Skip to content

Conversation

@lhutton1
Copy link
Contributor

Multiply can be supported when offloaded to the NPU by a conversion to a depthwise convolution operation. This is only supported when the multiply operation has a single single variable input with the other being a constant of shape [1, ..., C]. This commit adds a new pass "ConvertEquivalents" (name subject to change) to handle this conversion before codegen.

cc @NicolaLancellotti @leandron

Copy link
Contributor

@NicolaLancellotti NicolaLancellotti left a comment

Choose a reason for hiding this comment

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

LGTM!

@lhutton1
Copy link
Contributor Author

@tvm-bot rerun

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.

@leandron
Copy link
Contributor

@lhutton1 this now has a conflict, so when you have a moment and solve, I'm fine for this to be merged once CI is green again.

Multiply can be supported when offloaded to the NPU by a conversion to
a depthwise convolution operation. This is only supported when the
multiply operation has a single single variable input with the other
being a constant of shape [1, ..., C]. This commit adds a new pass
"ConvertEquivalents" (name subject to change) to handle this conversion
before codegen.

Change-Id: If8029373261364ed09fcd921ee71e31877a9125a
Change-Id: I7bb3a838c649158fb0f76c02e4af31e362d43937
@lhutton1 lhutton1 merged commit a0fe74b into apache:main Aug 24, 2022
@lhutton1 lhutton1 deleted the mul-support branch August 24, 2022 12:46
@lhutton1
Copy link
Contributor Author

Thanks @NicolaLancellotti, @leandron!

xinetzone pushed a commit to daobook/tvm that referenced this pull request Nov 25, 2022
Multiply can be supported when offloaded to the NPU by a conversion to a depthwise convolution operation. This is only supported when the multiply operation has a single single variable input with the other being a constant of shape [1, ..., C]. This commit adds a new pass "ConvertEquivalents" (name subject to change) to handle this conversion before codegen.
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