Intermediate FFT runlenghts

smh · 2002-11-30, 10:59

On http://www.hogranch.com/mayer/gimps_timings.html 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.

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

ewmayer · 2006-03-22, 22:21

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

http://hogranch.com/mayer/README.html

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Intermediate P-1 results	kruoli	Software	6	2018-06-24 13:44
just an intermediate arithmetic sum	MattcAnderson	MattcAnderson	0	2017-05-08 02:32
.bu file intermediate results	zabig	Information & Answers	3	2013-01-16 00:42
Error writing intermediate file	Unregistered	Information & Answers	6	2009-07-27 23:58
Intermediate Files	ndpowell	Software	3	2005-06-20 22:57

2006-03-22, 22:21	#2
ewmayer ∂²ω=0 Sep 2002 República de California 2·5,869 Posts	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 http://hogranch.com/mayer/README.html