I wonder if it can be done.
It would possibly be a horrendously expensive undertaking to develop a new architecture chip that :
1. outperforms the Intel latest generation
2. delivers comparable performance at a comparable price point
3. does not infringe on AMD or Intel IP (at least not getting away with it)
4. produce it at anysignificant quantities
5. produce the relevant industrial strength compilers and cross platform the software at the time of release.
6. Alternatively, develop new software from scratch. This would truly be a can of worms, migrating to completely new hard- and software from the ground floor ?
I only have to refer to AMD who, although they make exellent products, and were even the originators of the 64 bit instruction sets as we know it, have never been able to make a sizeable dent in the Intel armour, not even when they had superior hardware (I'm conveniently ignoring the Opterons, which had a good run...for a bit). And et's not forget that even Big Blue did not have the stomach to go up against Intel at the time of the PowerPC's
I imagine that as soon as someone adds up the numbers at Fruity Towers the whole idea will be quickly relegated to 'bargaining chip' status.
But, admittedly stranger things have happened.