0

I am using quasi random number generator from mkl Intel. I created my own wrappnig method to allow for definition of maximum and minimum bounds for rng. However, seems not to work when values for bounds aer FLT_MIN FLT_MAX. So that I wonder what is FLT_MAX actually. A big float? A fictive value not to be exceeded? Isn't it possible to sample between FLT_MIN and FLT_MAX? How to deal with?

thanks and regards.

mskfisher
  • 3,291
  • 4
  • 35
  • 48
kiriloff
  • 25,609
  • 37
  • 148
  • 229
  • `FLT_MAX` is the "maximum representable finite floating-point number" while `FLT_MIN` is the "minimum normalized positive floating-point number". Having a RNG return numbers in that range sounds odd, what are you trying to accomplish? – user786653 Apr 24 '12 at 16:00
  • 1
    Floating point numbers are tricky (see e.g. [here](http://docs.oracle.com/cd/E19957-01/806-3568/ncg_goldberg.html) and [this](http://www.altdevblogaday.com/2012/04/20/exceptional-floating-point/) series of posts). If you don't care about the distribution it should be fairly straight forward to create samples in that range, but it's unlikely to be what you actually want. – user786653 Apr 24 '12 at 16:21

0 Answers0