Design is not the problem. Having foundry space to manufacture is the bottleneck. It is just all being sucked up (with AI needs being the big additional load).

And to be clear, the foundry space for CPUs/GPUs is not the same as for RAM, which is printed with much larger feature size in order to lower the costs.

For CPUs, they are still licensing ARMs cores, of course with their own modifications, and they bought Intel’s modem businesses, which likely gave them the patents they needed. GPUs I can’t speak to on this though.