cuda.bindings.nvml.device_get_max_clock_info#

cuda.bindings.nvml.device_get_max_clock_info(intptr_t device, int type) → unsigned int#

Retrieves the maximum clock speeds for the device.

For Fermi ™️ or newer fully supported devices. See nvmlClockType_t for details on available clock information.

Parameters:

  • device (intptr_t) – The identifier of the target device.

  • type (ClockType) – Identify which clock domain to query.

Returns:

Reference in which to return the clock speed in MHz.

Return type:

unsigned int

Note

Current P0 clocks (reported by nvmlDeviceGetClockInfo) can differ from max clocks by a few MHz.

See also

nvmlDeviceGetMaxClockInfo