Reply To: A random smattering of questions.

My first two questions were originally about NaR + None, then I found a post that linked to this https://millcomputing.com/topic/metadata/#post-558 . To me, it makes the most sense given the use that the None is supposed to have, but I could be wrong.

Thinking more deeply, it really doesn’t matter whose metadata for a NaR wins. While I would want the location of the first generated NaR, it actually isn’t helpful. A pseudocode example:

A = 5 / 0
B = 6 / 0
C = A + B

If this is the code order, there is nothing that stops modern programming languages from reordering the divides as they see fit. Ideally, an unoptimized binary wouldn’t. Ideally.

As for the fast/slow multiplier question: my mistake was in what form genForm takes. I was putting it closer to the form in the hardware, which would make some specialization more difficult.