[microNPU][ETHOSU] Softmax int8 legalization support

[Aleksei-grovety]

Add support for legalizing Softmax int8 to list NPU operations as implemented in Vela.

cc @neildhickey, @lhutton1, @ekalda, @leandron, @ilyag-grovety

[tvm-bot]

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.

• cc @Mousius, @leandron, @lhutton1 _{See #10317 for details}

_{Generated by tvm-bot}

[ilyag-grovety]

To make a test more precise, I think it's also better to verify operator_type of each contrib.ethosu.binary_elementwise op. And maybe a corresponding parameter for pooling.

[Aleksei-grovety]

I'll add it.

[ekalda]

Thanks @Aleksei-grovety, looks good to me in general (bar @ilyag-grovety suggestion). Since it is a 500 line beast of an operator, I wonder if it would make sense to break it out into a separate file?

[Aleksei-grovety]

Thanks @Aleksei-grovety, looks good to me in general (bar @ilyag-grovety suggestion). Since it is a 500 line beast of an operator, I wonder if it would make sense to break it out into a separate file?

I will add a separate file for Softmax legalization.

[Aleksei-grovety]

There is a problem with run microTVM demos, which consists in a greatly increased time to execute lower_to_te, I'm trying to find out the reason for this.

[ekalda]

LGTM!

[ekalda]

Thanks @Aleksei-grovety and @ilyag-grovety, this is now merged!