This article makes me wonder if adding FPGA units to existing CPUs and GPUs that integrate with existing silicon makes a lot more sense than having a completely separate FPGA.
But not in household CPUs which I think is what GP meant. CPU speeds don't increase anymore, having an FPGA that can be programmed by software such as photo editors or encryption engines, things can be sped up a lot. (At least for crypto, one reason to stay with particular algorithms is hardware support; we'd be more agile if we could implement that in software without sacrificing much speed.)
