# DCGM FIELD                                                      ,Prometheus metric type ,help message
 
# Clocks
DCGM_FI_DEV_SM_CLOCK                                              ,gauge                  ,SM clock frequency (in MHz).
DCGM_FI_DEV_MEM_CLOCK                                             ,gauge                  ,Memory clock frequency (in MHz).
 
# Temperature
DCGM_FI_DEV_MEMORY_TEMP                                           ,gauge                  ,Memory temperature (in C).
DCGM_FI_DEV_GPU_TEMP                                              ,gauge                  ,GPU temperature (in C).
 
# Power
DCGM_FI_DEV_POWER_USAGE                                           ,gauge                  ,Power draw (in W).
DCGM_FI_DEV_TOTAL_ENERGY_CONSUMPTION                              ,counter                ,Total energy consumption since boot (in mJ).
 
# PCIE
DCGM_FI_DEV_PCIE_REPLAY_COUNTER                                   ,counter                ,Total number of PCIe retries.
 
# Utilization (the sample period varies depending on the product)
DCGM_FI_DEV_GPU_UTIL                                              ,gauge                  ,GPU utilization (in %).
DCGM_FI_DEV_MEM_COPY_UTIL                                         ,gauge                  ,Memory utilization (in %).
DCGM_FI_DEV_ENC_UTIL                                              ,gauge                  ,Encoder utilization (in %).
DCGM_FI_DEV_DEC_UTIL                                              ,gauge                  ,Decoder utilization (in %).
 
# Errors and violations
DCGM_FI_DEV_XID_ERRORS                                            ,gauge                  ,Value of the last XID error encountered.
 
# Memory usage
DCGM_FI_DEV_FB_FREE                                               ,gauge                  ,Framebuffer memory free (in MiB).
DCGM_FI_DEV_FB_USED                                               ,gauge                  ,Framebuffer memory used (in MiB).
 
# NVLink
DCGM_FI_DEV_NVLINK_BANDWIDTH_TOTAL                                ,counter                ,Total number of NVLink bandwidth counters for all lanes.
 
# VGPU License status
DCGM_FI_DEV_VGPU_LICENSE_STATUS                                   ,gauge                  ,vGPU License status
 
# Remapped rows
DCGM_FI_DEV_UNCORRECTABLE_REMAPPED_ROWS                           ,counter                ,Number of remapped rows for uncorrectable errors
DCGM_FI_DEV_CORRECTABLE_REMAPPED_ROWS                             ,counter                ,Number of remapped rows for correctable errors
DCGM_FI_DEV_ROW_REMAP_FAILURE                                     ,gauge                  ,Whether remapping of rows has failed
 
# DCP metrics
DCGM_FI_PROF_PCIE_TX_BYTES                                        ,counter                ,The number of bytes of active pcie tx data including both header and payload.
DCGM_FI_PROF_PCIE_RX_BYTES                                        ,counter                ,The number of bytes of active pcie rx data including both header and payload.
DCGM_FI_PROF_GR_ENGINE_ACTIVE                                     ,gauge                  ,Ratio of time the graphics engine is active (in %).
DCGM_FI_PROF_SM_ACTIVE                                            ,gauge                  ,The ratio of cycles an SM has at least 1 warp assigned (in %).
DCGM_FI_PROF_SM_OCCUPANCY                                         ,gauge                  ,The ratio of number of warps resident on an SM (in %).
DCGM_FI_PROF_PIPE_TENSOR_ACTIVE                                   ,gauge                  ,Ratio of cycles the tensor (HMMA) pipe is active (in %).
DCGM_FI_PROF_DRAM_ACTIVE                                          ,gauge                  ,Ratio of cycles the device memory interface is active sending or receiving data (in %).
DCGM_FI_PROF_PIPE_FP64_ACTIVE                                     ,gauge                  ,Ratio of cycles the fp64 pipes are active (in %).
DCGM_FI_PROF_PIPE_FP32_ACTIVE                                     ,gauge                  ,Ratio of cycles the fp32 pipes are active (in %).
DCGM_FI_PROF_PIPE_FP16_ACTIVE                                     ,gauge                  ,Ratio of cycles the fp16 pipes are active (in %).
 
# Datadog additional recommended fields
DCGM_FI_DEV_COUNT                                                 ,counter                ,Number of Devices on the node.
DCGM_FI_DEV_FAN_SPEED                                             ,gauge                  ,Fan speed for the device in percent 0-100.
DCGM_FI_DEV_SLOWDOWN_TEMP                                         ,gauge                  ,Slowdown temperature for the device.
DCGM_FI_DEV_POWER_MGMT_LIMIT                                      ,gauge                  ,Current power limit for the device.
DCGM_FI_DEV_PSTATE                                                ,gauge                  ,Performance state (P-State) 0-15. 0=highest
DCGM_FI_DEV_FB_TOTAL                                              ,gauge                  ,
DCGM_FI_DEV_FB_RESERVED                                           ,gauge                  ,
DCGM_FI_DEV_FB_USED_PERCENT                                       ,gauge                  ,
DCGM_FI_DEV_CLOCK_THROTTLE_REASONS                                ,gauge                  ,Current clock throttle reasons (bitmask of DCGM_CLOCKS_THROTTLE_REASON_*)
 
DCGM_FI_PROCESS_NAME                                              ,label                  ,The Process Name.
DCGM_FI_CUDA_DRIVER_VERSION                                       ,label                  ,
DCGM_FI_DEV_NAME                                                  ,label                  ,
DCGM_FI_DEV_MINOR_NUMBER                                          ,label                  ,
DCGM_FI_DRIVER_VERSION                                            ,label                  ,
DCGM_FI_DEV_BRAND                                                 ,label                  ,
DCGM_FI_DEV_SERIAL                                                ,label                  ,