# dcgmi diag -r 4 Successfully ran diagnostic for group. +---------------------------+------------------------------------------------+ | Diagnostic | Result | +===========================+================================================+ |----- Metadata ----------+------------------------------------------------| | DCGM Version | 3.3.7 | | Driver Version Detected | 535.129.03 | | GPU Device IDs Detected | 2330,2330,2330,2330,2330,2330,2330,2330 | |----- Deployment --------+------------------------------------------------| | Denylist | Pass | | NVML Library | Pass | | CUDA Main Library | Pass | | Permissions and OS Blocks | Pass | | Persistence Mode | Pass | | Environment Variables | Pass | | Page Retirement/Row Remap | Pass | | Graphics Processes | Pass | | Inforom | Pass | +----- Integration -------+------------------------------------------------+ | PCIe | Pass - All | +----- Hardware ----------+------------------------------------------------+ | GPU Memory | Pass - All | | Diagnostic | Pass - All | | Pulse Test | Pass - All | +----- Stress ------------+------------------------------------------------+ | Targeted Stress | Pass - All | | Targeted Power | Pass - GPUs: 0, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 1 | | Warning | GPU 1 Max power of 477.5 did not reach desire | | | d power minimum target_power_min_ratio of 525 | | | .0 for GPU 1 Verify that the clock speeds and | | | GPU utilization are high. | | Warning | GPU 1 Clocks are being throttled for GPU 1 be | | | cause of clock throttling starting 4.9 second | | | s into the test. clocks_throttle_reason_hw_sl | | | owdown: either the temperature is too high or | | | there is a power supply problem (the power b | | | rake assertion has been tripped). Check DCGM | | | and system logs for errors. Reset GPU. Restar | | | t DCGM. Rerun diagnostics. | | Info | GPU 0 GPU 0 max power: 646.2 W average power | | | usage: 635.5 W | | Info | GPU 2 GPU 2 max power: 666.7 W average power | | | usage: 654.8 W | | Info | GPU 3 GPU 3 max power: 644.8 W average power | | | usage: 637.5 W | | Info | GPU 4 GPU 4 max power: 649.9 W average power | | | usage: 642.3 W | | Info | GPU 5 GPU 5 max power: 644.7 W average power | | | usage: 633.6 W | | Info | GPU 6 GPU 6 max power: 651.6 W average power | | | usage: 641.0 W | | Info | GPU 7 GPU 7 max power: 671.4 W average power | | | usage: 659.7 W | | Memory Bandwidth | Pass - All | | Memtest | Pass - GPUs: 0, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 1 | | Warning | GPU 1 Temperature 96 of GPU 1 exceeded user-s | | | pecified maximum allowed temperature 95 Verif | | | y that the user-specified temperature maximum | | | is set correctly. If it is, check the coolin | | | g for this GPU and node: Verify that the cool | | | ing on this machine is functional, including | | | external, thermal material interface, fans, a | | | nd any other components. | | Warning | GPU 1 Clocks are being throttled for GPU 1 be | | | cause of clock throttling starting 35.0 secon | | | ds into the test. clocks_throttle_reason_sw_t | | | hermal_slowdown: the GPU or its memory have r | | | eached unsafe temperatures. Check DCGM and sy | | | stem logs for errors. Reset GPU. Restart DCGM | | | . Rerun diagnostics. | | EUD Test | Skip - All | +---------------------------+------------------------------------------------+