Indeed there is. However, they describe 44-bit floating point emulation.
It'd be nice to see if someone can come up with a 64-bit implementation and
how performance compares with a CPU.
-John
"scott" <spa### [at] spam com> wrote:
>
> In the link you posted there is a paper that explains how to emulate higher
> precision floats...
Post a reply to this message
|