Count_visible_devices () 2 igpu.visible_devices_index()Returns an index list, containing the device index for each visible GPU defined by the CUDA_VISIBLE_DEVICES environmnt variable. Visible_devices_index () igpu.visible_devices()Returns a GpuInfo list containing all visible devices defined by the CUDA_VISIBLE_DEVICES environmnt variable.All properties and methods of GpuInfo class are described in GPUInfo Class Description section. Name ) 1, GeForce GTX 1080 Ti 3, GeForce GTX 1080 Ti GPUInfo Class DescriptionThe GPUInfo is a helper class that handles the attributes of each GPU. The user can access all properties and stats accordingly with the GPU attributes categories. Name ) 2, GeForce GTX 1080 Ti vices()Returns a GpuInfo list containing all available devices.All properties and methods of GpuInfo class are described in GPUInfo Class Description section. Name ) 0, GeForce GTX 1080 Ti 1, GeForce GTX 1080 Ti 2, GeForce GTX 1080 Ti 3, GeForce GTX 1080 Ti Visible DevicesBy manually setting the environment variable CUDA_VISIBLE_DEVICES (or automatically, by other software, like SLURM cluster manager), the user can mask which GPUs should be visible to different Deep Learning frameworks (e.g. The main functions along with a short description of inputs, outputs, and functionality can be found in the next sections. Available DevicesThe igpu can manipulate information and stats for all available devices. Availability is determined based on the GPU boards installed on the host. unt_devices()Returns the number of available GPU devices installed on the host.
Count_devices () 4 vices_index()Returns an index list, containing the device index for each available GPU. Devices_index () igpu.get_device(device_index)Given a device_index, returns a GpuInfo object containing the device properties and stats.