Skip to content

Conversation

@lhutton1
Copy link
Contributor

@lhutton1 lhutton1 commented Aug 22, 2022

In similar fashion to the conversion of mul to depthwise, this commit converts add when one input is a constant of shape [1, ..., n] to a depthwise convolution. If neither input is a constant, the add is offloaded naturally like before.

The addition testing has been improved to use pytest features.

Note that this PR also contains the contents of #12403 until it is merged.

cc @NicolaLancellotti @leandron @ashutosh-arm

In similar fashion to the conversion of mul to depthwise, this commit
converts add when one input is a constant of shape [1, ..., n] to a
depthwise convolution. If neither input is a constant, the add is
offloaded naturally like before.

The addition testing has been improved to use pytest features.

Change-Id: I93e7b7619736767992e70aaa6e60e0d7a2875f76
@lhutton1 lhutton1 marked this pull request as ready for review August 24, 2022 14:07
Copy link
Contributor

@leandron leandron left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM. Thanks @lhutton1 and @NicolaLancellotti for the review.

@leandron leandron merged commit f7c1436 into apache:main Aug 25, 2022
@lhutton1 lhutton1 deleted the add-support branch September 6, 2022 22:06
xinetzone pushed a commit to daobook/tvm that referenced this pull request Nov 25, 2022
In similar fashion to the conversion of mul to depthwise, this commit
converts add when one input is a constant of shape [1, ..., n] to a
depthwise convolution. If neither input is a constant, the add is
offloaded naturally like before.

The addition testing has been improved to use pytest features.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants