> That you can't compile CUDA to AMD GPUs isn't NVIDIA's fault, it's AMD, for deciding to pursue OpenCL first, then HSA, and now HIP.
Using a branded & under patent concurrent proprietary technology and copying its API for your own implementation is Maddness that will lead you for sure in front of a court.
the MIT license doesn't have an express patent grant. If Nvidia has a patent on some technology used by the open source code, they could sue you for patent infringement if you use it in a way that displeases them. What they can't do is sue you for copyright infringement.
> Most other legal precedent was that it was fine to clone an API.
CUDA is more than an API. It is a technology under copyright and very likely patented too. Even the API itself contains multiple reference to "CUDA" in function calls and variable name.
None of that protects it from being cloned under previous 9th circuit precedent except maybe patents, but I'm not aware of any patents that'd protect another against CUDA implementation.
Using a branded & under patent concurrent proprietary technology and copying its API for your own implementation is Maddness that will lead you for sure in front of a court.
It seems that even Google understood that the hard way (https://en.wikipedia.org/wiki/Google_v._Oracle_America)