[OpenCLML] More ops and network coverage #12762
Merged
Conversation
This file contains hidden or 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
srkreddy1238
changed the title
leandron
reviewed
Sep 13, 2022
Contributor
leandron
left a comment
leandron
left a comment
There was a problem hiding this comment.
Hi @srkreddy1238, thanks for the PR. Can you improve the commit message with the actual operators are being added?
Contributor
@srkreddy1238 You can look at https://github.com/apache/tvm/blob/main/docs/contribute/pull_request.rst#commit-message-guideline for some guidelines on how to do that. HTH. Cheers. |
Added operators pooling (avg, max), binary operators (add, subtract, multiply, min, max) and concat. Clip operator with min=0 and max=6 is remapped to relu6 to take advantage of CLML acceleration without sub graphing this to fallback path. Added new test cases for above listed operators and also end-to-end network test cases for Resnet50 & InceptionV3. CLML support FP16 arithmetic mode which gives significant performance boost over FP32. This PR enhances FP16 usage based on Operator datatype in relay graph. Co-authored-by: Krishna Raju [email protected] Co-authored-by: Shwetank Singh [email protected]
Contributor
Author
|
@leandron pls take a look. |
leandron
approved these changes
Sep 14, 2022
Contributor
leandron
left a comment
leandron
left a comment
There was a problem hiding this comment.
LGTM, thanks @srkreddy1238 @gromero!
xinetzone
pushed a commit
to daobook/tvm
that referenced
this pull request
Nov 25, 2022
Added operators pooling (avg, max), binary operators (add, subtract, multiply, min, max) and concat. Clip operator with min=0 and max=6 is remapped to relu6 to take advantage of CLML acceleration without sub graphing this to fallback path. Added new test cases for above listed operators and also end-to-end network test cases for Resnet50 & InceptionV3. CLML support FP16 arithmetic mode which gives significant performance boost over FP32. This PR enhances FP16 usage based on Operator datatype in relay graph. Co-authored-by: Krishna Raju [email protected] Co-authored-by: Shwetank Singh [email protected]
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
Added operators pooling (avg, max), binary operators (add, subtract, multiply, min, max) and concat.
Clip operator with min=0 and max=6 is remapped to relu6 to take advantage of CLML acceleration
without sub graphing this to fallback path.
Added new test cases for above listed operators and also end-to-end network test cases for Resnet50
& InceptionV3.
CLML support FP16 arithmetic mode which gives significant performance boost over FP32. This PR
enhances FP16 usage based on Operator datatype in relay graph.
Co-authored-by: Krishna Raju [email protected]
Co-authored-by: Shwetank Singh [email protected]