[QNN] Multiplication operator

[tristan-arm]

Implementation of the qnn multiplication operator following the same pattern as the addition operator.

[anijain2305]

Thanks for the contribution! Please feel free to ping me for any QNN related PRs :)

I have a concern about the lowering.

[anijain2305]

I think that there is a mistake in the lowering. Can you please provide description of how the lowering instructions are decided?

[tristan-arm]

I think that there is a mistake in the lowering. Can you please provide description of how the lowering instructions are decided?

Same as the addition operator - only difference is that the requantized tensors are multiplied to provide the output. Let me know which part of the instructions you see an issue with and I'll take a closer look - Thanks

[tqchen]

@tristan-arm@anijain2305 please followup on this thread :)

[anijain2305]

@tristan-arm Sorry for the huge delay. This is what the lowering should look like. Let me know what do you think about this.

Quantized mul operation
scale_c * (Q_c - zp_c) = (scale_a * (Q_a - zp_a)) * (scale_b * (Q_b - zp_b))
scale_c * (Q_c - zp_c) = (scale_a * scale_b) * [ (Q_a - zp_a) * (Q_b - zp_b) ]
Going from right to left on the RHS
1) Shifted_input_A = Subtract Q_a - zp_a (Precision int32)
2) Shifted_input_B = Subtract Q_b - zp_b (Precision int32)
3) Int_tensors_muliplication = Shifted_input_A * Shifted_input_B
Our equation looks like this
scale_c * (Q_c - zp_c) = (scale_a * scale_b) * Int_tensors_muliplication
RHS can be thought of quantized tensor with (scale, zero_point) = (scale_a * scale_b, 0)
So, we can requantize.
4) Requantize the Int_tensors_muliplication with (input_scale, input_zero_point) = (scale_a * scale_b, 0)
And (output_scale, output_zero_point) = (scale_c, zp_c)

[tqchen]

ping @tristan-arm please follow up :)

[u99127]

@tqchen - tristan is on holidays , the other PR by @ekalda in #4141 should supersede this work and I think this PR should be abandoned.

[tqchen]

thanks @u99127@tristan-arm@anijain2305