Bright Side of News published another interesting GPGPU computing tale about researchers who need to run a 20 teraFLOPS system in the Australian outback with the only power source being a 20kW diesel generator. You can read it over here.
Given that you would need around 200 CPUs for the job, as 200 Xeon 5500 CPUs at 3.2 GHz [100 GFLOPS each] would consume a grand total of 24,000Watts [that's not counting the rest of the computer needed for these CPUs to function]. Overall estimate in CPU-based setup was in excess of 55,000 Watts [55kW] and obviously, it was a dead end.
In October 2006 nVidia launched CUDA, following up with GeForce 8 hardware in November 2006. According to scientists from this project, this was the beginning of a breakthrough, with GeForce GTX 280 and Tesla C1060 cards winning the computing challenge. In around 1kW of power, scientists managed to squeeze 4.5TFLOPS [dual GTX 295 card], meaning "only" 5.5kW is needed for 20TFLOPS.
With upcoming Fermi-based cards, Australians expect to build a 20TFLOPS setup using only 3.3kW.