We are using 4 pcs RTX2080 Ti with Supermicro SYS-7049GP-TRT and Intel Xeon 4110*2.
When we run GPU Burn 1.0 under Ubuntu 16.04.01, we found error occurred. The card dropped and disappeared in NVSMI.
After reboot, the card is back but at certain short time period, card will drop again.
Attached files are the error log.
Please help!
lspci-t-vvv.log (13.4 KB)
nvidia-bug-report.log.gz (1.92 MB)