Re:Tensorflow 0.6.0 Release
by oneofthose on Thursday December 10, 2015 @12:46PM
(#10712017)
It would not have to be like that if Nvidia opened up the source-code for cuFFT/cuDNN/cuBLAS. My guess is they are not doing that because it is fairly trivial to port code from CUDA to OpenCL. It can even be automated.
I'm not a big fan of vendor "standards", but I have very limited sympathy for OpenCL here.
I think the best hope for portability is at the higher level programming API layer. For example TensorFlow is careful to make switching between CPU and GPU painless.