for(uint32_t state_idx = 1; state_idx < STATE_SIZE; state_idx += 2) {
state_p[state_idx] = bitsliced_even_state[state_idx/2];
}
for(uint32_t state_idx = 1; state_idx < STATE_SIZE; state_idx += 2) {
state_p[state_idx] = bitsliced_even_state[state_idx/2];
}