What is the definition of output of bidirection RNN in cudnn?

Accelerated Computing GPU-Accelerated Libraries
1

Dear all,

cudnnStatus_t
cudnnRNNForwardTraining( cudnnHandle_t handle,
const cudnnRNNDescriptor_t rnnDesc,
const int seqLength,
const cudnnTensorDescriptor_t *xDesc,
const void * x,
const cudnnTensorDescriptor_t hxDesc,
const void * hx,
const cudnnTensorDescriptor_t cxDesc,
const void * cx,
const cudnnFilterDescriptor_t wDesc,
const void * w,
const cudnnTensorDescriptor_t *yDesc,
void * y,
const cudnnTensorDescriptor_t hyDesc,
void * hy,
const cudnnTensorDescriptor_t cyDesc,
void * cy,
void * workspace,
size_t workSpaceSizeInBytes,
void * reserveSpace,
size_t reserveSpaceSizeInBytes)

I found that if rnnDesc is bidirection, the size of y should be miniBatch * (hiddenSize *2)
Does any one know meaning of y? Is it arranged in the way that “forward hidden outputs” concatenate "backward hidden outputs " ?