How to parallelize this code?

[TruongQToan]

In this paper, you state that the key improvement between SRNN and plain RNN is that we can parallelize SRNN so that we can train multiple subsequences at the same time. But I don't see that improvement manifested in this code? So how can we parallelize this code? Thank you.

[zepingyu0512]

The timedistributed layer in keras could do this.