News for hackers. Stuff that matters.

A comment on HIP – Convert CUDA to Portable C++. Parent comment

Re:HIP – Convert CUDA to Portable C++ by TomVDB on Sunday March 18, 2018 @01:59PM (#16613239)
HIP is only useful to convert CUDA source code.

Tensorflow uses the cuDNN library, which is closed source. There is nothing for HIP to convert.

[ Parent | on HN ]
Re:HIP – Convert CUDA to Portable C++ by tgtweak on Sunday March 18, 2018 @04:34PM (#16614159)
AMD is working on a cudnn comptability layer iirc (MiOpen) and is ROCm group has created a cuda transpiler (to intermediary HIP then to amd binary via hcc)

https://instinct.radeon.com/en/6-deep-learning-projects-amd-...

[ Parent | on HN ]
Re:HIP – Convert CUDA to Portable C++ by mastazi on Sunday March 18, 2018 @05:50PM (#16614620)
Wait, I thought that AMD's cuDNN replacement was hipDNN, now I'm confused https://github.com/ROCmSoftwarePlatform/hipDNN

Edit: OK I was reading the docs, I think I got it: hipDNN is a wrapper that (once finished) will search and replace calls (from cuDNN to hipDNN), then hipDNN itself, in turn, will call MIOpen, not sure if that's right, I would appreciate if someone who knows more could confirm

[ Parent | on HN ]
Re:HIP – Convert CUDA to Portable C++ by nl on Monday March 19, 2018 @12:48AM (#16616237)
AMD is always working on random half-assed attempts to get to parity with NVidia for neural network training.

If they'd chosen one approach 5 years ago and put decent resources behind it they might be competitive by now.

[ Parent | on HN ]
Re:HIP – Convert CUDA to Portable C++ by TomV1971 on Sunday March 18, 2018 @04:41PM (#16614195)
Yes, but it means AMD will have to do the original work. They can’t use a CUDA to HIP converter.
[ Parent | on HN ]