Floating point calculations in a processor with no FPU

Question

Is it possible to perform floating point operations in an embedded processor that does not have a Floating Point Unit?

Answer 1

Yes, you just have to do it in software. Your compiler may provide support, or you may need to roll your own. There are freely-available implementations, too.

Answer 2

Yes, e.g. early Linux kernels did emulate i387 floating point instructions in the kernel. It was rather slow, but allowed you to use the same binary on computers with and without a floating point unit.