Mersenne: 1000 barrier
I've been with GIMPS for about two years and yesterday achieved a personal milestone; I finally broke thru the 1000 barrier and made it to 996 on the top producers list. Each step forward is getting smaller and smaller though; I think I'm approaching the knee of the curve and will eventually start going backwards. ID: rlbrooks 866MHz P3 450MHz P2 ( 133MHz P1 doing factoring) Cheers... Russ _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Re: Mersenne: 1000 barrier
On Fri, Jul 20, 2001 at 09:40:04PM +, Russel Brooks wrote: ID: rlbrooks 866MHz P3 450MHz P2 ( 133MHz P1 doing factoring) I took the liberty of running you though my perl script that tells you more or less what you want to know, the results are. Run Date: Sat 21 Jul 2001 Participants counted: 22,255 Extra details for user ID: rlbrooks Position User Name CPU YearsExponentsCPU P90 Tested Hrs Per Day 997 rlbrooks14.568 76222.96 142 people are faster than you but behind you, at an average speed of 330.62 CPU hours per day they are approximately 7.89 years behind you. You will be in the center of the chasing pack in something like 636.91 days. 357 people are slower than you but in front of you, at an average speed of 162.09 CPU hours per day they are approximately 5.08 years in front of you. You should be in the middle of the pack that you are chasing in something like 725.63 days. End of script results - From this I deduce that you are set to overtake more people than will overtake yourself, but given the timescales involved, many people will upgrade their processors within the next 725 days, one of those people may be you so really the results don't tell you very much do they:-) The script is called primestats and is available from my web page in the CGI Linux Stuff, section, there is documentation and a sample report bundled with the script. -- Cheers Steve email mailto:[EMAIL PROTECTED] %HAV-A-NICEDAY Error not enough coffee 0 pps. web http://www.zeropps.uklinux.net/ or http://start.at/zero-pps 3:04am up 7 days, 5:05, 2 users, load average: 1.12, 1.31, 1.23 _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers
Mersenne: Mlucas FFT Timing Questions...
Does there only need to be one FFT line in mlucas.cfg, for the one that matches your exponent, or do they all have to be there? I've run tests for the FFT that matches my exponent (352K), but I really do not want to run tests for all of them... Especially since there are two possible binary versions for my system... The times between having error correcting on and having it off are not that far apart in some cases... The shortest non-error corrected time (33.4s for prefetching off/radix 2) is very close to the shortest error corrected time (36.0s for prefetching on/radix 6)... In this case would using error correction be advisable? Thanks! Mike prefetching on error correction on 6 - 43.3s 5 - 49.6s 4 - 36.0s 3 - 41.7s 2 - 50.2s 1 - 46.8s 0 - 38.6s prefetching on error correction off 6 - 41.1s 5 - 50.9s 4 - 37.3s 3 - 40.1s 2 - 34.1s 1 - 38.4s 0 - 37.0s prefetching off error correction on 6 - 41.3s 5 - 42.6s 4 - 36.5s 3 - 42.3s 2 - 36.1s 1 - 40.8s 0 - 39.2s prefetching off error correction off 6 - 38.7s 5 - 39.9s 4 - 33.8s 3 - 39.7s 2 - 33.4s 1 - 38.1s 0 - 36.6s Mlucas 2.7b UltraSPARC IIi @ 270MHz _ Unsubscribe list info -- http://www.scruz.net/~luke/signup.htm Mersenne Prime FAQ -- http://www.tasam.com/~lrwiman/FAQ-mers