Nah, not necessary anymore: Bush and Cheney are gone.

You get the big speedup only if you're doing single precision floating point computations.

On the NVIDIA GTX 280 & 260, a multiprocessor has eight single-precision floating point ALUs (one per core) but only one double-precision ALU (shared by the eight cores). Thus, for applications whose execution time is dominated by floating point computations, switching from single-precision to double-precision will increase runtime by a factor of approximately eight.

A lot of my HPC customers do CFD with (1) double precision in (2) Fortran. 1 and 2 are not easy or fast with CUDA.