Some GPUs include a GPU System Processor (GSP) which can be used to offload GPU initialization and management tasks. This processor is driven by the gsp_*.bin firmware files under /lib/firmware/nvidia/550.78/. Each GSP firmware file is named after a GPU architecture (for example, gsp_tu10x.bin is named after Turing) and supports GPUs from one or more architectures. A few select products currently use GSP by default, and more products will take advantage of GSP in future driver releases.

Offloading tasks which were traditionally performed by the driver on the CPU can improve performance due to lower latency access to GPU hardware internals.

Query Mode

The nvidia-smi utility can be used to query the current use of GSP firmware. It will display a valid version if GSP firmware is enabled, or “N/A” if disabled:

    $ nvidia-smi -q
    ...
       GSP Firmware Version                  : 550.78
    ...

This information is also present in the per-GPU information file in the /proc file system.

    $ cat /proc/driver/nvidia/gpus/domain:bus:device.function/information
    ...
       GSP Firmware:    550.78

Disabling GSP Mode

The driver can be forced to disable use of GSP firmware by setting the kernel module parameter NVreg_EnableGpuFirmware=0.

Enabling GSP Mode

Turing and later GPUs are capable of using the GSP firmware by setting the kernel module parameter NVreg_EnableGpuFirmware=1. However, note feature and GPU support limitations below.

Supported GPUs

The following GPUs default to using the GSP firmware:

* If three IDs are listed, the first is the PCI Device ID, the second is the PCI Subsystem Vendor ID, and the third is the PCI Subsystem Device ID.