Unable to determine the device handle for GPU0: 0000:01:00.0: GPU is lost. Reboot the system to recover this GPU

Accelerated Computing CUDA CUDA Programming and Performance
1

Unable to determine the device handle for GPU0: 0000:01:00.0: GPU is lost. Reboot the system to recover this GPU

I have a PNY RTX 5080, 32 GB Corsair Vengeance RAM, a 3.1 atx 1000W PSU, an MSI-X870E-gaming-plus-wifi-motherboard, cuda 13.2, driver version 595.79, and all kinds of available ideas are applied, like pcie E1 to gen4, disable resize bar, GPU connectivity, display to 60 Hz, power to 90% manual fan speed acceleration, and temperature stays between 59 and 63 degrees Celsius. Now is my card faulty?

3

Is this error from using CUDA or does also the display stop?

Does it appear in syslog or on the console?

4

from cuda, after running my code for 2-3 hours for 95-99% GPU usage, and yes its from vscode terminal, the display also turns black, when I connect it to iGPU it shows this result after giving command nvidia-smi