[Question] Confused about the additional element of the output of InteractionLayer

[heroes999]

The output of InteractionLayer is of shape: batch_size * {num_elems + *(num_feas + 1) (num_feas + 2 ) / 2 - (num_feas + 1)* + 1}, according to code or user guide. num_elems is the dim of fc; (num_feas+1)(num_feas+2)/2 - (num_feas+1) stands for cross product of all embs and fc; So what is the additional element? It seems the additional element doesn't get assigned/calculated in interaction_layer.cu/interaction_layer_test.cpp. https://github.com/NVIDIA-Merlin/HugeCTR/blob/v4.2/test/utest/layers/interaction_layer_test.cpp#L175

Any hint will be appreciated, thanks.

[minseokl]

Hi @heroes999 are you mentioning this internal padding here? https://github.com/NVIDIA-Merlin/HugeCTR/blob/main/HugeCTR/src/layers/interaction_layer.cu#L637

[heroes999]

I think it really influece the output dim, and this is the link of introduction which tells 1 additional float element: https://nvidia-merlin.github.io/HugeCTR/v4.2/api/hugectr_layer_book.html#interaction-layer

Hi @heroes999 are you mentioning this internal padding here? https://github.com/NVIDIA-Merlin/HugeCTR/blob/main/HugeCTR/src/layers/interaction_layer.cu#L637

It looks like internal padding for __half, but float32 has one additional float output as well

[minseokl]

The padding was introduced to make the output easily vectorized and TensorCore-friendly for some common use cases back then. Yes it was mainly for __half but float has it as well to make the shape consistent regardless of if you do the mixed precision training or not.

[heroes999]

Got it. So this additional padding is always 0, right? @minseokl

[minseokl]

Yes it must be zero not to influence the result.

[heroes999]

Thanks. I'd like to close the issue