The problem is that if we make CUDA the standard, then they put nVidia in control of a standard. nVidia could try to manipulate the situation in future versions of CUDA by reworking it to fuck with this implementation, giving AMD a shaky name in the space.
We saw this happen with Wine, where although probably not deliberately, MS made Windows compatibility a moving and very unstable target.
The problem is that if we make CUDA the standard, then they put nVidia in control of a standard. nVidia could try to manipulate the situation in future versions of CUDA by reworking it to fuck with this implementation, giving AMD a shaky name in the space.
I get that but why woulde they fund development of ZLUDA for two years?
Reverse engineering CUDA can bring other benefits. It allows AMD to see what nVidia is doing right and potentially implement it in their own tech. Having not only documentation but a working implementation can help wonders in this regard.
Or maybe they did want to use it but was scared of getting SLAPPed by Nvidia, so instead let the dev open source it.
The problem is that if we make CUDA the standard, then they put nVidia in control of a standard. nVidia could try to manipulate the situation in future versions of CUDA by reworking it to fuck with this implementation, giving AMD a shaky name in the space.
We saw this happen with Wine, where although probably not deliberately, MS made Windows compatibility a moving and very unstable target.
I get that but why woulde they fund development of ZLUDA for two years?
Reverse engineering CUDA can bring other benefits. It allows AMD to see what nVidia is doing right and potentially implement it in their own tech. Having not only documentation but a working implementation can help wonders in this regard.
Or maybe they did want to use it but was scared of getting SLAPPed by Nvidia, so instead let the dev open source it.