easy to find the pass that users want. In addition, commercial compilers like LLVM also organize the passes similarly.This PR mainly separates the C++ side and creates
analysisandtransformsunder passes. A followup PR will refactor the Python side.Some discussion about this is here: https://discuss.tvm.ai/t/discuss-annotation-defined-subgraphs/5934/4
CC @tqchen @jroesch @icemelon9 @mbaret @comaniac