# HELP DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS Number of remapped rows for correctable errors # TYPE DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS counter DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_DEC_UTIL Decoder utilization (in %). # TYPE DCGM_FI_DEV_DEC_UTIL gauge DCGM_FI_DEV_DEC_UTIL{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_DEC_UTIL{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_ENC_UTIL Encoder utilization (in %). # TYPE DCGM_FI_DEV_ENC_UTIL gauge DCGM_FI_DEV_ENC_UTIL{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_ENC_UTIL{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_FB_FREE Framebuffer memory free (in MiB). # TYPE DCGM_FI_DEV_FB_FREE gauge DCGM_FI_DEV_FB_FREE{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 31035 DCGM_FI_DEV_FB_FREE{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 21351 # HELP DCGM_FI_DEV_FB_RESERVED Framebuffer memory reserved (in MiB). # TYPE DCGM_FI_DEV_FB_RESERVED gauge DCGM_FI_DEV_FB_RESERVED{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 766 DCGM_FI_DEV_FB_RESERVED{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 766 # HELP DCGM_FI_DEV_FB_USED Framebuffer memory used (in MiB). # TYPE DCGM_FI_DEV_FB_USED gauge DCGM_FI_DEV_FB_USED{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 50117 DCGM_FI_DEV_FB_USED{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 59802 # HELP DCGM_FI_DEV_GPU_TEMP GPU temperature (in C). # TYPE DCGM_FI_DEV_GPU_TEMP gauge DCGM_FI_DEV_GPU_TEMP{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 45 DCGM_FI_DEV_GPU_TEMP{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 43 # HELP DCGM_FI_DEV_GPU_UTIL GPU utilization (in %). # TYPE DCGM_FI_DEV_GPU_UTIL gauge DCGM_FI_DEV_GPU_UTIL{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_GPU_UTIL{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_MEMORY_TEMP Memory temperature (in C). # TYPE DCGM_FI_DEV_MEMORY_TEMP gauge DCGM_FI_DEV_MEMORY_TEMP{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 58 DCGM_FI_DEV_MEMORY_TEMP{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 56 # HELP DCGM_FI_DEV_MEM_CLOCK Memory clock frequency (in MHz). # TYPE DCGM_FI_DEV_MEM_CLOCK gauge DCGM_FI_DEV_MEM_CLOCK{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1512 DCGM_FI_DEV_MEM_CLOCK{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1512 # HELP DCGM_FI_DEV_MEM_COPY_UTIL Memory utilization (in %). # TYPE DCGM_FI_DEV_MEM_COPY_UTIL gauge DCGM_FI_DEV_MEM_COPY_UTIL{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_MEM_COPY_UTIL{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL Total number of NVLink bandwidth counters for all lanes. # TYPE DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL gauge DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_PCIE_REPLAY_COUNTER Total number of PCIe retries. # TYPE DCGM_FI_DEV_PCIE_REPLAY_COUNTER counter DCGM_FI_DEV_PCIE_REPLAY_COUNTER{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_PCIE_REPLAY_COUNTER{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_POWER_USAGE Power draw (in W). # TYPE DCGM_FI_DEV_POWER_USAGE gauge DCGM_FI_DEV_POWER_USAGE{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 114.253 DCGM_FI_DEV_POWER_USAGE{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 102.672 # HELP DCGM_FI_DEV_ROW_REMAP_FAILURE Whether remapping of rows has failed # TYPE DCGM_FI_DEV_ROW_REMAP_FAILURE gauge DCGM_FI_DEV_ROW_REMAP_FAILURE{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_ROW_REMAP_FAILURE{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_SM_CLOCK SM clock frequency (in MHz). # TYPE DCGM_FI_DEV_SM_CLOCK gauge DCGM_FI_DEV_SM_CLOCK{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1410 DCGM_FI_DEV_SM_CLOCK{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1410 # HELP DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION Total energy consumption since boot (in mJ). # TYPE DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION counter DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 7.5380531835e+10 DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 5.8744668981e+10 # HELP DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS Number of remapped rows for uncorrectable errors # TYPE DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS counter DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_DEV_VGPU_LICENSE_STATUS vGPU License status # TYPE DCGM_FI_DEV_VGPU_LICENSE_STATUS gauge DCGM_FI_DEV_VGPU_LICENSE_STATUS{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_DEV_VGPU_LICENSE_STATUS{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_PROF_DRAM_ACTIVE Ratio of cycles the device memory interface is active sending or receiving data. # TYPE DCGM_FI_PROF_DRAM_ACTIVE gauge DCGM_FI_PROF_DRAM_ACTIVE{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_PROF_DRAM_ACTIVE{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_PROF_GR_ENGINE_ACTIVE Ratio of time the graphics engine is active. # TYPE DCGM_FI_PROF_GR_ENGINE_ACTIVE gauge DCGM_FI_PROF_GR_ENGINE_ACTIVE{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_PROF_GR_ENGINE_ACTIVE{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 # HELP DCGM_FI_PROF_PCIE_RX_BYTES The rate of data received over the PCIe bus - including both protocol headers and data payloads - in bytes per second. # TYPE DCGM_FI_PROF_PCIE_RX_BYTES gauge DCGM_FI_PROF_PCIE_RX_BYTES{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1.127665e+06 DCGM_FI_PROF_PCIE_RX_BYTES{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1.127145e+06 # HELP DCGM_FI_PROF_PCIE_TX_BYTES The rate of data transmitted over the PCIe bus - including both protocol headers and data payloads - in bytes per second. # TYPE DCGM_FI_PROF_PCIE_TX_BYTES gauge DCGM_FI_PROF_PCIE_TX_BYTES{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1.320314e+06 DCGM_FI_PROF_PCIE_TX_BYTES{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 1.319025e+06 # HELP DCGM_FI_PROF_PIPE_TENSOR_ACTIVE Ratio of cycles the tensor (HMMA) pipe is active. # TYPE DCGM_FI_PROF_PIPE_TENSOR_ACTIVE gauge DCGM_FI_PROF_PIPE_TENSOR_ACTIVE{gpu="1",UUID="GPU-921e337a-50e7-5db4-836e-7dda50244f58",pci_bus_id="00000000:00:06.0",device="nvidia1",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0 DCGM_FI_PROF_PIPE_TENSOR_ACTIVE{gpu="0",UUID="GPU-c236902d-c61b-ca15-65bf-2cc0b363cb76",pci_bus_id="00000000:00:05.0",device="nvidia0",modelName="NVIDIA A100 80GB PCIe",hostname="90f87d6e2f36",DCGM_FI_DRIVER_VERSION="570.172.08"} 0