Not $100k, of course. But I think $5 or $6 million dollars could do it. For that, you'd get a scalable, self-balancing 16 or 32-core processor compatible with existing motherboards and chip sets, visual dev tools using multi-touch screens, and a fully built computer with an extensible parallel OS including a good set of device drivers.
The whole engineering/design phase would take about two years. After that, you enter the marketing and production phase which will require several busloads of dough but that's not my department.
In my opinion, that's exactly what they are doing. They have adopted a paralllel computing model (multithreading) that is known to be a pain in the ass to program. So far, they have no plans to change the model. They either don't know how or they are stuck in a rut because they need to maintain compatibility with legacy systems. They are in a state of panic right now, spending money left and right trying to find a solution that does not exist for their chosen model. This is a great opportunity for some other company (or a startup) to come on the scene and make a killing.
The whole engineering/design phase would take about two years. After that, you enter the marketing and production phase which will require several busloads of dough but that's not my department.