Question about back propagation

[dongyp13]

In cudamat/cudamat_kernels.cu line 1934, the code is "if (!init) d_c_in[p] = grad_c;".

But in the first state of decoder and future LSTM, both of their init_state are the last state of encoder. So I guess that the derivation of encoder's last cell state should be propagated from both decoder and future LSTM. Should the code be "if (!init) d_c_in[p] += grad_c;" ?