-
Notifications
You must be signed in to change notification settings - Fork 3.5k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[ETHOSN] Support multiply conversion to depthwise #12403
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM!
@tvm-bot rerun |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM, thanks @lhutton1 @NicolaLancellotti!
@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
Thanks @NicolaLancellotti, @leandron! |
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.
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