Hello all.
After changing the thermal pads on one of my rtx 3080s earlier today, the card has crashed 2 times until now.
These are the error messages so far:
2021.03.18:16:19:52.924: GPU4 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:52.924: GPU4 GPU4 search error: the launch timed out and was terminated
2021.03.18:16:19:52.924: wdog Fatal error detected. Restarting.
2021.03.18:16:19:53.009: GPU3 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:53.009: GPU1 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:53.009: GPU1 GPU1 search error: the launch timed out and was terminated
2021.03.18:16:19:53.009: GPU3 GPU3 search error: the launch timed out and was terminated
2021.03.18:16:19:53.009: GPU2 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:53.009: GPU2 GPU2 search error: the launch timed out and was terminated
2021.03.18:16:19:52.924: GPU4 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:52.924: GPU4 GPU4 search error: the launch timed out and was terminated
2021.03.18:16:19:52.924: wdog Fatal error detected. Restarting.
2021.03.18:16:19:53.009: GPU3 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:53.009: GPU1 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:53.009: GPU1 GPU1 search error: the launch timed out and was terminated
2021.03.18:16:19:53.009: GPU3 GPU3 search error: the launch timed out and was terminated
2021.03.18:16:19:53.009: GPU2 CUDA error in CudaProgram.cu:465 : the launch timed out and was terminated (702)
2021.03.18:16:19:53.009: GPU2 GPU2 search error: the launch timed out and was terminated
OVerall the temps are :
Avg - 89-90Celsius and the Highest went to 100 Celsius.
Both times the rigs was running for about 2 hours, give or take some minutes, before these events happen. Has anyone experienced any of these so far?
Any help would be much appreciated!