0

My code is calculating 3D-DCT, for a large set of data.

It's running on GeForce 9400M, compute capability 1.1 (which does not support double precision as far as I know).

Is there a way to enable it, or to handle the values correctly?

mickmackusa
  • 43,625
  • 12
  • 83
  • 136
Lamiaa Basyoni
  • 3
  • 1
  • 3
  • Is it mandatory to use double precision? – sgarizvi Mar 27 '13 at 18:20
  • 1
    See njuffa's answer in http://stackoverflow.com/questions/6769881/emulate-double-using-2-floats for a good answer (the gist is to use two floats to approximate a double) – alrikai Mar 27 '13 at 18:25

0 Answers0