Forgot your password?

Comment: Single precision (Score 1) 134

by Gerb (#28009859) Attached to: Five Nvidia CUDA-Enabled Apps Tested

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.

You can do this in a number of ways. IBM chose to do all of them. Why do you find that funny? -- D. Taylor, Computer Science 350