Commit 5fbb1fee authored by James Qin's avatar James Qin Committed by TensorFlower Gardener
Browse files

Temporarily set cudnn Rnn math precision to fp32. 

Problem:
When calling cudnnGetRNNLinLayerMatrixParams(), return error CUDNN_STATUS_BAD_PARAM if:

* RNN descriptor set math precision = CUDNN_DATA_FLOAT
* input descriptor dataType = CUDNN_DATA_HALF
* weight descriptor dataType= CUDNN_DATA_HALF

If updating Rnn descriptor math precision to CUDNN_DATA_HALF, then no error.

cudnn 7.1.4 will fix the problem.

PiperOrigin-RevId: 193696566
parent 570d90b9
Show whitespace changes
Inline Side-by-side
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Please to comment