[TOPI][Hexagon] Implement quantized depthwise conv2d #12499
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
gayatripk1
force-pushed
the
gayatripk1/quant-dwconv
branch
from
0b88533 to
024d856
Compare
gayatripk1
force-pushed
the
gayatripk1/quant-dwconv
branch
from
225c601 to
2af97a3
Compare
gayatripk1
force-pushed
the
gayatripk1/quant-dwconv
branch
from
c872acf to
55c7822
Compare
Collaborator
|
Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews from Reviewers by @-ing them in a comment. Generated by tvm-bot |
gayatripk1
force-pushed
the
gayatripk1/quant-dwconv
branch
from
e68d590 to
6690e8a
Compare
areusch
added
needs-triage
Member
|
@gayatripk1 please update the PR description |
Contributor
Author
Done. |
masahi
reviewed
Oct 28, 2022
| E-Bias+x+1 < 15 | ||
| E-Bias+x+1 <= 14 | ||
| Max x will make E-Bias+x+1 = 14 | ||
| x = 13 - E + Bias |
Member
There was a problem hiding this comment.
cc @ibsidorenko - I'm curious how the requantize operation done in QC "slice ops" (such as this PR) compares to the one done by QNN canonicalization.
masahi
approved these changes
Oct 28, 2022
xinetzone
pushed a commit
to daobook/tvm
that referenced
this pull request
Nov 10, 2022
* [TOPI][Hexagon] Implement quantized depthwise conv2d * Fix lint errors * Fix lint error * Fix lint errors
xinetzone
pushed a commit
to daobook/tvm
that referenced
this pull request
Nov 25, 2022
* [TOPI][Hexagon] Implement quantized depthwise conv2d * Fix lint errors * Fix lint error * Fix lint errors
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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Outdated suggestions cannot be applied.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.
This PR adds implementation for quantized depthwise convolution op for hexagon. The quantization method uses fixed-point number to replace floating point instructions.
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from Reviewers by @ them in the pull request thread.
cc @mehrdadh