Functions

nvmlReturn_t nvmlDeviceClearAccountingPids ( nvmlDevice_t device )

Parameters

device

The identifier of the target device

Returns

• NVML_SUCCESS if accounting information has been cleared
• NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized
• NVML_ERROR_INVALID_ARGUMENT if device are invalid
• NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature
• NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation
• NVML_ERROR_UNKNOWN on any unexpected error

Description

Clears accounting information about all processes that have already terminated.

For Kepler or newer fully supported devices. Requires root/admin permissions.

See nvmlDeviceGetAccountingMode See nvmlDeviceGetAccountingStats See nvmlDeviceSetAccountingMode

nvmlReturn_t nvmlDeviceGetAccountingBufferSize ( nvmlDevice_t device, unsigned int* bufferSize )

Parameters

device

The identifier of the target device

bufferSize

Reference in which to provide the size (in number of elements) of the circular buffer for accounting stats.

Returns

• NVML_SUCCESS if buffer size was successfully retrieved
• NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized
• NVML_ERROR_INVALID_ARGUMENT if device is invalid or bufferSize is NULL
• NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature or accounting mode is disabled
• NVML_ERROR_UNKNOWN on any unexpected error

Description

Returns the number of processes that the circular buffer with accounting pids can hold.

For Kepler or newer fully supported devices.

This is the maximum number of processes that accounting information will be stored for before information about oldest processes will get overwritten by information about new processes.

See also:

nvmlDeviceGetAccountingStats

nvmlDeviceGetAccountingPids

nvmlReturn_t nvmlDeviceGetAccountingMode ( nvmlDevice_t device, nvmlEnableState_t* mode )

Parameters

device

The identifier of the target device

mode

Reference in which to return the current accounting mode

Returns

• NVML_SUCCESS if the mode has been successfully retrieved
• NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized
• NVML_ERROR_INVALID_ARGUMENT if device is invalid or mode are NULL
• NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature
• NVML_ERROR_UNKNOWN on any unexpected error

Description

Queries the state of per process accounting mode.

For Kepler or newer fully supported devices.

See nvmlDeviceGetAccountingStats for more details. See nvmlDeviceSetAccountingMode

nvmlReturn_t nvmlDeviceGetAccountingPids ( nvmlDevice_t device, unsigned int* count, unsigned int* pids )

Parameters

device

The identifier of the target device

count

Reference in which to provide the pids array size, and to return the number of elements ready to be queried

pids

Reference in which to return list of process ids

Returns

• NVML_SUCCESS if pids were successfully retrieved
• NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized
• NVML_ERROR_INVALID_ARGUMENT if device is invalid or count is NULL
• NVML_ERROR_NOT_SUPPORTED if device doesn't support this feature or accounting mode is disabled or on vGPU host.
• NVML_ERROR_INSUFFICIENT_SIZE if count is too small (count is set to expected value)
• NVML_ERROR_UNKNOWN on any unexpected error

Description

Queries list of processes that can be queried for accounting stats. The list of processes returned can be in running or terminated state.

For Kepler or newer fully supported devices.

To query the number of processes under Accounting Mode, call this function with *count = 0 and pids=NULL. The return code will be NVML_ERROR_INSUFFICIENT_SIZE with an updated count value indicating the number of processes.

For more details see nvmlDeviceGetAccountingStats.

Note:

In case of PID collision some processes might not be accessible before the circular buffer is full.

See also:

nvmlDeviceGetAccountingBufferSize

nvmlReturn_t nvmlDeviceGetAccountingStats ( nvmlDevice_t device, unsigned int  pid, nvmlAccountingStats_t* stats )

Parameters

device

The identifier of the target device

pid

Process Id of the target process to query stats for

stats

Reference in which to return the process's accounting stats

Returns

• NVML_SUCCESS if stats have been successfully retrieved
• NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized
• NVML_ERROR_INVALID_ARGUMENT if device is invalid or stats are NULL
• NVML_ERROR_NOT_FOUND if process stats were not found
• NVML_ERROR_NOT_SUPPORTED if device doesn't support this feature or accounting mode is disabled or on vGPU host.
• NVML_ERROR_UNKNOWN on any unexpected error

Description

Queries process's accounting stats.

For Kepler or newer fully supported devices.

Accounting stats capture GPU utilization and other statistics across the lifetime of a process. Accounting stats can be queried during life time of the process and after its termination. The time field in nvmlAccountingStats_t is reported as 0 during the lifetime of the process and updated to actual running time after its termination. Accounting stats are kept in a circular buffer, newly created processes overwrite information about old processes.

See nvmlAccountingStats_t for description of each returned metric. List of processes that can be queried can be retrieved from nvmlDeviceGetAccountingPids.

Note:

• Accounting Mode needs to be on. See nvmlDeviceGetAccountingMode.

• Only compute and graphics applications stats can be queried. Monitoring applications stats can't be queried since they don't contribute to GPU utilization.

• In case of pid collision stats of only the latest process (that terminated last) will be reported

See also:

nvmlDeviceGetAccountingBufferSize

nvmlReturn_t nvmlDeviceSetAccountingMode ( nvmlDevice_t device, nvmlEnableState_t mode )

Parameters

device

The identifier of the target device

mode

The target accounting mode

Returns

• NVML_SUCCESS if the new mode has been set
• NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized
• NVML_ERROR_INVALID_ARGUMENT if device or mode are invalid
• NVML_ERROR_NOT_SUPPORTED if the device doesn't support this feature
• NVML_ERROR_NO_PERMISSION if the user doesn't have permission to perform this operation
• NVML_ERROR_UNKNOWN on any unexpected error

Description

Enables or disables per process accounting.

For Kepler or newer fully supported devices. Requires root/admin permissions.

Note:

• This setting is not persistent and will default to disabled after driver unloads. Enable persistence mode to be sure the setting doesn't switch off to disabled.

• Enabling accounting mode has no negative impact on the GPU performance.

• Disabling accounting clears all accounting pids information.

• On MIG-enabled GPUs, accounting mode would be set to DISABLED and changing it is not supported.

See nvmlDeviceGetAccountingMode See nvmlDeviceGetAccountingStats See nvmlDeviceClearAccountingPids

nvmlReturn_t nvmlDeviceSetPowerManagementLimit_v2 ( nvmlDevice_t device, nvmlPowerValue_v2_t* powerValue )

Parameters

device

The identifier of the target device

powerValue

Power management limit in milliwatts to set

Returns

• NVML_SUCCESS if limit has been set
• NVML_ERROR_UNINITIALIZED if the library has not been successfully initialized
• NVML_ERROR_INVALID_ARGUMENT if device is invalid or powerValue is NULL or contains invalid values
• NVML_ERROR_NOT_SUPPORTED if the device does not support this feature
• NVML_ERROR_GPU_IS_LOST if the target GPU has fallen off the bus or is otherwise inaccessible
• NVML_ERROR_UNKNOWN on any unexpected error

Description

Set new power limit of this device.

For Kepler or newer fully supported devices. Requires root/admin permissions.

See nvmlDeviceGetPowerManagementLimitConstraints to check the allowed ranges of values.

See nvmlPowerValue_v2_t for more information on the struct.

Note:

Limit is not persistent across reboots or driver unloads. Enable persistent mode to prevent driver from unloading when no application is using the device.

This API replaces nvmlDeviceSetPowerManagementLimit. It can be used as a drop-in replacement for the older version.

See also:

NVML_FI_DEV_POWER_AVERAGE

NVML_FI_DEV_POWER_INSTANT

NVML_FI_DEV_POWER_MIN_LIMIT

NVML_FI_DEV_POWER_MAX_LIMIT

NVML_FI_DEV_POWER_CURRENT_LIMIT