Hardware errors have occurred during the test!

[rgirard1]

I am getting the following message from running mprime on AMD® Ryzen 9 3950x 16-core processor × 32 32 GB memory with Ubuntu 18.04.5 LTS as OS:

"Hardware errors have occurred during the test!
1 Gerbicz/double-check error.
Confidence in final result is excellent."

Can anyone help to understand what is happening? I have this machine since January 2020 so realtively new. Have I an actual "hardware problem"?

[chalsall]

Originally Posted by rgirard1

Have I an actual "hardware problem"?

Possibly.

How hard have you pushed it to the limits (read: overclocked)?

Is this a new build you are trying to test the limits of?

Or is this a machine you've been using for a while, and suddenly it's reporting this?

Perspiring minds want to know...

[LaurV]

One error is not big deal. Even the most stable hardware has errors sometimes (electricity flashes, cosmic rays, bad luck, etc). Along the test, the message repeats periodically till the test is finished, to remind you about, but it is the same, 1 (one) error that occurred in the past. Nothing to worry about.

The message will be gone once you finish the exponent, report the result, and start a new exponent.

More errors is to worry. If they start growing, or appear regularly on subsequent tests, then yes, you may have a hardware issue. Meantime, try to monitor the temperatures closely. If they raise, reduce the clocks, clean the dust in the fans, or in the worst case, think about a re-seating of the CPU.

Right now, do nothing (beside monitoring the system).

[Viliam Furik]

Originally Posted by LaurV

or in the worst case, think about a re-seating of the CPU.

I don't think that could help, since AMD uses PGA socket, that has pins on the CPU, and holes in the socket. If there was something that could be wrong, it would have to be one of these:

1. CPU is a tiny bit higher placed than it should be. - But that would most probably mean non-operability of the whole CPU.
2. One pin is missing, all other pins are in place. - THAT would be very interesting, but if the CPU is working, it would most probably cause some RAM to not be detected.

[De Wandelaar]

Originally Posted by rgirard1

"Hardware errors have occurred during the test!
1 Gerbicz/double-check error.
Confidence in final result is excellent."

I had the same problem when the undervolting of my CPU was too borderline.

[LaurV]

Originally Posted by Viliam Furik

I don't think that could help

Re-seating has nothing to do with the pins side. Or, well, it has , but what we mean by it (and by we, in turn, we meen overclocking geeks, hihi) is: taking out the cooler, clean it, remove dust clogs, if any, but most of all, clean the dry thermal paste, apply a new thermal paste. That's re-seating. To not be confused with "resetting". Put everything back carefully. As said, this would be his last resort, and I don't believe it's the case, for a computer bought this year, unless his cat sleeps inside of the computer housing and it's full of dust and hairs. On the other hand, I also don't know much about making t-shirts... (to which, if mentioned, I want to buy one! I will come back to it, hopefully, you wont exhaust the second lot till I got the time to measure myself and order it, hehe).

[rgirard1]

I have dusted up the PC and restarted "mprime" but still getting the same error message. I am not overclocking the CPU (AMD 3950X) and "Throttle = 30" so CPU runs 30% of the time. The CPU temperature is about 50 degC.

I am using 4 workers and each has 4 threads as shown below:


Resuming primality test of M54111917 using FMA3 FFT length 2880K, Pass1=1280, Pass2=2304, clm=2, 4 threads
Resuming Gerbicz error-checking PRP test of M103884359 using FMA3 FFT length 5600K, Pass1=896, Pass2=6400, clm=2, 4 threads
Resuming Gerbicz error-checking PRP test of M103884401 using FMA3 FFT length 5600K, Pass1=896, Pass2=6400, clm=2, 4 threads
Resuming Gerbicz error-checking PRP test of M105836671 using FMA3 FFT length 5600K, Pass1=896, Pass2=6400, clm=2, 4 threads


Note that for the first exponent M54111917 FFT length is 2880K and for the others (where I believe the "hardware error" is from) have FFT length of 5600 K. Is this a problem?

Is there a way to stop this calculation and start a complete and fresh new one for a new set of 4 exponents?

The above message of "Harware error" has appeared only recently.

Thank in advance for any help you can provide.

[Xyzzy]

What speed are you running your memory? What kind of memory is it? Have you tried a memory test?

https://www.memtest86.com/download.htm

[Xyzzy]

Also, have you run the torture test?

./mprime -m

Select the torture test option. The defaults are fine.

[Prime95]

Originally Posted by rgirard1

I I am not overclocking the CPU (AMD 3950X) and "Throttle = 30" so CPU runs 30% of the time. The CPU temperature is about 50 degC.

Is there a way to stop this calculation and start a complete and fresh new one for a new set of 4 exponents?

Do not use Throttle. Nowadays heat is rarely the cause of hardware problems. Usually it is memory related.

Do not restart your calculations. The PRP error-checking has caught and corrected the problem. Your results will be just fine.

Right now you should do nothing. Just keep an eye on the things. If you get more errors (do not worry about prime95 whining about the one error that has already occurred), then look at upping the memory voltage or reducing the RAM speed.

[rgirard1]

I ran the torture test for over 48 hrs with default settings, no overclocking, no Throttle=30 basically the machine normal state. In the "results.txt" I got a very long listing like this:
.
.
.
[Sun Aug 30 09:36:01 2020]
Self-test 240K passed!
Self-test 256K passed!
Self-test 256K passed!
.
.
.
Self-test 256K passed!
[Sun Aug 30 09:41:11 2020]
Self-test 280K passed!

i.e. all "Self-tests" passed and no error messages.

I am concluding that hardware problems with my desktop are unlikely. I will stop the torture test and resume the prime95 calculations and if there are error message I will let them be until new exponents are assigned after the completion of the current calculations.

I am wondering if the "restart" files are not somehow corrupted and bring these error messages. I do stop prime95 when I must do a Software Update for Ubuntu 18.04 and then resume the calculations after the Software Update.

Is there a way to start a "fresh" new calculation with new assigned exponents?