__float2uint_rd() Undocumented? Anybody know this guy?

Hello,

I have recently come across __float2uint_rd() being used in some CUDA code that I find extremely useful.
(See: http://forums.nvidia.com/index.php?showtop…amp;mode=linear, 2nd Post)

Unfortunately, I don’t fully understand what __float2uint_rd() does entirely. I have searched the forums, Google, NVIDA docs, etc, but alas… to no avail.

Could somebody explain what this does or (even better) point me to where it is documented?

Thanks in advance,
I really appreciate the forum userbase and the time you guys ('n gals) take to answer questions!
Hopefully soon I can begin to return the favor.

Programming guide, appendix B.2. There is a type however, the second _rz should be _rd

Thanks, don’t know how I missed it. :">

well, I expected to find it in the reference manual, but there it was not ;)