I want to access the reserveSpace that was computed in the forward and re-use it in the backward to pass it to a cudnn function for re-use purpose. The reserveSpace is produced by calling the function:
cudnnStatus_t cudnnRNNForwardInference(
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)
However, I could not find a way to do it from the python level yet.
Any idea is appreciated,
Thanks