what does this mean?

Question

This error occurred whilst running a gpu stress test.

Answer 1

1

That error indicates most likely the graphics drivers crashed during the test, were you previously experiencing problems with the graphics on your PC, is that why you were stress testing your GPU?

2

Open File Explorer,

Go to C:\Windows\LiveKernelReports

IN the two sub-folders in that folder, are there any WATCHDOG dmp files?

If so, copy them out onto your Desktop and zip them up.

Then upload the zip file to the Cloud (OneDrive... etc.), then choose to share those and get a share link.

Then post the link here to the zip file, so I can take a look for you.

Answer 2

The Reliability Monitor entry shows a LiveKernelEvent with code 117, logged as a Hardware error while the GPU stress test was running.

In this context, code 117 indicates that Windows’ graphics watchdog (TDR – Timeout Detection and Recovery) detected that the GPU or its driver stopped responding under heavy load and had to be reset. Instead of a full blue-screen crash, Windows logged this as a hardware error and attempted to recover the graphics stack.

In practical terms this means:

• The GPU or GPU driver became unresponsive during the stress test (for example due to high load, overheating, or a driver fault).
• Windows triggered a watchdog timeout and reset the graphics device, generating the LiveKernelEvent entry and the WATCHDOG-*.dmp file.

Typical contributing factors (as seen in similar cases in the context):

• GPU overheating or inadequate cooling during heavy load.
• Unstable or problematic GPU driver versions that cause TDRs during games or stress tests.
• Underlying hardware issues (e.g., aging thermal paste, power/VRM issues, or faulty GPU/SSD/motherboard components) that only surface under stress.

Recommended next steps based on similar resolved cases:

1. Check GPU thermals and cooling
   • Monitor GPU temperature during stress tests; ensure it stays well below the card’s thermal limit.
   • Clean dust, ensure fans and airflow are working, and consider replacing dried thermal paste if temperatures are high.
2. Try a different GPU driver version
   • Use a clean uninstall tool (such as DDU) to remove the current driver, then install a known-stable or slightly older WHQL driver. In a similar case, downgrading the GPU driver resolved repeated TDR and crash issues.
3. Reduce stress/overclocks
   • Remove any GPU overclock or undervolt and test at stock settings.
   • If the error only appears under synthetic stress but not in normal use, it may indicate the stress level is beyond what the current cooling or hardware can handle safely.
4. Inspect hardware if problems persist
   • If LiveKernelEvent 117 or related watchdog/TDR errors continue under normal workloads, investigate for hardware faults (GPU, motherboard, SSD, or power delivery), as other users have traced persistent complex errors back to failing components.

The error itself does not specify exactly which component is bad, but it clearly points to the GPU path (hardware or driver) failing to respond in time under heavy load.

---

References:

• WDDM Sch_Stress
• WDDM Scheduler Stress (AlwaysRepatch)
• WDDM Scheduler Stress (No PrePatching)
• TDR2 - Long Running Graphics Packet Expect NO TDR (Interactive)
• "Stop 0x0000007E SYSTEM_THREAD_EXCEPTION_NOT_HANDLED" error when the GPU is under heavy load conditions in Windows 7 or Windows Server 2008 R2
• "0x000000D5" Stop error message when you run an automated test job in Windows 7 or in Windows Server 2008 R2
• Recurring "LiveKernelEvent 1b8" hardware error (Watchdog Timeout) - Microsoft Q&A
• Constant BSOD - Microsoft Q&A
• Minecraft for windows is crashing - Microsoft Q&A
• WinSxS Corruptions Despite Numerous Formats to Windows, Silent Corruption and Deletion of Windows Update Files - Microsoft Q&A
• My Windows 11 PC Hard Freezes for about 30 seconds to a minute when I play certain games. - Microsoft Q&A