User Profile

[GruenSein]

It has more of a "list of demands"-vibe...

[GruenSein]

It is a question of optimization. There is no reason why an OpenGL driver should not be multi-threaded while talking directly to the hardware. In theory,...

[GruenSein]

I think, the main purpose of this are less mainstream projects. AMD, Nvidia, and Intel all provide decent OpenGL drivers for their hardware and usually...

[GruenSein]

I was just about to say that. Double the performance over a 2080 was promised. The blatant lie about having twice the CUDA cores with a bogus figure of...

[GruenSein]

There are two things that I am not sure you are aware of. Firstly, the article is concerned with the kernel driver portion. This is by no means the entire...

[GruenSein]

Hardly any if these results and Nvidia's numbers are to be believed. What I was actually getting at is that the miraculous doubling of CUDA cores Nvidia...

[GruenSein]

So the 30 TFlops as claimed by Nvidia are just 30% faster than 13 TFlops of a 2080 Ti. Interesting...

[GruenSein]

People seem to forget that the AMD backend in LLVM needs to be maintained anyway. The reason is simple: Lots of people use clang or flang for HPC stuff...

[GruenSein]

Please simply fork instead of merging. Yes, tracking upstream will be more tedious but it is much better than all other LLVM development having to consider...