mersenneforum.org

mersenneforum.org (https://www.mersenneforum.org/index.php)
-   Software (https://www.mersenneforum.org/forumdisplay.php?f=10)
-   -   Prime95 30.7 (https://www.mersenneforum.org/showthread.php?t=27180)

kriesel 2022-05-06 22:10

[QUOTE=Prime95;605369]Try v30.8b15[/QUOTE]Downloadable where?
Last I found in the v30.8 beta thread is b14, [url]https://mersenneforum.org/showpost.php?p=603242&postcount=501[/url]

James Heinrich 2022-05-06 22:16

[QUOTE=kriesel;605373]Downloadable where?[/QUOTE]Usual place, you just haven't given George time to post his changelog and links in the thread.
[url]https://www.mersenne.org/ftp_root/gimps/p95v308b15.win64.zip[/url]

edit: George has posted now: [url]https://www.mersenneforum.org/showpost.php?p=605385&postcount=551[/url]

tshinozk 2022-05-07 01:46

Thanks,
v30.8b15 fixed the issue.
I can find a sweet spot for multi-core scaling.

Timings for 2048K FFT length (1 core, 1 worker): 5.16 ms. Throughput: 193.83 iter/sec.
Timings for 2048K FFT length (2 cores, 1 worker): 2.63 ms. Throughput: 380.49 iter/sec.
...

kriesel 2022-05-13 23:26

Prime95 v30.7b9 undoc.txt says:
[CODE]In prime.txt,
ProofPower=x (x can be from 5 to 12)
ProofPowerAdjust=y (y can be from -2 to +3)
these override the selection of proof power based on temporary disk space available.[/CODE]I've put ProofPower=11 or =12 in prime.txt (before the [primenet] or [worker] sections) of various installs of prime95 V30.7b9 and v30.8b14.
It seems to have NO effect.

I still get proof power 9 for 60M PRP DC assignments, or power 10 for 109M PRP assignments.
The .residues files are preallocated to ~4 and 14GB (not the 32-160 GB resource limit). Worker window text is also consistent with default proof powers not the specified values.
Stopping and exiting the program, switching to ProofPowerAdjust=3, deleting the brief run attempts' residue and save files, and starting again from scratch, also fails on v30.7b9 and v30.8b14; resulted in 4 and 14GB residue files again, and the worker windows still indicate 4 GB and 14GB residue file required, and proof power 9 and 10, as if ProofPowerAdjust=0.

Forum search "ProofPower" shows that it worked for some users and not others, back at v30.4/5/6. Even if placed in both prime.txt and local.txt.

(My current use case is to get actual prime95 squarings counts for high proof powers on several sample exponents, quickly, without running large exponents that would default to high proof powers, take months each to complete, and not help the wavefronts. Trying to fill a table for powers 5-12 for reference info and understanding actual costs versus exponent of various proof powers.)

tdulcet 2022-05-17 12:21

[QUOTE=kriesel;605844]I've put ProofPower=11 or =12 in prime.txt (before the [primenet] or [worker] sections) of various installs of prime95 V30.7b9 and v30.8b14.
It seems to have NO effect.[/QUOTE]

Those options are for setting the maximum PRP proof power, but it will not let one set a higher proof power than the optimal for each exponent. You can override this by putting it in the [C][PrimeNet][/C] section, as Prime95/MPrime allows the PrimeNet server to reduce the proof power.

kriesel 2022-05-19 16:49

[QUOTE=tdulcet;605976]You can override this by putting it in the [C][PrimeNet][/C] section, as Prime95/MPrime allows the PrimeNet server to reduce the proof power.[/QUOTE]Thanks for the tip. That was not clear from the docs. Putting both[code]ProofPower=12
ProofPowerAdjust=3[/code]in the [PrimeNet] section of prime.txt & stop, exit & restart the app seems to be working; worker window includes:
[code][May 19 11:08] Setting affinity to run helper thread 1 on CPU core #2
[May 19 11:08] Setting affinity to run helper thread 2 on CPU core #3
[May 19 11:08] Setting affinity to run helper thread 3 on CPU core #4
[May 19 11:08] Starting Gerbicz error-checking PRP test of M61686073 using AVX-512 FFT length 3360K, Pass1=640, Pass2=5376, clm=1, 4 threads
[May 19 11:08] Preallocating disk space for the proof interim residues file p68B6073.residues
[May 19 11:09] PRP proof using power=[B]12[/B] and 64-bit hash size.
[May 19 11:09] Proof requires [B]31.6GB[/B] of temporary disk space and uploading a 100MB proof file.
[May 19 11:10] Iteration: 10000 / 61686073 [0.01%], ms/iter: 8.488, ETA: 6d 01:24
[May 19 11:12] Iteration: 20000 / 61686073 [0.03%], ms/iter: 8.185, ETA: 5d 20:12
...[/code]Being able to cause higher than optimal proof levels is the difference between getting level 11 squarings counts in several days at 60M, or in several months at 415+M, and getting any level 12 squarings counts from prime95 soon or never. (For proof effort [URL="https://www.mersenneforum.org/showpost.php?p=604768&postcount=24"]reference info;[/URL] link may change; & for George re actual observed algorithm behavior for proof level exponent transitions selection, documentation)

tdulcet 2022-05-20 09:01

[QUOTE=kriesel;606107]Thanks for the tip. That was not clear from the docs. Putting both[code]ProofPower=12
ProofPowerAdjust=3[/code]in the [PrimeNet] section of prime.txt & stop, exit & restart the app seems to be working[/QUOTE]

Yeah, it is an undocumented option only designed to be used by the PrimeNet server in an emergency. See @Prime95's comment (source: [C]commonb.c[/C], lines 11,827-11,828):
[CODE] // We have a way for the PrimeNet server to change (reduce) the proof power. This would reduce server proof
// processing load somewhat and reduce the bandwidth required for obtaining proof files. We hope to never use this option.[/CODE]Note that only [C]ProofHashLength[/C], [C]ProofPower[/C] and [C]ProofPowerMult[/C] can be set in the [C][PrimeNet][/C] section.

[QUOTE=kriesel;606107]Being able to cause higher than optimal proof levels is the difference between getting level 11 squarings counts in several days at 60M, or in several months at 415+M, and getting any level 12 squarings counts from prime95 soon or never.[/QUOTE]

Yes, this is currently the only way to use proof power 12 in Prime95/MPrime. You actually may be able to go higher than 12 (or lower than 5) if you wanted, as from looking at the code, I do not see any obvious assert statements or other checks like GpuOwl has. Anyway, I am looking forward to seeing your results.

tha 2022-05-20 14:35

If one adds lines to worktodo and then start mprime -m, the program starts by reading the worktodo file and makes reservations with the server. The new assignment keys are written to the worktodo file. Upon completing this nothing happens, and nothing signals it is waiting for input.

On the other hand, after choosing option 4, mprime starts by resending the menu to the output as if it is expecting further input.

So, requested is:

A: Output of the menu after finishing making reservations with the server.
B. Suppressing the output of the menu after menu option 4 is chosen.


All times are UTC. The time now is 04:23.

Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2022, Jelsoft Enterprises Ltd.