On Fri, 8 Jan 2021 13:10:22 +0000
The Natural Philosopher  wrote:

>Actually I am not sure how that would sit in parallel cores - I suppose
>you would do partial results. The problem is of course that you need to
>access the same delay line in memory for all cores, and its actually
>those accesses that take the cycles. Assuming you have a fast floating
>point multiplym anyway.
>
>

Good point. I hadn't thought of access time!

--
W J G

--- SoupGate-Win32 v1.05