Problem with cudnnAddTensor() function

Hi all,

I tried 3D convolution using cuDNN v3 RC, it works fine.
However, when I used cudnnAddTensor() function to add biases to the convolution results, it returns CUDNN_STATUS_NOT_SUPPORTED.
I used CUDNN_ADD_SAME_C mode.

I want to add bias (each unit has one, 1x1x1 size) to every position of the corresponding unit. (Please see
following image)
http://i.imgur.com/SJyryYn.png

My source code looks like the following. Almost the same as the cudnn-v3 sample code, but using cudnnSetTensorNdDescriptor is different.

int biasDimA[tensorDims] = { 1, c, 1, 1, 1 };
int biasStrideA[tensorDims] = { c, 1, 1, 1, 1 };
checkCUDNN( cudnnSetTensorNdDescriptor(biasTensorDesc, 
        dataType, tensorDims, biasDimA, biasStrideA) );

value_type b_alpha = (value_type)1;
value_type b_beta = (value_type)1;

checkCUDNN( cudnnAddTensor(cudnnHandle, CUDNN_ADD_SAME_C, 
        &b_alpha, biasTensorDesc, conv.bias_device, &b_beta, dstTensorDesc, *dstData) );

Someone do you know how to solve it or do you have any ideas?
Thank you for your kind cooperation.

Hi all,

It seems that cudnnAddTensor does not support 3D in cudnn v3 RC.

Thank you.

Hi all,

It seems that cudnnAddTensor does not support 3D in cudnn v3 RC.

Thank you.

The incoming cudnn v3 Prod will provide a routine cudnnAddTensor_v3 that has a simpler API and also handle 3D