Hi all,
I am having errors on two Intel I7-12700H Dell Precision 5570 laptops (6 performance(hyperthreaded) and 8 efficiency BIG.little system). Prime95 64bit 30.8 build17, windows10.
The problems go away if I limit the cores to 6p (no hyperthreads) and 2e. Memory tests do not show issues.
What is strange is that when the fail occurs, it often involves two or three cores at the same time.
Looks like HW issue in the chipset (uncore?) to me.
Does somebody know about such a problem? If not, I hope there are people that are willing to torture test similar systems.
Under load, the CPU cores are at about 80DegC, and at 2GHz clock.
Errors may occur on the first minute, or it may sometimes work through the night without issues. but usually I find 2-3 workers stopped on the next morning with errors like these:
FATAL ERROR: Rounding was 3.904203594e+59, expected less than 0.4
Hardware failure detected running 560K FFT size, consult stress.txt file.
FATAL ERROR: Rounding was 1.599713869e+237, expected less than 0.4
Hardware failure detected running 21K FFT size, consult stress.txt file.
FATAL ERROR: Rounding was 1.348361105e+272, expected less than 0.4
Hardware failure detected running 20K FFT size, consult stress.txt file.
Self-test 25K passed!
FATAL ERROR: Final result was 00000000, expected: 4D58EEF3.
Hardware failure detected running 20K FFT size, consult stress.txt file.
FATAL ERROR: Final result was 00000000, expected: 4C1D976F.
Hardware failure detected running 864K FFT size, consult stress.txt file.
Self-test 1024K passed!
FATAL ERROR: Final result was 00000000, expected: 4C1D976F.
Hardware failure detected running 864K FFT size, consult stress.txt file.
I am having errors on two Intel I7-12700H Dell Precision 5570 laptops (6 performance(hyperthreaded) and 8 efficiency BIG.little system). Prime95 64bit 30.8 build17, windows10.
The problems go away if I limit the cores to 6p (no hyperthreads) and 2e. Memory tests do not show issues.
What is strange is that when the fail occurs, it often involves two or three cores at the same time.
Looks like HW issue in the chipset (uncore?) to me.
Does somebody know about such a problem? If not, I hope there are people that are willing to torture test similar systems.
Under load, the CPU cores are at about 80DegC, and at 2GHz clock.
Errors may occur on the first minute, or it may sometimes work through the night without issues. but usually I find 2-3 workers stopped on the next morning with errors like these:
FATAL ERROR: Rounding was 3.904203594e+59, expected less than 0.4
Hardware failure detected running 560K FFT size, consult stress.txt file.
FATAL ERROR: Rounding was 1.599713869e+237, expected less than 0.4
Hardware failure detected running 21K FFT size, consult stress.txt file.
FATAL ERROR: Rounding was 1.348361105e+272, expected less than 0.4
Hardware failure detected running 20K FFT size, consult stress.txt file.
Self-test 25K passed!
FATAL ERROR: Final result was 00000000, expected: 4D58EEF3.
Hardware failure detected running 20K FFT size, consult stress.txt file.
FATAL ERROR: Final result was 00000000, expected: 4C1D976F.
Hardware failure detected running 864K FFT size, consult stress.txt file.
Self-test 1024K passed!
FATAL ERROR: Final result was 00000000, expected: 4C1D976F.
Hardware failure detected running 864K FFT size, consult stress.txt file.