Intermediate FFT runlenghts
 

On [url]http://www.hogranch.com/mayer/gimps_timings.html[/url] i read about MLucas 2.7b

[quote]Supports the same non-power-of-2 runlengths as Prime95, i.e. (1,3,5,7)*2n, plus a full set of 4 additional intermediate radices (9,11,13,15)*2n. This allows every interval between adjacent power-of-2 runlengths to be broken into eight roughly equal pieces, and runtimes to increase very gradually as exponents get larger. [/quote]

Are these planned for a future version of prime95? From the timings it looks like a 10M digit test can be about 10% faster with a 1680K FFT

Can't speak for George's plans (if any) in this area - the extra FFT radices may not be a good option on x86-style CPUs due to limited number of registers.

Note that the above timings page no longer exists - the current & future Mlucas main page is

[url]http://hogranch.com/mayer/README.html[/url]