It does have the FPU emulator for processors without a FPU. I remember reading an email sometime ago on linux-kernel about unreliable precision of the FPU, I'll have to try and find it before I put my foot in my mouth. Again :) Tom On Tue, 30 Jul 2002, Seth Arnold wrote: > On Tue, Jul 30, 2002 at 01:19:10PM -0600, Tom Bradley wrote: > > There are 2 main why you shouldn't use the 'float' or 'double' data > > type inside of the kernel. > > > > - The kernel does not save the FPU registers, therefore the FPU is > > always in an unknown state. > > Yes. :) (Well, I think I've heard that somewhere in the kernel, the FPU > is used, but I can't recall where I heard that now. Unless anyone can > confirm this, it might be best to forget it. :) > > > - Due to percision differences on different platforms the value of a > > 'float' or 'double' can not be completely trusted to be the same. > > No; this would only be a problem for sharing float/double data among > machines, and this problem is _very_ well known among floating point > users, so it doesn't provide a compelling reason to not use floating > point in the kernel. > > -- > http://www.wirex.com/ > -- Kernelnewbies: Help each other learn about the Linux kernel. Archive: http://mail.nl.linux.org/kernelnewbies/ FAQ: http://kernelnewbies.org/faq/
