# 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: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 Thermal violations totaling 15764.5 sec | | | onds started at 344.8 seconds into the test f | | | or GPU 0 Verify that the cooling on this mach | | | ine is functional, including external, therma | | | l material interface, fans, and any other com | | | ponents. | | Warning | GPU 0 Temperature 91 of GPU 0 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 0 Clocks are being throttled for GPU 0 be | | | cause of clock throttling starting 344.8 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. | | Info | GPU 0 GPU to Host bandwidth: 55.05 GB/s, GPU | | | 0 Host to GPU bandwidth: 54.83 GB/s, GPU 0 | | | bidirectional bandwidth: 100.67 GB/s, GPU 0 G | | | PU to Host latency: 1.870 us, GPU 0 Host to | | | GPU latency: 2.157 us, GPU 0 bidirectional l | | | atency: 3.040 us | | Info | GPU 1 GPU to Host bandwidth: 55.01 GB/s, GPU | | | 1 Host to GPU bandwidth: 54.86 GB/s, GPU 1 | | | bidirectional bandwidth: 100.72 GB/s, GPU 1 G | | | PU to Host latency: 1.872 us, GPU 1 Host to | | | GPU latency: 2.188 us, GPU 1 bidirectional l | | | atency: 3.047 us | | Info | GPU 2 GPU to Host bandwidth: 55.03 GB/s, GPU | | | 2 Host to GPU bandwidth: 54.80 GB/s, GPU 2 | | | bidirectional bandwidth: 100.65 GB/s, GPU 2 G | | | PU to Host latency: 1.902 us, GPU 2 Host to | | | GPU latency: 2.193 us, GPU 2 bidirectional l | | | atency: 3.022 us | | Info | GPU 3 GPU to Host bandwidth: 55.03 GB/s, GPU | | | 3 Host to GPU bandwidth: 54.83 GB/s, GPU 3 | | | bidirectional bandwidth: 100.66 GB/s, GPU 3 G | | | PU to Host latency: 1.889 us, GPU 3 Host to | | | GPU latency: 2.178 us, GPU 3 bidirectional l | | | atency: 3.041 us | | Info | GPU 4 GPU to Host bandwidth: 55.01 GB/s, GPU | | | 4 Host to GPU bandwidth: 54.84 GB/s, GPU 4 | | | bidirectional bandwidth: 100.69 GB/s, GPU 4 G | | | PU to Host latency: 1.955 us, GPU 4 Host to | | | GPU latency: 2.184 us, GPU 4 bidirectional l | | | atency: 3.437 us | | Info | GPU 5 GPU to Host bandwidth: 55.00 GB/s, GPU | | | 5 Host to GPU bandwidth: 54.84 GB/s, GPU 5 | | | bidirectional bandwidth: 100.68 GB/s, GPU 5 G | | | PU to Host latency: 1.951 us, GPU 5 Host to | | | GPU latency: 2.181 us, GPU 5 bidirectional l | | | atency: 3.420 us | | Info | GPU 6 GPU to Host bandwidth: 55.04 GB/s, GPU | | | 6 Host to GPU bandwidth: 54.85 GB/s, GPU 6 | | | bidirectional bandwidth: 100.68 GB/s, GPU 6 G | | | PU to Host latency: 1.961 us, GPU 6 Host to | | | GPU latency: 2.317 us, GPU 6 bidirectional l | | | atency: 3.408 us | | Info | GPU 7 GPU to Host bandwidth: 55.01 GB/s, GPU | | | 7 Host to GPU bandwidth: 54.89 GB/s, GPU 7 | | | bidirectional bandwidth: 100.72 GB/s, GPU 7 G | | | PU to Host latency: 1.942 us, GPU 7 Host to | | | GPU latency: 2.178 us, GPU 7 bidirectional l | | | atency: 3.265 us | +----- Hardware ----------+------------------------------------------------+ | GPU Memory | Pass - GPUs: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 Thermal violations totaling 952.1 secon | | | ds started at 9.8 seconds into the test for G | | | PU 0 Verify that the cooling on this machine | | | is functional, including external, thermal ma | | | terial interface, fans, and any other compone | | | nts. | | Info | GPU 0 Allocated 83537716779 bytes (98.3%) | | Info | GPU 1 Allocated 83537716779 bytes (98.3%) | | Info | GPU 2 Allocated 83537716779 bytes (98.3%) | | Info | GPU 3 Allocated 83537716779 bytes (98.3%) | | Info | GPU 4 Allocated 83537716779 bytes (98.3%) | | Info | GPU 5 Allocated 83537716779 bytes (98.3%) | | Info | GPU 6 Allocated 83537716779 bytes (98.3%) | | Info | GPU 7 Allocated 83537716779 bytes (98.3%) | | Diagnostic | Pass - GPUs: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 Thermal violations totaling 5119.6 seco | | | nds started at 9.8 seconds into the test for | | | GPU 0 Verify that the cooling on this machine | | | is functional, including external, thermal m | | | aterial interface, fans, and any other compon | | | ents. | | Warning | GPU 0 Clocks are being throttled for GPU 0 be | | | cause of clock throttling starting 9.8 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. | | 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 852 | | | .86 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 230 | | | 2.72 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 230 | | | 2.72 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 230 | | | 2.72 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 235 | | | 1.46 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 238 | | | 8.01 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 230 | | | 2.72 gigaflops during this test | | Pulse Test | Pass - GPUs: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 Thermal violations totaling 15001.8 sec | | | onds started at 1509.9 seconds into the test | | | for GPU 0 Verify that the cooling on this mac | | | hine is functional, including external, therm | | | al material interface, fans, and any other co | | | mponents. | | Warning | GPU 0 Clocks are being throttled for GPU 0 be | | | cause of clock throttling starting 1509.9 sec | | | onds into the test. clocks_throttle_reason_sw | | | _thermal_slowdown: the GPU or its memory have | | | reached unsafe temperatures. Check DCGM and | | | system logs for errors. Reset GPU. Restart DC | | | GM. Rerun diagnostics. | +----- Stress ------------+------------------------------------------------+ | Targeted Stress | Pass - GPUs: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 There were thermal violations totaling | | | 899.6 seconds for GPU 0 Verify that the cooli | | | ng on this machine is functional, including e | | | xternal, thermal material interface, fans, an | | | d any other components. | | Info | GPU 0 GPU 0 relative stress level 5620 | | Info | GPU 1 GPU 1 relative stress level 5711 | | Info | GPU 2 GPU 2 relative stress level 5590 | | Info | GPU 3 GPU 3 relative stress level 5565 | | Info | GPU 4 GPU 4 relative stress level 4178 | | Info | GPU 5 GPU 5 relative stress level 4128 | | Info | GPU 6 GPU 6 relative stress level 4187 | | Info | GPU 7 GPU 7 relative stress level 4144 | | Targeted Power | Pass - GPUs: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 Max power of 462.7 did not reach desire | | | d power minimum target_power_min_ratio of 525 | | | .0 for GPU 0 Verify that the clock speeds and | | | GPU utilization are high. | | Warning | GPU 0 Thermal violations totaling 3089.9 seco | | | nds started at 4.8 seconds into the test for | | | GPU 0 Verify that the cooling on this machine | | | is functional, including external, thermal m | | | aterial interface, fans, and any other compon | | | ents. | | Warning | GPU 0 Temperature 90 of GPU 0 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 0 Clocks are being throttled for GPU 0 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. | | Info | GPU 1 GPU 1 max power: 651.9 W average power | | | usage: 641.9 W | | Info | GPU 2 GPU 2 max power: 697.9 W average power | | | usage: 681.5 W | | Info | GPU 3 GPU 3 max power: 663.1 W average power | | | usage: 654.6 W | | Info | GPU 4 GPU 4 max power: 679.8 W average power | | | usage: 671.9 W | | Info | GPU 5 GPU 5 max power: 644.7 W average power | | | usage: 635.3 W | | Info | GPU 6 GPU 6 max power: 649.1 W average power | | | usage: 637.2 W | | Info | GPU 7 GPU 7 max power: 664.5 W average power | | | usage: 656.2 W | | Memory Bandwidth | Pass - GPUs: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 There were thermal violations totaling | | | 128.5 seconds for GPU 0 Verify that the cooli | | | ng on this machine is functional, including e | | | xternal, thermal material interface, fans, an | | | d any other components. | | Memtest | Pass - GPUs: 1, 2, 3, 4, 5, 6, 7 | | | Fail - GPU: 0 | | Warning | GPU 0 Thermal violations totaling 15001.8 sec | | | onds started at 69.9 seconds into the test fo | | | r GPU 0 Verify that the cooling on this machi | | | ne is functional, including external, thermal | | | material interface, fans, and any other comp | | | onents. | | Warning | GPU 0 Temperature 96 of GPU 0 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 0 Clocks are being throttled for GPU 0 be | | | cause of clock throttling starting 69.9 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 | +---------------------------+------------------------------------------------+