News for hackers. Stuff that matters.
Re:The Nvidia DGX-1 Deep Learning Supercomputer in a Box by DeepYogurt on Tuesday April 05, 2016 @06:14PM (#11434989)
Would you mind trying the AMD compiler? http://gpuopen.com/compute-product/hip-convert-cuda-to-porta... I'd be interested in seeing a benchmark between some original cuda code and the opencl output of this compiler on the same gpu.
Re:The Nvidia DGX-1 Deep Learning Supercomputer in a Box by dharma1 on Tuesday April 05, 2016 @06:45PM (#11435192)
It doesn't look like AMD's HIP effort compiles to OpenCL, but to C++, that works on specific AMD GPUs (Fiji R9 Fury X, R9 Fury, R9 Nano).

Also, much of the speed gains for ML on NVidia hardware come from CuDNN - there is no equivalent for OpenCL or AMD hardware

Re:The Nvidia DGX-1 Deep Learning Supercomputer in a Box by mon_insider on Tuesday April 05, 2016 @08:36PM (#11435759)
I don't think CUDA vs OpenCL is the real issue. It's the libraries that come with them. It matters little in which language they were written, since they are closed source for the most part.

AMD's Boltzmann initiative won't solve the lack of libraries.