PrimeGrid
Please visit donation page to help the project cover running costs for this month

Toggle Menu

Join PrimeGrid

Returning Participants

Community

Leader Boards

Results

Other

drummers-lowrise

Advanced search

Message boards : Project Staging Area : genefercuda.exe and roundofferr

Author Message
pabliedungProject donor
Volunteer tester
Send message
Joined: 2 Jan 11
Posts: 87
ID: 79535
Credit: 223,567,883
RAC: 1,001
Eliminated 1 conjecture "k"Discovered 1 Sophie Germain pair321 LLR Turquoise: Earned 5,000,000 credits (5,084,460)Cullen LLR Turquoise: Earned 5,000,000 credits (5,116,758)ESP LLR Turquoise: Earned 5,000,000 credits (5,857,992)Generalized Cullen/Woodall LLR Turquoise: Earned 5,000,000 credits (5,160,553)PPS LLR Turquoise: Earned 5,000,000 credits (7,716,351)PSP LLR Turquoise: Earned 5,000,000 credits (5,102,730)SoB LLR Turquoise: Earned 5,000,000 credits (6,758,211)SR5 LLR Turquoise: Earned 5,000,000 credits (9,425,210)SGS LLR Turquoise: Earned 5,000,000 credits (5,063,747)TRP LLR Turquoise: Earned 5,000,000 credits (6,284,268)Woodall LLR Turquoise: Earned 5,000,000 credits (5,224,737)321 Sieve Turquoise: Earned 5,000,000 credits (5,107,390)Cullen/Woodall Sieve (suspended) Jade: Earned 10,000,000 credits (10,903,006)Generalized Cullen/Woodall Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,059,213)PPS Sieve Emerald: Earned 50,000,000 credits (50,293,728)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,054,382)TRP Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,057,704)AP 26/27 Turquoise: Earned 5,000,000 credits (5,061,836)GFN Sapphire: Earned 20,000,000 credits (20,204,632)PSA Emerald: Earned 50,000,000 credits (50,030,975)
Message 34613 - Posted: 30 Mar 2011 | 0:36:38 UTC

Hi all,

I have two GPUs that I want to use to run Generalized Fermat Number Prime searches. Both are GTX 460 cards.
One of the cards is running is running just fine while the majority of the wu's on the other card abort with a "roundofferr" message in the test_results file [1]

I started with the GFN262144 subproject but received a lot of "roundofferr" messages on my first card (gpuaffinity=0). I then switched to GFN65536 and saw almost all wu's complete.

However the other GTX 460 card (gpuaffinity=1) seems to complete GFN262144 wu's just fine. No error messages there.

I have only geneferexe=genefercuda.exe enabled in both gpu-subfolders and I have set gpuaffinity=0 for the first card, and gpuaffinity=1 set for the second.

Can someone help point me in the right direction on how to debug this? Are some of my settings incorrect?

Thanks in advance!


[1]
...
[2011-03-29 07:46:17 EDT] Server: GFN262144, Candidate: 1*214314^262144+1 Program: genefercuda.exe Residue: roundofferr Time: 0 seconds
[2011-03-29 08:16:18 EDT] Server: GFN262144, Candidate: 1*214316^262144+1 Program: genefercuda.exe Residue: roundofferr Time: 0 seconds
[2011-03-29 08:32:59 EDT] Server: GFN65536, Candidate: 1*1265078^65536+1 Program: genefercuda.exe Residue: 5d62b9dac49057ef Time: 0 seconds
[2011-03-29 08:44:55 EDT] Server: GFN65536, Candidate: 1*1265094^65536+1 Program: genefercuda.exe Residue: 176d76334403da2b Time: 0 seconds
[2011-03-29 08:56:52 EDT] Server: GFN65536, Candidate: 1*1265122^65536+1 Program: genefercuda.exe Residue: 4bb7d36e90cfcfe1 Time: 0 seconds
...
[2011-03-29 17:29:50 EDT] Server: GFN65536, Candidate: 1*1266036^65536+1 Program: genefercuda.exe Residue: 736bec6aa3a81805 Time: 0 seconds
[2011-03-29 17:41:44 EDT] Server: GFN65536, Candidate: 1*1266060^65536+1 Program: genefercuda.exe Residue: 6e48f3ffcba0319a Time: 0 seconds
[2011-03-29 17:41:51 EDT] Server: GFN32768, Candidate: 1*3904230^32768+1 Program: genefercuda.exe Residue: roundofferr Time: 0 seconds
[2011-03-29 17:41:59 EDT] Server: GFN32768, Candidate: 1*3904244^32768+1 Program: genefercuda.exe Residue: roundofferr Time: 0 seconds
[2011-03-29 17:42:06 EDT] Server: GFN32768, Candidate: 1*3904246^32768+1 Program: genefercuda.exe Residue: roundofferr Time: 0 seconds
...

rogue
Volunteer developer
Avatar
Send message
Joined: 8 Sep 07
Posts: 1196
ID: 12001
Credit: 18,565,548
RAC: 0
PPS LLR Bronze: Earned 10,000 credits (31,229)PSA Jade: Earned 10,000,000 credits (18,533,435)
Message 34615 - Posted: 30 Mar 2011 | 2:37:29 UTC

The problem is that the CUDA version of genefer has limits for b above which it gets roundoff errors. The PRPNet client will switch to another version of genefer (if configured in the ini file) to attempt the PRP test. It just so happens that GFN65536 is below the limit for b that triggers roundoff errors and GFN262144 is over that limit.

If you want to only use genefercuda, then don't do work for GFN262144. If you want to do work for GFN262144, then you need to install one or more of the other versions of genefer and configure them.

Profile NeoProject donor
Volunteer tester
Avatar
Send message
Joined: 28 Oct 10
Posts: 710
ID: 71509
Credit: 91,178,992
RAC: 0
321 LLR Ruby: Earned 2,000,000 credits (2,050,605)Cullen LLR Silver: Earned 100,000 credits (104,070)ESP LLR Amethyst: Earned 1,000,000 credits (1,018,623)Generalized Cullen/Woodall LLR Silver: Earned 100,000 credits (198,013)PPS LLR Amethyst: Earned 1,000,000 credits (1,642,058)PSP LLR Gold: Earned 500,000 credits (897,619)SoB LLR Amethyst: Earned 1,000,000 credits (1,683,694)SR5 LLR Amethyst: Earned 1,000,000 credits (1,002,127)SGS LLR Gold: Earned 500,000 credits (580,961)TRP LLR Amethyst: Earned 1,000,000 credits (1,025,151)Woodall LLR Silver: Earned 100,000 credits (123,136)321 Sieve Bronze: Earned 10,000 credits (20,061)Cullen/Woodall Sieve (suspended) Amethyst: Earned 1,000,000 credits (1,074,349)Generalized Cullen/Woodall Sieve (suspended) Silver: Earned 100,000 credits (167,039)PPS Sieve Sapphire: Earned 20,000,000 credits (45,234,841)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Silver: Earned 100,000 credits (108,377)TRP Sieve (suspended) Silver: Earned 100,000 credits (100,605)AP 26/27 Amethyst: Earned 1,000,000 credits (1,115,868)GFN Jade: Earned 10,000,000 credits (14,691,481)PSA Jade: Earned 10,000,000 credits (18,340,315)
Message 34616 - Posted: 30 Mar 2011 | 2:57:31 UTC - in response to Message 34615.

The problem is that the CUDA version of genefer has limits for b above which it gets roundoff errors. The PRPNet client will switch to another version of genefer (if configured in the ini file) to attempt the PRP test. It just so happens that GFN65536 is below the limit for b that triggers roundoff errors and GFN262144 is over that limit.

If you want to only use genefercuda, then don't do work for GFN262144. If you want to do work for GFN262144, then you need to install one or more of the other versions of genefer and configure them.


Rogue,

I successfully run GFN524K, GFN262K and GFN65K with geneferCUDA all the time (maybe I'm getting lucky with the b ranges??? but, for only having a GT430 with only 96 cuda cores, I've run a heck of a lot of GFN w/u's).
____________

JohnProject donor
Honorary cruncher
Avatar
Send message
Joined: 21 Feb 06
Posts: 2875
ID: 2449
Credit: 2,681,934
RAC: 0
321 LLR Bronze: Earned 10,000 credits (11,773)Cullen LLR Bronze: Earned 10,000 credits (14,945)ESP LLR Bronze: Earned 10,000 credits (26,855)PPS LLR Bronze: Earned 10,000 credits (84,876)PSP LLR Bronze: Earned 10,000 credits (15,311)SoB LLR Bronze: Earned 10,000 credits (21,440)SR5 LLR Bronze: Earned 10,000 credits (29,270)SGS LLR Bronze: Earned 10,000 credits (26,616)TPS LLR (retired) Bronze: Earned 10,000 credits (36,288)TRP LLR Bronze: Earned 10,000 credits (41,655)Woodall LLR Bronze: Earned 10,000 credits (15,807)321 Sieve Bronze: Earned 10,000 credits (20,014)Cullen/Woodall Sieve (suspended) Bronze: Earned 10,000 credits (23,405)PPS Sieve Bronze: Earned 10,000 credits (36,192)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Bronze: Earned 10,000 credits (20,306)TRP Sieve (suspended) Bronze: Earned 10,000 credits (21,738)GFN Bronze: Earned 10,000 credits (86,217)PSA Ruby: Earned 2,000,000 credits (2,143,756)
Message 34617 - Posted: 30 Mar 2011 | 3:29:31 UTC - in response to Message 34615.

It just so happens that GFN65536 is below the limit for b that triggers roundoff errors and GFN262144 is over that limit.

Only N=32768 has reached any of the b limits. Getting close is N=65536. From the PSA PRPNet Projects thread:

    Top b limits are listed as GeneferCUDA, Genefx64, Genefer, Genefer80

    N=32768
    Top limits: 1.87M, 1.5M, 2.1M, 65M+

    N=65536
    Top limits: 1.53M, 1.2M, 1.7M, 51M+

    N=131072
    Top limits: 1.255M, 1M, 1.4M, 42M+

    N=262144
    Top limits: 815K, 865K, 1,2M, 35M+

    N=524288
    Top limits: 710K, 735K, 975K, 29M+


____________

pabliedungProject donor
Volunteer tester
Send message
Joined: 2 Jan 11
Posts: 87
ID: 79535
Credit: 223,567,883
RAC: 1,001
Eliminated 1 conjecture "k"Discovered 1 Sophie Germain pair321 LLR Turquoise: Earned 5,000,000 credits (5,084,460)Cullen LLR Turquoise: Earned 5,000,000 credits (5,116,758)ESP LLR Turquoise: Earned 5,000,000 credits (5,857,992)Generalized Cullen/Woodall LLR Turquoise: Earned 5,000,000 credits (5,160,553)PPS LLR Turquoise: Earned 5,000,000 credits (7,716,351)PSP LLR Turquoise: Earned 5,000,000 credits (5,102,730)SoB LLR Turquoise: Earned 5,000,000 credits (6,758,211)SR5 LLR Turquoise: Earned 5,000,000 credits (9,425,210)SGS LLR Turquoise: Earned 5,000,000 credits (5,063,747)TRP LLR Turquoise: Earned 5,000,000 credits (6,284,268)Woodall LLR Turquoise: Earned 5,000,000 credits (5,224,737)321 Sieve Turquoise: Earned 5,000,000 credits (5,107,390)Cullen/Woodall Sieve (suspended) Jade: Earned 10,000,000 credits (10,903,006)Generalized Cullen/Woodall Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,059,213)PPS Sieve Emerald: Earned 50,000,000 credits (50,293,728)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,054,382)TRP Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,057,704)AP 26/27 Turquoise: Earned 5,000,000 credits (5,061,836)GFN Sapphire: Earned 20,000,000 credits (20,204,632)PSA Emerald: Earned 50,000,000 credits (50,030,975)
Message 34618 - Posted: 30 Mar 2011 | 4:48:10 UTC - in response to Message 34617.

thanks for your replies.

what's odd is that my other GTX 460 card has been running GFN262K w/u's without these errors. It takes about 70min to complete a w/u and it reports a Residue value each time.

I am only seeing the roundoff errors on my second card. I even stopped all CPU w/u's to see if that has any effect... but I am still getting the roundoff errors.

Profile rroonnaallddProject donor
Volunteer developer
Volunteer tester
Avatar
Send message
Joined: 3 Jul 09
Posts: 1213
ID: 42893
Credit: 34,634,263
RAC: 0
321 LLR Silver: Earned 100,000 credits (101,692)Cullen LLR Silver: Earned 100,000 credits (104,876)ESP LLR Silver: Earned 100,000 credits (101,979)PPS LLR Silver: Earned 100,000 credits (148,018)PSP LLR Silver: Earned 100,000 credits (140,441)SoB LLR Silver: Earned 100,000 credits (119,475)SR5 LLR Silver: Earned 100,000 credits (120,939)SGS LLR Silver: Earned 100,000 credits (122,783)TRP LLR Silver: Earned 100,000 credits (100,115)Woodall LLR Silver: Earned 100,000 credits (107,459)321 Sieve Silver: Earned 100,000 credits (202,757)Cullen/Woodall Sieve (suspended) Turquoise: Earned 5,000,000 credits (6,908,135)PPS Sieve Sapphire: Earned 20,000,000 credits (25,450,104)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Silver: Earned 100,000 credits (130,966)TRP Sieve (suspended) Silver: Earned 100,000 credits (201,525)AP 26/27 Silver: Earned 100,000 credits (100,015)GFN Silver: Earned 100,000 credits (246,369)PSA Silver: Earned 100,000 credits (226,594)
Message 34625 - Posted: 30 Mar 2011 | 14:18:04 UTC - in response to Message 34618.

I am only seeing the roundoff errors on my second card. I even stopped all CPU w/u's to see if that has any effect... but I am still getting the roundoff errors.

I would suggest to run some other graphic tests with monitoring of GPU temperatures and see what happens. You can also change the slot for both cards. If the error comes with, then this card is dying. If the first card in the second slot produces errors, then you need only a better cooling for this slot.
____________
Best wishes. Knowledge is power. by jjwhalen

pabliedungProject donor
Volunteer tester
Send message
Joined: 2 Jan 11
Posts: 87
ID: 79535
Credit: 223,567,883
RAC: 1,001
Eliminated 1 conjecture "k"Discovered 1 Sophie Germain pair321 LLR Turquoise: Earned 5,000,000 credits (5,084,460)Cullen LLR Turquoise: Earned 5,000,000 credits (5,116,758)ESP LLR Turquoise: Earned 5,000,000 credits (5,857,992)Generalized Cullen/Woodall LLR Turquoise: Earned 5,000,000 credits (5,160,553)PPS LLR Turquoise: Earned 5,000,000 credits (7,716,351)PSP LLR Turquoise: Earned 5,000,000 credits (5,102,730)SoB LLR Turquoise: Earned 5,000,000 credits (6,758,211)SR5 LLR Turquoise: Earned 5,000,000 credits (9,425,210)SGS LLR Turquoise: Earned 5,000,000 credits (5,063,747)TRP LLR Turquoise: Earned 5,000,000 credits (6,284,268)Woodall LLR Turquoise: Earned 5,000,000 credits (5,224,737)321 Sieve Turquoise: Earned 5,000,000 credits (5,107,390)Cullen/Woodall Sieve (suspended) Jade: Earned 10,000,000 credits (10,903,006)Generalized Cullen/Woodall Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,059,213)PPS Sieve Emerald: Earned 50,000,000 credits (50,293,728)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,054,382)TRP Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,057,704)AP 26/27 Turquoise: Earned 5,000,000 credits (5,061,836)GFN Sapphire: Earned 20,000,000 credits (20,204,632)PSA Emerald: Earned 50,000,000 credits (50,030,975)
Message 34636 - Posted: 31 Mar 2011 | 2:08:09 UTC - in response to Message 34625.

I am only seeing the roundoff errors on my second card. I even stopped all CPU w/u's to see if that has any effect... but I am still getting the roundoff errors.

I would suggest to run some other graphic tests with monitoring of GPU temperatures and see what happens. You can also change the slot for both cards. If the error comes with, then this card is dying. If the first card in the second slot produces errors, then you need only a better cooling for this slot.


The card that is generating the errors (GPU 0) is actually running a couple degrees cooler than the other one.
Could it be that overclocking is causing the error? GPU 0 is a factory overclocked PNY GTX 460 OC XLR8 card. Whereas GPU 1 is a GTX card from a different manufacturer with stock speed.

NVIDIA GPU 0: GeForce GTX 460 (driver version 26658, CUDA version 3020, compute capability 2.1, 994MB, 708 GFLOPS peak)
NVIDIA GPU 1: GeForce GTX 460 (driver version 26658, CUDA version 3020, compute capability 2.1, 993MB, 685 GFLOPS peak)

While I ran the Proth Prime and Cullen/Woodall Sieves on these cards I never encountered any errors. Are the roundoff errors due to the nature of the genefer application compared to sieve application?

Profile Michael GoetzProject donor
Volunteer moderator
Project administrator
Avatar
Send message
Joined: 21 Jan 10
Posts: 13399
ID: 53948
Credit: 229,129,930
RAC: 142,316
The "Shut up already!" badge:  This loud mouth has mansplained on the forums over 10 thousand times!  Sheesh!!!Discovered the World's First GFN-19 prime!!!Discovered 1 mega primeFound 1 prime in the 2018 Tour de PrimesFound 1 prime in the 2019 Tour de PrimesFound 1 prime in the 2020 Tour de Primes321 LLR Ruby: Earned 2,000,000 credits (2,822,730)Cullen LLR Ruby: Earned 2,000,000 credits (2,005,249)ESP LLR Turquoise: Earned 5,000,000 credits (5,009,577)Generalized Cullen/Woodall LLR Ruby: Earned 2,000,000 credits (2,145,754)PPS LLR Jade: Earned 10,000,000 credits (15,528,453)PSP LLR Turquoise: Earned 5,000,000 credits (5,197,957)SoB LLR Sapphire: Earned 20,000,000 credits (34,291,181)SR5 LLR Jade: Earned 10,000,000 credits (10,007,110)SGS LLR Ruby: Earned 2,000,000 credits (2,276,330)TRP LLR Turquoise: Earned 5,000,000 credits (5,084,329)Woodall LLR Ruby: Earned 2,000,000 credits (2,195,123)321 Sieve Jade: Earned 10,000,000 credits (10,061,196)Cullen/Woodall Sieve (suspended) Ruby: Earned 2,000,000 credits (4,170,256)Generalized Cullen/Woodall Sieve (suspended) Turquoise: Earned 5,000,000 credits (5,059,304)PPS Sieve Sapphire: Earned 20,000,000 credits (22,885,121)Sierpinski (ESP/PSP/SoB) Sieve (suspended) Amethyst: Earned 1,000,000 credits (1,035,522)TRP Sieve (suspended) Ruby: Earned 2,000,000 credits (2,051,121)AP 26/27 Jade: Earned 10,000,000 credits (10,118,303)GFN Emerald: Earned 50,000,000 credits (74,741,233)PSA Jade: Earned 10,000,000 credits (12,445,029)
Message 34644 - Posted: 31 Mar 2011 | 11:15:16 UTC - in response to Message 34636.

Several possibilities come to mind:

It could be the overclocking.

It could be insufficient power.

It could be a defective card.

It could be a software problem.

The first thing to test is to lower the clock speeds to stock. If that solves the problem, then the card is defective since it was sold as factory overclocked.

Next thing I would try is removing the GOOD gtx460 and see if the bad gtx460 works by itself. Also switch the power connectors.

If it works fine when the other card is removed, then the problem most likely isn't the card itself. Likely culprits would be power, heat, or software.

If the bad GTX 340 still gives errors with the other card removed, try putting it in the PCIe slot where the good card was. The problem could, potentially, be on the motherboard -- or the card might simply not be seated fully.
____________
My lucky number is 75898524288+1

Message boards : Project Staging Area : genefercuda.exe and roundofferr

[Return to PrimeGrid main page]
DNS Powered by DNSEXIT.COM
Copyright © 2005 - 2020 Rytis Slatkevičius (contact) and PrimeGrid community. Server load 4.08, 4.40, 3.62
Generated 31 Oct 2020 | 2:27:27 UTC