S6S0MD000104 dcgmi diag -r 4 Successfully ran diagnostic for group. +---------------------------+------------------------------------------------+ | Diagnostic | Result | +===========================+================================================+ |----- Metadata ----------+------------------------------------------------| | DCGM Version | 3.3.8 | | 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 - GPUs: 0, 1, 3, 4, 7 | | | Fail - GPUs: 2, 5, 6 | | Warning | GPU 2 Temperature 90 of GPU 2 exceeded user-s | | | pecified maximum allowed temperature 87 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 2 Clocks are being throttled for GPU 2 be | | | cause of clock throttling starting 395.8 seco | | | nds into the test. clocks_throttle_reason_sw_ | | | thermal_slowdown: the GPU or its memory have | | | reached unsafe temperatures. Check DCGM and s | | | ystem logs for errors. Reset GPU. Restart DCG | | | M. Rerun diagnostics. | | Warning | GPU 5 Clocks are being throttled for GPU 5 be | | | cause of clock throttling starting 424.7 seco | | | nds into the test. clocks_throttle_reason_sw_ | | | thermal_slowdown: the GPU or its memory have | | | reached unsafe temperatures. Check DCGM and s | | | ystem logs for errors. Reset GPU. Restart DCG | | | M. Rerun diagnostics. | | Warning | GPU 6 GPU 6 is running at PCI link width 8X, | | | which is below the minimum allowed link gener | | | ation of 16 (parameter 'min_pci_width') Check | | | DCGM and system configuration. This error ma | | | y be eliminated with an updated configuration | | | . | | Warning | GPU 6 Clocks are being throttled for GPU 6 be | | | cause of clock throttling starting 890.0 seco | | | nds into the test. clocks_throttle_reason_sw_ | | | thermal_slowdown: the GPU or its memory have | | | reached unsafe temperatures. Check DCGM and s | | | ystem logs for errors. Reset GPU. Restart DCG | | | M. Rerun diagnostics. | | Info | GPU 0 GPU to Host bandwidth: 55.24 GB/s, GPU | | | 0 Host to GPU bandwidth: 55.03 GB/s, GPU 0 | | | bidirectional bandwidth: 100.81 GB/s, GPU 0 G | | | PU to Host latency: 1.887 us, GPU 0 Host to | | | GPU latency: 2.172 us, GPU 0 bidirectional l | | | atency: 3.002 us | | Info | GPU 1 GPU to Host bandwidth: 55.24 GB/s, GPU | | | 1 Host to GPU bandwidth: 55.04 GB/s, GPU 1 | | | bidirectional bandwidth: 100.79 GB/s, GPU 1 G | | | PU to Host latency: 1.884 us, GPU 1 Host to | | | GPU latency: 2.166 us, GPU 1 bidirectional l | | | atency: 3.014 us | | Info | GPU 2 GPU to Host bandwidth: 55.24 GB/s, GPU | | | 2 Host to GPU bandwidth: 55.01 GB/s, GPU 2 | | | bidirectional bandwidth: 100.77 GB/s, GPU 2 G | | | PU to Host latency: 1.873 us, GPU 2 Host to | | | GPU latency: 2.161 us, GPU 2 bidirectional l | | | atency: 3.009 us | | Info | GPU 3 GPU to Host bandwidth: 55.23 GB/s, GPU | | | 3 Host to GPU bandwidth: 55.03 GB/s, GPU 3 | | | bidirectional bandwidth: 100.80 GB/s, GPU 3 G | | | PU to Host latency: 1.875 us, GPU 3 Host to | | | GPU latency: 2.160 us, GPU 3 bidirectional l | | | atency: 3.019 us | | Info | GPU 4 GPU to Host bandwidth: 55.22 GB/s, GPU | | | 4 Host to GPU bandwidth: 55.02 GB/s, GPU 4 | | | bidirectional bandwidth: 100.75 GB/s, GPU 4 G | | | PU to Host latency: 1.927 us, GPU 4 Host to | | | GPU latency: 2.161 us, GPU 4 bidirectional l | | | atency: 3.405 us | | Info | GPU 5 GPU to Host bandwidth: 55.25 GB/s, GPU | | | 5 Host to GPU bandwidth: 55.02 GB/s, GPU 5 | | | bidirectional bandwidth: 100.72 GB/s, GPU 5 G | | | PU to Host latency: 1.926 us, GPU 5 Host to | | | GPU latency: 2.155 us, GPU 5 bidirectional l | | | atency: 3.385 us | | Info | GPU 6 GPU to Host bandwidth: 28.90 GB/s, GPU | | | 6 Host to GPU bandwidth: 28.59 GB/s, GPU 6 | | | bidirectional bandwidth: 51.87 GB/s, GPU 6 GP | | | U to Host latency: 1.936 us, GPU 6 Host to G | | | PU latency: 2.171 us, GPU 6 bidirectional la | | | tency: 3.348 us | | Info | GPU 7 GPU to Host bandwidth: 55.24 GB/s, GPU | | | 7 Host to GPU bandwidth: 55.04 GB/s, GPU 7 | | | bidirectional bandwidth: 100.75 GB/s, GPU 7 G | | | PU to Host latency: 1.928 us, GPU 7 Host to | | | GPU latency: 2.194 us, GPU 7 bidirectional l | | | atency: 3.156 us | +----- Hardware ----------+------------------------------------------------+ | GPU Memory | Pass - All | | Diagnostic | Pass - GPUs: 0, 1, 2, 3, 4, 5, 7 | | | Fail - GPU: 6 | | Warning | GPU 6 Temperature 92 of GPU 6 exceeded user-s | | | pecified maximum allowed temperature 87 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 6 Clocks are being throttled for GPU 6 be | | | cause of clock throttling starting 30.0 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. | | Info | GPU 0 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 0 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 0 GPU 0 calculated at approximately 229 | | | 0.54 gigaflops during this test | | Info | GPU 1 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 1 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 1 GPU 1 calculated at approximately 235 | | | 1.46 gigaflops during this test | | Info | GPU 2 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 2 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 2 GPU 2 calculated at approximately 755 | | | .39 gigaflops during this test | | Info | GPU 3 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 3 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 3 GPU 3 calculated at approximately 237 | | | 5.82 gigaflops during this test | | Info | GPU 4 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 4 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 4 GPU 4 calculated at approximately 235 | | | 1.46 gigaflops during this test | | Info | GPU 5 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 5 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 5 GPU 5 calculated at approximately 755 | | | .39 gigaflops during this test | | Info | GPU 6 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 6 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 6 GPU 6 calculated at approximately 682 | | | .28 gigaflops during this test | | Info | GPU 7 Allocated space for 137 output matricie | | | s from 75945266380 bytes available., GPU 7 Ru | | | nning with precisions: FP64 1, FP32 1, FP16 1 | | | , GPU 7 GPU 7 calculated at approximately 235 | | | 1.46 gigaflops during this test | | Pulse Test | Pass - All | +----- Stress ------------+------------------------------------------------+ | Targeted Stress | Pass - All | | Targeted Power | Pass - GPUs: 0, 1, 3, 4, 7 | | | Fail - GPUs: 2, 5, 6 | | Warning | GPU 2 Max power of 420.9 did not reach desire | | | d power minimum target_power_min_ratio of 525 | | | .0 for GPU 2 Verify that the clock speeds and | | | GPU utilization are high. | | Warning | GPU 2 Temperature 90 of GPU 2 exceeded user-s | | | pecified maximum allowed temperature 87 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 2 Clocks are being throttled for GPU 2 be | | | cause of clock throttling starting 5.0 second | | | s into the test. clocks_throttle_reason_sw_th | | | ermal_slowdown: the GPU or its memory have re | | | ached unsafe temperatures. Check DCGM and sys | | | tem logs for errors. Reset GPU. Restart DCGM. | | | Rerun diagnostics. | | Warning | GPU 5 Max power of 475.5 did not reach desire | | | d power minimum target_power_min_ratio of 525 | | | .0 for GPU 5 Verify that the clock speeds and | | | GPU utilization are high. | | Warning | GPU 5 Clocks are being throttled for GPU 5 be | | | cause of clock throttling starting 4.8 second | | | s into the test. clocks_throttle_reason_sw_th | | | ermal_slowdown: the GPU or its memory have re | | | ached unsafe temperatures. Check DCGM and sys | | | tem logs for errors. Reset GPU. Restart DCGM. | | | Rerun diagnostics. | | Warning | GPU 6 Max power of 424.8 did not reach desire | | | d power minimum target_power_min_ratio of 525 | | | .0 for GPU 6 Verify that the clock speeds and | | | GPU utilization are high. | | Warning | GPU 6 Temperature 88 of GPU 6 exceeded user-s | | | pecified maximum allowed temperature 87 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 6 Clocks are being throttled for GPU 6 be | | | cause of clock throttling starting 4.9 second | | | s into the test. clocks_throttle_reason_sw_th | | | ermal_slowdown: the GPU or its memory have re | | | ached unsafe temperatures. Check DCGM and sys | | | tem logs for errors. Reset GPU. Restart DCGM. | | | Rerun diagnostics. | | Info | GPU 0 GPU 0 max power: 668.1 W average power | | | usage: 658.6 W | | Info | GPU 1 GPU 1 max power: 663.4 W average power | | | usage: 650.0 W | | Info | GPU 3 GPU 3 max power: 648.4 W average power | | | usage: 637.5 W | | Info | GPU 4 GPU 4 max power: 663.5 W average power | | | usage: 652.8 W | | Info | GPU 7 GPU 7 max power: 655.5 W average power | | | usage: 640.4 W | | Memory Bandwidth | Pass - All | | Memtest | Pass - GPUs: 0, 1, 3, 4, 7 | | | Fail - GPUs: 2, 5, 6 | | Warning | GPU 2 Temperature 96 of GPU 2 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 2 Clocks are being throttled for GPU 2 be | | | cause of clock throttling starting 15.3 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. | | Warning | GPU 5 Temperature 88 of GPU 5 exceeded user-s | | | pecified maximum allowed temperature 87 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 5 Temperature 97 of GPU 5 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 5 Clocks are being throttled for GPU 5 be | | | cause of clock throttling starting 14.8 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. | | Warning | GPU 6 Temperature 88 of GPU 6 exceeded user-s | | | pecified maximum allowed temperature 87 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 6 Temperature 96 of GPU 6 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 6 Clocks are being throttled for GPU 6 be | | | cause of clock throttling starting 15.4 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 | +---------------------------+------------------------------------------------+