On Sun, Aug 03, 2003 at 07:47:31 +0100, Simon Jenkins wrote:
Here's where I've got to so far. Comments are
welcome.
Looks fine in theory, but it forces an extra branch per MUL, which is not
really practical.
I haven't had a chance to try your fixes to FLUSH_TO_ZERO, but I'l try
this week.
- Steve